Fractional-Order Systems Optimal Control via Actor-Critic Reinforcement Learning and Its Validation for Chaotic MFET

Since the existence of fractional order dynamics, it is difficult to obtain an optimality equation to solve for fractional-order optimal control. In this paper, a fractional Hamilton-Jacobi-Bellman (HJB) equation based on error derivative is proposed, and a corresponding online learning algorithm is...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on automation science and engineering Ročník 22; s. 1173 - 1182
Hlavní autori: Li, Dongdong, Dong, Jiuxiang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: IEEE 2025
Predmet:
adaptive dynamic programming
Automation
Cost function
Costs
Fractional-order systems
Heuristic algorithms
neural networks
Nonlinear systems
Optimal control
reinforcement learning (RL)
Trajectory
ISSN:1545-5955, 1558-3783
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Since the existence of fractional order dynamics, it is difficult to obtain an optimality equation to solve for fractional-order optimal control. In this paper, a fractional Hamilton-Jacobi-Bellman (HJB) equation based on error derivative is proposed, and a corresponding online learning algorithm is designed. The scheme can handle the optimal tracking problem for the <inline-formula> <tex-math notation="LaTeX">0< \alpha \leq 1 </tex-math></inline-formula> order nonlinear systems. Since the traditional quadratic cost function is unbounded at infinite time and the optimal control derived from the discounted cost function fails to stabilize the system asymptotically, a cost function based on the error derivative is proposed, which can avoid these problems, and the system is not restricted to be zero equilibrium. Then, the fractional HJB equation is derived by constructing an auxiliary signal without directly using the chain rule of differentiation. The optimality, stability and convergence of its solution are proved, and actor-critic neural networks (NNs) are established to perform the RL algorithm. Finally, the algorithm is applied to a chaotic magnetic-field electromechanical transducer (MFET) system to verify the effectiveness and advantages. Note to Practitioners-In engineering, fractional-order dynamics properties are used in many practical systems such as chaotic MFET systems, chaotic arch micro-electro-mechanical systems and fractional order resonant controllers, etc. For these fractional-order systems, traditional integer-order control methods cannot be applied. Moreover, optimal performance with minimal cost/resources can be achieved through optimal control. Therefore, a intelligent control method based on reinforcement learning is proposed in this paper to realize the optimal control for fractional-order systems. The proposed method is applicable to most fractional-order systems and can achieve stable control while optimizing the objective performance and reducing energy consumption. Finally, the proposed algorithm is successfully applied to the chaotic MFET systems.
ISSN:1545-5955
1558-3783
DOI:10.1109/TASE.2024.3361213