Scholarlink

<p>Induction motors (IMs) are widely used in industrial and automation applications, but achieving robust and high-performance control remains challenging, especially under parameter variations, external disturbances, and sensor limitations. This paper introduces a sliding mode control with radial basis function speed estimation (SMC-RBFSE) strategy to enhance the efficiency, stability, and dynamic performance of sensorless IM drives. The proposed SMC-based controller ensures strong disturbance rejection and fast dynamic response, while the radial basis function neural network eliminates traditional speed sensors by providing an adaptive, learning-based speed estimation approach, reducing reliance on complex mathematical models. To evaluate the proposed method, MATLAB/Simulink simulations and real-time experiments on an OPAL-RT platform are conducted. The results confirm that SMC-RBFSE effectively tracks reference speed, enhances dynamic response, and maintains stable flux regulation, even under parameter variations and external disturbances. Additionally, the RBF-based speed estimator demonstrates high accuracy across different operating conditions, particularly in the low-speed range, overcoming a key limitation of conventional sensorless techniques. With its ability to improve motor performance while reducing computational complexity and hardware dependencies, the proposed SMC-RBFSE strategy provides a practical and scalable solution for high-precision sensorless IM control in industrial 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

Sensorless induction motor drive featuring learning-based speed estimation and disturbance tolerance

  • 期刊论文

  • 发表日期：

    2025年11月22日

查看全文
  • Thanh-Lam Le,
  • Nguyen Quan Vinh

摘要

Induction motors (IMs) are widely used in industrial and automation applications, but achieving robust and high-performance control remains challenging, especially under parameter variations, external disturbances, and sensor limitations. This paper introduces a sliding mode control with radial basis function speed estimation (SMC-RBFSE) strategy to enhance the efficiency, stability, and dynamic performance of sensorless IM drives. The proposed SMC-based controller ensures strong disturbance rejection and fast dynamic response, while the radial basis function neural network eliminates traditional speed sensors by providing an adaptive, learning-based speed estimation approach, reducing reliance on complex mathematical models. To evaluate the proposed method, MATLAB/Simulink simulations and real-time experiments on an OPAL-RT platform are conducted. The results confirm that SMC-RBFSE effectively tracks reference speed, enhances dynamic response, and maintains stable flux regulation, even under parameter variations and external disturbances. Additionally, the RBF-based speed estimator demonstrates high accuracy across different operating conditions, particularly in the low-speed range, overcoming a key limitation of conventional sensorless techniques. With its ability to improve motor performance while reducing computational complexity and hardware dependencies, the proposed SMC-RBFSE strategy provides a practical and scalable solution for high-precision sensorless IM control in industrial applications.