Scholarlink

Purpose <p>There has been a lot of interest in double-stator switched reluctance motors (DSSRMs) due to their higher torque and power capabilities when compared to segmented-rotor and traditional switched reluctance motors. For industrial applications, their high torqueripple (TR) is still a significant drawback. To overcome these issues, this manuscript proposes an innovative technique for mitigating torque ripple in DSSRMs with single-tooth windings. The primary objective of the proposed technique is to minimize torque ripple, increase rated&#xa0;efficiency, and develop the overall performance of the DSSRM.&#xa0;</p> Methods <p>The proposed approach combines the Deer Hunting Optimization (DHO) and Diffractive Deep Neural Network (D2NN), which is termed as DHO-D2NN technique. The DHO algorithm is employed to optimize the parameters of the controller. The D2NN algorithm is employed to predict the performance of DSSRM with single-tooth winding. The proposed technique is evaluated and compared to other existing methods on the MATLAB platform. The proposed approach combines the Deer Hunting Optimization (DHO) and Diffractive Deep Neural Network (D2NN), which is termed as DHO-D2NN technique. The DHO algorithm is employed to optimize the parameters of the controller. The D2NN algorithm is employed to predict the performance of DSSRM with single-tooth winding. The proposed technique is evaluated and compared to other existing methods on the MATLAB platform.</p> Results <p>The proposed method displays better outcomes in all existing like Spotted Hyena Optimizer (SHO), Flower Pollination Algorithm (FPA), and Particle Swarm Optimization (PSO). The torque ripple of the proposed method is 6.3%, while the SHO, FPA, and PSO values of the existing methods are higher at 19.7%, 13.5%, and 9.6%, respectively.</p> Conclusion <p>For industrial DSSRM applications, the DHO-D2NN approach is a highly successful solution because of the notable decrease in torque ripple, which translates into smoother torque delivery, increased rated efficiency, and improved overall performance.</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

Torque Ripple Solutions for Double-Stator Switched Reluctance Motors with Single-Tooth Windings through DHO-D2NN Approach

  • 期刊论文

  • 发表日期：

    2025年12月4日

查看全文
  • R. Senthil Kumar,
  • P. Rajesh,
  • S. Vijay Shankar,
  • T. Logeswaran

摘要

Purpose

There has been a lot of interest in double-stator switched reluctance motors (DSSRMs) due to their higher torque and power capabilities when compared to segmented-rotor and traditional switched reluctance motors. For industrial applications, their high torqueripple (TR) is still a significant drawback. To overcome these issues, this manuscript proposes an innovative technique for mitigating torque ripple in DSSRMs with single-tooth windings. The primary objective of the proposed technique is to minimize torque ripple, increase rated efficiency, and develop the overall performance of the DSSRM. 

Methods

The proposed approach combines the Deer Hunting Optimization (DHO) and Diffractive Deep Neural Network (D2NN), which is termed as DHO-D2NN technique. The DHO algorithm is employed to optimize the parameters of the controller. The D2NN algorithm is employed to predict the performance of DSSRM with single-tooth winding. The proposed technique is evaluated and compared to other existing methods on the MATLAB platform. The proposed approach combines the Deer Hunting Optimization (DHO) and Diffractive Deep Neural Network (D2NN), which is termed as DHO-D2NN technique. The DHO algorithm is employed to optimize the parameters of the controller. The D2NN algorithm is employed to predict the performance of DSSRM with single-tooth winding. The proposed technique is evaluated and compared to other existing methods on the MATLAB platform.

Results

The proposed method displays better outcomes in all existing like Spotted Hyena Optimizer (SHO), Flower Pollination Algorithm (FPA), and Particle Swarm Optimization (PSO). The torque ripple of the proposed method is 6.3%, while the SHO, FPA, and PSO values of the existing methods are higher at 19.7%, 13.5%, and 9.6%, respectively.

Conclusion

For industrial DSSRM applications, the DHO-D2NN approach is a highly successful solution because of the notable decrease in torque ripple, which translates into smoother torque delivery, increased rated efficiency, and improved overall performance.