SPCA和OCHD相结合的旋转机械早期微弱故障检测方法

doi:10.3969/j.issn.1004-132X.2023.15.005

中国机械工程 ›› 2023, Vol. 34 ›› Issue (15): 1805-1812.DOI: 10.3969/j.issn.1004-132X.2023.15.005

SPCA和OCHD相结合的旋转机械早期微弱故障检测方法

李鑫1,2;程军圣1,2;吴小伟3,4;王健4;杨宇1,2

1.湖南大学汽车车身先进设计制造国家重点实验室，长沙，410082
2.湖南大学装备服役质量保障湖南省重点实验室，长沙，410082
3.中国航发湖南动力机械研究所直升机传动技术国家级重点实验室，株洲，412002
4.中国航发湖南动力机械研究所航空发动机振动技术重点实验室，株洲，412002

出版日期:2023-08-10 发布日期:2023-08-14
通讯作者: 程军圣（通信作者），男，1968年生，教授、博士研究生导师。研究方向为复杂机电设备的动态感知与智能运维。E-mail:chengjunsheng@hnu.edu.cn。
作者简介:李鑫，男，1993年生，博士研究生。研究方向为故障诊断、机器学习。
基金资助:
国家自然科学基金（51975193，51875183）

Early Weak Fault Detection Method of Gear Rotating Machinery by Combining SPCA and OCHD

LI Xin1,2;CHENG Junsheng1,2;WU Xiaowei3,4;WANG Jian4;YANG Yu1,2

1.State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body,Hunan University,
Changsha,410082
2.Hunan Provincial Key Laboratory of Equipment Service Quality Assurance,Hunan University,
Changsha,410082
3.AECC Hunan Aviation Powerplant Research Institute,Zhuzhou,Hunan,412002
4.AECC Key Laboratory of Aero-engine Vibration Technology,Zhuzhou,Hunan,412002

Online:2023-08-10 Published:2023-08-14

摘要/Abstract

摘要： 针对旋转机械早期微弱故障难以被及时准确检测的问题，提出了一种基于辛主成分分析（SPCA）和单分类超圆盘（OCHD）的智能检测方法。首先，采用SPCA将振动信号映射到辛空间，并提取最能表征信号主要能量和有效信息的辛特征值作为旋转机械故障特征。然后，将超圆盘模型引入单分类领域，提出了OCHD模型，该模型采用超圆盘模型评估已知样本的类别分布，并通过寻找几何模型上距离原点最近的点来构建最优单分类超平面，从而实现早期微弱故障的智能检测。最后，采用辛辛那提大学轴承全寿命周期数据验证所提方法的有效性，实验结果表明：SPCA能够有效提取轴承的敏感故障信息，且OCHD的故障检测性能明显优于其他单分类模型。

关键词: 微弱故障检测, 旋转机械, 辛主成分分析, 超圆盘模型, 单分类超圆盘

Abstract: Aiming at the problems that early weak faults of rotating machinery were difficult to detect in time and accurately, an intelligent detection method was proposed based on SPCA and OCHD. Firstly, SPCA was used to map vibration signals to a symplectic space, and the symplectic eigenvalues which might best characterize the main energy and effective information of the signals were extracted as the fault features of rotating machinery. Then, the hyperdisk model was introduced into the one-class classification domain to propose the OCHD model. OCHD used the hyperdisk model to evaluate the class distribution of known samples, and the optimal one-class hyperplane was constructed by finding the closest points on the geometric model to the origin, so as to realize the intelligent detection of early weak faults. Finally, the effectiveness of the proposed method was verified by the bearing life cycle data from the university of Cincinnati. The experimental results show that SPCA may effectively extract the sensitive fault information of bearings, and the fault detection performance of OCHD is significantly better than that of other one-class models.

Key words: weak fault detection, rotating machinery, symplectic principal component analysis(SPCA), hyperdisk model, one-class hyperdisk(OCHD)

中图分类号:

TH17

李鑫, 程军圣, 吴小伟, 王健, 杨宇, . SPCA和OCHD相结合的旋转机械早期微弱故障检测方法[J]. 中国机械工程, 2023, 34(15): 1805-1812.

