Recursive Terminal Sliding-Mode Control Method for Nonlinear System Based on Double Hidden Layer Fuzzy Emotional Recurrent Neural Network

Jia, Chao; Kong, Deding; Du, Liang

doi:10.1109/access.2022.3220800

Cited by 9 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most systems such as robots and spacecraft are second-order nonlinear systems. Hence we take the following form as the model [26]. The goal of control is to design a control law u to make the system trajectory reach the desired trajectory.…”

Section: B Problem Formulationmentioning

confidence: 99%

Tunable Predefined Time Nonsingular Terminal Sliding Mode Control Based on Neural Network for Nonlinear Systems

Jia,

Liu

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel predefined time nonsingular terminal sliding mode control (TSMC) based on radial basis function neural network (RBFNN) for nonlinear systems. Firstly, a new lemma of tunable predefined time stability (PTS) is proposed, where the introduction of an adjustable parameter can adjust the stability time of the system and makes the design of the controller more flexible. Secondly, based on the proposed lemma, a new control method is proposed, which not only guarantees the PTS of the system, but also solves the singularity problem of the traditional TSMC and the problem of unknown model information. Finally, through comparative simulation, it is verified that the proposed method has good control performance. INDEX TERMSTerminal sliding mode control, Predefined time control, Neural network control, Robust nonlinear control, Nonsingular control.

show abstract

Section: B Problem Formulationmentioning

confidence: 99%

Tunable Predefined Time Nonsingular Terminal Sliding Mode Control Based on Neural Network for Nonlinear Systems

Jia,

Liu

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…where λ > 0, β ∈ (0, 1) with σ I (0) = −λ −1 σ(0) is initial value of the integral term to reduce the convergence time [19], [20], [21], [22], and [23]. Further, the derivative of the recursive terminal sliding mode control (RTSMC) is calculated as…”

Section: Proposed Control Schemementioning

confidence: 99%

“…Non-singular terminal sliding mode (NTSM) control has been developed to offer the singularity avoidance and fast convergence under environmental variations [17], [18], [19], [20]. Recently, with the development of fractional controls, the most prominent method used is fractional order sliding mode control (FSMC) which is introduced to enhance the robustness and the performance of the control systems [21], [22], [23]. Inspired by abovementioned works, we propose a novel optimal strategy for the pump systems that is composed of a recursive integral terminal sliding function and a fast nonsingular terminal sliding surface related to the cost function of the LQR.…”

Section: Introductionmentioning

confidence: 99%

Optimal Recursive Terminal Sliding-Mode Control Using Super-Twisting Algorithm for Improving High Efficiency and Reliability of Pump Systems

Nassiri,

Labbadi,

Chatri

et al. 2023

IEEE Control Syst. Lett.

View full text Add to dashboard Cite

In this letter, we propose an optimal recursive terminal sliding-mode control (ORTSMC) combined with super-twisting algorithm (STA) for a pump system under uncertainties. The main objective of the approach developed is to ensure rapid convergence of the pumping system with minimal power losses. To calculate the optimal input parameters of the pump system, a quantum particle swarm optimization algorithm (QPSO) is used. Next, we introduce a non-linear sliding variable into the cost function of the linear quadratic regulator (LQR). This proposal, along with the ORTSM manifold, aims to achieve fast convergence, dynamic stability, and minimize energy consumption. Additionally, the STA is employed to enhance performance during the reaching phase and reduce the chattering problem. The stability of the closed-loop control system is guaranteed using the Lyapunov theory. Finally, we conduct a comparative simulation analysis with two existing control schemes to demonstrate the superiority and effectiveness of our proposed control strategy.

show abstract

“…The BEL approach is gaining traction across various applications, including earthquake prediction, where emotional impact plays a significant role in understanding and preparing for seismic events [21]. Novel control strategies that integrate Brain Emotional Learning with Adaptive Model Predictive Control [22] have been developed for induction motor drives, while methods combining Recursive Terminal Sliding-Mode Control (RTSMC) with Double Hidden Layer Fuzzy Emotional Recurrent Neural Network (DHL-FERNN) have improved robustness and adaptability in controlling nonlinear systems [23]. However, emotional learning-based controllers, including the nonparametric ELBC, encounter challenges such as computational complexity and lack of robustness, especially in uncertain environments [24].…”

Section: Introductionmentioning

confidence: 99%

Bias-Boosted ELM for Knowledge Transfer in Brain Emotional Learning for Time Series Forecasting

Iamsa-At,

Horata,

Sunat

2024

IEEE Access

View full text Add to dashboard Cite

This paper presents the Bias-Boosted Extreme Learning Machine guided Brain Emotional Learning (B2ELM-BEL) model, a significant advancement in chaotic time series prediction that effectively incorporates knowledge transfer learning. Integrating traditional Brain Emotional Learning (BEL) with the novel Biased-ELM method, the B2ELM-BEL introduces a bias term into the output weights of Extreme Learning Machines (ELM). This addition enhances the model's predictive accuracy, proving particularly beneficial in configurations with a minimal number of hidden nodes. Our evaluation of the B2ELM-BEL model across various datasets, including complex chaotic time-series benchmarks and real-world scenarios, demonstrates its superior performance over several BEL models. It achieves lower mean RMSE, MAE, and SMAPE values, and exhibits enhanced generalizability and efficiency. The findings indicate that while the single hidden node variant of B2ELM-BEL is apt for simpler tasks, the multi-node version is more adept at handling challenging environments. This highlights the necessity of tailoring the model to the complexity of the specific dataset being analyzed.

show abstract

Recursive Terminal Sliding-Mode Control Method for Nonlinear System Based on Double Hidden Layer Fuzzy Emotional Recurrent Neural Network

Abstract: This work was supported by the National Natural Science Foundation of China under grants 62103298 and the Natural Science Foundation of Tianjin under grants 18JCYBJC87700; and the Training plan for young and middle-adged backbone innovative talents in colleges and universities in Tianjin.

Cited by 9 publications

References 27 publications

Tunable Predefined Time Nonsingular Terminal Sliding Mode Control Based on Neural Network for Nonlinear Systems

Tunable Predefined Time Nonsingular Terminal Sliding Mode Control Based on Neural Network for Nonlinear Systems

Optimal Recursive Terminal Sliding-Mode Control Using Super-Twisting Algorithm for Improving High Efficiency and Reliability of Pump Systems

Bias-Boosted ELM for Knowledge Transfer in Brain Emotional Learning for Time Series Forecasting

Contact Info

Product

Resources

About