<p>This research poses an important challenge in controlling nonlinear robotic systems due to uncertainty, which makes it difficult to determine the mathematical equations in the object’s model. This article proposes a method of using Wavelet Function Hybrid Controller (WFHC) to improve the precision of the robot control system. The WFHC controller is designed to adjust and learn from the system’s uncertain components automatically. The structure of the WFHC controller consists of two main subsystems: the Brain Emotional Learning (BEL) and the Cerebellar Model Articulation Control Network (CMAC). BEL and CMAC use the signed distance between the actual and sliding surfaces to process the input and overcome chattering from the SMC. The learning rules and parameters of the proposed controller are designed based on Lyapunov theory to ensure stability and global convergence of the control system. Eventually, the proposed structure is tested on a five-bar parallel robot system and compared with other control methods to evaluate the effectiveness and advantages of WFHC in actual environments. The results show that the MSE at <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42835_2025_2247_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="20" /> </InlineMediaObject> <EquationSource Format="TEX">\({\theta _A}\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42835_2025_2247_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="21" /> </InlineMediaObject> <EquationSource Format="TEX">\({\theta _B}\)</EquationSource> </InlineEquation> hows that the proposed method achieves high accuracy, especially in uncertain situations. When there is no uncertainty, the MSE of <InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42835_2025_2247_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="20" /> </InlineMediaObject> <EquationSource Format="TEX">\({\theta _A}\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq4"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42835_2025_2247_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="21" /> </InlineMediaObject> <EquationSource Format="TEX">\({\theta _B}\)</EquationSource> </InlineEquation> is 3.270e-04 and 4.43e-04, indicating stability and accuracy in the control process. However, even when there is uncertainty, the system still maintains high performance (MSE at <InlineEquation ID="IEq5"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42835_2025_2247_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="20" /> </InlineMediaObject> <EquationSource Format="TEX">\({\theta _A}\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq6"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42835_2025_2247_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="21" /> </InlineMediaObject> <EquationSource Format="TEX">\({\theta _B}\)</EquationSource> </InlineEquation> are 1.54e-03 and 9.45e-04), demonstrating the good ability of this method to deal with unpredictable factors. This research promises to open new directions of development and progress in nonlinear control while enhancing the applicability and precision of robot control systems in uncertain environments.</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

Adaptive Single Input Tracking Controller for Parallel Robot System Based on Hybrid Brain Emotion and Cerebellar Model Articulation Control Network Using Wavelet Function

  • Thanh Quyen Ngo,
  • Thanh Hai Tran,
  • Van Tho Nguyen,
  • Tong Tan Hoa Le

摘要

This research poses an important challenge in controlling nonlinear robotic systems due to uncertainty, which makes it difficult to determine the mathematical equations in the object’s model. This article proposes a method of using Wavelet Function Hybrid Controller (WFHC) to improve the precision of the robot control system. The WFHC controller is designed to adjust and learn from the system’s uncertain components automatically. The structure of the WFHC controller consists of two main subsystems: the Brain Emotional Learning (BEL) and the Cerebellar Model Articulation Control Network (CMAC). BEL and CMAC use the signed distance between the actual and sliding surfaces to process the input and overcome chattering from the SMC. The learning rules and parameters of the proposed controller are designed based on Lyapunov theory to ensure stability and global convergence of the control system. Eventually, the proposed structure is tested on a five-bar parallel robot system and compared with other control methods to evaluate the effectiveness and advantages of WFHC in actual environments. The results show that the MSE at \({\theta _A}\) and \({\theta _B}\) hows that the proposed method achieves high accuracy, especially in uncertain situations. When there is no uncertainty, the MSE of \({\theta _A}\) and \({\theta _B}\) is 3.270e-04 and 4.43e-04, indicating stability and accuracy in the control process. However, even when there is uncertainty, the system still maintains high performance (MSE at \({\theta _A}\) and \({\theta _B}\) are 1.54e-03 and 9.45e-04), demonstrating the good ability of this method to deal with unpredictable factors. This research promises to open new directions of development and progress in nonlinear control while enhancing the applicability and precision of robot control systems in uncertain environments.