{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/29734"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/29734","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Machine Learning and Artificial Intelligence Application in Process Control","abstract":"This thesis consists of four chapters including two main contributions on the application of machine learning and artificial intelligence on process modeling and controller design. Chapter 2 will talk about applying AI to controller design. This chapter proposes and implements a novel reinforcement learning (RL)--based controller design on chemical engineering examples. To address the issue of costly and unsafe training of model-free RL-based controllers, we propose an implementable RL-based controller design that leverages offline MPC calculations, that have already developed based on a step-response model. In this method, a RL agent is trained to imitate the MPC performance. Then, the trained agent is utilized in a model-free RL framework to interact with the actual process so as to continuously learn and optimize its performance under a safe operating range of processes. This contribution is marked as the first implementable RL-based controller for practical industrial application. Chapter 3 will focus on AI applications in process modeling. As nonlinear dynamics are widely encountered and challenging to simulate, nonlinear MPC (NMPC) is recognized as a promising tool to tackle this challenge. However, the lack of a reliable nonlinear model remains a roadblock for this technique. To address this issue, we develop a novel data-driven modeling method that utilizes the nonlinear autoencoder, to result in a modeling technique where the nonlinearity in the model stems from the analysis of the measured variables. Moreover, a quadratic program (QP) based MPC is developed based on this model, by utilizing an autoencoder as a transformer between the controller and process. This work contributes as an extension of the classic Koopman operator modeling method and a remarkable linear MPC design that can outperform other NMPCs such as neural network-based MPC.","abstract_html":"This thesis consists of four chapters including two main contributions on the application of machine learning and artificial intelligence on process modeling and controller design. Chapter 2 will talk about applying AI to controller design. This chapter proposes and implements a novel reinforcement learning (RL)--based controller design on chemical engineering examples. To address the issue of costly and unsafe training of model-free RL-based controllers, we propose an implementable RL-based controller design that leverages offline MPC calculations, that have already developed based on a step-response model. In this method, a RL agent is trained to imitate the MPC performance. Then, the trained agent is utilized in a model-free RL framework to interact with the actual process so as to continuously learn and optimize its performance under a safe operating range of processes. This contribution is marked as the first implementable RL-based controller for practical industrial application. Chapter 3 will focus on AI applications in process modeling. As nonlinear dynamics are widely encountered and challenging to simulate, nonlinear MPC (NMPC) is recognized as a promising tool to tackle this challenge. However, the lack of a reliable nonlinear model remains a roadblock for this technique. To address this issue, we develop a novel data-driven modeling method that utilizes the nonlinear autoencoder, to result in a modeling technique where the nonlinearity in the model stems from the analysis of the measured variables. Moreover, a quadratic program (QP) based MPC is developed based on this model, by utilizing an autoencoder as a transformer between the controller and process. This work contributes as an extension of the classic Koopman operator modeling method and a remarkable linear MPC design that can outperform other NMPCs such as neural network-based MPC.","abstract_has_math":false,"creators":["Wang, Xiaonian"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Chemical Engineering","school":null,"contributors":[],"advisors":["Prashant, Mhaskar"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-11-18T19:36:46Z","subjects":["Process control","Machine learning","Reinforcement learning","Koopman operator","modeling","optimization"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/17386"],"render_values":[{"text":"https://doi.org/10.71548/17386","href":"https://doi.org/10.71548/17386","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/29734","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/29734","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F29734","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Prashant, Mhaskar"]},{"key":"dc:contributor.department","label":"Department","values":["Chemical Engineering"]},{"key":"dc:creator","label":"Author","values":["Wang, Xiaonian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-05-04T01:34:18Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-05-04T01:34:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Process control","Machine learning","Reinforcement learning","Koopman operator","modeling","optimization"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11375/29734","https://doi.org/10.71548/17386"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis consists of four chapters including two main contributions on the application of machine learning and artificial intelligence on process modeling and controller design. Chapter 2 will talk about applying AI to controller design. This chapter proposes and implements a novel reinforcement learning (RL)--based controller design on chemical engineering examples. To address the issue of costly and unsafe training of model-free RL-based controllers, we propose an implementable RL-based controller design that leverages offline MPC calculations, that have already developed based on a step-response model. In this method, a RL agent is trained to imitate the MPC performance. Then, the trained agent is utilized in a model-free RL framework to interact with the actual process so as to continuously learn and optimize its performance under a safe operating range of processes. This contribution is marked as the first implementable RL-based controller for practical industrial application. Chapter 3 will focus on AI applications in process modeling. As nonlinear dynamics are widely encountered and challenging to simulate, nonlinear MPC (NMPC) is recognized as a promising tool to tackle this challenge. However, the lack of a reliable nonlinear model remains a roadblock for this technique. To address this issue, we develop a novel data-driven modeling method that utilizes the nonlinear autoencoder, to result in a modeling technique where the nonlinearity in the model stems from the analysis of the measured variables. Moreover, a quadratic program (QP) based MPC is developed based on this model, by utilizing an autoencoder as a transformer between the controller and process. This work contributes as an extension of the classic Koopman operator modeling method and a remarkable linear MPC design that can outperform other NMPCs such as neural network-based MPC."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Applied Science (MASc)"]},{"key":"dc:title","label":"Title","values":["Machine Learning and Artificial Intelligence Application in Process Control"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Prashant, Mhaskar"],"dc:contributor.department":["Chemical Engineering"],"dc:creator":["Wang, Xiaonian"],"dc:date.accessioned":["2024-05-04T01:34:18Z"],"dc:date.available":["2024-05-04T01:34:18Z"],"dc:date.issued":["2024"],"dc:description.abstract":["This thesis consists of four chapters including two main contributions on the application of machine learning and artificial intelligence on process modeling and controller design. Chapter 2 will talk about applying AI to controller design. This chapter proposes and implements a novel reinforcement learning (RL)--based controller design on chemical engineering examples. To address the issue of costly and unsafe training of model-free RL-based controllers, we propose an implementable RL-based controller design that leverages offline MPC calculations, that have already developed based on a step-response model. In this method, a RL agent is trained to imitate the MPC performance. Then, the trained agent is utilized in a model-free RL framework to interact with the actual process so as to continuously learn and optimize its performance under a safe operating range of processes. This contribution is marked as the first implementable RL-based controller for practical industrial application. Chapter 3 will focus on AI applications in process modeling. As nonlinear dynamics are widely encountered and challenging to simulate, nonlinear MPC (NMPC) is recognized as a promising tool to tackle this challenge. However, the lack of a reliable nonlinear model remains a roadblock for this technique. To address this issue, we develop a novel data-driven modeling method that utilizes the nonlinear autoencoder, to result in a modeling technique where the nonlinearity in the model stems from the analysis of the measured variables. Moreover, a quadratic program (QP) based MPC is developed based on this model, by utilizing an autoencoder as a transformer between the controller and process. This work contributes as an extension of the classic Koopman operator modeling method and a remarkable linear MPC design that can outperform other NMPCs such as neural network-based MPC."],"dc:description.degree":["Master of Applied Science (MASc)"],"dc:identifier.uri":["http://hdl.handle.net/11375/29734","https://doi.org/10.71548/17386"],"dc:language.iso":["en"],"dc:subject":["Process control","Machine learning","Reinforcement learning","Koopman operator","modeling","optimization"],"dc:title":["Machine Learning and Artificial Intelligence Application in Process Control"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:36:46Z"}