文献类型：期刊文献

英文题名：Current signal-based power frequency filtering and Clark transform for ship propulsion motor fault diagnosis

作者：Liao, Zhiqiang[1,2,3];Yan, Zhijia[1];Cai, Renchao[1];Liang, Guanlong[1];Huang, Zhende[1];Jia, Baozhu[1,2,3];Song, Xuewei[1,2,3]

机构：[1]Guangdong Ocean Univ, Naval Architecture & Shipping Coll, Zhanjiang 524088, Peoples R China;[2]Tech Res Ctr Ship Intelligence & Safety Engn Guang, Zhanjiang 524088, Peoples R China;[3]Guangdong Prov Key Lab Intelligent Equipment South, Zhanjiang 524088, Peoples R China

年份：2025

卷号：36

期号：10

外文期刊名：MEASUREMENT SCIENCE AND TECHNOLOGY

收录：SCI-EXPANDED(收录号：WOS:001589489800001)、、EI(收录号：20254119312929)、Scopus(收录号：2-s2.0-105018304430)、WOS

基金：This research was funded by National Natural Science Foundation of China (52201355, 52401418), the Program for Scientific Research Start-Up Funds of Guangdong Ocean University (060302132304, 060302132101), Zhanjiang Non-funded Science and Technology Tesearch Project (2022B01049, 2023B01046).

语种：英文

外文关键词：ship propulsion motor; current signal; power frequency filtering; Clark transform; fault diagnosis

外文摘要：To address the challenges of weak fault feature extraction and accumulated multi-source interference for ship propulsion motors under unsteady operating conditions and harsh environments, a current signal-based method based on power frequency filtering and Clark transform method is proposed. This method first uses a designed power frequency filtering technique to effectively suppress power frequency and its harmonic interference, enhancing the recognizability of fault characteristics. Subsequently, by combining the Clark transform and wavelet transform with signal dimensionality reduction characteristics, the fault features of the current signal were accurately extracted; on this basis, a SE ResNet18 network model with integrated attention mechanism is constructed, and its powerful ability to capture two-dimensional image features is utilized to ultimately establish an end-to-end fault diagnosis framework. Through two case experiments and multiple method comparisons, the results show that the diagnostic accuracy of the proposed method can reach 99.58%, -100%, which is significantly superior to existing approaches. This fully demonstrates the superiority of the method in fault diagnosis for ship propulsion motors.