Aiming at the problem that the performance of the stage multi-axis synchronous system cannot meet the time limit of the control task due to the degradation of the actuators, and the existing maintenance strategy is difficult to reach the optimization, this paper proposes a reinforcement learning-based predictive maintenance strategy for the stage multi-axis synchronous system. Firstly, reinforcement learning is introduced in a cascaded manner, and constructing a control architecture with capabilities for lifespan prediction and autonomous maintenance, which operates with different sampling rates. Secondly, focusing on the intervening maintenance strategy and the influence of multi-source uncertainty on the actuator degradation process, based on the algorithms of Kalman filtering, Expectation-Maximum, and Rauch-Tung-Striebel smoothing, by the real-time perception and estimation of actuator degradation state, and a daptive update of degradation model, the prediction accuracy of the remaining life of the multi-axis synchronous system is ensured. Combined with the real-time perception, deviation of remaining life prediction, and the actuator degradation state, the objective function of a Q-learning algorithm is constructed. The optimal adjustment of maintenance control is carried out through trials and errors to obtain the maximum life extension reward and realize intelligent optimization maintenance of the stage multi-axis synchronous system. Finally, the effectiveness of the proposed method is verified by simulation experiments of the stage multi-axis synchronous control system, improving the system maintenance efficiency.
Q-learning算法中超参数包括学习速率,折扣系数,贪婪搜索速率,分别设置为,,,奖励函数中的半正定矩阵 S 、 R 、 P 初始值分别设置为、、, 迭代次数.对比实验DMC的控制参数与文献[12]相同,具体参数包括:预测步长为10,控制步长,误差约束矩阵的初值设置为, 控制约束矩阵的初值设置为.
CHRISTIANF. Safety requirements for stage machinery control systems and the characteristics and applications of axis control technology[J]. Entertainment Technology,2012(2):1-4.(in Chinese).
ZHIH, WANGQ, JINY L,et al .Stage machinery technology,craft,application series talk: diversity and development trend of stage machinery and equipment[J].Entertainment Technology,2021(6):29-33.(in Chinese)
ZHOUD H, WEIM H, SIX S. A survey on anomaly detection,life prediction and maintenance decision for industrial processes[J].Acta Automatica Sinica, 2013, 39(6): 711-722.(in Chinese)
[7]
YANJ H, MENGY, LUL,et al .Industrial big data in an industry 4.0 environment:challenges,schemes,and applications for predictive maintenance[J].IEEE Access,2017,5:23484-23491.
[8]
SELCUKS. Predictive maintenance,its implementation and latest trends[J]. Proceedings of the Institution of Mechanical Engineers,Part B:Journal of Engineering Manufacture, 2017,231(9):1670-1679.
LUN Y, CHENC, JIANGB,et al .Latest progress on maintenance strategy of complex system:from condition-based maintenance to predictive maintenance[J]. Acta Automatica Sinica,2021,47(1):1-17.(in Chinese)
[11]
SALAZARJ C, WEBERP, NEJJARIF,et al. System reliability aware Model Predictive Control framework[J].Reliability Engineering & System Safety,2017,167:663-672.
[12]
BOUGACHAO, VARNIERC, ZERHOUNIN .Review of post-prognostics decision-making in prognostics and health management[J].International Journal of Prognostics and Health Management,2021, 11(2): 1-31.
[13]
LANGERONY, GRALLA, BARROSA .Actuator health prognosis for designing LQR control in feedback systems[J].Chemical Engineering Transactions (CET Journal),2013,33:979-984.
[14]
SANCHEZH, ESCOBETT, PUIGV,et al .Health-aware model predictive control of wind turbines using fatigue prognosis[J].IFAC-PapersOnLine,2015,48(21):1363-1368.
[15]
LANGERONY, GRALLA, BARROSA .A modeling framework for deteriorating control system and predictive maintenance of actuators[J].Reliability Engineering & System Safety,2015,140:22-36.
LIW, YANW J, MAOH J .Research on life prediction and extension method of multi-axis synchronous control system[J].Control and Decision,2023,38(9): 2587-2596.(in Chinese)
SHENF Y, LIW, JIANGD N .Life prediction and self-maintenance method of quad-rotor unmanned aerial vehicle[J].Journal of Jilin University (Engineering and Technology Edition),2023,53(3): 841-852.(in Chinese)
[20]
SUTTONR S, BARTOA G .Reinforcement learning:an introduction[J].IEEE Transactions on Neural Networks, 1998, 9(5): 1054.
JHAM S, WEBERP, THEILLIOLD,et al .A reinforcement learning approach to health aware control strategy[C]//2019 27th Mediterranean Conference on Control and Automation (MED).July 1-4,2019,Akko,Israel:IEEE,2019:171-176.
LIT M, SIX S, LIUX,et al. Data-model interactive remaining useful life prediction technologies for stochastic degrading devices with big data[J]. Acta Automatica Sinica,2022,48(9):2119-2141.(in Chinese)
[26]
KHANS, YAIRIT .A review on the application of deep learning in system health management[J].Mechanical Systems and Signal Processing,2018,107: 241-265.
[27]
SIX S, RENZ Q, HUX X,et al .A novel degradation modeling and prognostic framework for closed-loop systems with degrading actuator[J].IEEE Transactions on Industrial Electronics,2020,67(11): 9635-9647.
ZHENGJ F, HUC H, SIX S,et al .Remaining useful life prognostic for the stochastic degradation device subject to imperfect maintenance[J]. Acta Electronica Sinica,2017,45(7):1740-1749.(in Chinese)
YEY H, PENGF, HUANGY K .Overview of multi-motor synchronous motion control technology[J].Transactions of China Electrotechnical Society,2021,36(14):2922-2935.(in Chinese)
LUC G, WEIZ Q, QIAOH X,et al .Prediction of durability life of reinforced concrete under underground corrosion environment based on Wiener random process[J]. Journal of Hunan University (Natural Sciences), 2021,48(7): 119-128.(in Chinese)
SIX S, HUC H .Data-driven remaining useful life prediction theory and applications for equipment[M]. Beijing:National Defense Industry Press,2016:60-72.(in Chinese)