西华大学学报（自然科学版）2025，Vol.44Issue(6)：13-27,15.DOI:10.12198/j.issn.1673-159X.5125
基于机器学习的旋转机械故障识别算法的输入特征综述
A Review of Machine Learning-Based Input Features for Rotating Machinery Fault Identification
摘要
Abstract
The continuous application of machine learning theory has promoted the in-depth develop-ment of fault diagnosis.There are various types of machine learning-based fault diagnosis algorithms for ro-tating machinery with various input feature forms.In order to deeply understand the effects of various fea-ture forms,the existing research on the input feature forms of machine learning algorithms is reviewed in the light of the current research status in this field.The basic generation principles,application status,ad-vantages and disadvantages of statistical features,information entropy,time-frequency map feature para-meters and grayscale map,Gramian angular field image,spectral kurtosis map,wavelet coefficient matrix,and time-frequency map feature forms are discussed.Then the challenges and future development direc-tions of machine learning-based rotating machinery fault diagnosis are summarized.Finally,the challenges and development prospects of machine learning-based fault diagnosis of rotating machinery are summar-ized and it points out that the development trend of machine learning input features in the future will focus on automated feature engineering,feature dimension reduction technology and multimodal fusion.关键词
旋转机械/故障诊断/机器学习/数字特征/图像特征Key words
rotating machinery/fault diagnosis/machine learning/digital features/image features分类
机械制造引用本文复制引用
徐五一,杨岗,卫昱乾,邓琴..基于机器学习的旋转机械故障识别算法的输入特征综述[J].西华大学学报（自然科学版）,2025,44(6):13-27,15.基金项目
国家重点研发计划(2020YFB1200300ZL). （2020YFB1200300ZL）
