Scholarlink

<p>In this paper, based on the KPCA-SVDD fault detection model, five kinds of faults in the process of compressor performance tests are detected and compared with the traditional PCA, KPCA and SVDD methods. Besides, this paper proposes to use Autoencoder for deep learning of data features and uses KPCA to calculate the kernel principal component of the processed data to establish SVM fault identification model. Five kinds of faults that occurred in the test process are identified and compared with the traditional SVM and PNN methods. The experimental results show that the health management method of the marine compressor test system fault diagnosis based on KPCA-SVDD and AE-KPCA-SVM proposed in this paper can effectively diagnose the corresponding fault causes so that the corresponding measures can be quickly adopted for troubleshooting, so as to ensure the normal and stable operation of the system.</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

Research on health management method of marine screw compressor performance test system

  • 期刊论文

  • 发表日期：

    2025年5月31日

查看全文
  • Pengcheng Li,
  • Zhifang Hu,
  • Zhibing Liu,
  • Zhenfeng Yang,
  • Junjun Gu

摘要

In this paper, based on the KPCA-SVDD fault detection model, five kinds of faults in the process of compressor performance tests are detected and compared with the traditional PCA, KPCA and SVDD methods. Besides, this paper proposes to use Autoencoder for deep learning of data features and uses KPCA to calculate the kernel principal component of the processed data to establish SVM fault identification model. Five kinds of faults that occurred in the test process are identified and compared with the traditional SVM and PNN methods. The experimental results show that the health management method of the marine compressor test system fault diagnosis based on KPCA-SVDD and AE-KPCA-SVM proposed in this paper can effectively diagnose the corresponding fault causes so that the corresponding measures can be quickly adopted for troubleshooting, so as to ensure the normal and stable operation of the system.