[1]马 进,刘 畅,陈文庆,等. 基于改进CAE-KPCA 特征融合的轴承故障诊断[J].机械与电子,2026,44(02):53-61.
　MA Jin,LIU Chang,CHEN Wenqing,et al. Fault Diagnosis of Bearings Based on Improved CAE KPCA Feature Fusion[J].Machinery & Electronics,2026,44(02):53-61.
点击复制

 基于改进CAE-KPCA 特征融合的轴承故障诊断()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年02期
页码:
53-61
栏目:
智能检测
出版日期:
2026-02-26

文章信息/Info

Title:
 Fault Diagnosis of Bearings Based on Improved CAE KPCA Feature Fusion
文章编号:
1001-2257(2026)02-0053-09
作者:
 马 进1; 刘 畅2; 陈文庆3; 胡雪年3
 (1.陕煤集团神南产业发展有限公司,陕西 神木 719300;2.徐州工程学院机电工程学院,江苏 徐州 221018;
3.中国矿业大学机电工程学院,江苏 徐州 221116)
Author(s):
 MA Jin1; LIU Chang2; CHEN Wenqing3; HU Xuenian3
 (1.Shaanxi Coal Group Shennan Industry Development Co.,Ltd.,Shenmu 719300,China;
2.School of Mechanical and Electrical Engineering,Xuzhou University of Technology,Xuzhou 221018,China;
3.School of Mechanical and Electronic Engineering,China University of Mining and Technology,Xuzhou 221116,China)
关键词:
滚动轴承; 故障脉冲; 特征融合; 抽象特征; 统计特征
Keywords:
rolling bearing; fault impulse; feature fusion; abstract feature; statistical features
分类号:
TH133.3;TP391
文献标志码:
A
摘要:
针对传统滚动轴承特征提取方法难以充分挖掘故障脉冲、特征提取能力有限的问题,提出一种改进CAE KPCA 的滚动轴承特征融合方法。采用点对称分析方法将原始信号转换为SDP图像;通过改进的卷积自编码器提取SDP图像的抽象特征,并利用Adam 优化算法训练模型,实现高效的多参数优化;通过直方图均衡化处理SDP图像并计算其统计特征集,利用故障响应增益指标筛选出故障响应显著的统计特征,以提升统计特征质量;利用KPCA 方法对抽象特征与统计特征进行降维融合,消除特征间的冗余信息。实验结果表明,与单独使用抽象特征或统计特征相比,改进CAE KPCA 方法得到的融合特征在多个常用故障诊断模型中的故障诊断准确率最高。
Abstract:
 To address the issues that traditional rolling bearing feature extraction methods have difficulty fully extracting fault pulses and exhibit limited feature extraction capabilities,this paper proposes a feature extraction method for rolling bearings based on improved CAE KPCA framework.The original vibration signals are first converted into SDP images using the point symmetry analysis method.Abstract features are then extracted from these SDP images by an improved Convolutional Autoencoder (CAE),with the model trained efficiently using the Adam optimization algorithm for multi parameter tuning.Subsequently,the histogram equalization is applied to process SDP images and calculate their statistical feature set.A fault response gain index is used to screen for statistical features that demonstrate significant fault responses,so as to improve their quality.Finally,the Kernel Principal Component Analysis (KPCA) method is employed to reduce dimensionality and fuse the abstract features with the selected statistical features,eliminating redundancy among them.Experimental results show that compared to using either abstract features or statistical features alone,the fused features obtained by the improved CAE KPCA method achieve the highest fault diagnosis accuracy across several commonly used fault diagnosis models.

