An Expert System To Diagnose Performance Limiting Factors at

Chapter 9

Downloaded via UNIV OF BATH on August 20, 2019 at 12:15:18 (UTC). See https://pubs.acs.org/sharingguidelines for options on how to legitimately share published articles.

An Expert System To Diagnose Performance Limiting Factors at Publicly Owned Treatment Works Linda Berkman, Mark Lennon, and Keith Law Eastern Research Group, 6 Wittmore Street, Arlington, MA 02174

This paper introduces POTW EXPERT, a diagnostic expert system based on an economic, non construction-oriented approach for optimizing Publicly Owned Treatment Plant (POTW) performance. Approximately two-thirds of the nation's operating POTWs have effluent quality or public health problems; it has been estimated that $36.2 b i l l i o n would be required to address these problems. POTW EXPERT, a joint effort implemented by the U.S. Environmental Protection Agency and Eastern Research Group, Inc., assists evaluators i n recognizing plant performance problems by modeling the actual evaluation strategy employed by experts concerned with diagnosing POTWs. By observing symptoms and using experiential rules of thumb, POTW EXPERT identifies factors which impede the optimization of plant performance. This paper discusses our knowledge engineering and elicitation approach, the formulation of heuristically guided diagnosis procedures, and our methods for qualifying information and dealing with suspect or marginal data. Validation of the system w i l l be examined both in terms of how the system should be validated and who should perform the validation. Wastewater i s t h e f l o w o f used water from a community. Wastewater comes from f i v e s o u r c e s : r e s i d e n t i a l , c o m m e r c i a l , and i n d u s t r i a l s o u r c e s , and storm and ground water. Treatment o f wastewater i s concerned w i t h the removal o f c o n s t i t u e n t s w h i c h : w i l l d e p l e t e oxygen r e s o u r c e s o f the r e c e i v i n g w a t e r s t o w h i c h they a r e d i s c h a r g e d ; may s t i m u l a t e u n d e s i r a b l e growth o f p l a n t s and organisms i n the r e c e i v i n g w a t e r ; o r w i l l have adverse h e a l t h o r o t h e r e f f e c t s on downstream water uses. I n the U n i t e d S t a t e s , the need f o r b e t t e r performance from e x i s t i n g wastewater t r e a t m e n t f a c i l i t i e s i s e x t e n s i v e . I n 1986, the U.S. E n v i r o n m e n t a l P r o t e c t i o n Agency (EPA) r e p o r t e d t h a t 10,131 o f 15,438 o p e r a t i n g P u b l i c l y Owned Treatment Works (POTWs) have documented e f f l u e n t q u a l i t y o r p u b l i c h e a l t h problems. EPA 0097-6156/90/0431-0120$06.00A) © 1990 American Chemical Society

Hushon; Expert Systems for Environmental Applications ACS Symposium Series; American Chemical Society: Washington, DC, 1990.

9.

B E R K M A N ET AL.

Diagnosing Performance Limiting Factors

111

e s t i m a t e d t h a t $36.2 b i l l i o n would be r e q u i r e d t o address t h e s e problems ( 1 ) . F e d e r a l f u n d i n g t o s u p p o r t POTW improvements has been d e c r e a s i n g , however, as t h e f e d e r a l government has asked s t a t e s and l o c a l governments t o s h o u l d e r an i n c r e a s i n g share o f t h e f i n a n c i a l r e s p o n s i b i l i t y f o r m a i n t a i n i n g and u p g r a d i n g POTW performance. A c l e a r need among POTW r e g u l a t o r s and o p e r a t o r s i s t o o p t i m i z e t h e performance o f e x i s t i n g f a c i l i t i e s b e f o r e i m p l e m e n t i n g c o s t l y new d e s i g n m o d i f i c a t i o n and c o n s t r u c t i o n p r o j e c t s . A number o f e n g i n e e r i n g f i r m s and o t h e r o r g a n i z a t i o n s have developed methodologies ( i n c l u d i n g s e v e r a l software products) t o a s s i s t i n d i a g n o s i n g t h e causes o f POTW performance problems. One o f the most s u c c e s s f u l o f these m e t h o d o l o g i e s i s t h e Comprehensive Performance E v a l u a t i o n / C o m p o s i t e C o r r e c t i o n Program (CPE/CCP) approach d e v e l o p e d by P r o c e s s A p p l i c a t i o n s , I n c . , o f F o r t C o l l i n s , C o l o r a d o . Based on n e a r l y a decade o f EPA- and s t a t e - s p o n s o r e d i n v e s t i g a t i o n , the CPE/CCP approach r e p r e s e n t s a s t r u c t u r e d methodology (1) t o e v a l u a t e t h e c a p a c i t y o f e x i s t i n g POTW p r o c e s s e s t o meet e f f l u e n t permit r e q u i r e m e n t s and (2) t o i d e n t i f y c o s t - e f f e c t i v e , non c o n s t r u c t i o n - o r i e n t e d o p t i o n s t o improve p l a n t performance. P r o c e s s A p p l i c a t i o n s ' methodology has been documented i n EPA's Handbook, Improving POTW Performance Using the Composite Corrective Action Approach ( 2 ) . Based on the p r o v e n t r a c k r e c o r d and w i d e s p r e a d a p p l i c a b i l i t y o f the CPE/CCP approach, EPA's O f f i c e o f R e s e a r c h and Development/Center f o r E n v i r o n m e n t a l Research I n f o r m a t i o n d e c i d e d i n 1988 t o f u n d development o f an e x p e r t system t o i n c o r p o r a t e the e x p e r t i s e embodied i n t h e CPE/CCP methodology. This report describes the concept, d e s i g n , and i m p l e m e n t a t i o n o f t h i s e x p e r t system. The system, POTW EXPERT, was b e t a - t e s t e d i n September, 1989, and i s c u r r e n t l y i n l i m i t e d - d i s t r i b u t i o n t e s t i n g by EPA. The CPE/CCP Approach t o POTW E v a l u a t i o n The CPE/CCP approach t o POTW e v a l u a t i o n proceeds i n two d i s t i n c t b u t l i n k e d phases. The Comprehensive Performance E v a l u a t i o n i d e n t i f i e s and prioritizes the design, operational, maintenance, and a d m i n i s t r a t i v e f a c t o r s which may be the c a u s e ( s ) o f s u b o p t i m a l POTW performance. The Composite C o r r e c t i o n Program implements p r o c e d u r e s ( e . g . , changes i n p l a n t o p e r a t i o n s , t r a i n i n g f o r p l a n t o p e r a t o r s ) t o address t h e s e f a c t o r s . The CPE and CCP a r e l i n k e d i n t h a t i m p l e m e n t a t i o n o f the CCP may f e e d back t o a f f e c t the c o n t e n t o r o r d e r o f the p r i o r i t i z e d l i s t o f f a c t o r s a f f e c t i n g p l a n t performance. The d i s t i n c t i o n between CPE and CCP marks a l o g i c a l problem boundary f o r an e x p e r t system b u i l t around t h e CPE/CCP approach; development o f POTW EXPERT t o date has f o c u s e d on t h e Comprehensive Performance Evaluation. A Comprehensive Performance E v a l u a t i o n encompasses two p r i m a r y sets of a c t i v i t i e s : 1. 2.

E v a l u a t i o n o f Major U n i t P r o c e s s e s I d e n t i f i c a t i o n and P r i o r i t i z a t i o n o f Performance Factors


Limiting

122

E X P E R T SYSTEMS FOR

ENVIRONMENTAL APPLICATIONS

E v a l u a t i o n o f Major U n i t P r o c e s s e s . The g o a l o f t h i s e v a l u a t i o n i s to d e t e r m i n e whether e x i s t i n g b i o l o g i c a l and c h e m i c a l t r e a t m e n t p r o c e s s e s a r e adequate t o meet e f f l u e n t q u a l i t y g o a l s , g i v e n e x i s t i n g and p r o j e c t e d i n f l u e n t volumes and o r g a n i c l o a d i n g . The e v a l u a t i o n i s based on a n a l y s i s o f d a t a and o n - s i t e o b s e r v a t i o n s made f o r each major u n i t p r o c e s s i n the p l a n t , and assignment o f p o i n t s based on p r o c e s s d e s i g n and c a p a c i t y . The end r e s u l t o f the e v a l u a t i o n i s a c a t e g o r i z a t i o n o f the p l a n t i n t o one o f t h r e e t y p e s : Type 1

C a p a b i l i t y o f major u n i t p r o c e s s e s does n o t l i m i t p l a n t performance. Performance problems a r e p o t e n t i a l l y r e l a t e d to p l a n t o p e r a t i o n , maintenance, o r a d m i n i s t r a t i o n , o r t o u n i t p r o c e s s m a l f u n c t i o n s which can be c o r r e c t e d w i t h o n l y minor f a c i l i t y m o d i f i c a t i o n s .

Type 2

C a p a b i l i t y o f one o r more major u n i t p r o c e s s e s i s m a r g i n a l . E f f o r t s t o o p t i m i z e a l l a s p e c t s a f f e c t i n g the u n i t ' s c a p a b i l i t y are w a r r a n t e d p r i o r t o upgrade o f the u n i t process.

