{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T22:54:12Z","timestamp":1785884052826,"version":"3.56.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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","award":["52275206"],"award-info":[{"award-number":["52275206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004912","name":"Sichuan University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004912","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115316","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:47:10Z","timestamp":1781110030000},"page":"115316","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Proximal Policy Optimization reinforcement learning-optimized Active Disturbance Rejection Control parameter tuning for adaptive disturbance suppression in Control Moment Gyroscope"],"prefix":"10.1016","volume":"181","author":[{"given":"Siyun","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuehang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialuo","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianghai","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.engappai.2026.115316_b1","doi-asserted-by":"crossref","first-page":"105","DOI":"10.2514\/2.4855","article-title":"Adaptive control of double-gimbal control-moment gyro with unbalanced rotor","volume":"25","author":"Ahmed","year":"2002","journal-title":"J. Guid. Control Dyn."},{"issue":"4","key":"10.1016\/j.engappai.2026.115316_b2","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1007\/s40194-024-01742-4","article-title":"An RBF neural network\u2013based parameter tuning for an ADRC regulator of electrode wire feed mechanism: arc welding applications","volume":"68","author":"Babes","year":"2024","journal-title":"Weld. the World"},{"issue":"5","key":"10.1016\/j.engappai.2026.115316_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e26337","article-title":"Design and performances improvement of a UWB antenna with DGS structure using a grey wolf optimization algorithm","volume":"10","author":"Bouchachi","year":"2024","journal-title":"Heliyon"},{"issue":"5","key":"10.1016\/j.engappai.2026.115316_b4","doi-asserted-by":"crossref","first-page":"3798","DOI":"10.1109\/TIE.2016.2644620","article-title":"Friction compensation based on time-delay control and internal model control for a gimbal system in magnetically suspended CMG","volume":"64","author":"Cui","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"key":"10.1016\/j.engappai.2026.115316_b5","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P., 2016. Benchmarking deep reinforcement learning for continuous control. In: Proc. 33rd International Conference on Machine Learning. pp. 1329\u20131338."},{"key":"10.1016\/j.engappai.2026.115316_b6","unstructured":"Gao, Z., 2003. Scaling and bandwidth-parameterization based controller tuning. In: Proc. American Control Conference. pp. 4989\u20134996."},{"key":"10.1016\/j.engappai.2026.115316_b7","doi-asserted-by":"crossref","unstructured":"Hamouda, N., Babes, B., Boutaghane, A., Kahla, S., Mezaache, M., 2020. Optimal tuning of PI\u03bbD\u03bc controller for PMDC motor speed control using ant colony optimization algorithm for enhancing robustness of WFSs. In: Proc. 1st International Conference on Communications, Control Systems and Signal Processing. pp. 364\u2013369. http:\/\/dx.doi.org\/10.1109\/CCSSP49278.2020.9151609.","DOI":"10.1109\/CCSSP49278.2020.9151609"},{"issue":"3","key":"10.1016\/j.engappai.2026.115316_b8","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1109\/TIE.2008.2011621","article-title":"From PID to active disturbance rejection control","volume":"56","author":"Han","year":"2009","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"1","key":"10.1016\/j.engappai.2026.115316_b9","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","volume":"32","author":"Henderson","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"6","key":"10.1016\/j.engappai.2026.115316_b10","doi-asserted-by":"crossref","DOI":"10.3390\/machines13060523","article-title":"Deep reinforcement learning-based active disturbance rejection control for trajectory tracking of autonomous ground electric vehicles","volume":"13","author":"Jin","year":"2025","journal-title":"Machines"},{"issue":"1","key":"10.1016\/j.engappai.2026.115316_b11","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1109\/TFUZZ.2023.3294928","article-title":"Fuzzy weight-based reinforcement learning for event-triggered optimal backstepping control of fractional-order nonlinear systems","volume":"32","author":"Li","year":"2024","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.engappai.2026.115316_b12","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-025-4737-8","article-title":"Adaptive optimal control of discrete-time systems by reinforcement learning: Damping coefficients-based stabilizing policy iterations","volume":"69","author":"Li","year":"2026","journal-title":"Sci. China Inf. Sci."