ISCWAP: A knowledge-based system for supervising activated sludge processes

doi:10.1016/0098-1354(95)00258-8

Computers & Chemical Engineering

Volume 21, Issue 2, 20 October 1997, Pages 211-221

https://doi.org/10.1016/0098-1354(95)00258-8 Get rights and content

Abstract

A Knowledge-Based System for the on-line supervision of activated sludge processes in wastewater treatment is presented. The system performs on-line data acquisition from the sensors installed in the plant, off-line data management of results from analytical determinations in the plant laboratory, and qualitative information supplied by the supervisors of the process. All these elements are integrated in the Intelligent System for Supervision and Control of WAste water treatment Plants (ISCWAP), which includes a set of diagnosis, detection, prediction and operation rules, making the system capable to handle with several usual situations (where mathematical control can be useful) and also with some unusual situations (where quantitative and qualitative information must be considered).

References (27)

A.G. Capodaglio et al.
Sludge bulking analysis and forecasting: application of system identification and artificial neural computing technologies
Water Research
(1991)
D. Couillard et al.
Control strategy for the activated sludge process under shock loading
Water Research
(1992)
S.G. Dellepiane et al.
Model generation and model matching of medical images by a fuzzy approach
Pattern Recognition
(1992)
C.S. Fu et al.
System identification and real-time pattern recognition by neural networks for an activated sludge process
Environ. International
(1995)
K.Y. Ko et al.
Adaptive control and identification of the dissolved oxygen process
Automatica
(1982)
J. Lapointe et al.
Bioexpert an Expert System for Wastewater Treatment process diagnosis
Computer Chem. Engng
(1989)
K. Maeda
A knowledge-based system for the wastewater treatment plant
P. Serra et al.
DEPUR: a knowledge based tool for wastewater treatment plants
Engineering Applications of Artificial Intelligence
(1994)
G. Stephanopoulos et al.
Artificial Intelligence in the Development and Design of Biochemical Processes
Trends in Biotechnology
(1986)
R. Bañares-Alcántara et al.
Artificial Intelligence techniques in Chemical Engineering Process Design

M.B. Beck

Identification, Estimation and Control of Biological Wastewater Treatment Processes

J. Béjar et al.

LINNEO⁺: Herramienta para la adquisición de conocimiento y generación de reglas de clasificación en dominios poco estructurados

Li Belanche et al.

A knowledge-based system for the diagnosis of waste water treatment plants

Cited by (22)