Type 3

One o r more major u n i t p r o c e s s e s i s i n a d e q u a t e to s a t i s f a c t o r i l y t r e a t e x i s t i n g i n f l u e n t volumes o r o r g a n i c loads. P l a n t performance cannot be e x p e c t e d t o improve s i g n i f i c a n t l y u n t i l the l i m i t i n g p r o c e s s ( e s ) a r e upgraded.

Analysis of major unit process capacity allows POTW owner/operators t o p i n p o i n t many d e s i g n - r e l a t e d causes o f p l a n t performance problems. C a t e g o r i z a t i o n o f a p l a n t as Type 1 o r Type 2 suggests that the c a p a b i l i t y e x i s t s and performance can be s i g n i f i c a n t l y upgraded w i t h o u t a major c o n s t r u c t i o n program, and t h a t degraded p l a n t performance can be r e l a t e d t o problems i n p l a n t o p e r a t i o n , maintenance, and/or a d m i n i s t r a t i o n which can be a d d r e s s e d with r e l a t i v e l y low-cost s o l u t i o n s . I d e n t i f i c a t i o n and P r i o r i t i z a t i o n o f Performance L i m i t i n g F a c t o r s . Once the p l a n t has been s c o r e d , a Comprehensive Performance E v a l u a t i o n proceeds t o i d e n t i f y and p r i o r i t i z e the f a c t o r s t h a t can be c o r r e l a t e d w i t h p l a n t performance problems. W i t h a database o f hundreds o f p l a n t a n a l y s e s completed, P r o c e s s A p p l i c a t i o n s has i d e n t i f i e d a s e t o f 66 f a c t o r s -- r e l a t e d t o p l a n t a d m i n i s t r a t i o n , maintenance, d e s i g n , and o p e r a t i o n - - w h i c h may cause degraded p l a n t performance. The r e a l expertise d e v e l o p e d by Process A p p l i c a t i o n s consists of the e n g i n e e r i n g and s o c i o - e c o n o m i c knowledge and judgment r e q u i r e d t o s i f t t h r o u g h l i t e r a l l y hundreds o f o b s e r v a t i o n s and d a t a p o i n t s r e l a t e d t o plant d e s i g n and performance, and t o g l e a n i n f o r m a t i o n from i n t e r a c t i o n s w i t h p l a n t o p e r a t o r s and a d m i n i s t r a t o r s , i n o r d e r t o i d e n t i f y those few f a c t o r s which are the p r i m a r y causes o f p l a n t performance problems. The Performance L i m i t i n g F a c t o r s (PLFs) a r e s t r u c t u r e d as a s e r i e s o f q u e s t i o n s which r e q u i r e the e v a l u a t o r t o j u d g e the e x t e n t to w h i c h each PLF may be r e l a t e d t o an i d e n t i f i e d performance problem. An i n i t i a l a n a l y s i s e l i m i n a t e s most PLFs from c o n s i d e r a t i o n as causes o f poor p l a n t performance, and l e a v e s a s u b s e t ( u s u a l l y no more t h a n 10 t o 15 PLFs) w h i c h c o n t r i b u t e d i r e c t l y t o the i d e n t i f i e d performance


9.

BERKMAN E T A L .


123

problem. The e v a l u a t o r t h e n p r i o r i t i z e s t h e s e r e m a i n i n g f a c t o r s . The end r e s u l t o f the p r o c e s s i s a p r i o r i t i z e d l i s t o f PLFs w h i c h d e f i n e s those a r e a s o f p l a n t o p e r a t i o n , a d m i n i s t r a t i o n , d e s i g n , and/or maintenance w h i c h s h o u l d be a d d r e s s e d f i r s t i n a t t e m p t i n g t o upgrade p l a n t performance. The CPE/CCP methodology r e c o g n i z e s t h a t c o r r e c t i o n of one PLF may r e s u l t i n the i d e n t i f i c a t i o n o f a d d i t i o n a l PLFs, n o t i n c l u d e d on t h e o r i g i n a l p r i o r i t i z e d l i s t , w h i c h c o n t r i b u t e t o degraded performance b u t which were masked by PLFs on the o r i g i n a l list. The CPE/CCP i s t h e r e f o r e an i t e r a t i v e p r o c e s s -- the l i s t o f PLFs s h o u l d be r e - a n a l y z e d and r e - o r d e r e d as improvements a r e made t o the f a c t o r s f i r s t i d e n t i f i e d as the most l i k e l y causes o f u n a c c e p t a b l e p l a n t performance. The E x p e r t System The o b j e c t i v e o f the POTW EXPERT development e f f o r t i s t o a l l o w u s e r s to r a p i d l y and e f f e c t i v e l y e v a l u a t e t h e c a u s e ( s ) o f degraded performance a t POTWs t h a t f a i l t o meet e f f l u e n t q u a l i t y t a r g e t s . The system a c h i e v e s t h i s o b j e c t i v e by making t h e p r o v e n d i a g n o s t i c e x p e r t i s e embodied i n the CPE/CCP approach a v a i l a b l e t o the community of wastewater t r e a t m e n t r e g u l a t o r s and o p e r a t o r s r e s p o n s i b l e f o r a c h i e v i n g and m a i n t a i n i n g POTW e f f l u e n t q u a l i t y . POTW EXPERT address t h r e e types o f secondary wastewater t r e a t m e n t p r o c e s s e s : suspended growth, f i x e d f i l m , and s t a b i l i z a t i o n ponds. The e x p e r t system emphasizes meeting N a t i o n a l P o l l u t a n t D i s c h a r g e E l i m i n a t i o n Standards (NPDES) f o r secondary t r e a t m e n t f a c i l i t i e s (30 mg/1 B0D and TSS) w i t h a maximum average d a i l y f l o w o f 20 m i l l i o n g a l l o n s per day (mgd). 5

Hardware and Software Requirements and S e l e c t i o n . A number o f r e q u i r e m e n t s i n f l u e n c e d t h e e a r l y d e s i g n phases f o r POTW EXPERT. These were r e l a t e d p r i m a r i l y t o the u s e r community f o r t h e system, development and d e l i v e r y hardware, and the need t o c o n t i n u a l l y update the system. Users

POTW EXPERT i s t a r g e t e d t o a u s e r community o f p o t e n t i a l l y thousands o f POTW o w n e r / o p e r a t o r s , s t a t e and l o c a l r e g u l a t o r s , and c o n s u l t i n g e n g i n e e r s , among whom t h e development team c o u l d assume o n l y r u d i m e n t a r y computer knowledge. I n a d d i t i o n , a fundamental premise o f t h e development e f f o r t has been t h a t t h e system would be p r o v i d e d t o u s e r s a t l i t t l e o r no c o s t ; t h e s i z e o f t h e u s e r community t h e r e f o r e p r e c l u d e d t h e s e l e c t i o n o f commercial e x p e r t system s o f t w a r e w i t h s i g n i f i c a n t runt i m e , d i s t r i b u t i o n , o r hardware c o s t s .

Platform

Because o f the n a t u r e o f the i n t e n d e d u s e r community, POTW EXPERT has been d e v e l o p e d f o r d e l i v e r y on PC/XT c l a s s machines w i t h no more t h a n 640K o f memory. (Better performance i s o b t a i n e d , however, i f t h e system i s i n s t a l l e d on an AT c l a s s machine.) Because o f the v e r y l a r g e knowledge base we a n t i c i p a t e d f o r t h e system, we attempted t o i d e n t i f y an e x p e r t system s h e l l w i t h an



124


e f f i c i e n t p a g i n g mechanism to a l l o w e f f e c t i v e use o f memory and the s t o r a g e c a p a c i t y o f a h a r d d i s k . Updates

Because t h e knowledge base i n c o r p o r a t e d i n t o t h e CPE p r o c e s s i s c o n t i n u a l l y b e i n g expanded and r e f i n e d , and because POTW performance r e q u i r e m e n t s a r e t h e s u b j e c t o f a c t i v e r e g u l a t o r y i n t e r v e n t i o n , we f a c e d t h e demand t o c o n s t r u c t a v e r y r o b u s t system -- r o b u s t b o t h i n a l l o w i n g s t r a i g h t f o r w a r d e x p a n s i o n t o t h e knowledge base and inference mechanism, and i n a s s u r i n g that system performance would not become u n p r e d i c t a b l e as changes and updates are i n c o r p o r a t e d .

