Scholarlink

<p>This paper investigates the sliding mode control (SMC) of uncertain networked discrete-time singular systems (DTSSs) with unknown nonlinearity based on neural network (NN) via the dynamic event-triggered mechanism (ETM). First, a dynamic ETM is proposed to reduce communication frequency and save network resources. Also, the unknown nonlinearity is approximated by using NN, thereby removing the strict assumption on nonlinearity <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(f_{k}\)</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>f</mi> <mi>k</mi> </msub> </math></EquationSource> </InlineEquation> from the existing results results. A linear sliding mode surface (SMS) is designed for DTSSs, and a newly adaptive NN-based sliding mode controller is presented. Sufficient conditions are derived to relax constraints and guarantee that the sliding mode dynamics is bounded, and the sliding mode region (SMR) can be reached. Furthermore, a differential evolution optimization(DE) algorithm is employed to further acquire the optimized SMR. Finally, two practical examples have demonstrated the effectiveness of the proposed method by utilizing the proposed SMC law.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Neural adaptive dynamic event-triggered SMC for DTSSs with unknown nonlinearity via DE

  • 期刊论文

  • 发表日期：

    2025年12月3日

查看全文
  • Aowei Xing,
  • Zufeng Peng

摘要

This paper investigates the sliding mode control (SMC) of uncertain networked discrete-time singular systems (DTSSs) with unknown nonlinearity based on neural network (NN) via the dynamic event-triggered mechanism (ETM). First, a dynamic ETM is proposed to reduce communication frequency and save network resources. Also, the unknown nonlinearity is approximated by using NN, thereby removing the strict assumption on nonlinearity \(f_{k}\) f k from the existing results results. A linear sliding mode surface (SMS) is designed for DTSSs, and a newly adaptive NN-based sliding mode controller is presented. Sufficient conditions are derived to relax constraints and guarantee that the sliding mode dynamics is bounded, and the sliding mode region (SMR) can be reached. Furthermore, a differential evolution optimization(DE) algorithm is employed to further acquire the optimized SMR. Finally, two practical examples have demonstrated the effectiveness of the proposed method by utilizing the proposed SMC law.