},{"issue":"4","key":"10.1016\/j.engappai.2026.115316_b13","doi-asserted-by":"crossref","first-page":"2746","DOI":"10.1109\/TAC.2025.3631555","article-title":"Cooperative optimal output tracking for discrete-time multiagent systems: stabilizing policy iteration frameworks","volume":"71","author":"Li","year":"2026","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.engappai.2026.115316_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111485","article-title":"Improved active disturbance rejection control for electro-hydrostatic actuators via actor-critic reinforcement learning","volume":"158","author":"Li","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115316_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2024.119157","article-title":"Design and implementation of a model-following controller for autonomous surface ships based on actor\u2013critic reinforcement learning","volume":"312","author":"Li","year":"2024","journal-title":"Ocean Eng."},{"issue":"17","key":"10.1016\/j.engappai.2026.115316_b16","doi-asserted-by":"crossref","DOI":"10.3390\/math11173794","article-title":"Attitude control of UAVs with search optimization and disturbance rejection strategies","volume":"11","author":"Li","year":"2023","journal-title":"Mathematics"},{"issue":"3","key":"10.1016\/j.engappai.2026.115316_b17","doi-asserted-by":"crossref","first-page":"5745","DOI":"10.1109\/TAES.2024.3524198","article-title":"Active disturbance rejection control based on electromechanical tribo-dynamic model compensation of single-gimbal control moment gyroscope","volume":"61","author":"Liu","year":"2025","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"10.1016\/j.engappai.2026.115316_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejcon.2024.101005","article-title":"Improved current control for PMSM via an active disturbance rejection controller","volume":"78","author":"Liu","year":"2024","journal-title":"Eur. J. Control"},{"key":"10.1016\/j.engappai.2026.115316_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106475","article-title":"A fixed-time disturbance rejection control framework based on artificial intelligence for the flight environment testbed system","volume":"123","author":"Lun","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"19","key":"10.1016\/j.engappai.2026.115316_b20","doi-asserted-by":"crossref","first-page":"4496","DOI":"10.1016\/j.jsv.2013.03.034","article-title":"Dynamic modelling and observation of micro-vibrations generated by a single gimbal control moment gyro","volume":"332","author":"Luo","year":"2013","journal-title":"J. Sound Vib."},{"issue":"1","key":"10.1016\/j.engappai.2026.115316_b21","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1080\/21642583.2020.1863279","article-title":"Low-speed control of PMSM based on ADRC + FOPID","volume":"9","author":"Luo","year":"2021","journal-title":"Syst. Sci. Control. Eng."},{"key":"10.1016\/j.engappai.2026.115316_b22","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/s42401-024-00283-4","article-title":"Finite time sliding mode control for agile rigid satellite with CMG actuators using fast high-order sliding mode observer","volume":"7","author":"Nazari","year":"2024","journal-title":"Aerosp. Syst."},{"key":"10.1016\/j.engappai.2026.115316_b23","article-title":"Actor\u2013critic learning based PID control for robotic manipulators","volume":"151","author":"Nohooji","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.engappai.2026.115316_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2026.133040","article-title":"Congestion-aware platoon re-sequencing optimization for electric vehicles using deep reinforcement learning","volume":"676","author":"Peng","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2026.115316_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.rser.2026.116733","article-title":"Reinforcement learning as a control layer for electric vehicle interaction with multi-energy systems: A comprehensive review","volume":"231","author":"Rehman","year":"2026","journal-title":"Renew. Sustain. Energy Rev."},{"issue":"3","key":"10.1016\/j.engappai.2026.115316_b26","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1007\/s12555-021-0062-8","article-title":"Grey wolf optimization based active disturbance rejection control parameter tuning for ship course","volume":"20","author":"Ren","year":"2022","journal-title":"Autom. Syst."},{"key":"10.1016\/j.engappai.2026.115316_b27","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.engappai.2026.115316_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2021.107062","article-title":"Adaptive neural network-based active disturbance rejection flight control of an unmanned helicopter","volume":"119","author":"Shen","year":"2021","journal-title":"Aerosp. Sci. Technol."},{"issue":"3","key":"10.1016\/j.engappai.2026.115316_b29","doi-asserted-by":"crossref","first-page":"2947","DOI":"10.1109\/TIE.2021.3066916","article-title":"Position extraction of ultralow-speed gimbal servo system with linear hall sensors","volume":"69","author":"Shi","year":"2022","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"5","key":"10.1016\/j.engappai.2026.115316_b30","doi-asserted-by":"crossref","first-page":"3155","DOI":"10.1109\/TPWRD.2023.3266898","article-title":"Active disturbance rejection control of photovoltaic three-phase grid following inverters under uncertainty and grid voltage variations","volume":"38","author":"Singh","year":"2023","journal-title":"IEEE Trans. Power Deliv."