D u r i n g p r o j e c t i n i t i a t i o n , we e v a l u a t e d over f i f t e e n c a n d i d a t e e x p e r t system s h e l l s f o r s u i t a b i l i t y f o r t h e p r o p o s e d system. The m a j o r i t y o f s h e l l s o p e r a t i n g i n our r e q u i r e d d e l i v e r y environment are s i m p l e , r u l e - b a s e d systems. Many o f t h e s e t o o l s are v e r y s i m p l e t o l e a r n and use, o f f e r i n g a p p e a l i n g d e v e l o p e r and u s e r i n t e r f a c e s . As such, they are a t t r a c t i v e f o r l i m i t e d a p p l i c a t i o n s o r f o r r e l a t i v e l y inexperienced developers. However, a problem as l a r g e and complex as t h a t d e f i n e d by POTW EXPERT cannot be f o r c e - f i t i n t o t h e s i n g l e p r o c e s s i n g paradigm o f f e r e d by most PC-based s h e l l s . The n a t u r e o f the POTW EXPERT'S d i a g n o s t i c / c l a s s i f i c a t i o n i s b e s t s u i t e d t o a h y b r i d knowledge r e p r e s e n t a t i o n s t r u c t u r e , c o u p l e d w i t h f l e x i b l e i n f o r m a t i o n p r o c e s s i n g c a p a b i l i t i e s . H i g h end s h e l l s a v a i l a b l e f o r the PC ( e . g . , Goldworks, N e x p e r t / O b j e c t , KEE) o f f e r p o w e r f u l i m p l e m e n t a t i o n s o f a h y b r i d system, b u t e i t h e r demanded s i g n i f i c a n t enhancements t o the PC d e l i v e r y p l a t f o r m o r e n t a i l e d p r o h i b i t i v e r u n - t i m e charges f o r t h e l a r g e POTW EXPERT u s e r community. We u l t i m a t e l y s e l e c t e d the s h e l l ALEX, d e v e l o p e d by H a r r i s and H a l l A s s o c i a t e s (P.O. Box 1900, P o r t A n g e l e s , WA 98362), as t h e development v e h i c l e f o r POTW EXPERT. Developed s p e c i f i c a l l y t o s u p p o r t d i a g n o s t i c p r o c e d u r e s f o r complex e n g i n e e r e d systems, ALEX i s a c o l l e c t i o n o f c l a s s e s and methods w h i c h a l l o w s programmers t o d e v e l o p o b j e c t - o r i e n t e d e x p e r t systems. The s h e l l employs a s t r u c t u r e o f a c t i v e demons and c h a n g i n g l e v e l s o f b e l i e f o r p r o b a b i l i t y t o s i m u l t a n e o u s l y m o n i t o r a l a r g e number o f f a c t o r s w h i c h may c o n t r i b u t e t o degraded performance o f t h e e n g i n e e r e d system under a n a l y s i s . W r i t t e n i n S m a l l t a l k / V , a PC-based i m p l e m e n t a t i o n o f X e r o x ' s o b j e c t o r i e n t e d S m a l l t a l k language, ALEX met t h e e x a c t i n g r e q u i r e m e n t s imposed on hardware and s o f t w a r e s e l e c t i o n : •

Window- and menu-driven, ALEX's u s e r i n t e r f a c e i s c l e a r , s i m p l e , and c o n c i s e . ALEX may be run w i t h o r w i t h o u t a Mouse.

•

ALEX and S m a l l t a l k / V c r e a t e a v i r t u a l memory s t r u c t u r e w i t h an e f f i c i e n t p a g i n g f a c i l i t y t o m i n i m i z e the memory l i m i t a t i o n s o f the PC d e l i v e r y p l a t f o r m .

•

ALEX a l l o w s e x p e r t systems t o be s t r u c t u r e d i n c o m p l e t e l y independent modules. V a r i a b l e s , once d e f i n e d , can be s h a r e d by a number o f modules. The e x p e r t system can thus be d e v e l o p e d i n s t a g e s , and system b e h a v i o r remains p r e d i c t a b l e as the system i s m o d i f i e d and expanded.


9.



US

•

I n f e r e n c i n g i s c o n t r o l l e d by the l e v e l o f b e l i e f o r p r o b a b i l i t y a t t a c h e d t o o b j e c t s ("demons," d e f i n e d b e l o w ) , w h i c h c a n be examined a t any p o i n t d u r i n g system development o r c o n s u l t a t i o n . This i n f e r e n c e mechanism a l l o w s the developer to retain s t r a i g h t f o r w a r d and p r e c i s e c o n t r o l over i n f e r e n c i n g .

•

The development p l a t f o r m i s t o t a l l y open. S p e c i f i c a l l y , both the ALEX and S m a l l t a l k / V source code a r e a v a i l a b l e t o t h e developer. T h i s f e a t u r e has a l l o w e d us t o develop a number o f in-house enhancements b o t h t o f i n e - t u n e ALEX as a development t o o l f o r POTW EXPERT, and t o improve the performance o f ALEX and S m a l l t a l k / V i n the PC/XT d e l i v e r y environment.

Knowledge E n g i n e e r i n g Because POTW EXPERT was based on the e x i s t i n g EPA/Process A p p l i c a t i o n s Handbook, the domain e x p e r t s f o r the system were p r e - s e l e c t e d . A l s o , much o f the knowledge t o be i n c o r p o r a t e d i n POTW EXPERT was c o d i f i e d in t h e Handbook prior to i n i t i a t i o n o f system development; s p e c i f i c a l l y , many o f t h e p r o c e d u r a l c a l c u l a t i o n s r e q u i r e d f o r t h e major u n i t p r o c e s s e v a l u a t i o n were s p e c i f i e d i n the Handbook, and the s t r u c t u r e and c o n t e n t o f t h e Performance L i m i t i n g F a c t o r s were outlined. F o r these r e a s o n s , f u n c t i o n a l s p e c i f i c a t i o n s and much o f the e a r l y system d e s i g n c o u l d be completed b e f o r e f o r m a l knowledge e n g i n e e r i n g was i n i t i a t e d . Formal knowledge e n g i n e e r i n g w i t h t h e P r o c e s s A p p l i c a t i o n s e x p e r t s was a l s o s i m p l i f i e d , b o t h because much o f the r e q u i r e d knowledge had a l r e a d y been s t r u c t u r e d and r e c o r d e d , and because we were a b l e t o produce l i m i t e d f u n c t i o n p r o t o t y p e s o f POTW EXPERT f o r d e m o n s t r a t i o n t o the domain e x p e r t s v e r y e a r l y i n the knowledge e n g i n e e r i n g p r o c e s s . N o n e t h e l e s s , knowledge e n g i n e e r i n g f o r POTW EXPERT was complex. The major knowledge e n g i n e e r i n g e f f o r t has been f o c u s e d on t h e Performance L i m i t i n g F a c t o r s . Most o f t h e s o p h i s t i c a t e d e x p e r t i s e r e q u i r e d t o complete a CPE i s r e l a t e d t o i d e n t i f i c a t i o n and r a n k i n g o f t h e PLFs, b u t t h e Handbook p r o v i d e s l i t t l e o f t h e i n f o r m a t i o n r e q u i r e d t o complete the PLF e v a l u a t i o n . The Handbook i n c l u d e s some 600 d a t a p o i n t s t h a t may c o n t r i b u t e t o assessment o f the PLFs, and the s t r u c t u r e o f the PLFs themselves p r o v i d e s some guidance on the d a t a most i m p o r t a n t t o a s s e s s i n g each f a c t o r . But, i n general, the Handbook does n o t p r o v i d e s u f f i c i e n t i n f o r m a t i o n t o make t h e s o p h i s t i c a t e d judgments r e q u i r e d t o i d e n t i f y and p r i o r i t i z e the PLFs most d i r e c t l y r e l a t e d t o poor POTW performance. The major u n i t p r o c e s s e v a l u a t i o n a l s o demanded a s i g n i f i c a n t knowledge e n g i n e e r i n g e f f o r t . D u r i n g i m p l e m e n t a t i o n o f t h i s l a r g e l y p r o c e d u r a l module o f POTW EXPERT, we encountered many i n s t a n c e s i n w h i c h complex e n g i n e e r i n g judgment was r e q u i r e d t o a s s e s s p r o c e s s capacity. These s i t u a t i o n s -- r e l a t e d p r i m a r i l y t o assessment o f oxygen t r a n s f e r c a p a c i t y , e s t i m a t i o n o f sludge volumes, and e v a l u a t i o n o f sludge h a n d l i n g c a p a c i t y -- were r a r e l y apparent i n the c a l c u l a t i o n s p r e s e n t e d i n t h e Handbook, and r e q u i r e d e x t e n s i v e i n t e r a c t i o n w i t h the domain e x p e r t s t o e l i c i t the h e u r i s t i c s c r u c i a l to t h e i r r e s o l u t i o n . Knowledge e n g i n e e r i n g f o r the system was c o m p l i c a t e d by the f a c t t h a t the domain e x p e r t s were l o c a t e d 2,000 m i l e s from the development


126

E X P E R T SYSTEMS F O R ENVIRONMENTAL APPLICATIONS

team, and so were n o t a c c e s s i b l e f o r r o u t i n e , f a c e - t o - f a c e communications. For t h i s r e a s o n , we employed a knowledge e n g i n e e r i n g approach c e n t e r e d on t h r e e c r i t i c a l s t r a t a g e m s : (1) we devoted more e f f o r t t h a n i s t y p i c a l l y r e q u i r e d t o d e v e l o p i n g domain e x p e r t i s e among our design/development team; (2) we completed as much p r o t o t y p e d e s i g n and development as p o s s i b l e on t h e b a s i s o f t h e Handbook b e f o r e initiating o n - s i t e knowledge engineering; and (3) we devoted s i g n i f i c a n t e f f o r t t o p r e p a r i n g d e t a i l e d b u t u n c o m p l i c a t e d paper models o f the major u n i t p r o c e s s and PLF h e u r i s t i c s f o r r e v i e w by the domain e x p e r t s . O n - s i t e knowledge e n g i n e e r i n g f o r t h e i n i t i a l p r o t o t y p e was c o m p l e t e d i n two t h r e e - t o f o u r - d a y s e s s i o n s between t h e domain e x p e r t s and two members o f t h e design/development team. These s e s s i o n s took t h e form o f s t r u c t u r e d i n t e r v i e w s ; t h e s t r u c t u r e f o r the i n t e r v i e w s was determined j o i n t l y by t h e o r g a n i z a t i o n o f t h e EPA/Process A p p l i c a t i o n s Handbook and b y the d e s i g n o f the p r o t o t y p e POTW EXPERT. O n - s i t e knowledge e n g i n e e r i n g was supplemented by f r e q u e n t t e l e p h o n e and m a i l communications b e f o r e and a f t e r the two knowledge e n g i n e e r i n g s e s s i o n s . V i r t u a l l y a l l o f the s i g n i f i c a n t elements o f r e a s o n i n g i n c o r p o r a t e d i n t o POTW EXPERT were c o n f i r m e d b y a f o r m a l r e v i e w o f t h e PLF and major u n i t p r o c e s s paper models d e v e l o p e d as p a r t o f our knowledge e n g i n e e r i n g s t r a t e g y . S t r u c t u r e o f POTW EXPERT POTW EXPERT'S t o p - l e v e l a r c h i t e c t u r e c o n s i s t s o f f o u r modules ( F i g u r e 1 ) . These are : 1. 2. 3. 4.

