Skip to main content

DESARROLLO DE TECNICAS DE CONTROL DISTRIBUIDO INTELIGENTE BASADAS EN TEORIA DE JUEGOS

PID2019-105434RB-C31

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2019
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE SALAMANCA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Adapting WWTP performance to seasonality and climate change, Temperature-driven strategies for enhanced nitrogen removal

  • Revollar, Silvana|||0000-0001-9869-6437
  • Meneses, Montse|||0000-0002-5846-2676
  • Vilanova, Ramon|||0000-0002-8035-5199
  • Francisco, Mario|||0000-0002-6505-0936
  • Vega, Pastora|||0000-0002-3504-2273
A Temperature Driven Control Strategy that combines modifications on DO set-point, external carbon dosage and Solids Retention Time (SRT) is proposed to address the effect of seasonal and abnormal variations of temperature in the operation of Wastewater Treatment Plants. The medium-sized municipal WWTP, represented by Benchmark Simulation Model No. 2 (BSM2) that includes a Nitrogen Removal Activated Sludge Process (N-Removal ASP) with Dissolved Oxygen (DO) control has been selected as reference plant. The objective is to formulate a control strategy that improves the efficiency of the N-Removal ASP despite seasonal and unexpected variations of temperature of the influent, considering the trade-offs between temperature effects and control action effects on dynamic behavior. Simulations were carried out to evaluate the temperature and control actions effects on global average and dynamic behavior over a 30 days operation window, considering the BSM2 range from 10°C to 20 °C. A comprehensive analysis is carried out to look for potential solutions to improve performance at different temperature scenarios through the proper adjustment of DO set-points, carbon addition and sludge retention time (SRT). At low temperatures, the control actions are selected to improve N-Removal balance, since nitrification and denitrification rates are slowed producing violations of effluent quality limits in the presence of strong disturbances in influent flowrate. At high temperatures operational goals are to reduce the electricity consumption and the use of chemicals (external carbon), maintaining satisfactory performance. The Temperature Driven Control Strategy with different settings was tested considering a one year operating period. The proposed strategy address satisfactorily the seasonal and unexpected changes of temperature modelled by the annual BSM2 influent profile, attaining an appropriated trade-off between effluent quality and electricity consumption. The violations of required total Nitrogen limits are reduced up to 50 % in frequency and 33 % in length, while violations of required ammonium limits are reduced up to 36 % in frequency and 40 % in length. Annual average ammonium levels are reduced up to 19 % and annual average total Nitrogen is reduced up to 11 %. All these improvements are attained together with a slight decrease on electricity consumption. The proposed strategy is evaluated in a simulation platform, but it can be the starting point for the formulation of temperature driven advanced control strategies able to face climate change effects in the operation of for full-scale WWTPs.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Integración de la estrategia FMBPC en una estructura de control predictivo en lazo cerrado. Aplicación al control de fangos activados, Integration of the FMBPC strategy in a Closed-Loop Predictive Control structure. Application to the control of activated sludge

