Adaptive PID controller tuning via deep reinforcement learning
Systems and methods are provided for using a Deep Reinforcement Learning (DRL) agent to provide adaptive tuning of process controllers, such as Proportional-Integral-Derivative (PID) controllers. The agent can monitor process controller performance, and if unsatisfactory, can attempt to improve it b...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Badgwell, Thomas A Subrahmanya, Niranjan A Kovalski, Michael H Liu, Wei D Liu, Kuang-Hung |
| description | Systems and methods are provided for using a Deep Reinforcement Learning (DRL) agent to provide adaptive tuning of process controllers, such as Proportional-Integral-Derivative (PID) controllers. The agent can monitor process controller performance, and if unsatisfactory, can attempt to improve it by making incremental changes to the tuning parameters for the process controller. The effect of a tuning change can then be observed by the agent and used to update the agent's process controller tuning policy. It has been unexpectedly discovered that providing adaptive tuning based on incremental changes in tuning parameters, as opposed to making changes independent of current values of the tuning parameters, can provide enhanced or improved control over a controlled variable of a process. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US10915073B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US10915073B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US10915073B23</originalsourceid><addsrcrecordid>eNrjZLBzTEksKMksS1UI8HRRSM7PKynKz8lJLVIoKc3LzEtXKMtMVEhJTS1QKErNzEvLL0pOzU3NK1HISU0sAsnzMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JL40GBDA0tDUwNzYycjY2LUAABPKTCw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Adaptive PID controller tuning via deep reinforcement learning</title><source>esp@cenet</source><creator>Badgwell, Thomas A ; Subrahmanya, Niranjan A ; Kovalski, Michael H ; Liu, Wei D ; Liu, Kuang-Hung</creator><creatorcontrib>Badgwell, Thomas A ; Subrahmanya, Niranjan A ; Kovalski, Michael H ; Liu, Wei D ; Liu, Kuang-Hung</creatorcontrib><description>Systems and methods are provided for using a Deep Reinforcement Learning (DRL) agent to provide adaptive tuning of process controllers, such as Proportional-Integral-Derivative (PID) controllers. The agent can monitor process controller performance, and if unsatisfactory, can attempt to improve it by making incremental changes to the tuning parameters for the process controller. The effect of a tuning change can then be observed by the agent and used to update the agent's process controller tuning policy. It has been unexpectedly discovered that providing adaptive tuning based on incremental changes in tuning parameters, as opposed to making changes independent of current values of the tuning parameters, can provide enhanced or improved control over a controlled variable of a process.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; CONTROL OR REGULATING SYSTEMS IN GENERAL ; CONTROLLING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS ; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS ; PHYSICS ; REGULATING</subject><creationdate>2021</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210209&DB=EPODOC&CC=US&NR=10915073B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25555,76308</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210209&DB=EPODOC&CC=US&NR=10915073B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Badgwell, Thomas A</creatorcontrib><creatorcontrib>Subrahmanya, Niranjan A</creatorcontrib><creatorcontrib>Kovalski, Michael H</creatorcontrib><creatorcontrib>Liu, Wei D</creatorcontrib><creatorcontrib>Liu, Kuang-Hung</creatorcontrib><title>Adaptive PID controller tuning via deep reinforcement learning</title><description>Systems and methods are provided for using a Deep Reinforcement Learning (DRL) agent to provide adaptive tuning of process controllers, such as Proportional-Integral-Derivative (PID) controllers. The agent can monitor process controller performance, and if unsatisfactory, can attempt to improve it by making incremental changes to the tuning parameters for the process controller. The effect of a tuning change can then be observed by the agent and used to update the agent's process controller tuning policy. It has been unexpectedly discovered that providing adaptive tuning based on incremental changes in tuning parameters, as opposed to making changes independent of current values of the tuning parameters, can provide enhanced or improved control over a controlled variable of a process.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>CONTROL OR REGULATING SYSTEMS IN GENERAL</subject><subject>CONTROLLING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>FUNCTIONAL ELEMENTS OF SUCH SYSTEMS</subject><subject>MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS</subject><subject>PHYSICS</subject><subject>REGULATING</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLBzTEksKMksS1UI8HRRSM7PKynKz8lJLVIoKc3LzEtXKMtMVEhJTS1QKErNzEvLL0pOzU3NK1HISU0sAsnzMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JL40GBDA0tDUwNzYycjY2LUAABPKTCw</recordid><startdate>20210209</startdate><enddate>20210209</enddate><creator>Badgwell, Thomas A</creator><creator>Subrahmanya, Niranjan A</creator><creator>Kovalski, Michael H</creator><creator>Liu, Wei D</creator><creator>Liu, Kuang-Hung</creator><scope>EVB</scope></search><sort><creationdate>20210209</creationdate><title>Adaptive PID controller tuning via deep reinforcement learning</title><author>Badgwell, Thomas A ; Subrahmanya, Niranjan A ; Kovalski, Michael H ; Liu, Wei D ; Liu, Kuang-Hung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US10915073B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>CONTROL OR REGULATING SYSTEMS IN GENERAL</topic><topic>CONTROLLING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>FUNCTIONAL ELEMENTS OF SUCH SYSTEMS</topic><topic>MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS</topic><topic>PHYSICS</topic><topic>REGULATING</topic><toplevel>online_resources</toplevel><creatorcontrib>Badgwell, Thomas A</creatorcontrib><creatorcontrib>Subrahmanya, Niranjan A</creatorcontrib><creatorcontrib>Kovalski, Michael H</creatorcontrib><creatorcontrib>Liu, Wei D</creatorcontrib><creatorcontrib>Liu, Kuang-Hung</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Badgwell, Thomas A</au><au>Subrahmanya, Niranjan A</au><au>Kovalski, Michael H</au><au>Liu, Wei D</au><au>Liu, Kuang-Hung</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Adaptive PID controller tuning via deep reinforcement learning</title><date>2021-02-09</date><risdate>2021</risdate><abstract>Systems and methods are provided for using a Deep Reinforcement Learning (DRL) agent to provide adaptive tuning of process controllers, such as Proportional-Integral-Derivative (PID) controllers. The agent can monitor process controller performance, and if unsatisfactory, can attempt to improve it by making incremental changes to the tuning parameters for the process controller. The effect of a tuning change can then be observed by the agent and used to update the agent's process controller tuning policy. It has been unexpectedly discovered that providing adaptive tuning based on incremental changes in tuning parameters, as opposed to making changes independent of current values of the tuning parameters, can provide enhanced or improved control over a controlled variable of a process.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US10915073B2 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING CONTROL OR REGULATING SYSTEMS IN GENERAL CONTROLLING COUNTING ELECTRIC DIGITAL DATA PROCESSING FUNCTIONAL ELEMENTS OF SUCH SYSTEMS MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS PHYSICS REGULATING |
| title | Adaptive PID controller tuning via deep reinforcement learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T18%3A44%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Badgwell,%20Thomas%20A&rft.date=2021-02-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS10915073B2%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |