{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T07:16:41Z","timestamp":1783754201157,"version":"3.55.0"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Chemical Engineering"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.compchemeng.2026.109783","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:45:50Z","timestamp":1783061150000},"page":"109783","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Safe and robust control of chemical processes under disturbances using a Q-value adaptive evaluation twin delayed deep deterministic policy gradient model"],"prefix":"10.1016","volume":"214","author":[{"given":"Jiaxin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5788-2460","authenticated-orcid":false,"given":"Xiao","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuyue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-9160","authenticated-orcid":false,"given":"Yiyang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lichun","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.compchemeng.2026.109783_bib0013","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1080\/23744731.2019.1680234","article-title":"Application of deep Q-networks for model-free optimal control balancing between different HVAC systems","volume":"26","author":"Ahn","year":"2020","journal-title":"Sci. Technol. Built Environ."},{"issue":"1","key":"10.1016\/j.compchemeng.2026.109783_bib0036","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1146\/annurev-control-042920-020211","article-title":"Safe learning in robotics: From learning-based control to safe reinforcement learning","volume":"5","author":"Brunke","year":"2022","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0009","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1016\/j.psep.2024.10.116","article-title":"Application of hyperspectral band selection method based on deep reinforcement learning to low-value recyclable waste classification","volume":"192","author":"Cai","year":"2024","journal-title":"Process Saf. Environ. Prot."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108393","article-title":"Entropy-maximizing TD3-based reinforcement learning for adaptive PID control of dynamical systems","volume":"178","author":"Chowdhury","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0035","article-title":"Robust reinforcement learning for nonlinear process control with stability guarantees","author":"Cui","year":"2026","journal-title":"Digit. Chem. Eng."},{"issue":"2","key":"10.1016\/j.compchemeng.2026.109783_bib0032","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1109\/LRA.2022.3229236","article-title":"Adaptively calibrated critic estimates for deep reinforcement learning","volume":"8","author":"Dorka","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0048","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0025","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"issue":"3","key":"10.1016\/j.compchemeng.2026.109783_bib0043","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/TSMCB.2011.2170565","article-title":"Efficient model learning methods for actor\u2013critic control","volume":"42","author":"Grondman","year":"2011","journal-title":"IEEE Trans. Syst. Man Cybern. B (Cybern.)"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0030","series-title":"2020 IEEE 32nd international conference on tools with artificial intelligence (ICTAI)","first-page":"391","article-title":"Wd3: taming the estimation bias in deep reinforcement learning","author":"He","year":"2020"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0053","first-page":"1","article-title":"Root mean square error (RMSE) or mean absolute error (MAE): when to use them or not","volume":"2022","author":"Hodson","year":"2022","journal-title":"Geosci. Model Dev. Discuss."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0024","series-title":"2019 19th International Conference on Advanced Robotics (ICAR)","first-page":"362","article-title":"Deep deterministic policy gradient for navigation of mobile robots in simulated environments","author":"Jesus","year":"2019"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2021.107527","article-title":"Twin actor twin delayed deep deterministic policy gradient (TATD3) learning for batch process control","volume":"155","author":"Joshi","year":"2021","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0007","article-title":"Robustness of NMPC compared to MPC under off-nominal conditions: Application to a gas lift system","author":"Karacelik","year":"2025","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0052","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1016\/j.ins.2021.11.036","article-title":"Root mean square error or mean absolute error? Use their ratio as well","volume":"585","author":"Karunasingha","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.dche.2025.100277","article-title":"Utilizing reinforcement learning in feedback control of nonlinear processes with stability guarantees","author":"Khodaverdian","year":"2025","journal-title":"Digit. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0034","article-title":"Uniting neural network-based control and model predictive control: Application to a large-scale nonlinear process","author":"Khodaverdian","year":"2025","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0019","series-title":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","first-page":"2456","article-title":"End-to-end reinforcement learning for autonomous longitudinal control using advantage actor critic with temporal context","author":"Kuutti","year":"2019"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2021.117900","article-title":"Coordinated load frequency control of multi-area integrated energy system using multi-agent deep reinforcement learning","volume":"306","author":"Li","year":"2022","journal-title":"Appl. Energy"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0022","unstructured":"Lillicrap, T. P. