To tackle the time and batchwise uncertainty involved in nonlinear batch process, this paper proposes a deep reinforcement learning (DRL) based ILC scheme via Koopman operator. Using the Koopman operator, the original nonlinear system is reformulated into a high-dimensional linear space form. Then, a DRL agent with neural network is introduced into the 2D ILC framework to compensate for non-repetitive uncertainty. ; Meanwhile, the convergence conditions of the proposed ILC scheme are analyzed with a proof through the linear matrix inequality. The proposed method is subsequently applied to a continuous stirring tank reactor (CSTR), and the output of the highdimensional linear model is found to be almost identical to that of the original nonlinear model, with an output error of less than 5%. ; In contrast to the linearized ILC near the equilibrium point, the control performance of the ILC under the high-dimensional model based on Koopman operator is conspicuously augmented. Eventually, the utilisation of deep reinforcement learning to address non-repetitive uncertainty and model mismatch significantly enhances the control performance in comparison to dynamic iterative linearisation and PD-type classical ILC approach.
artykuł zamieszczony w: "Journal of Process Control", Vol. 148
10.1016/j.jprocont.2025.103402
Biblioteka Uniwersytetu Zielonogórskiego
27 mar 2026
27 mar 2026
0
https://zbc.uz.zgora.pl/repozytorium/publication/105888
Tao, Xinyue Tao, Hongfeng Gao, Luyuan Paszke, Wojciech (1975- ) Rogers, Eric
Maniarski, Robert Paszke, Wojciech (1975- ) Hao, Shoulin Tao, Hongfeng
Maniarski, Robert Paszke, Wojciech (1975- ) Tao, Hongfeng Hao, Shoulin
Zhuang, Zhihe Tao, Hongfeng Chen, Yiyang Stojanovic, Vladimir Paszke, Wojciech (1975- )
Zhuang, Zhihe Tao, Hongfeng Chen, Yiyang Stojanovic, Vladimir Paszke, Wojciech (1975- )
Wang, Rui Zhuang, Zhihe Tao, Hongfeng Paszke, Wojciech (1975- ) Stojanovic, Vladimir
Zhuang, Zhihe González, Rodrigo A. Tao, Hongfeng Paszke, Wojciech (1975- ) Oomen, Tom
Maniarski, Robert Paszke, Wojciech (1975- ) Rogers, Eric Tao, Hongfeng