Argumentation-based framework for industrial wastewater discharges management
2012, Engineering Applications of Artificial Intelligence
Citation Excerpt :
Several studies have been carried out to improve and increase the knowledge of WWTP operational problems related to influent characteristics (Ayesa et al., 1998; Comas et al., 2003, 2008; Henze et al., 1993; Jenkins et al., 2003). This knowledge, based on on-line and off-line data as well as on the experts' heuristics, is mainly represented by means of decision trees and/or knowledge-based flow diagrams (Cortés et al., 2003; Poch et al., 2004; Rodríguez-Roda et al., 2002; Serra et al., 1994, 1997). The knowledge is organized in a hierarchical manner: top-down descriptions of interactions between different parameters and factors used to solve a problem.
The daily operation of wastewater treatment plants (WWTPs) in unitary sewer systems of industrialized areas is of special concern. Severe problems can occur due to the characteristics of incoming flow. In order to avoid decision that leads to hazardous situations, guidelines and regulations exist. However, there are still no golden standards by which to a priori decide whether a WWTP can cope with critical discharges. Strict adherence to regulations may not always be convenient, since special circumstances may motivate operators to accept discharges that are above established thresholds or to reject discharges that comply with guidelines. Nonetheless, such decisions must be well justified. This paper proposes an argumentation-based model by which to formulate a flexible decision-making process. An example of the model application describes how experts deliberate the safety of a discharge and adapt each decision to the particular characteristics of the industrial discharge and the WWTP.
Supporting decision making in urban wastewater systems using a knowledge-based approach
2011, Environmental Modelling and Software
Citation Excerpt :
The literature describes many applications of environmental decision-support systems, particularly of the UWS domain, specifically designed to improve and increase knowledge of WWTP operational problems related to influent characteristics (Comas et al., 2003, 2008; Jenkins et al., 2003). This knowledge is often articulated by means of decision trees and if-then rules (rule-based systems) expressing the cause-effect relations for a specific problem (Cortés et al., 2003; Poch et al., 2004; Rodríguez-Roda et al., 2002; Serra et al., 1994, 1997). This type of organization tends to perform well if a few highly relevant attributes exist, but less so if many complex interactions are present, such as in the UWS domain.
The use of knowledge-based systems has been shown to be a suitable approach to support decision making in environmental systems. Capturing and managing the huge quantity of data/information that has to be considered is an intrinsic factor that makes environmental systems a sophisticated domain. Organizing this data in a naive way can impact the efficacy of any knowledge-based system. Another intrinsic factor is the variety of data sources, which can result in inconsistent, uncertain or incomplete knowledge bases when different data sources are considered. Accordingly, two central issues of a successful knowledge-based system are the organization of its knowledge base and the expressiveness of its specification language.
In this paper, we introduce a stratified framework for structuring any environmental knowledge base. We will argue that a declarative specification language, such as Answer Set Programming, is expressive enough to capture environmental knowledge bases that are inconsistent, uncertain and incomplete. We also present an automata-based approach to manage actions in knowledge-based systems. By solving a use case, specifically the diagnosis of the safety of a particular industrial wastewater discharge in an urban wastewater system, we illustrate how to represent relevant abstractions to model related complex processes. We show that by using them it is also possible to automate the diagnosis process (in the present case, for example, to diagnose problems at a wastewater treatment plant and afterward in the river) and hence support the decision-making task.
Scenario analysis for the role of sanitation infrastructures in integrated urban wastewater management
2009, Environmental Modelling and Software
Citation Excerpt :
Improvement of simulation tools: New software that can model and simulate water quality in different conditions and environments has appeared (Rauch et al., 2002; Fu et al., 2008) such as deterministic models, geographical information systems, real time control systems or knowledge-based systems. Use of Artificial Intelligence (AI) tools in the environmental scope: The AI tools enable the incorporation of expert knowledge in the decision-making processes (Serra et al., 1997; Poch et al., 2004; Denzer, 2005; Gibert et al., 2006; Nguyen et al., 2007; Evers, 2008; Makropoulos et al., 2008). There are certain pressure elements that are accelerating the change from the individual and separated management model to the integrated management paradigm:
