DEPUR: A knowledge-based tool for wastewater treatment plants

Artificial Intelligence in Engineering, 1996

The activated sludge process -the main biological technology usually applied to wastewater treatment plants (WWTP)-directly depends on live beings (microorganisms), and therefore, on unforeseen changes experimented by them. It could be possible to get a good plant operation if the supervisory control system is able to react to the changes and deviations of the system and can take the necessary actions to restore the system's performance. These decisions are often based both in Physical, Chemical, Microbiological principles (suitable to be modelled by conventional control algorithms) and in some knowledge (suitable to be modelled by Knowledge-Based Systems). But one of the key problems in Knowledge-Based control systems design is the development of an architecture able to manage efficiently the different elements of the process (integrated architecture), to learn from previous cases (specific experimental knowledge) and to acquire the domain knowledge (general expert knowledge). These problems increase when the process belongs to an ill-structured domain and is composed by several complex operational units. Therefore, an integrated and distributed AI architecture seems to be a good choice. This paper, proposes an integrated and distributed supervisory multi-level architecture for the supervision of WWTP, that overcomes some of the main troubles of classical control techniques and those of Knowledge-Based Systems applied to real world systems.

Environmental Modelling and Software, 2021

This paper proposes an Intelligent Decision Support (IDS) methodology based on the integration of data-driven and model-driven techniques for control, supervision and decision support on environmental systems. Design stage of control and decision support tools for environmental systems tend to be somehow ad-hoc regarding to the nature of the processes involved. Hence, an automated approach is proposed here for the sake of scalability to different types and configurations of environmental systems, and the methodology has been designed in a general fashion to allow scalability to further types of systems. The interoperation of a data-driven technique-Case-Based Reasoning (CBR)-and a model-driven technique-Rule-Based Reasoning (RBR)-is considered in this work. The proposed hybrid scheme provides complementarity and supervised redundancy in the setpoint generation for the process controllers and actuators, increasing the reliability of the Intelligent Process Control System (IPCS), which is the core component of the IDS methodology. A Decision module selects which reasoning approach to use-i.e. CBR or RBRdepending on a metric quantifying the confidence in the CBR solution. Furthermore, the IDS methodology is flexible and dynamic enough to be able to cope with the dynamic evolution of environmental systems, learning from its relevant experienced situations. The approach presented has been implemented in a real facility within the ambit of a local water administration in the area of Barcelona.