Scholarlink

Purpose <p>The purpose of this research is to develop an optimized Artificial Neural Network-based Fractional-Order Proportional Integral Derivative (ANN-FOPID) controller for a sensorless Brushless Direct Current (BLDC) motor drive to achieve improved rotor speed control, enhanced regulation accuracy and reduced settling time.</p> Methods <p>The proposed controller integrates an Artificial Neural Network (ANN) with a Fractional-Order PID (FOPID) controller to identify system patterns requiring regulation and improve control performance. The controller parameters are optimally tuned using the Random Weighted Chimp Optimization (RW-CHO) algorithm, an enhanced version of the conventional Chimp Optimization Algorithm. The optimized ANN-FOPID approach is applied to a sensorless BLDC motor drive and its performance is evaluated using key dynamic response metrics.</p> Results <p>The simulation results demonstrate that the proposed ANN-FOPID controller provides superior speed regulation performance compared with existing methods. The developed model achieves a settling time of 0.36318 s, which is lower than CH (0.3634 s), WOA (0.3634 s), FF (0.3632 s), BAT (0.3637 s), PID-GWO (0.5561 s) and conventional PID (0.4247 s) controllers. The proposed method also improves rotor speed accuracy and transient response characteristics.</p> Conclusion <p>The proposed RW-CHO optimized ANN-FOPID controller effectively enhances the performance of sensorless BLDC motor drives by providing faster settling time, improved speed regulation accuracy and better dynamic response.</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 Network Based Optimization of FOPID Controller for Speed Regulation of a Sensorless BLDC Motor Drive

  • 期刊论文

  • 发表日期：

    2026年5月22日

查看全文
  • D. S. Purushothaman,
  • KR Santha

摘要

Purpose

The purpose of this research is to develop an optimized Artificial Neural Network-based Fractional-Order Proportional Integral Derivative (ANN-FOPID) controller for a sensorless Brushless Direct Current (BLDC) motor drive to achieve improved rotor speed control, enhanced regulation accuracy and reduced settling time.

Methods

The proposed controller integrates an Artificial Neural Network (ANN) with a Fractional-Order PID (FOPID) controller to identify system patterns requiring regulation and improve control performance. The controller parameters are optimally tuned using the Random Weighted Chimp Optimization (RW-CHO) algorithm, an enhanced version of the conventional Chimp Optimization Algorithm. The optimized ANN-FOPID approach is applied to a sensorless BLDC motor drive and its performance is evaluated using key dynamic response metrics.

Results

The simulation results demonstrate that the proposed ANN-FOPID controller provides superior speed regulation performance compared with existing methods. The developed model achieves a settling time of 0.36318 s, which is lower than CH (0.3634 s), WOA (0.3634 s), FF (0.3632 s), BAT (0.3637 s), PID-GWO (0.5561 s) and conventional PID (0.4247 s) controllers. The proposed method also improves rotor speed accuracy and transient response characteristics.

Conclusion

The proposed RW-CHO optimized ANN-FOPID controller effectively enhances the performance of sensorless BLDC motor drives by providing faster settling time, improved speed regulation accuracy and better dynamic response.