Data E n t r y Major U n i t Process E v a l u a t i o n E v a l u a t i o n o f Performance L i m i t i n g F a c t o r s Report G e n e r a t i o n

Data E n t r y . The Data E n t r y module r e q u e s t s i n f o r m a t i o n on s p e c i f i c p h y s i c a l p l a n t c h a r a c t e r i s t i c s and on t h e c h a r a c t e r i s t i c s o f p l a n t influent. I n f o r m a t i o n c o l l e c t e d i n t h i s module d e f i n e s t h e d a t a c o l l e c t e d and p r o c e s s i n g o p e r a t i o n s p e r f o r m e d i n subsequent modules. Data e n t r y s c r e e n s a r e g e n e r a t e d d y n a m i c a l l y based on t h e s p e c i f i c p l a n t c h a r a c t e r i s t i c s d e f i n e d i n the i n i t i a l d a t a e n t r y s c r e e n s ; they are t a i l o r e d s p e c i f i c a l l y t o the d e s i g n and equipment c h a r a c t e r i s t i c s f o r the POTW under a n a l y s i s ( F i g u r e 2 ) . A l t h o u g h most POTWs have a s i m i l a r o v e r a l l l a y o u t ( e . g . , p r i m a r y c l a r i f i e r , a e r a t o r , secondary c l a r i f i e r , s l u d g e h a n d l i n g s y s t e m ) , t h e r e i s tremendous v a r i a t i o n i n the p a r t i c u l a r equipment employed and i n t h e s p e c i f i c s o f p r o c e s s configuration. F o r example, c l a r i f i e r s d i f f e r i n s i z e , shape, c a p a c i t y , means o f s l u d g e removal, and o t h e r v a r i a b l e s ; a e r a t o r s d i f f e r i n t h e a e r a t i o n p r o c e s s employed, oxygen t r a n s f e r c a p a c i t y , oxygen t r a n s f e r e f f i c i e n c y , and o t h e r v a r i a b l e s . POTW EXPERT has been d e v e l o p e d t o be u s e f u l a c r o s s a b r o a d spectrum o f the POTW community, and t h e r e f o r e i s a b l e t o a n a l y z e t h e c a p a b i l i t y and o p e r a t i o n o f a l a r g e number o f c o m b i n a t i o n s o f s p e c i f i c u n i t p r o c e s s e s . The f i r s t two d a t a e n t r y s c r e e n s r e q u e s t i n f o r m a t i o n on s p e c i f i c process c h a r a c t e r i s t i c s o f the POTW under a n a l y s i s , and use t h i s i n f o r m a t i o n to s e t b r a n c h i n g o p t i o n s t h a t c o n t r o l d a t a e n t r y r e q u e s t s and



Retrieve Previous Session

Primary Clarifier

F i g u r e 1.

1

SESSION

POTW EXPERT t o p l e v e l

OLD

— • Sludge Handling

— • Oxygen Handling

> Secondary Clarifier

—•

Major Unit Process Evaluation

NEW SESSION

architecture.

Identify & Rank Performance Limiting Factors

I

I

Ο

o

r

End Point

Beg'"

I Major Units

I Process

KEY

EXPERT SYSTEMS F O R ENVIRONMENTAL APPLICATIONS

128

CLARIFIER - CIRCULAR

Greater Flow for Clarifier (see detail) Configuration Sludge Removal Mechanism Surface Area Depth near the Weirs Minimum Return Sludge Flow Possible Maximum Return Sludge Flow Possible Is there a rag problem? Is There a Grit Build-up Problem? Secondary Clarifier Blanket Depth Testing RAS Flow Rate Testing Mass Control Testing Settling Rate Testing

ESC:

Quit Data Entry

F3: Text

F8: Clear Field

F10: Menu

Enter: Accept

CLARIFIER - RECTANGULAR

Greater Flow for Clarifier (see detail) Is the Launder at the very end Surface Area of Launders Return Sludge Removal Mechanism Surface Area Depth near the Weirs Minimum Return Sludge Flow Possible Maximum Return Sludge Flow Possible Is there a rag problem? Is There a Grit Build-up Problem? Secondary Clarifier Blanket Depth Testing RAS Flow Rate Testing Mass Control Testing Settling Rate Testing 9

ESC:

Quit Data Entry

F3: Text

F8: Clear Field

F10: Menu

Enter: Accept

F i g u r e 2. POTW EXPERT d a t a e n t r y s c r e e n s t a i l o r e d t o t h e s p e c i f i c c h a r a c t e r i s t i c s o f t h e POTW under a n a l y s i s .


9.



129

i n f o r m a t i o n p r o c e s s i n g i n t h e subsequent Data E n t r y and M a j o r U n i t P r o c e s s E v a l u a t i o n Modules. Because o f the g r e a t v a r i a t i o n i n the d e t a i l s o f POTW d e s i g n and equipment, use o f s t a n d a r d i z e d d a t a e n t r y s c r e e n s might have p r o v e d c o n f u s i n g t o u s e r s , and would have r e s u l t e d i n t h e c o l l e c t i o n o f s u p e r f l u o u s d a t a (both s l o w i n g system o p e r a t i o n and t a x i n g the memory l i m i t a t i o n s o f our d e l i v e r y p l a t f o r m ) . The o b j e c t - o r i e n t e d knowledge r e p r e s e n t a t i o n s t r u c t u r e made p o s s i b l e by ALEX and S m a l l t a l k have a l l o w e d us t o implement a v e r y f l e x i b l e d a t a e n t r y system matched s p e c i f i c a l l y t o t h e i n d i v i d u a l POTW under a n a l y s i s . An " e x p l a i n " f a c i l i t y i s a v a i l a b l e f o r a l l d a t a r e q u e s t e d , and d e f a u l t v a l u e s may be used i f a u s e r i s u n a b l e t o p r o v i d e s e l e c t e d p l a n t i n f o r m a t i o n . U s e r s need n o t complete data i n p u t i n t h e Data E n t r y module. Any i n f o r m a t i o n o m i t t e d by the u s e r w i l l be r e q u e s t e d i n t e r a c t i v e l y when r e q u i r e d by POTW EXPERT d u r i n g the Major U n i t P r o c e s s E v a l u a t i o n or E v a l u a t i o n o f Performance L i m i t i n g F a c t o r s . POTW EXPERT w i l l attempt t o r e a s o n i n t h e absence o f u s e r i n p u t d a t a , b u t w i l l n o t conclude i t s reasoning process i f c r i t i c a l input i s missing. Major U n i t Process E v a l u a t i o n . Along with the Evaluation o f Performance L i m i t i n g F a c t o r s , the Major U n i t P r o c e s s E v a l u a t i o n forms the h e a r t o f POTW EXPERT. T h i s module e v a l u a t e s the c a p a b i l i t y o f the POTW's e n g i n e e r e d and b i o l o g i c a l p r o c e s s e s t o h a n d l e p l a n t i n f l u e n t l o a d s and meet e f f l u e n t p e r m i t r e q u i r e m e n t s . Processes evaluated i n c l u d e : p r i m a r y c l a r i f i e r , a e r a t i o n system, secondary c l a r i f i e r , and s l u d g e h a n d l i n g system ( F i g u r e 1 ) . T h i s module o f f e r s the c a p a b i l i t y to analyze a l a r g e number o f c o m b i n a t i o n s o f s p e c i f i c plant c o n f i g u r a t i o n and p r o c e s s d e s i g n and equipment. Much o f t h i s module i s p r o c e d u r a l , b u t i t uses e x p e r t systems r e a s o n i n g i n a number o f a r e a s . One o f the most common causes o f degraded POTW performance i d e n t i f i e d by P r o c e s s A p p l i c a t i o n s i s t h e m i s u n d e r s t a n d i n g o r m i s i n t e r p r e t a t i o n o f p l a n t o p e r a t i o n s and/or performance c h a r a c t e r i s t i c s on the p a r t o f POTW o p e r a t o r s . For t h i s r e a s o n , some o f the most d i f f i c u l t judgments made d u r i n g the c o u r s e o f a CPE i n v o l v e comparing r e p o r t e d p l a n t c h a r a c t e r i s t i c s and performance a g a i n s t e s t i m a t e s based on an e n g i n e e r i n g e v a l u a t i o n o f p l a n t d e s i g n . POTW EXPERT mimics t h i s r e a s o n i n g p r o c e s s i n the Major U n i t P r o c e s s E v a l u a t i o n ; p a r t i c u l a r l y c r i t i c a l a r e a s are the a e r a t i o n system and the s l u d g e h a n d l i n g system. I f POTW EXPERT d e t e r m i n e s t h a t u s e r - s u p p l i e d i n f o r m a t i o n about these p r o c e s s e s i s s u s p e c t , the system w i l l r e q u e s t the user t o c o n f i r m the i n f o r m a t i o n . I f i n f o r m a t i o n so confirmed remains q u e s t i o n a b l e , t h e system uses i t s i n t e r n a l e n g i n e e r i n g - b a s e d v a l u e s to e s t i m a t e major u n i t p r o c e s s c a p a c i t y , and f l a g s the operator's understanding and o r a p p l i c a t i o n o f POTW p r o c e s s e s as a p r o b a b l e f a c t o r c o n t r i b u t i n g t o degraded p l a n t performance. The p r i m a r y o u t p u t o f t h i s module i s a c a t e g o r i z a t i o n o f the POTW a c c o r d i n g t o i t s c a p a b i l i t y t o produce e f f l u e n t o f r e q u i r e d q u a l i t y . The module a l s o r e p o r t s a comparison o f p r o c e s s c a p a c i t y a g a i n s t p l a n t i n f l u e n t l o a d s , and i n d i c a t e s which p r o c e s s ( e s ) may be l i m i t i n g t h e p l a n t ' s a b i l i t y t o meet e f f l u e n t q u a l i t y g o a l s . Many o f t h e c a l c u l a t e d r e s u l t s g e n e r a t e d by t h i s module a l s o s e r v e as i n p u t t o the E v a l u a t i o n o f Performance L i m i t i n g F a c t o r s .



