Artificial neural network to estimate deterministic indices in control loop performance monitoring

In many industrial processes, the control systems are the most critical components. Evaluate performance and robustness of a control loops is an important task to maintain the health of a control system and an efficiency in the process. In the area of Control-Loop Performance Monitoring (CPM), there are two groups of indices to evaluate the performance of the control loops: stochastic and deterministic. Using stochastic indices, a control engineer can calculate the performance indices of a control loop with the data in normal operation and a minimum knowledge of the process; but the problem is that to do a performance analysis is so hard, due it is necessary an advanced knowledge about the interpretation. Instead, an interpretation or analysis of deterministic indices is simpler; however, the problem with this approach is that an invasive monitoring of the plant is required to calculate the indices. In this paper, it is proposed to use an Artificial Neural Network to estimate deterministic indices, considering as input the stochastic indices and some process information, taking advantage of the fact that data collection for stochastic indices is simpler.

• Autores: Gómez-Múnera, John A.; Díaz-Charris, Luis; Jiménez-Cabas, Javier
• Tipo de recurso: Part of book
• Fecha de publicación: 2024
• Institución: Corporación Universidad de la Costa
• Repositorio: REDICUC - Repositorio CUC
• Idioma: eng
• OAI Identifier: oai:repositorio.cuc.edu.co:11323/13486
• Acceso en línea: https://hdl.handle.net/11323/13486; https://repositorio.cuc.edu.co/
• Palabra clave: Artificial neural network; Control loop performance monitoring; Deterministic indices; Stochastic indices
• Rights: closedAccess
• License: Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)