Microcontroller-Based Intelligent Control for Reaction Wheel Pendulums Using a Fuzzy Broad-Learning System

Chen, Bo‐Rui; Hsu, Chun‐Fei; Wu, Bing-Fei

doi:10.1109/ifuzzy55320.2022.9985220

Cited by 2 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reaction wheel is a spinning flywheel that can generate a torque when its angular momentum is changed. The dynamic equation of the reaction wheel pendulum is given as (Zhang et al, 2020;Jiang and Astolfi, 2021;Chen et al, 2022):…”

Section: Reaction Wheel Pendulummentioning

confidence: 99%

“…To investigate the effectiveness of the proposed HBRNC method, a payload scenario and a disturbance scenario are tested. A comparison among the fuzzy neural control (FNC) (Chang et al, 2018), the fuzzy broad-learning neural control (FBNC) (Chen et al, 2022), and the proposed HBRNC is made.…”

Section: Reaction Wheel Pendulummentioning

confidence: 99%

“…Although these BLS controllers outperform deep-learning neural controllers in terms of robustness and convergence speed, the sparse autoencoder in the BLS requires numerous iterations to converge to an optimal solution. To mitigate the computational burden, a fuzzy broad learning system (FBLS) was proposed, where each feature node is replaced by a set of fuzzy logic systems (Tsai et al, 2020;Han et al, 2022;Bai et al, 2022;Chen et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hermite broad-learning recurrent neural control with adaptive learning rate for nonlinear systems

Hsu,

Chen

2023

Soft Comput

View full text Add to dashboard Cite

Although conventional control systems are simple and widely used, they may not be effective for complex and uncertain systems. This study proposes a Hermite broad-learning recurrent neural network (HBRNN) to address such challenges. The HBRNN has a wide network structure and incorporates an internal feedback loop that enables fast learning and dynamic mapping. Furthermore, a Hermite broad-learning recurrent neural control (HBRNC) with the HBRNN as the main controller is proposed. All the network parameters of the HBRNN are updated online according to parameter learning laws through the gradient descent approach. To prevent network parameter overtraining of the HBRNN, an adaptive learning rate (ALR) is established using a discrete-type Lyapunov function to determine the least upper bound for the learning rate. The ALR can dynamically adjust the learning rates within specified ranges during the training process, thus achieving an appropriate balance between convergence speed and system stability. Finally, the HBRNC system with ALR is applied to a chaotic circuit and a reaction wheel pendulum, and its effectiveness is validated through simulation and experimentation.

show abstract

Section: Reaction Wheel Pendulummentioning

confidence: 99%

Section: Reaction Wheel Pendulummentioning

confidence: 99%