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2022.108105","article-title":"A new PID controller design using differential operator for the integrating process","volume":"170","author":"Lim","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0046","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.neunet.2022.10.016","article-title":"Accelerating reinforcement learning with case-based model-assisted experience augmentation for process control","volume":"158","author":"Lin","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0011","series-title":"arXiv preprint arXiv","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0017","series-title":"arXiv preprint arXiv","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"Mnih","year":"2016"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108360","article-title":"Data driven performance monitoring and retuning using PID controllers","volume":"178","author":"Munaro","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0014","series-title":"International conference on computational data and social networks","first-page":"26","article-title":"Efficient SDN-based traffic monitoring in IoT networks with double deep Q-network","author":"Nguyen","year":"2020"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0050","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1016\/j.asoc.2014.06.037","article-title":"Control of a nonlinear liquid level system using a new artificial neural network-based reinforcement learning approach","volume":"23","author":"Noel","year":"2014","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0015","series-title":"31st International Conference on Advanced Information Networking and Applications Workshops (WAINA)","first-page":"195","article-title":"Design and implementation of a simulation system based on deep Q-network for mobile actor node control in wireless sensor and actor networks","author":"Oda","year":"2017"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0049","doi-asserted-by":"crossref","DOI":"10.1002\/aic.17658","article-title":"Integration of reinforcement learning and model predictive control to optimize semi-batch bioreactor","volume":"68","author":"Oh","year":"2022","journal-title":"AIChE J."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108232","article-title":"A practical Reinforcement Learning implementation approach for continuous process control","volume":"174","author":"Patel","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.rser.2020.110618","article-title":"Applications of reinforcement learning in energy systems","volume":"137","author":"Perera","year":"2021","journal-title":"Renew. Sustain. Energy Rev."},{"issue":"8","key":"10.1016\/j.compchemeng.2026.109783_bib0005","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1016\/j.compchemeng.2007.08.019","article-title":"PID controller tuning for desired closed-loop responses for SISO systems using impulse response","volume":"32","author":"Ramasamy","year":"2008","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0012","series-title":"arXiv preprint arXiv","article-title":"Implementing the deep q-network","author":"Roderick","year":"2017"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0044","series-title":"2021 IEEE 33rd international conference on tools with artificial intelligence (ICTAI)","first-page":"137","article-title":"Estimation error correction in deep reinforcement learning for deterministic actor-critic methods","author":"Saglam","year":"2021"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0028","series-title":"2021 18th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)","first-page":"1","article-title":"Low-level control of a quadrotor using twin delayed deep deterministic policy gradient (td3)","author":"Shehab","year":"2021"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0021","series-title":"International conference on machine learning","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"Silver","year":"2014"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0051","series-title":"2017 IEEE winter conference on applications of computer vision (WACV)","first-page":"464","article-title":"Cyclical learning rates for training neural networks","author":"Smith","year":"2017"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0016","first-page":"12","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"Sutton","year":"1999","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2025.109137","article-title":"Multi-loop PID tuning strategy based on non-iterative linear matrix inequalities","volume":"199","author":"Trica","year":"2025","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0055","doi-asserted-by":"crossref","first-page":"71422","DOI":"10.1109\/ACCESS.2020.2987387","article-title":"A Hankel matrix based reduced order model for stability analysis of hybrid power system using PSO-GSA optimized cascade PI-PD controller for automatic load frequency control","volume":"8","author":"Veerasamy","year":"2020","journal-title":"IEEE Access"},{"issue":"3","key":"10.1016\/j.compchemeng.2026.109783_bib0042","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1007\/s12555-020-0809-7","article-title":"Online actor-critic reinforcement learning control for uncertain surface vessel systems with external disturbances","volume":"20","author":"Vu","year":"2022","journal-title":"Int. J. Control Autom. Syst."