ABSTRACT Problems in operation of wastewater treatment processes can often be traced to a knowledge limitation at the plant level. To address this limitation, computer based decision support systems can be developed using tools and techniques from the field of knowledge based systems. Research on first generation systems developed for anaerobic digestion and activated sludge processes has shown several areas where improvement is needed before practical systems can be implemented. Several issues related to design of this type of system are discussed and technologies proposed for dealing with existing deficiencies. Progress is required in structuring knowledge in the process diagnosis and control task domain and developing a common framework to facilitate design. Systems able to use deep knowledge of processes to support diagnosis and control would enhance the robustness of knowledge based systems. Since knowledge bases are dynamic, systems should be developed which are capable of learning and adapting to process and environmental changes. Though many challenges remain, there is good reason to expect that the next generation of knowledge based systems will have considerable potential for improving the operation of wastewater treatment processes.
[1]
Lotfi A. Zadeh,et al.
Outline of a New Approach to the Analysis of Complex Systems and Decision Processes
,
1973,
IEEE Trans. Syst. Man Cybern..
[2]
K. Maeda.
AN INTELLIGENT DECISION SUPPORT SYSTEM FOR ACTIVATED SLUDGE WASTEWATER TREATMENT PROCESSES
,
1985
.
[3]
Johan de Kleer,et al.
A Qualitative Physics Based on Confluences
,
1984,
Artif. Intell..
[4]
James J. Anderson,et al.
FROM THE STANDPOINT OF AN OPERATOR — WHAT IS REALLY NEEDED IN THE AUTOMATION OF A WASTEWATER TREATMENT PLANT
,
1985
.
[5]
William P. Jones,et al.
Back Propagation
,
1987,
Principles of Artificial Neural Networks.
[6]
K. A. Loparo,et al.
Artificial intelligence, simulation, and modeling: a critical survey
,
1989
.