Scholarlink

Purpose <p>This paper presents an innovative control strategy that integrates Radial Basis Function Neural Networks-based Adaptive Multi-Mode Input Shaping (RBF-MIS) with Active Disturbance Rejection Control (ADRC) to enhance the operational efficiency of double pendulum cranes. Overhead cranes are essential for material handling, yet they face challenges from payload oscillations that compromise precision and safety.</p> Methods <p>The proposed methodology integrates RBF-MIS with ADRC to addresses these challenges by independently regulating trolley position and cable length while dynamically adapting to varying payload characteristics.</p> Results and Conclusion <p>Experimental results demonstrate significant reductions in vibrations, with the RBF-MIS approach achieving superior performance in mitigating oscillations compared to traditional methods. The findings highlight the effectiveness of combining advanced neural network techniques with established control frameworks, offering a practical solution for improving crane operations in real-world applications.</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

Integrating Radial Basis Function Neural Networks based Adaptive Multi-Mode Input Shaping with Active Disturbance Rejection Control for Double Pendulum Crane

  • 期刊论文

  • 发表日期：

    2026年1月26日

查看全文
  • Trong Hieu Do,
  • Minh Duc Nguyen,
  • Minh Duc Duong

摘要

Purpose

This paper presents an innovative control strategy that integrates Radial Basis Function Neural Networks-based Adaptive Multi-Mode Input Shaping (RBF-MIS) with Active Disturbance Rejection Control (ADRC) to enhance the operational efficiency of double pendulum cranes. Overhead cranes are essential for material handling, yet they face challenges from payload oscillations that compromise precision and safety.

Methods

The proposed methodology integrates RBF-MIS with ADRC to addresses these challenges by independently regulating trolley position and cable length while dynamically adapting to varying payload characteristics.

Results and Conclusion

Experimental results demonstrate significant reductions in vibrations, with the RBF-MIS approach achieving superior performance in mitigating oscillations compared to traditional methods. The findings highlight the effectiveness of combining advanced neural network techniques with established control frameworks, offering a practical solution for improving crane operations in real-world applications.