  • Vallejo, Pedro M.
  • Vega, Pastora
[ES] En este trabajo se aborda la integración de dos métodos o estrategias de Control Predictivo basado en Modelos, a saber: Control Predictivo basado en Modelos Borrosos (FMBPC) y Control Predictivo en Lazo Cerrado (CLP MPC). La primera de estas estrategias utiliza principios de Control Predictivo Funcional (PFC) y está enmarcada, al mismo tiempo, en el ámbito del Control Inteligente (IC). La integración tiene como principal objetivo proporcionar a la estrategia de control no lineal FMBPC un procedimiento de optimización que permita el manejo automático de restricciones en la variable de control. La solución propuesta consiste en hacer uso de una estructura complementaria de tipo CLP MPC para determinar mediante optimización, en cada instante de muestreo, los valores óptimos de un cierto término aditivo, a sumar a la ley de control FMBPC, de tal modo que se satisfagan las restricciones. El modelo de predicciones y la ley de control base necesarios para realizar los cálculos en la estructura CLP MPC son proporcionados por la estrategia FMBPC. La estrategia mixta FMBPC/CLP propuesta ha sido validada, en simulación, aplicándola al control de fangos activados en plantas de tratamiento de aguas residuales (EDAR), poniendo el foco en la imposición de restricciones a la acción de control. Los resultados obtenidos son satisfactorios, observando un buen rendimiento del algoritmo de control diseñado, al tiempo que se garantiza tanto la satisfacción de las restricciones, que era el principal objetivo, como la estabilidad del sistema en lazo cerrado., [EN] This work addresses the integration of two methods or strategies of Model-Based Predictive Control, namely: Fuzzy Model-Based Predictive Control (FMBPC) and Closed-Loop Predictive Control (CLP-MPC). The first of these strategies uses principles of Predictive Functional Control (PFC) and is framed, at the same time, in the field of Intelligent Control (IC). The main objective of the integration is to provide to the FMBPC nonlinear control strategy an optimization procedure that allows the automatic handling of constraints in the control variable. The proposed solution consists of making use of a complementary structure of the CLP-MPC type to determine by optimization, at each sampling instant, the optimal values of a certain additive term, to be added to the FMBPC control law, in such a way that they are satisfied the constraints. The prediction model and base control law necessary to perform the calculations on the CLP-MPC structure are provided by the FMBPC strategy. The proposed FMBPC/CLP mixed strategy has been validated, in simulation, applying it to the control of activated sludge processes in wastewater treatment plants (WWTP), focusing on the imposition of constraints on the control action. The results obtained are satisfactory, observing a good performance of the designed control algorithm, while guaranteeing both the satisfaction of the constraints, which was the main objective, and the stability of the closed-loop system., Este trabajo contó con el apoyo económico del Gobierno de España a través del proyecto MICINN PID2019-105434RB-C31 y de la Fundación Samuel Solórzano a través del proyecto FS / 20-2019.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Eco-Efficiency Assessment of Control Actions in Wastewater Treatment Plants

  • Revollar, Silvana|||0000-0001-9869-6437
  • Meneses, Montse|||0000-0002-5846-2676
  • Vilanova, Ramon|||0000-0002-8035-5199
  • Vega, Pastora|||0000-0002-3504-2273
  • Francisco, Mario|||0000-0002-6505-0936
This work explores the possibilities of improving the eco-efficiency of Wastewater Treatment Plants (WWTPs) introducing a plant-wide perspective in the formulation of the control strategy. Eco-efficiency goals are contemplated in the analysis of the appropriateness of control actions, considering the seasonal effects of temperature into the decision-making process. Plant-wide control strategy handles are the operation variables of the activated sludge process, the volume of the primary clarifier, and the temperature of the anaerobic digester. Performance is evaluated in terms of energy use, biogas production, effluent quality, emissions to air and soil, considering annual and bimestrial average values of indicators to capture seasonal effect of temperature. The result is a set of possible solutions, obtained from a multi-objective decision-making procedure, consisting on a sequence of control actions applied at different temporal windows that improve the eco-efficiency indicators of the plant. The results obtained when applying the different solutions make evident how the application of plant-wide control strategies is useful to improve performance indicators that represent individual goals, leading to trade-off solutions that describe WWTPs' eco-efficiency.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Intelligent Control of Wastewater Treatment Plants Based on Model-Free Deep Reinforcement Learning

  • Aponte-Rengifo, Oscar
  • Francisco, Mario|||0000-0002-6505-0936
  • Vilanova, Ramon|||0000-0002-8035-5199
  • Vega, Pastora|||0000-0002-3504-2273
  • Revollar, Silvana|||0000-0001-9869-6437
In this work, deep reinforcement learning methodology takes advantage of transfer learning methodology to achieve a reasonable trade-off between environmental impact and operating costs in the activated sludge process of Wastewater treatment plants (WWTPs). WWTPs include complex nonlinear biological processes, high uncertainty, and climatic disturbances, among others. The dynamics of complex real processes are difficult to accurately approximate by mathematical models due to the complexity of the process itself. Consequently, model-based control can fail in practical application due to the mismatch between the mathematical model and the real process. Control based on the model-free reinforcement deep learning (RL) methodology emerges as an advantageous method to arrive at suboptimal solutions without the need for mathematical models of the real process. However, convergence of the RL method to a reasonable control for complex processes is data-intensive and time-consuming. For this reason, the RL method can use the transfer learning approach to cope with this inefficient and slow data-driven learning. In fact, the transfer learning method takes advantage of what has been learned so far so that the learning process to solve a new objective does not require so much data and time. The results demonstrate that cumulatively achieving conflicting objectives can efficiently be used to approach the control of complex real processes without relying on mathematical models.