Traditionally, the sanitation infrastructures of most of the Urban Wastewater Systems (UWSs) have been managed individually, without considering the many relationships among the sewer systems, Wastewater Treatment Plants (WWTPs) and receiving waters. The main objective of WWTP management was to comply with the emission limits, without considering the ecological state of the receiving waters. However, the European Union approved the Water Framework Directive (WFD) in 2000 that changes the conventional practice by introducing the integrated approach concept in the hydraulic infrastructure management. The same Directive also promotes the availability and use of decision support tools for water management, specifically where water resources are becoming increasingly scarce. This paper describes the work conducted in the Besòs catchment (Catalonia, NE of Spain) in order to deal with this European legislation. A study site was selected to develop an integrated model as a support tool for the UWS management. Specifically, two sewer systems, their WWTPs and a reach of the Congost River (a tributary of the Besòs River) have been modelled. The selected software to model flow and water quality were Infoworks CS, GPS-X and Infoworks RS for the sewer systems, WWTPs and stream reach, respectively. Besides these, a specific program was developed to be used as a data transfer interface between software. Once this model integration platform was built, and taking into account the expert knowledge of the managers, several management scenarios were defined including some critical events such as industrial spills, rainfall episodes, inhibition of nitrification, WWTP shutdowns, obstruction of a sewer system conduit and episodes of minimum river flow rates as well as potential control actions such as the implementation of storage tanks or the use of bypasses between sewer systems or WWTPs. All these scenarios were modelled and simulated and the results obtained were then analysed, focusing the attention on the river water quality, with the main objective being to gain relevant knowledge to deal with the tested scenarios.
Improving the nitrogen removal efficiency of an A<sup>2</sup>/O based WWTP by using an on-line Knowledge Based Expert System
2002, Water Research
The results obtained using an expert system to control an activated sludge process involving nutrient removal are reported. The study was conducted at a pilot plant using an Anaerobic/Anoxic/Oxic (A²/O) scheme for which a distributed control system was specially developed. The system allows various expert operational approaches to be developed with a view to minimize nitrogen levels in the outlet while using the minimum amount of energy. The proposed distributed control system is supervised by a Knowledge Based Expert System (KBES) constructed with G2^© (a tool for expert system development) and permits the on-line implementation of every operating strategy of the experimental system. A set of experiments involving variable loads and flow-rates was carried out. It revealed that the amount of removed nitrogen could be increased by 11% compared to the usual operating conditions. This increase resulted in a decrease in the amount of total nitrogen and ammonium nitrogen in the outlet by 49% and 64%, respectively. These improvements were achieved with little energy cost because the performance of the treatment plant was optimised using operating rules implemented in real time.
Prediction of the bulking phenomenon in wastewater treatment plants
2000, Artificial Intelligence in Engineering
The control and prediction of wastewater treatment plants poses an important goal: to avoid breaking the environmental balance by always keeping the system in stable operating conditions. It is known that qualitative information — coming from microscopic examinations and subjective remarks — has a deep influence on the activated sludge process. In particular, on the total amount of effluent suspended solids, one of the measures of overall plant performance. The search for an input–output model of this variable and the prediction of sudden increases (bulking episodes) is thus a central concern to ensure the fulfillment of current discharge limitations. Unfortunately, the strong interrelation between variables, their heterogeneity and the very high amount of missing information makes the use of traditional techniques difficult, or even impossible. Through the combined use of several methods — rough set theory and artificial neural networks, mainly — reasonable prediction models are found, which also serve to show the different importance of variables and provide insight into the process dynamics.
An expert supervisory system for a pilot WWTP
1999, Environmental Modelling and Software
This paper presents the development and implementation of a Real-Time Expert System (RTES) for the supervision and control of a wastewater treatment pilot plant (WWTPP) with biological removal of organic matter and nutrients. The hardware architecture contains different supervision levels, including two autonomous process computers (plant control and analysers control) and a PLC, being the ES the top supervisory level. The RTES has been developed using a commercial, industrially validated RTES-development software G2™ (by Gensym Corp). It actuates as the master in a supervisory setpoint control (SSC) scheme and it is based on a distributed architecture. The knowledge is organised in several agents, representing the available knowledge for every sub-process of the WWTPP. In addition to these independent agents, a supervisor agent acts as the master of the multi-agent distributed system.

View all citing articles on Scopus

View full text

ISCWAP: A knowledge-based system for supervising activated sludge processes

Abstract

Water Research

Water Research

Pattern Recognition

Environ. International

Automatica

Computer Chem. Engng

Engineering Applications of Artificial Intelligence

Trends in Biotechnology

Artificial Intelligence techniques in Chemical Engineering Process Design

Identification, Estimation and Control of Biological Wastewater Treatment Processes

LINNEO+: Herramienta para la adquisición de conocimiento y generación de reglas de clasificación en dominios poco estructurados

A knowledge-based system for the diagnosis of waste water treatment plants

LINNEO⁺: Herramienta para la adquisición de conocimiento y generación de reglas de clasificación en dominios poco estructurados