130


E v a l u a t i o n o f Performance L i m i t i n g F a c t o r s . The 66 PLFs i d e n t i f i e d by P r o c e s s A p p l i c a t i o n s f a l l i n t o f o u r c a t e g o r i e s : d e s i g n ; o p e r a t i o n ; maintenance; and a d m i n i s t r a t i o n . A few examples o f Performance L i m i t i n g Factors are: Type: Factor:

Administration P l a n t A d m i n i s t r a t o r s ' F a m i l i a r i t y w i t h P l a n t Needs

Do the a d m i n i s t r a t o r s have a f i r s t - h a n d knowledge o f p l a n t needs t h r o u g h p l a n t v i s i t s , d i s c u s s i o n s w i t h o p e r a t o r s , etc.? I f n o t , has t h i s been a cause o f poor p l a n t performance and r e l i a b i l i t y through poor budget d e c i s i o n s , poor staff morale, poor operation and maintenance p r o c e d u r e s , poor d e s i g n d e c i s i o n s , e t c . ? Type: Factor:

Design U n i t D e s i g n Adequacy, Secondary P r o c e s s

Flexibility

Does the u n a v a i l a b i l i t y o f adequate v a l v e s , p i p i n g , e t c . l i m i t p l a n t performance and r e l i a b i l i t y when o t h e r modes o f o p e r a t i o n o f the e x i s t i n g p l a n t can be u t i l i z e d t o improve performance (e.g., o p e r a t e a c t i v a t e d s l u d g e p l a n t i n p l u g , s t e p , o r c o n t a c t s t a b i l i z a t i o n mode; o p e r a t e RBCs i n s t e p l o a d i n g mode)? Type : Factor:

Operational Process Control Adjustments -Application Concepts and T e s t i n g t o P r o c e s s C o n t r o l

of

Is the s t a f f d e f i c i e n t i n the a p p l i c a t i o n o f t h e i r knowledge o f sewage t r e a t m e n t and i n t e r p r e t a t i o n o f p r o c e s s control testing such t h a t improper p r o c e s s control adjustments a r e made? T h i s module e v a l u a t e s each o f the 66 f a c t o r s , and r a n k s them according t o t h e i r impact on p l a n t performance. Factors are c l a s s i f i e d i n t o one o f f o u r c a t e g o r i e s : Class A

C o n t i n u i n g major impact on p l a n t performance

Class Β

Continuing minor impact on plant performance, s i g n i f i c a n t impact on a p e r i o d i c b u t i n f r e q u e n t b a s i s

Class C

M i n o r , o c c a s i o n a l impact on p l a n t performance

NR

F a c t o r not a s s o c i a t e d w i t h degraded p l a n t performance; no rating

or

Much o f the i n f o r m a t i o n r e q u i r e d t o r e a s o n about the PLFs i s c a r r i e d from the Data E n t r y and Major U n i t P r o c e s s E v a l u a t i o n modules. U s i n g an e s s e n t i a l l y f o r w a r d - c h a i n i n g i n f e r e n c e mechanism, the system uses i n f o r m a t i o n a l r e a d y a v a i l a b l e from t h e s e modules t o complete a p r e l i m i n a r y assessment o f each PLF. The i n i t i a l assessment c o l l e c t s and a n a l y z e s i n f o r m a t i o n t o c o n c l u d e whether a f a c t o r a d v e r s e l y


9.

BERKMANETAL.

affects plant points :


performance.

This

131

e v a l u a t i o n has two p o s s i b l e end

a)

C i t e the f a c t o r as a Performance L i m i t i n g F a c t o r

b)

C i t e the f a c t o r as "No R a t i n g " (does n o t l i m i t p l a n t performance)

A l l f a c t o r s t h a t have been c i t e d as PLFs a r e t h e n f u r t h e r e v a l u a t e d t o a s s e s s the n a t u r e and s e v e r i t y o f t h e i r impact on p l a n t performance. U s i n g i n f o r m a t i o n a v a i l a b l e w i t h i n i t s knowledge base, POTW EXPERT recommends a c l a s s i f i c a t i o n ( C l a s s Α, Β, o r C) f o r c i t e d PLFs. I n i t s c u r r e n t v e r s i o n , POTW EXPERT g e n e r a t e s a recommended c l a s s i f i c a t i o n f o r a p p r o x i m a t e l y h a l f o f a l l PLFs ( t h o s e r e l a t e d t o p l a n t d e s i g n and o p e r a t i o n ) ; t h e u s e r i s r e q u e s t e d t o make t h i s c l a s s i f i c a t i o n f o r t h e r e m a i n i n g c i t e d PLFs ( r e l a t e d t o p l a n t a d m i n i s t r a t i o n and maintenance) . The u s e r a l s o h a s t h e o p t i o n t o m a n u a l l y o v e r r i d e t h e s y s t e m - g e n e r a t e d c l a s s i f i c a t i o n o f any PLF. " E x p l a i n " t e x t i s a v a i l a b l e f o r each c i t e d f a c t o r t o a s s i s t the u s e r i n making o r r e v i e w i n g a c l a s s i f i c a t i o n . Output from t h i s module c o n s i s t s o f a r a n k e d l i s t i n g o f t h e Performance L i m i t i n g F a c t o r s . POTW EXPERT does n o t r a n k PLFs w i t h i n each C l a s s , b u t g e n e r a t e s a r e p o r t l i s t i n g PLFs by C l a s s and p r o v i d i n g the i n f o r m a t i o n t h a t r e s u l t e d i n each c l a s s i f i c a t i o n . Report Generation.

R e p o r t s g e n e r a t e d by POTW EXPERT i n c l u d e :

1.

C l a s s i f i c a t i o n o f the POTW a c c o r d i n g t o i t s u n i t p r o c e s s c a p a c i t y and c a p a b i l i t y t o meet e f f l u e n t q u a l i t y g o a l s . This report i n c l u d e s i n f o r m a t i o n on each major u n i t and the o v e r a l l r a t i n g o f the p l a n t .

2.

Ranked l i s t i n g o f Performance L i m i t i n g F a c t o r s . groups PLFs by C l a s s , and r e p o r t s on the r e a s o n i n g i n each c l a s s i f i c a t i o n .

Knowledge

This report that resulted

Representation

POTW EXPERT'S knowledge base i s r e p r e s e n t e d

i n two p r i m a r y s t r u c t u r e s :

1.

I n the M a j o r U n i t P r o c e s s E v a l u a t i o n module, i n f o r m a t i o n about p l a n t d e s i g n and o p e r a t i n g c h a r a c t e r i s t i c s i s s t o r e d i n a hierarchy of frame-like classes. The l o g i c f o r g a t h e r i n g t h i s i n f o r m a t i o n i s c o n t r o l l e d by a s t r u c t u r e o f ALEX demons and variables.

2.

I n t h e E v a l u a t i o n o f Performance L i m i t i n g F a c t o r s module, knowledge about the PLFs i s m a i n t a i n e d by a s t r u c t u r e o f demons and v a r i a b l e s coded i n ALEX.