参考文献/References:

 [1] CHEN Y Y,MAO Z W,HOU X Q,et al.Noise robust
adaptive feature mode decomposition method for
accurate feature extraction in rotating machinery fault diagnosis[J].Mechanical systems and signal processing,2024,211:111213.
[2] XIAO M H,WANG Z Y,ZHAO Y F,et al.A new fault feature extraction method of rolling bearings based on the improved self selection ICEEMDAN permutation entropy[J].ISA Transactions,2023,143:536 547.
[3] ZHOU P,CHEN S Q,HE Q B,et al.Rotating machinery fault induced vibration signal modulation effects:a review with mechanisms,extraction methods and applications for diagnosis[J].Mechanical systems and signal processing,2023,200:110489.
[4] 窦桂东,白艺硕,王均利,等.基于深度学习的矿井滚动轴承故障诊断方法[J].工矿自动化,2024,50(1):96 103.
[5] LI Y,ZHANG H Y,MA S C,et al.Weak feature extraction method for bearing faults under low speed heavy duty conditions[J].IEEE Access,2024,12:126033 126042.
[6] 卜闯,刘艳军,张伟.基于PSO SVM 的采煤机轴承故障诊断模型[J].工矿自动化,2025,51(增刊1):44 46.
[7] 苗永浩,石惠芳,李晨辉,等.周期精炼的最大相关峭度解卷积在滚动轴承微弱故障特征提取中的应用[J].振动工程学报,2025,38(6):1317 1325.
[8] HE G L,DING K,LI W H,et al.A novel order tracking method for wind turbine planetary gearbox vibration analysis based on discrete spectrum correction technique[J].Renewable energy,2016,87:364 375.
[9] 高艺源,于德介,王好将,等.基于图谱指标的滚动轴承故障特征提取方法[J].航空动力学报,2018,33(8):2033 2040.
[10] CHEN Z X,YANG Y,HE C B,et al.Feature extraction based on hierarchical improved envelope spectrum entropy for rolling bearing fault diagnosis[J].IEEE Transactions on instrumentation and measurement,2023,72:1 12.
[11] 雷亚国,贾峰,周昕,等.基于深度学习理论的机械装备大数据健康监测方法[J].机械工程学报,2015,51(21):49 56.
[12] 刘渊博,陈相,刘妤.基于卷积自编码器和时间卷积网络的轴承性能退化趋势预测[J].振动与冲击,2023,42(13):214 225.
[13] 赵国超,刘崇德,宋宇宁,等.基于特征交叉注意力机制融合的轴承故障诊断方法[J].振动与冲击,2025,44(12):228 237.
[14] 袁静,任港星,蒋会明,等.基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J].机械工程学报,2024,60(12):51 64.
[15] 申龙,单浩然,裴文良,等.基于卷积自编码器的煤矿带式输送机异常声音检测方法[J].工矿自动化,2025,51(2):100 105.
[16] XU J,LIANG S K,DING X,et al.A zero shot fault semantics learning model for compound fault diagnosis[J].Expert systems with applications,2023,221:119642.
[17] KINGMA D P,BA J.Adam:a method for stochastic optimization[EB/OL].(2014 12 22).https:∥arxiv.org/abs/1412.6980.
[18] DENG X G,CAI P P,CAO Y P,et al.Two step localized kernel principal component analysis based incipient fault diagnosis for nonlinear industrial processes[J].Industrial and engineering chemistry research,2020,59(13):5956 5968.
[19] 王辉,宋思蒙,钱勇,等.基于CLAHE增强的GIS局放脉冲序列识别算法[J].高电压技术,2021,47(11):3836 3844.
[20] ZHANG J S,ZHANG K,AN Y Y,et al.An integrated multitasking intelligent bearing fault diagnosis scheme based on representation learning under imbalanced sample condition[J].IEEE Transactions on neural networks and learning systems,2024,35(5):6231 6242.
[21] LI Y B,XU M Q,WEI Y,et al.A new rolling bearing fault diagnosis method based on multiscale permutation entropy and improved support vector machine based binary tree[J].Measurement,2016,77:80 94.
[22] 梁晓龙,李金刚,徐平平,等.基于卷积神经网络和Transformer的供热管网泄漏故障诊断[J].科学技术与工程,2025,25(13):5589 5601.
[23] 何群,余志红,陈志刚,等.基于改进信息熵和LSTM网络的轴承故障诊断[J].科学技术与工程,2024,24(12):4969 4975.

