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

Saved in:

Bibliographic Details
Title:	Research on health management method of marine screw compressor performance test system.
Authors:	Li, Pengcheng¹ (AUTHOR) zcbm7668118@163.com, Hu, Zhifang¹ (AUTHOR), Liu, Zhibing¹ (AUTHOR), Yang, Zhenfeng¹ (AUTHOR), Gu, Junjun² (AUTHOR)
Source:	Journal of Mechanical Science & Technology. Jun2025, Vol. 39 Issue 6, p3525-3538. 14p.
Subjects:	Compressor performance, Test systems, Fault diagnosis, Screw compressors, Autoencoders
Abstract:	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. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Mechanical Science & Technology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	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. [ABSTRACT FROM AUTHOR]
ISSN:	1738494X
DOI:	10.1007/s12206-025-0544-3