Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226162222> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4226162222 endingPage "3" @default.
- W4226162222 startingPage "3" @default.
- W4226162222 abstract "Proportional-Integral-Derivative (PID) control has been the dominant control strategy in the process industry due to its simplicity in design and effectiveness in controlling a wide range of processes. However, most traditional PID tuning methods rely on trial and error for complex processes where insights about the system are limited and may not yield the optimal PID parameters. To address the issue, this work proposes an automatic PID tuning framework based on reinforcement learning (RL), particularly the deterministic policy gradient (DPG) method. Different from existing studies on using RL for PID tuning, in this work, we explicitly consider the closed-loop stability throughout the RL-based tuning process. In particular, we propose a novel episodic tuning framework that allows for an episodic closed-loop operation under selected PID parameters where the actor and critic networks are updated once at the end of each episode. To ensure the closed-loop stability during the tuning, we initialize the training with a conservative but stable baseline PID controller and the resultant reward is used as a benchmark score. A supervisor mechanism is used to monitor the running reward (e.g., tracking error) at each step in the episode. As soon as the running reward exceeds the benchmark score, the underlying controller is replaced by the baseline controller as an early correction to prevent instability. Moreover, we use layer normalization to standardize the input to each layer in actor and critic networks to overcome the issue of policy saturation at action bounds, to ensure the convergence to the optimum. The developed methods are validated through setpoint tracking experiments on a second-order plus dead-time system. Simulation results show that with our scheme, the closed-loop stability can be maintained throughout RL explorations and the explored PID parameters by the RL agent converge quickly to the optimum. Moreover, through simulation verification, the developed RL-based PID tuning method can adapt the PID parameters to changes in the process model automatically without requiring any knowledge about the underlying operating condition, in contrast to other adaptive methods such as the gain scheduling control." @default.
- W4226162222 created "2022-05-05" @default.
- W4226162222 creator A5050365865 @default.
- W4226162222 creator A5057981108 @default.
- W4226162222 creator A5085695601 @default.
- W4226162222 date "2022-01-01" @default.
- W4226162222 modified "2023-10-01" @default.
- W4226162222 title "Stability-preserving automatic tuning of PID control with reinforcement learning" @default.
- W4226162222 doi "https://doi.org/10.20517/ces.2021.15" @default.
- W4226162222 hasPublicationYear "2022" @default.
- W4226162222 type Work @default.
- W4226162222 citedByCount "1" @default.
- W4226162222 countsByYear W42261622222023 @default.
- W4226162222 crossrefType "journal-article" @default.
- W4226162222 hasAuthorship W4226162222A5050365865 @default.
- W4226162222 hasAuthorship W4226162222A5057981108 @default.
- W4226162222 hasAuthorship W4226162222A5085695601 @default.
- W4226162222 hasBestOaLocation W42261622221 @default.
- W4226162222 hasConcept C112972136 @default.
- W4226162222 hasConcept C119857082 @default.
- W4226162222 hasConcept C127413603 @default.
- W4226162222 hasConcept C13280743 @default.
- W4226162222 hasConcept C133731056 @default.
- W4226162222 hasConcept C154945302 @default.
- W4226162222 hasConcept C17744445 @default.
- W4226162222 hasConcept C183356978 @default.
- W4226162222 hasConcept C185798385 @default.
- W4226162222 hasConcept C199539241 @default.
- W4226162222 hasConcept C205649164 @default.
- W4226162222 hasConcept C2775924081 @default.
- W4226162222 hasConcept C2779110517 @default.
- W4226162222 hasConcept C41008148 @default.
- W4226162222 hasConcept C47116090 @default.
- W4226162222 hasConcept C47446073 @default.
- W4226162222 hasConcept C536315585 @default.
- W4226162222 hasConcept C97541855 @default.
- W4226162222 hasConceptScore W4226162222C112972136 @default.
- W4226162222 hasConceptScore W4226162222C119857082 @default.
- W4226162222 hasConceptScore W4226162222C127413603 @default.
- W4226162222 hasConceptScore W4226162222C13280743 @default.
- W4226162222 hasConceptScore W4226162222C133731056 @default.
- W4226162222 hasConceptScore W4226162222C154945302 @default.
- W4226162222 hasConceptScore W4226162222C17744445 @default.
- W4226162222 hasConceptScore W4226162222C183356978 @default.
- W4226162222 hasConceptScore W4226162222C185798385 @default.
- W4226162222 hasConceptScore W4226162222C199539241 @default.
- W4226162222 hasConceptScore W4226162222C205649164 @default.
- W4226162222 hasConceptScore W4226162222C2775924081 @default.
- W4226162222 hasConceptScore W4226162222C2779110517 @default.
- W4226162222 hasConceptScore W4226162222C41008148 @default.
- W4226162222 hasConceptScore W4226162222C47116090 @default.
- W4226162222 hasConceptScore W4226162222C47446073 @default.
- W4226162222 hasConceptScore W4226162222C536315585 @default.
- W4226162222 hasConceptScore W4226162222C97541855 @default.
- W4226162222 hasLocation W42261622221 @default.
- W4226162222 hasLocation W42261622222 @default.
- W4226162222 hasOpenAccess W4226162222 @default.
- W4226162222 hasPrimaryLocation W42261622221 @default.
- W4226162222 hasRelatedWork W2001862331 @default.
- W4226162222 hasRelatedWork W2024770392 @default.
- W4226162222 hasRelatedWork W2132899637 @default.
- W4226162222 hasRelatedWork W2373166766 @default.
- W4226162222 hasRelatedWork W2386513265 @default.
- W4226162222 hasRelatedWork W2772015535 @default.
- W4226162222 hasRelatedWork W3159051687 @default.
- W4226162222 hasRelatedWork W3211847530 @default.
- W4226162222 hasRelatedWork W4200476563 @default.
- W4226162222 hasRelatedWork W4318070856 @default.
- W4226162222 hasVolume "2" @default.
- W4226162222 isParatext "false" @default.
- W4226162222 isRetracted "false" @default.
- W4226162222 workType "article" @default.