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2020.115036","article-title":"Reinforcement learning for building controls: the opportunities and challenges","volume":"269","author":"Wang","year":"2020","journal-title":"Appl. Energy"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2026.109637","article-title":"AI-driven digital twin and delay-aware surrogate MPC framework for biogas production","volume":"210","author":"Wang","year":"2026","journal-title":"Comput. Chem. Eng."},{"issue":"9","key":"10.1016\/j.compchemeng.2026.109783_bib0041","doi-asserted-by":"crossref","first-page":"4969","DOI":"10.1109\/TII.2019.2894282","article-title":"Optimized adaptive nonlinear tracking control using actor\u2013critic reinforcement learning strategy","volume":"15","author":"Wen","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"5","key":"10.1016\/j.compchemeng.2026.109783_bib0038","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1109\/JSAC.2020.2980909","article-title":"Reinforcement learning-based control and networking co-design for industrial internet of things","volume":"38","author":"Xu","year":"2020","journal-title":"IEEE J. Sel. Areas Commun."},{"issue":"15","key":"10.1016\/j.compchemeng.2026.109783_bib0031","doi-asserted-by":"crossref","first-page":"4962","DOI":"10.3390\/s24154962","article-title":"End-to-end autonomous driving decision method based on improved TD3 algorithm in complex scenarios","volume":"24","author":"Xu","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2019.07.026","article-title":"Cooperative traffic signal control using multi-step return and off-policy asynchronous advantage actor-critic graph algorithm","volume":"183","author":"Yang","year":"2019","journal-title":"Knowl.-Based Syst."},{"issue":"2","key":"10.1016\/j.compchemeng.2026.109783_bib0023","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1109\/TGCN.2020.3045075","article-title":"Deep reinforcement learning-assisted energy harvesting wireless networks","volume":"5","author":"Ye","year":"2020","journal-title":"IEEE Trans. Green Commun. Netw."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2020.107133","article-title":"Reinforcement learning based optimal control of batch processes using Monte-Carlo deep deterministic policy gradient with phase segmentation","volume":"144","author":"Yoo","year":"2021","journal-title":"Comput. Chem. Eng."},{"issue":"12","key":"10.1016\/j.compchemeng.2026.109783_bib0027","doi-asserted-by":"crossref","first-page":"1244","DOI":"10.3390\/machines10121244","article-title":"Reinforcement learning control of hydraulic servo system based on TD3 algorithm","volume":"10","author":"Yuan","year":"2022","journal-title":"Machines"},{"key":"10.1016\/j.compchemeng.2026.109783_bib0037","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ins.2021.10.070","article-title":"Reinforcement learning-based control using Q-learning and gravitational search algorithm with experimental validation on a nonlinear servo system","volume":"583","author":"Zamfirache","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0010","article-title":"Supervised integrated deep deterministic policy gradient model for enhanced control of chemical processes","author":"Zhang","year":"2024","journal-title":"Chem. Eng. Sci."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0008","article-title":"Improving process safety in industrial control systems using the policy collaborative twin delayed deep deterministic policy gradient model","author":"Zhang","year":"2025","journal-title":"Process Saf. Environ. Prot."},{"key":"10.1016\/j.compchemeng.2026.109783_bib0018","doi-asserted-by":"crossref","first-page":"3093","DOI":"10.1007\/s12555-019-0278-z","article-title":"Balance control for the first-order inverted pendulum based on the advantage actor-critic algorithm","volume":"18","author":"Zheng","year":"2020","journal-title":"Int. J. Control Autom. Syst."},{"issue":"4","key":"10.1016\/j.compchemeng.2026.109783_bib0029","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.5755\/j01.itc.52.4.33125","article-title":"Design of Intelligent Controller for Aero-engine Based on TD3 Algorithm","volume":"52","author":"Zhu","year":"2023","journal-title":"Inf. Technol. Control"}],"container-title":["Computers & Chemical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S009813542600236X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S009813542600236X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T07:06:17Z","timestamp":1783753577000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S009813542600236X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":55,"alternative-id":["S009813542600236X"],"URL":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109783","relation":{},"ISSN":["0098-1354"],"issn-type":[{"value":"0098-1354","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Safe and robust control of chemical processes under disturbances using a Q-value adaptive evaluation twin delayed deep deterministic policy gradient model","name":"articletitle","label":"Article Title"},{"value":"Computers & Chemical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109783","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109783"}}