Frames. I n d e s i g n i n g and i m p l e m e n t i n g t h e M a j o r U n i t P r o c e s s E v a l u a t i o n , we needed t o address t h e f a c t t h a t most POTWs s h a r e a common b a s i c l a y o u t , b u t d i f f e r i n a l a r g e number o f d e s i g n and process d e t a i l s . To e f f i c i e n t l y r e q u e s t , h a n d l e , and p r o c e s s i n f o r m a t i o n about the major u n i t p r o c e s s e s , we r e q u i r e d a s t r u c t u r e


132

E X P E R T SYSTEMS F O R E N V I R O N M E N T A L APPLICATIONS

t h a t r e c o g n i z e d t h e b a s i c s i m i l a r i t i e s between a l l POTWs, and t h e i n f o r m a t i o n common t o a l l major u n i t p r o c e s s a n a l y s e s , b u t p r o v i d e d the f l e x i b i l i t y t o h a n d l e t h e l a r g e number o f s p e c i f i c p r o c e s s t y p e s and d e s i g n d e t a i l s r e p r e s e n t e d i n the POTW p o p u l a t i o n . S m a l l t a l k ' s o b j e c t - o r i e n t e d system o f c l a s s e s a l l o w e d us t o a c h i e v e t h e s e ends. S m a l l t a l k ' s o b j e c t - o r i e n t e d paradigm a l l o w s d e v e l o p e r s t o d e s i g n systems t h a t model human r e a s o n i n g and language i n terms o f o b j e c t s and a c t i o n s t a k e n on o b j e c t s . As a n a l y t i c a l t h i n k e r s , humans u s u a l l y c l a s s i f y knowledge h i e r a r c h i c a l l y , b r e a k i n g problems down i n t o more e a s i l y r e s o l v e d subproblems. S m a l l t a l k mimics t h i s p r o c e s s by c l a s s i f y i n g i n f o r m a t i o n i n t o a h i e r a r c h y o f c l a s s e s with related characteristics. A t each l e v e l i n a h i e r a r c h y , a c l a s s s t o r e s i n f o r m a t i o n common t o a l l c l a s s e s deeper i n the h i e r a r c h y ( F i g u r e 3) . S u c c e e d i n g l e v e l s s t o r e more s p e c i f i c i n f o r m a t i o n p a r t i c u l a r t o a unique p l a n t c o n f i g u r a t i o n o r p r o c e s s type; a t t h e bottom o f t h e h i e r a r c h y a r e c l a s s e s that s t o r e i n f o r m a t i o n r e l a t e d t o the s p e c i f i c types o f machinery o p e r a t i n g o r t h e s p e c i f i c d e t a i l s o f p r o c e s s o p e r a t i o n s . For example, a l l POTW EXPERT c o n s u l t a t i o n s a c c e s s a t o p - l e v e l c l a s s c a l l e d "CPE," w h i c h h o l d s v e r y g e n e r a l i n f o r m a t i o n about t h e p l a n t and t h e p a r t i c u l a r CPE b e i n g performed. The n e x t l e v e l c l a s s i s "SuspendedGrowthFacility," a subclass o f "CPE," w h i c h h a n d l e s i n f o r m a t i o n common t o a l l suspended growth POTWs. S u c c e e d i n g l e v e l s h a n d l e i n f o r m a t i o n on s p e c i f i c u n i t p r o c e s s e s o f the POTW and s p e c i f i c d e s i g n and equipment c h a r a c t e r i s t i c s o f t h e p l a n t . This hierarchical class s t r u c t u r e was a l s o c r i t i c a l to i m p l e m e n t a t i o n o f an e f f i c i e n t d a t a i n p u t system f o r POTW EXPERT, and t o e f f i c i e n t p r o c e s s i n g throughout t h e system. Preliminary plant d e s i g n i n f o r m a t i o n i n p u t by t h e u s e r i d e n t i f i e s t o t h e system those frames w h i c h w i l l be a c t i v e d u r i n g a system c o n s u l t a t i o n . The d a t a e n t r y module then r e q u e s t s o n l y i n f o r m a t i o n r e q u i r e d t o complete t h e s e frames. I n t u r n , once a unique frame p a t h has been d e f i n e d f o r each major u n i t p r o c e s s d u r i n g an a n a l y s i s , t h e Major U n i t P r o c e s s E v a l u a t i o n and E v a l u a t i o n o f Performance L i m i t i n g F a c t o r s need r e f e r o n l y t o a t o p - l e v e l frame t o a c c e s s a l l g e n e r a l and s p e c i f i c information concerning that process. Demons and V a r i a b l e s . ALEX p r o v i d e s a t h r e e - t i e r e d knowledge r e p r e s e n t a t i o n s t r u c t u r e o f c o n t e x t s , demons, and v a r i a b l e s . C o n t e x t s are t o p - l e v e l s t r u c t u r e s t h a t i s o l a t e i n d i v i d u a l major a r e a s o f t h e problem under analysis. Demons a r e t h e c e n t r a l knowledge r e p r e s e n t a t i o n s t r u c t u r e ; they are e s s e n t i a l l y frame-based i n f o r m a t i o n s t o r a g e nodes w i t h s l o t s b o t h t o h o l d i n f o r m a t i o n on t h e c o n t e n t o f the demon and t o r e f l e c t the impact o f one o r more v a r i a b l e s on t h e s t a t u s o f t h e demon. V a r i a b l e s may h o l d u s e r - i n p u t , d e f a u l t , o r calculated information. CONTEXTS -- The l a r g e r problem o f e v a l u a t i n g POTW Performance L i m i t i n g Factors i s divided i n t o contexts. Contexts define the s k e l e t o n o f an e x p e r t system implemented i n ALEX; they c o r r e s p o n d t o r e l a t i v e l y i s o l a t e d s e c t i o n s o f the problem under i n v e s t i g a t i o n , i n our c a s e , t o t h e major e v a l u a t i o n a r e a s o f t h e POTW performance analysis. A h i e r a r c h y o f c o n t e x t s can be d e f i n e d , so t h a t t h i s t o p l e v e l a r c h i t e c t u r e c a n be s u b d i v i d e d i n t o a number o f s u b l e v e l s . I n POTW EXPERT, t h e t o p l e v e l c o n t e x t s a r e system managers, w h i c h


Hushon; Expert Systems for Environmental Applications ACS Symposium Series; American Chemical Society: Washington, DC, 1990. Subclass

RECTANGULAR

CIRCULAR

Subclass

CIII.ORINATION

SLUDGE HANDLING SYSTEM

CIRCULAR WITH FLOW EQUALIZATION

Subclass

Subclass

Subclass

F i g u r e 3. S m a l l t a l k ' s h i e r a r c h i c a l system o f c l a s s e s and s u b c l a s s e s as implemented i n POTW EXPERT.

