Monitoramento de desempenho e ressintonia de controladores PID baseado em dados para malhas em cascata a partir de variações na referência ou na entrada de controle

• Ano de defesa: 2024
• Autor(a) principal: Pimentel, Matheus Rangel
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; BR; Mestrado em Engenharia Elétrica; Centro Tecnológico; UFES; Programa de Pós-Graduação em Engenharia Elétrica
• Palavras-chave em Português: Monitoramento de desempenho de malha de controle; Controladores PID; Sistemas de controle baseados em dados; Integral of Absolute Error (IAE); Control Loop Performance Monitoring; PID controllers; Data-driven control systems; Engenharia Elétrica
• Link de acesso: http://repositorio.ufes.br/handle/10/18174

This dissertation explores a data-driven methodology for monitoring and retuning PID controllers in cascaded control loops. The methodology uses data collected from a closed loop process to evaluate the performance of inner and outer loops. The study focuses on two approaches: monitoring based on changes in outer loop reference signal and monitoring based on changes in outer loop control input. The methodology employs an Exponentially Weighted Moving Average (EWMA) control chart using a statistic derived from the Integral of Absolute Error (IAE) to detect poor performance. If poor performance is detected, the Optimal Controller Identification (OCI) tuning method, based on prediction error, is employed to retuning the inner and outer controller gains. The monitoring and retuning steps are performed exclusively using closed-loop data, and statistical tests are performed to demonstrate that both steps were successful. The methodology is applied to a pilot plant, where the cascade control configuration is used for the level (outer) and flow (inner) loops. As shown, the proposed methodology can be applied even in the presence of very noisy signals, without assumptions about the tuning method used for the driver design. The dissertation is structured in six chapters, covering topics such as performance monitoring, data-driven driver design, a methodology proposal and its application to a pilot plant, culminating in discussion and conclusions on the topic addressed.