Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149836039> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3149836039 endingPage "100030" @default.
- W3149836039 startingPage "100030" @default.
- W3149836039 abstract "This paper is a study of reinforcement learning (RL) as an optimal-control strategy for control of nonlinear valves. It is evaluated against the PID (proportional–integral–derivative) strategy, using a unified framework. RL is an autonomous learning mechanism that learns by interacting with its environment. It is gaining increasing attention in the world of control systems as a means of building optimal-controllers for challenging dynamic and nonlinear processes. Published RL research often uses open-source tools (Python and OpenAI Gym environments). We use MATLAB’s recently launched (R2019a) Reinforcement Learning Toolboxtexttrademark to develop the valve controller; trained using the DDPG (Deep Deterministic Policy-Gradient) algorithm and Simulink® to simulate the nonlinear valve and create the experimental test-bench for evaluation. Simulink allows industrial engineers to quickly adapt and experiment with other systems of their choice. Results indicate that the RL controller is extremely good at tracking the signal with speed and produces a lower error with respect to the reference signal. The PID, however, is better at disturbance rejection and hence provides a longer life for the valves. Successful machine learning involves tuning many hyperparameters requiring significant investment of time and efforts. We introduce “Graded Learning” as a simplified, application oriented adaptation of the more formal and algorithmic “Curriculum for Reinforcement Learning”. It is shown via experiments that it helps converge the learning task of complex non-linear real world systems. Finally, experiential learnings gained from this research are corroborated against published research." @default.
- W3149836039 created "2021-04-13" @default.
- W3149836039 creator A5074120519 @default.
- W3149836039 date "2021-06-01" @default.
- W3149836039 modified "2023-10-14" @default.
- W3149836039 title "Reinforcement learning for control of valves" @default.
- W3149836039 cites W1992526709 @default.
- W3149836039 cites W2017957151 @default.
- W3149836039 cites W2033735082 @default.
- W3149836039 cites W2064815992 @default.
- W3149836039 cites W2124280092 @default.
- W3149836039 cites W2152161277 @default.
- W3149836039 cites W2395579298 @default.
- W3149836039 cites W2610148085 @default.
- W3149836039 cites W2612149825 @default.
- W3149836039 cites W2613233762 @default.
- W3149836039 cites W2809540795 @default.
- W3149836039 cites W2897090992 @default.
- W3149836039 doi "https://doi.org/10.1016/j.mlwa.2021.100030" @default.
- W3149836039 hasPublicationYear "2021" @default.
- W3149836039 type Work @default.
- W3149836039 sameAs 3149836039 @default.
- W3149836039 citedByCount "14" @default.
- W3149836039 countsByYear W31498360392022 @default.
- W3149836039 countsByYear W31498360392023 @default.
- W3149836039 crossrefType "journal-article" @default.
- W3149836039 hasAuthorship W3149836039A5074120519 @default.
- W3149836039 hasBestOaLocation W31498360391 @default.
- W3149836039 hasConcept C111919701 @default.
- W3149836039 hasConcept C121332964 @default.
- W3149836039 hasConcept C127413603 @default.
- W3149836039 hasConcept C133731056 @default.
- W3149836039 hasConcept C154945302 @default.
- W3149836039 hasConcept C158622935 @default.
- W3149836039 hasConcept C199360897 @default.
- W3149836039 hasConcept C203479927 @default.
- W3149836039 hasConcept C2775924081 @default.
- W3149836039 hasConcept C2777655017 @default.
- W3149836039 hasConcept C41008148 @default.
- W3149836039 hasConcept C47116090 @default.
- W3149836039 hasConcept C47446073 @default.
- W3149836039 hasConcept C519991488 @default.
- W3149836039 hasConcept C536315585 @default.
- W3149836039 hasConcept C62520636 @default.
- W3149836039 hasConcept C6557445 @default.
- W3149836039 hasConcept C86803240 @default.
- W3149836039 hasConcept C97541855 @default.
- W3149836039 hasConceptScore W3149836039C111919701 @default.
- W3149836039 hasConceptScore W3149836039C121332964 @default.
- W3149836039 hasConceptScore W3149836039C127413603 @default.
- W3149836039 hasConceptScore W3149836039C133731056 @default.
- W3149836039 hasConceptScore W3149836039C154945302 @default.
- W3149836039 hasConceptScore W3149836039C158622935 @default.
- W3149836039 hasConceptScore W3149836039C199360897 @default.
- W3149836039 hasConceptScore W3149836039C203479927 @default.
- W3149836039 hasConceptScore W3149836039C2775924081 @default.
- W3149836039 hasConceptScore W3149836039C2777655017 @default.
- W3149836039 hasConceptScore W3149836039C41008148 @default.
- W3149836039 hasConceptScore W3149836039C47116090 @default.
- W3149836039 hasConceptScore W3149836039C47446073 @default.
- W3149836039 hasConceptScore W3149836039C519991488 @default.
- W3149836039 hasConceptScore W3149836039C536315585 @default.
- W3149836039 hasConceptScore W3149836039C62520636 @default.
- W3149836039 hasConceptScore W3149836039C6557445 @default.
- W3149836039 hasConceptScore W3149836039C86803240 @default.
- W3149836039 hasConceptScore W3149836039C97541855 @default.
- W3149836039 hasLocation W31498360391 @default.
- W3149836039 hasLocation W31498360392 @default.
- W3149836039 hasOpenAccess W3149836039 @default.
- W3149836039 hasPrimaryLocation W31498360391 @default.
- W3149836039 hasRelatedWork W1971360108 @default.
- W3149836039 hasRelatedWork W2002991661 @default.
- W3149836039 hasRelatedWork W2118816625 @default.
- W3149836039 hasRelatedWork W2187808779 @default.
- W3149836039 hasRelatedWork W2355593051 @default.
- W3149836039 hasRelatedWork W2358087060 @default.
- W3149836039 hasRelatedWork W2358696185 @default.
- W3149836039 hasRelatedWork W2373166766 @default.
- W3149836039 hasRelatedWork W2387486085 @default.
- W3149836039 hasRelatedWork W4206227994 @default.
- W3149836039 hasVolume "4" @default.
- W3149836039 isParatext "false" @default.
- W3149836039 isRetracted "false" @default.
- W3149836039 magId "3149836039" @default.
- W3149836039 workType "article" @default.