RECTANGULAR WITH FLOW EQUALIZATION

SECONDARY CURIFIER

AERATION BASIN

PRIMARY CLARIFIER

Subclass

Subclass

Subclass

Subclass

SUSPENDED GROWTH

Subclass

134

E X P E R T SYSTEMS F O R E N V I R O N M E N T A L APPLICATIONS

determine w h i c h o f t h e most g e n e r a l system f u n c t i o n s w i l l be o p e r a t e d d u r i n g a s e s s i o n ( e . g . , d a t a e n t r y , major u n i t p r o c e s s e v a l u a t i o n , i d e n t i f i c a t i o n and p r i o r i t i z a t i o n o f PLFs, r e p o r t g e n e r a t i o n ) . Below t h e s e , a second l e v e l o f c o n t e x t s d e f i n e s t h e f o u r f u n c t i o n a l a r e a s examined d u r i n g o p e r a t i o n o f POTW EXPERT -- a e r a t o r , secondary c l a r i f i e r , s l u d g e h a n d l i n g , and Performance L i m i t i n g F a c t o r s . Each o f t h e s e c o n t e x t s , i n t u r n , may p r e s i d e over a t h i r d l e v e l o f c o n t e x t s , each d e f i n i n g a s p e c i f i c c l a s s i f i c a t i o n o f i n f o r m a t i o n t o be examined d u r i n g the c o u r s e o f a system c o n s u l t a t i o n . F o r example, the "Performance L i m i t i n g F a c t o r " c o n t e x t c o n t r o l s i n v e s t i g a t i o n o f a l l PLFs r e l a t e d t o t h e p l a n t by managing a number o f demons ( e x p l a i n e d below) , each a s s i g n e d t o a s i n g l e PLF. Each o f t h e s e demons, i n t u r n , t r a n s f e r s c o n t r o l t o a P L F - s p e c i f i c c o n t e x t t h a t manages t h e i n v e s t i g a t i o n o f a s i n g l e PLF by r e s p o n d i n g t o and a c t i n g on i n f o r m a t i o n accumulated i n a d d i t i o n a l demon(s) a s s o c i a t e d w i t h t h e context. DEMONS - - Demons a r e t h e c e n t r a l knowledge r e p r e s e n t a t i o n s t r u c t u r e i n an ALEX e x p e r t system and a r e one o f t h e a c t u a l r e p o s i t o r i e s o f knowledge. I n t h e S m a l l t a l k v e r n a c u l a r , t h e demon i s an o b j e c t t h a t has a f a i r l y l a r g e number o f i n s t a n c e v a r i a b l e s . A demon c o r r e s p o n d s t o each o f t h e a r e a s i n w h i c h a cause o f a POTW performance problem may be i s o l a t e d ; i n POTW EXPERT, a t l e a s t one demon has been d e f i n e d f o r each o f t h e 66 p o t e n t i a l Performance L i m i t i n g F a c t o r s i d e n t i f i e d by P r o c e s s A p p l i c a t i o n s . Three i n s t a n c e v a r i a b l e s a s s o c i a t e d w i t h each demon a r e i t s "initial belief," "current belief," and "minimum threshold" (Figure 4). I n i t i a l b e l i e f i s a developer-defined d e f a u l t . A t the b e g i n n i n g o f an ALEX c o n s u l t a t i o n , c u r r e n t b e l i e f e q u a l s i n i t i a l b e l i e f ; c u r r e n t b e l i e f changes as v a r i a b l e s r e l a t e d t o t h e demon a r e r e s o l v e d . The minimum t h r e s h o l d d e f i n e s t h e minimum l e v e l o f c u r r e n t b e l i e f t h a t must be o b t a i n e d i n o r d e r f o r a c t i o n s a s s o c i a t e d w i t h t h e demon t o be p r o c e s s e d . Each demon accumulates e v i d e n c e t h a t i t s a s s o c i a t e d PLF i s o r i s not a f a c t o r t h a t l i m i t s p l a n t performance. This evidence i s r e p r e s e n t e d by t h e demon's l e v e l o f c u r r e n t b e l i e f , w h i c h i s d e t e r m i n e d by t h e e f f e c t o f t h e i n d i v i d u a l v a r i a b l e s r e l a t e d t o t h e demon. Many demons may "observe" the same v a r i a b l e , b u t each demon w i l l have a d i s t i n c t r e a c t i o n t o t h e v a l u e o f t h e v a r i a b l e . F o r example, r e s o l u t i o n o f a v a r i a b l e which i n c r e a s e s t h e l e v e l o f b e l i e f i n one demon c a n s i m u l t a n e o u s l y decrease t h e l e v e l o f b e l i e f i n one o r any number o f o t h e r demons. A c r i t i c a l d e s i g n component o f an ALEX e x p e r t system, t h e r e f o r e , i s t h e d e f i n i t i o n o f w h i c h v a r i a b l e s w i l l be o b s e r v e d by each demon, and d e t e r m i n a t i o n o f t h e impact each v a r i a b l e w i l l have on the b e l i e f o f each a s s o c i a t e d demon. Once a demon a c q u i r e s c o n t r o l o f a system c o n s u l t a t i o n , i n v e s t i g a t i o n o f v a r i a b l e s r e l a t e d t o the demon c o n t i n u e s u n t i l a l l v a r i a b l e s r e l a t e d to t h a t demon have been e v a l u a t e d . A t t h e end o f t h e c o n s u l t a t i o n , the f i n a l l e v e l o f b e l i e f o f t h e demons a l s o d e f i n e s t h e system's c o n c l u s i o n s -- w i t h POTW EXPERT, t h e PLF demons' f i n a l l e v e l s o f c u r r e n t b e l i e f determine whether o r n o t each PLF i s j u d g e d t o be a cause o f degraded p l a n t performance. VARIABLES -- I n d i v i d u a l p i e c e s o f i n f o r m a t i o n i n an ALEX knowledge base a r e s t o r e d i n v a r i a b l e s . V a r i a b l e s may be e i t h e r c o n d i t i o n a l (True, F a l s e , Unknown), m u l t i p l e c h o i c e , o r n u m e r i c a l .


9.

BERKMAN E T A L .


135

Figure 4. A L E X demons' current level of belief changes during system consultation, triggering action if threshold belief is exceeded.


136

EXPERT SYSTEMS FOR ENVIRONMENTAL APPLICATIONS

V a r i a b l e s may be r e s o l v e d e i t h e r by u s i n g a default value, i n t e r a c t i v e l y r e q u e s t i n g u s e r i n p u t , by c o n s u l t i n g a d a t a b a s e , o r computing a v a l u e from o t h e r v a r i a b l e s . V a r i a b l e s a r e r e l a t e d t o one or more demons. The d e v e l o p e r d e f i n e s w h i c h demons w i l l watch each v a r i a b l e , and t h e impact w h i c h t h e r e s o l v e d v a r i a b l e w i l l have on each w a t c h i n g demon; f o r example, a v a r i a b l e r e s o l v e d as " F i l t e r R a r e l y C l e a n e d " might s i m u l t a n e o u s l y i n c r e a s e t h e b e l i e f o f a demon w a t c h i n g f o r problems i n p l a n t o p e r a t i o n and d e c r e a s e t h e b e l i e f o f a demon w a t c h i n g f o r problems w i t h f i l t e r c a p a c i t y . A v a r i a b l e a f f e c t s the l e v e l o f b e l i e f o f a g i v e n demon t h r o u g h a s e r i e s o f " w e i g h t s . " A d i f f e r e n t weight i s attached t o each p o s s i b l e r e s o l u t i o n o f a variable. A w e i g h t o f one w i l l l e a v e a demon's b e l i e f level u n a f f e c t e d ; a w e i g h t g r e a t e r t h a n one w i l l i n c r e a s e a demon's b e l i e f , w h i l e a w e i g h t l e s s than one w i l l cause a demon's b e l i e f t o d e c r e a s e . Each s e t o f w e i g h t s d e f i n e s the impact o f one r e s o l v e d v a r i a b l e on one demon; r e s o l u t i o n o f a s i n g l e v a r i a b l e c a n a f f e c t a number o f demons i n d i f f e r e n t ways because independent s e t s o f w e i g h t s d e f i n e a l l demon-variable r e l a t i o n s h i p s . Inference

Mechanism

A l t h o u g h ALEX's i n f e r e n c e engine does n o t f i t n e a t l y i n t o a r u l e - b a s e d paradigm, POTW EXPERT'S mode o f r e a s o n i n g c a n be d e s c r i b e d as a c o m b i n a t i o n o f backward and f o r w a r d c h a i n i n g . One o f t h e d e f i n i n g c h a r a c t e r i s t i c s o f t h e CPE/CCP methodology i s t h a t i t i n v e s t i g a t e s a l l 66 o f t h e Performance L i m i t i n g F a c t o r s . That i s , POTW EXPERT does n o t employ backward c h a i n i n g i n f e r e n c e t o r e a s o n from d e t a i l e d i n f o r m a t i o n on p l a n t d e s i g n and o p e r a t i o n back t o t h e one o r few f a c t o r s t h a t a r e the p r i m a r y causes o f degraded POTW performance. I n o r d e r t o a c h i e v e a d e f i n i t i v e c a t e g o r i z a t i o n o f t h e impact o f each PLF, POTW EXPERT a c t i v e l y s o l i c i t s u s e r i n f o r m a t i o n on each f a c t o r ; t h i s p r o c e s s i s e s s e n t i a l l y forward chaining. P r o c e s s A p p l i c a t i o n s has found t h i s problem-solving methodology t o be i m p o r t a n t f o r two r e a s o n s : (1) s y s t e m a t i c i n v e s t i g a t i o n o f a l l PLFs o f t e n d i s c l o s e s i m p a c t s on POTW performance t h a t would n o t be d i s c e r n e d b y s i m p l y r e a s o n i n g backward from symptoms t o causes; (2) i n f o r m a t i o n on a s p e c t s o f POTW o p e r a t i o n t h a t a r e f u n c t i o n i n g w e l l i s as i m p o r t a n t as i n f o r m a t i o n on t h e d i r e c t causes o f poor performance ( e . g . , i n a s s u r i n g o p e r a t o r s t h a t p r o c e s s c a p a c i t y i s s u f f i c i e n t o r t h a t maintenance p r o c e d u r e s a r e adequate t o s u s t a i n d e s i r e d p l a n t performance). A f t e r completion o f Data E n t r y and t h e M a j o r U n i t P r o c e s s E v a l u a t i o n , POTW EXPERT has accumulated a l a r g e body o f e v i d e n c e , s t o r e d i n v a r i a b l e s , r e l a t i n g t o t h e Performance L i m i t i n g F a c t o r s . POTW EXPERT uses t h i s i n f o r m a t i o n t o complete a p r e l i m i n a r y assessment and c l a s s i f i c a t i o n o f the PLFs; t h i s i s e s s e n t i a l l y a f o r w a r d c h a i n i n g p r o c e s s , as d e t a i l e d d e s i g n and o p e r a t i n g i n f o r m a t i o n i s e v a l u a t e d t o i d e n t i f y each PLF as a c a n d i d a t e f o r f u r t h e r i n v e s t i g a t i o n ( t h e PLF i s p o t e n t i a l l y C l a s s Α, Β, o r C) o r t o e x c l u d e i t from f u r t h e r c o n s i d e r a t i o n (the PLF r e c e i v e s "No R a t i n g " ) . A f t e r t h i s p r e l i m i n a r y assessment i s completed, POTW EXPERT f o l l o w s a f o r w a r d chaining paradigm t o complete i t s i n v e s t i g a t i o n o f each u n r e s o l v e d PLF. I n v e s t i g a t i o n c o n t i n u e s u n t i l t h e system has enough e v i d e n c e t o make a d e f i n i t i v e c l a s s i f i c a t i o n o f t h e PLF.


9.

BERKMANETAL.