相似文献/References:

[1]吕明珠１,２,苏晓明 １,等. 改进粒子群算法优化的支持向量机在滚动轴承故障诊断中的应用[J].机械与电子,2019,(01):42.
　,,et al.Application of SVM Optimized by IPSO in Rolling Bearing Fault Diagnosis[J].Machinery & Electronics,2019,(02):42.
[2]吕明珠 苏晓明 陈长征 刘世勋.小波包能量熵与EMD结合分析法在风机滚动轴承故障诊断中的应用[J].机械与电子,2018,(06):8.
　LYU Mingzhu,SU Xingming,CHEN Changzheng,et al.Application of Wavelet Packet Energy Entropy and EMD Conjoint Analysis in Fault Diagnosis of Wind Turbine Bearing[J].Machinery & Electronics,2018,(02):8.
[3]石大磊,傅 攀.基于CEEMD的滚动轴承振动信号自适应降噪方法[J].机械与电子,2018,(11):3.
　SHI Dalei,FU Pan.Adaptive De-noising Method of Rolling Bearing Vibration Signal Based on CEEMD[J].Machinery & Electronics,2018,(02):3.
[4]马益书,黄亚宇,吴 政.基于包络分析的滚动轴承故障诊断研究[J].机械与电子,2016,(01):63.
　MA Yishu,HUANG Yayu,WU Zheng.Study on Fault Diagnosis of Rolling Bearing Based on Envelope Analysis[J].Machinery & Electronics,2016,(02):63.
[5]朱亮亮,高 瞩,吉晓民.基于多重因素的滚动轴承寿命计算新方法[J].机械与电子,2015,(11):12.
　ZHU Liangliang,GAO Zhu,JI Xiaomin.A New Method of Calculating the Rolling Bearing Life Based on the Effect of Multiple Factors[J].Machinery & Electronics,2015,(02):12.
[6]杨伟力,于阳阳,罗达灿.基于小波包和PSO-Elman神经网络的滚动轴承故障诊断[J].机械与电子,2016,(05):13.
　YANG Weili,YU Yangyang,LUO Dacan.Rolling Bearing Fault Diagnosis Using Wavelet Packet Analysis and PSO-Elman Neural Network[J].Machinery & Electronics,2016,(02):13.
[7]王振亚,刘 韬,王廷轩,等.不平衡技术在轴承故障诊断中的应用[J].机械与电子,2021,(06):29.
　WANG Zhenya,LIU Tao,WANG Tingxuan,et al.Application of Unbalance Technique in Bearing Fault Diagnosis[J].Machinery & Electronics,2021,(02):29.
[8]周正南,刘 美,吴斌鑫,等.改进的布谷鸟算法优化极限学习机的石化轴承故障分类[J].机械与电子,2022,(07):3.
　ZHOU Zhengnan,LIU Mei,et al.Improved Cuckoo Algorithm for Optimizing Extreme Learning Machine for Petrochemical Bearing Fault Classification[J].Machinery & Electronics,2022,(02):3.
[9]陈 宇,程道来,马向华,等.基于 WDCNN-LSTM 混合模型的滚动轴承故障诊断[J].机械与电子,2025,(02):9.
　CHEN Yu,CHENG Daolai,MA Xianghua,et al.Fault Diagnosis of Rolling Bearing Based on WDCNN-LSTM Hybrid Model[J].Machinery & Electronics,2025,(02):9.
[10]夏 平,高龙飞,张立金,等.强噪声背景下的 GWO-VMD 滚动轴承故障诊断方法[J].机械与电子,2025,(11):68.
　XIA Ping,GAO Longfei,ZHANG Lijin,et al.GWO-VMD Method for Rolling Bearing Fault Diagnosis under Strong Noise Conditions[J].Machinery & Electronics,2025,(02):68.

备注/Memo

备注/Memo:
 收稿日期:2025-10-11
基金项目:国家自然科学基金青年基金项目(52304179);徐州市科技计划资助项目(KC22030)
作者简介:马 进 (1988-),男,陕西绥德人,高级工程师,研究方向为设备状态监测;刘 畅 (1991-),男,江苏徐州人,博士,讲师,研究方向为机电设备可靠性及故障预诊技术,通信作者,E mail:liuchang@xzit.edu.cn。
更新日期/Last Update: 2026-04-28