{"id":"https://openalex.org/W2992650903","doi":"https://doi.org/10.1109/ccta.2019.8920472","title":"Optimization control of a fed-batch process using an improved reinforcement learning algorithm","display_name":"Optimization control of a fed-batch process using an improved reinforcement learning algorithm","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2992650903","doi":"https://doi.org/10.1109/ccta.2019.8920472","mag":"2992650903"},"language":"en","primary_location":{"id":"doi:10.1109/ccta.2019.8920472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta.2019.8920472","pdf_url":null,"source":{"id":"https://openalex.org/S4306498490","display_name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100364172","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0002-7518-4743"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["School of Engineering, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685752","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-9745-664X"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["School of Engineering, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031969180","display_name":"Bingzhang Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bingzhang Hu","raw_affiliation_strings":["School of Computing, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011037821","display_name":"Yang Long","orcid":"https://orcid.org/0000-0002-2445-6112"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Long","raw_affiliation_strings":["Department of Computer science, Duram University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer science, Duram University, Newcastle upon Tyne, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100364172"],"corresponding_institution_ids":["https://openalex.org/I84884186"],"apc_list":null,"apc_paid":null,"fwci":0.5704,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68308703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"314","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9668999910354614,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7906594276428223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6592026948928833},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6160131692886353},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.5303013324737549},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.48914340138435364},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47265613079071045},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.44634199142456055},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4099873900413513},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3622169494628906},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.35050976276397705},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33764296770095825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33134621381759644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1693040132522583}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7906594276428223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6592026948928833},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6160131692886353},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.5303013324737549},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.48914340138435364},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47265613079071045},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.44634199142456055},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4099873900413513},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3622169494628906},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35050976276397705},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33764296770095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33134621381759644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1693040132522583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccta.2019.8920472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta.2019.8920472","pdf_url":null,"source":{"id":"https://openalex.org/S4306498490","display_name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3000430873","display_name":null,"funder_award_id":"MR/S003916/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G7197601580","display_name":null,"funder_award_id":"MR/S003916/2","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1606868664","https://openalex.org/W1977440921","https://openalex.org/W2029062311","https://openalex.org/W2062859931","https://openalex.org/W2067561969","https://openalex.org/W2075079150","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2127818367","https://openalex.org/W2145952809","https://openalex.org/W2173248099","https://openalex.org/W2343442488","https://openalex.org/W2738109916","https://openalex.org/W2762085884","https://openalex.org/W2787691009","https://openalex.org/W2792636771","https://openalex.org/W2900566525","https://openalex.org/W2963262099","https://openalex.org/W2963864421","https://openalex.org/W4214717370","https://openalex.org/W6684921986","https://openalex.org/W6703271639","https://openalex.org/W6748921869","https://openalex.org/W6756278137"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Batch":[0],"processes":[1],"are":[2,17,128],"important":[3],"manufacturing":[4,9],"route":[5],"for":[6],"the":[7,82,109,119,139],"agile":[8],"of":[10,111,121,144],"high":[11],"value":[12],"added":[13],"products":[14],"and":[15,29,35,44,53,101,108,130,142,156],"they":[16,49],"typically":[18],"difficult":[19],"to":[20,23,42,56,137,151],"control":[21,43,161,165],"due":[22],"highly":[24],"non-linear":[25],"characteristic,":[26],"unknown":[27],"disturbance":[28],"model":[30],"plant":[31],"mismatches.":[32],"Neural":[33],"networks":[34],"traditional":[36],"reinforcement":[37],"learning":[38,112],"have":[39],"been":[40],"applied":[41,103,150],"optimize":[45],"batch":[46],"processes.":[47],"However,":[48],"usually":[50],"lack":[51],"robustness":[52],"accuracy":[54],"leading":[55],"unsatisfactory":[57],"performance.":[58],"To":[59],"overcome":[60],"these":[61],"problems,":[62],"this":[63],"paper":[64],"proposes":[65],"a":[66,105,131,152],"stochastic":[67],"multi-step":[68],"action":[69,77,83],"Q-learning":[70,78],"algorithm":[71,134],"(SMSA)":[72],"based":[73],"on":[74],"multiple":[75],"step":[76],"(MSA).":[79],"In":[80],"MSA,":[81,118],"space":[84],"is":[85,123,135,149],"divided":[86],"into":[87],"some":[88,95],"same":[89],"time":[90,107,126],"steps,":[91],"which":[92],"means":[93],"that":[94,124],"non-optimal":[96],"actions":[97],"will":[98],"be":[99,114],"continuously":[100],"compulsively":[102],"in":[104],"long":[106],"speed":[110],"might":[113],"slow.":[115],"Compared":[116],"with":[117],"modification":[120],"SMSA":[122],"several":[125],"steps":[127],"different":[129],"modified":[132],"greedy":[133],"used":[136],"improve":[138],"speed,":[140],"efficiency":[141],"flexibility":[143],"algorithm.":[145],"The":[146],"proposed":[147],"method":[148],"simulated":[153],"fed-batch":[154],"process":[155],"it":[157],"gives":[158],"better":[159],"optimization":[160],"performance":[162],"than":[163],"other":[164],"strategies.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}