Diagnosing Performance IJmiting Factors

137

Each ALEX demon "watches" one o r any number o f v a r i a b l e s . R e s o l u t i o n o f v a r i a b l e s a t t a c h e d t o the demon a f f e c t s t h e l e v e l o f " b e l i e f " t h a t t h e demon i s r e l a t e d t o poor POTW performance. Analogous t o an e s t i m a t e o f p r o b a b i l i t y , b e l i e f may t a k e a v a l u e between z e r o and one. V a r i a b l e r e s o l u t i o n a f f e c t s a demon's b e l i e f t h r o u g h a system o f w e i g h t s ; each demon h o l d s a l i s t i n g o f t h e v a r i a b l e s i t watches, and o f the w e i g h t s a t t a c h e d t o each p o s s i b l e r e s o l u t i o n o f these v a r i a b l e s . Weights g r e a t e r t h a n one i n c r e a s e a demon's b e l i e f , w h i l e w e i g h t s l e s s t h a n one d e c r e a s e t h e demons's belief. When a v a r i a b l e i s r e s o l v e d , i t b r o a d c a s t s i t s r e s o l u t i o n throughout the ALEX e x p e r t system. Each w a t c h i n g demon n o t e s t h a t the v a r i a b l e has been r e s o l v e d , a t t a c h e s the a p p r o p r i a t e w e i g h t , and recalculates i t s belief. Backward c h a i n i n g i n f e r e n c i n g i n POTW EXPERT p r o c e e d s upon c o m p l e t i o n o f Data E n t r y and the M a j o r U n i t P r o c e s s E v a l u a t i o n . A l a r g e number o f v a r i a b l e s have been r e s o l v e d a t t h i s p o i n t ( e i t h e r by u s e r i n p u t o r by c a l c u l a t i o n s completed i n the M a j o r U n i t P r o c e s s E v a l u a t i o n ) , and POTW EXPERT uses these v a r i a b l e s t o complete as much r e a s o n i n g about each o f the 66 PLFs as i t can. F o r some number o f PLFs, t h i s p r o c e s s a l l o w s a d e f i n i t i v e c l a s s i f i c a t i o n a c c o r d i n g t o t h e i r impact on POTW performance, and i n v e s t i g a t i o n o f t h e s e demons terminates. I f a demon cannot be d e f i n i t i v e l y c l a s s i f i e d a t t h i s p o i n t , however, i t s b e l i e f w i l l be such t h a t ALEX w i l l f o l l o w a f o r w a r d c h a i n i n g paradigm t o s o l i c i t a d d i t i o n a l i n f o r m a t i o n ( i . e . , a t t e m p t t o r e s o l v e a d d i t i o n a l v a r i a b l e s watched b y the demon) u n t i l a d e f i n i t i v e c l a s s i f i c a t i o n can be made. example: A e r a t i o n B a s i n D e s i g n Performance L i m i t i n g F a c t o r . A e r a t i o n B a s i n D e s i g n p r o v i d e s a v e r y s t r a i g h t f o r w a r d example o f POTW EXPERT'S use o f ALEX demons and v a r i a b l e s t o i n f e r e n c e about PLFs. T h i s PLF makes the f o l l o w i n g assessment: Does the t y p e , s i z e , shape, o r l o c a t i o n o f the a e r a t o r h i n d e r i t s a b i l i t y t o a d e q u a t e l y t r e a t the sewage and p r o v i d e f o r stable operation? T h i s PLF i s r e p r e s e n t e d i n POTW EXPERT b y a c o n t e x t c o n t a i n i n g two demons t h a t l o o k f o r f a u l t s i n the a e r a t o r . B o t h demons watch the same v a r i a b l e , A e r a t i o n B a s i n T y p e , o u t p u t from t h e M a j o r U n i t P r o c e s s E v a l u a t i o n ; t h i s v a r i a b l e , i n t u r n r e p r e s e n t s a summary o f e v i d e n c e on adequacy o f the t y p e , s i z e ( i . e . , t o t a l oxygen t r a n s f e r c a p a c i t y ) , shape, and l o c a t i o n o f the a e r a t o r t o h a n d l e l o a d s p l a c e d upon i t . One demon ( A e r a t i o n B F a c t o r ) watches f o r a Type 2 a e r a t o r c l a s s i f i c a t i o n (AerationBasinType-2; a e r a t o r m a r g i n a l l y capable o f h a n d l i n g i n f l u e n t sewage), and one demon ( A e r a t i o n A F a c t o r ) watches f o r a Type 3 a e r a t o r c l a s s i f i c a t i o n (AerationBasinType-3; aerator inadequate t o h a n d l e i n f l u e n t sewage). I f AerationBasinType equals 2, t h e n the b e l i e f l e v e l o f the demon A e r a t i o n B F a c t o r i n c r e a s e s , and the b e l i e f o f A e r a t i o n A F a c t o r s i m u l t a n e o u s l y d e c r e a s e s ; a e r a t i o n b a s i n d e s i g n i s c l a s s i f i e d as a C l a s s Β Performance L i m i t i n g F a c t o r . I f AerationBasinType e q u a l s 3, however, t h e n t h e b e l i e f l e v e l o f A e r a t i o n B F a c t o r decreases and the b e l i e f o f A e r a t i o n A F a c t o r i n c r e a s e s ; a e r a t i o n b a s i n d e s i g n i s c l a s s i f i e d as a C l a s s A PLF. I f A e r a t i o n B a s i n T y p e e q u a l s 1 ( a e r a t o r c a p a c i t y more t h a n adequate t o


E X P E R T SYSTEMS F O R ENVIRONMENTAL APPLICATIONS

138 h a n d l e sewage AerationAFactor b a s i n d e s i g n PLF and i s n o t c i t e d

loads), then the b e l i e f level o f b o t h demons and A e r a t i o n B F a c t o r remains low, and t h e a e r a t i o n i s a s s i g n e d a c l a s s i f i c a t i o n o f "NR." , ("No R a t i n g " ) , as a f a c t o r p o t e n t i a l l y l i m i t i n g p l a n t performance.

Q u a l i t y Assurance The Q u a l i t y A s s u r a n c e (QA) phase has been an i n t e g r a t e d p a r t o f t h e system development p r o c e s s . The QA phase i s d e s i g n e d t o v e r i f y t h a t the system reliably reflects t h e d e s i g n s p e c i f i c a t i o n s and methodology. T h i s a n a l y s i s has been performed on an ongoing b a s i s by t h e system d e v e l o p e r s and a Q u a l i t y Assurance i n d i v i d u a l , and t h r o u g h f o r m a l , s t r u c t u r e d r e v i e w s by the domain e x p e r t . The QA phase i s a l s o d e s i g n e d t o v a l i d a t e t h e r e s u l t s and t h e r e a s o n i n g o f t h e system. V a l i d a t i o n has been performed a g a i n s t t e s t c a s e s d e s i g n e d t o e x e r c i s e t h e system's c r i t i c a l areas o f a n a l y s i s and r e a s o n i n g , and a g a i n s t a c t u a l case d a t a o b t a i n e d d u r i n g two a l l - d a y workshops i n v o l v i n g a t o t a l o f f o r t y - t h r e e wastewater p r o f e s s i o n a l s . F o l l o w u p w i t h many o f these i n d i v i d u a l s has p r o v i d e d a d d i t i o n a l i n p u t t o t h e v a l i d a t i o n process. Conclusion The POTW EXPERT system demonstrates t h a t a microcomputer-based e x p e r t system c a n e f f e c t i v e l y r e p r e s e n t a complex e v a l u a t i o n methodology, e v a l u a t e the c a p a b i l i t y o f a secondary wastewater t r e a t m e n t f a c i l i t y ' s major u n i t p r o c e s s e s , d e t e c t f a c t o r s which p o t e n t i a l l y limit performance, and c a t e g o r i z e them a c c o r d i n g t o t h e i r i n f l u e n c e on p l a n t performance. The model i s p r e s e n t e d i n a l o g i c a l and s t r u c t u r e d manner t o a l l o w wastewater p r o f e s s i o n a l s u n f a m i l i a r w i t h t h e CPE p r o c e s s t o e f f e c t i v e l y employ t h i s wastewater t r e a t m e n t methodology.

Acknowledgments Development o f POTW EXPERT has been funded by t h e U n i t e d S t a t e s E n v i r o n m e n t a l P r o t e c t i o n Agency under C o n t r a c t 68-C8-0014, Work Assignment No. 0-01. The c o n t e n t s o f t h i s a r t i c l e , however, r e f l e c t the v i e w s o f the a u t h o r s and do not n e c e s s a r i l y r e f l e c t those o f the U.S. E n v i r o n m e n t a l P r o t e c t i o n Agency. M e n t i o n o f t r a d e names, p r o d u c t s , o r s e r v i c e s i s n o t , and s h o u l d n o t be i n t e r p r e t e d as c o n v e y i n g o f f i c i a l EPA a p p r o v a l , endorsement, o r recommendation.

Literature Cited 1.

The 1986 Needs Survey. U.S. Environmental Protection Agency, Office of Municipal Pollution Control: Washington, DC, 1986.

2.

Handbook: Improving POTW Performance Using the Composite Correction Program Approach. U.S. Environmental Protection Agency, Center for Environmental Research Information: Cincinnati, OH, October 1984. RECEIVED March 8, 1990


An Expert System To Diagnose Performance Limiting Factors at

Recommend Documents