Learning-based tuning of supervisory model predictive control for drinking water networks

• Published in: Engineering applications of artificial intelligence Vol. 26; no. 7; pp. 1741 - 1750
• Main Authors: Grosso, J.M., Ocampo-Martínez, C., Puig, V.
• Format: Journal Article Publication
• Language: English
• Published: Elsevier Ltd 01.08.2013
• Subjects: Abastament; Aigua potable; Automàtica i control; Barcelona; Control automàtic; Control systems; Drinking water; Drinking water networks; Enginyeria civil; Enginyeria hidràulica, marítima i sanitària; Enginyeria sanitària; Feedback control; Fuzzy-logic; Informàtica; Mathematical models; Model predictive control; Multilayer controller; Networks; Neural networks; Predictive control; Self-tuning; Spain; Tuning; Àrees temàtiques de la UPC; Model predictive control; Self-tuning; Fuzzy-logic; Neural networks; Multilayer controller; Drinking water networks
• ISSN: 0952-1976; 1873-6769
• DOI: 10.1016/j.engappai.2013.03.003

This paper presents a constrained Model Predictive Control (MPC) strategy enriched with soft-control techniques as neural networks and fuzzy logic, to incorporate self-tuning capabilities and reliability aspects for the management of drinking water networks (DWNs). The control system architecture consists in a multilayer controller with three hierarchical layers: learning and planning layer, supervision and adaptation layer, and feedback control layer. Results of applying the proposed approach to the Barcelona DWN show that the quasi-explicit nature of the proposed adaptive predictive controller leads to improve the computational time, especially when the complexity of the problem structure can vary while tuning the receding horizons.