},{"key":"10.1016\/j.engappai.2026.115316_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2025.106522","article-title":"Reinforcement learning based automatic tuning of PID controllers in multivariable grinding mill circuits","volume":"165","author":"van Niekerk","year":"2025","journal-title":"Control Eng. Pract."},{"key":"10.1016\/j.engappai.2026.115316_b32","doi-asserted-by":"crossref","DOI":"10.1007\/s42452-025-07529-6","article-title":"A systematic review of reinforcement learning-based control for microgrids: trends, challenges, and emerging algorithms","volume":"7","author":"Waghmare","year":"2025","journal-title":"Discov. Appl. Sci."},{"issue":"4","key":"10.1016\/j.engappai.2026.115316_b33","doi-asserted-by":"crossref","first-page":"4117","DOI":"10.1109\/TPEL.2019.2933613","article-title":"A new reaching law for antidisturbance sliding-mode control of PMSM speed regulation system","volume":"35","author":"Wang","year":"2020","journal-title":"IEEE Trans. Power Electron."},{"key":"10.1016\/j.engappai.2026.115316_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2026.114416","article-title":"Cognitive entropy proximal policy optimization for autonomous ship collision avoidance based on deep reinforcement learning","volume":"172","author":"Wang","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115316_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2023.113935","article-title":"Prediction and ephemeris fitting of LEO navigation satellites orbits computed at the antenna phase center","volume":"224","author":"Wang","year":"2024","journal-title":"Measurement"},{"issue":"11","key":"10.1016\/j.engappai.2026.115316_b36","doi-asserted-by":"crossref","first-page":"10957","DOI":"10.1109\/TIE.2022.3225829","article-title":"Multiscenarios parameter optimization method for active disturbance rejection control of PMSM based on deep reinforcement learning","volume":"70","author":"Wang","year":"2023","journal-title":"IEEE Trans. Ind. Electron."},{"key":"10.1016\/j.engappai.2026.115316_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2024.106200","article-title":"Design and validation of ADRC-based variable thrust control for a low-cost ethanol-oxygen rocket engine","volume":"156","author":"Xiong","year":"2025","journal-title":"Control Eng. Pract."},{"issue":"19","key":"10.1016\/j.engappai.2026.115316_b38","doi-asserted-by":"crossref","DOI":"10.3390\/app151910467","article-title":"Research on position tracking performance optimization of permanent magnet synchronous motors based on improved active disturbance rejection control","volume":"15","author":"Xu","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.engappai.2026.115316_b39","series-title":"Proc. 2024 Int. Conf. Control, Mechatronics and Automation","article-title":"Reinforcement learning-tuned active disturbance rejection controller for tracking control of a 4-dof robot manipulator","author":"Yousef","year":"2024"},{"issue":"12","key":"10.1016\/j.engappai.2026.115316_b40","doi-asserted-by":"crossref","first-page":"9410","DOI":"10.1109\/TIE.2017.2711538","article-title":"Active disturbance rejection control for the ranger neutral buoyancy vehicle: A delta operator approach","volume":"64","author":"Yuan","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"11","key":"10.1016\/j.engappai.2026.115316_b41","doi-asserted-by":"crossref","first-page":"6977","DOI":"10.1109\/TCYB.2022.3174613","article-title":"Trajectory tracking control of pneumatic servo system: a variable gain ADRC approach","volume":"53","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Cybern."},{"issue":"3","key":"10.1016\/j.engappai.2026.115316_b42","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1109\/TPEL.2012.2206610","article-title":"Nonlinear speed control for PMSM system using sliding-mode control and disturbance compensation techniques","volume":"28","author":"Zhang","year":"2013","journal-title":"IEEE Trans. Power Electron."},{"key":"10.1016\/j.engappai.2026.115316_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.113609","article-title":"Efficient surrogate-based optimization framework integrating physics-informed neural networks, deep active learning and deep reinforcement learning: Multilayer thin films case study","volume":"166","author":"Zheng","year":"2026","journal-title":"Eng. Appl. Artif. Intell."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626016003?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626016003?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T22:38:57Z","timestamp":1785883137000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626016003"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":43,"alternative-id":["S0952197626016003"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115316","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Proximal Policy Optimization reinforcement learning-optimized Active Disturbance Rejection Control parameter tuning for adaptive disturbance suppression in Control Moment Gyroscope","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115316","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":"115316"}}