LI Xin, CHENG Junsheng, WU Xiaowei, WANG Jian, YANG Yu, . Early Weak Fault Detection Method of Gear Rotating Machinery by Combining SPCA and OCHD[J]. China Mechanical Engineering, 2023, 34(15): 1805-1812.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.cmemo.org.cn/CN/10.3969/j.issn.1004-132X.2023.15.005

http://www.cmemo.org.cn/CN/Y2023/V34/I15/1805

参考文献

［1］杨路航,李宝庆,王平,等.基于概率输出弹性凸包的滚动轴承故障诊断方法［J］.中国机械工程,2021,32(1):40-46.
YANG Luhang, LI Baoqing, WANG Ping, et al. Fault Diagnosis Method of Rolling Bearings Based on Probability Output Flexible Convex Hull［J］. China Mechanical Engineering, 2021,32(1):40-46.
［2］余浩帅, 汤宝平, 张楷, 等.小样本下混合自注意力原型网络的风电齿轮箱故障诊断方法［J］.中国机械工程, 2021, 32(20):2475-2481.
YU Haoshuai, TANG Baoping, ZHANG Kai, et al. Fault Diagnosis Method of Wind Turbine Gearboxes Mixed with Attention Prototype Networks under Small Samples［J］. China Mechanical Engineering, 2021,32(20):2475-2481.
［3］QIAO Z, LEI Y, LI N. Applications of Stochastic Resonance to Machinery Fault Detection:a Review and Tutorial［J］. Mechanical Systems and Signal Processing, 2019, 122:502-536.
［4］赵志宏, 李乐豪, 杨绍普, 等. 一种无监督的轴承健康指标及早期故障检测方法［J］. 中国机械工程, 2022, 33(10):1234-1243.
ZHAO Zhihong, LI Lehao, YANG Shaopu, et al. An Unsupervised Bearing Health Indicator and Early Fault Detection Method［J］. China Mechanical Engineering, 2022, 33(10):1234-1243.
［5］LEI M, MENG G, DONG G. Fault Detection for Vibration Signals on Rolling Bearings Based on the Symplectic Entropy Method［J］. Entropy, 2017, 19(11):607.
［6］CHENG J, YANG Y, LI X, et al. An Early Fault Diagnosis Method of Gear Based on Improved Symplectic Geometry Mode Decomposition［J］. Measurement, 2020, 151:107140.
［7］PAN H, YANG Y, LI X, et al. Symplectic Geometry Mode Decomposition and Its Application to Rotating Machinery Compound Fault Diagnosis［J］. Mechanical Systems and Signal Processing, 2019, 114:189-211.
［8］郑直,高崇一,宋金超,等.基于SGMD敏感参数和KFCMC的滚动轴承故障诊断方法［J］.机床与液压,2020,48(11):189-193.
ZHENG Zhi, GAO Chongyi, SONG Jinchao, et al. Fault Diagnosis Method of Rolling Bearings Based on SGMD Sensitive Parameters and KFCMC［J］. Machine Tool ＆ Hydraulics,2020,48(11):189-193.
［9］LI X, YANG Y, SHAO H, et al. Symplectic Weighted Sparse Support Matrix Machine for Gear Fault Diagnosis［J］. Measurement, 2021, 168:108392.
［10］LEI M, MENG G. Symplectic Principal Component Analysis:a New Method for Time Series Analysis［J］. Mathematical Problems in Engineering, 2011, 2011:793429.
［11］HEJAZI M, SINGH Y P. One-class Support Vector Machines Approach to Anomaly Detection［J］. Applied Artificial Intelligence, 2013, 27(5):351-366.
［12］ZHANG F, FAN H, WANG R, et al. Deep Dual Support Vector Data Description for Anomaly Detection on Attributed Networks［J］. International Journal of Intelligent Systems, 2022, 37(2):1509-1528.
［13］FERNNDEZ-FRANCOS D, FONTENLA-ROMERO, ALONSO-BETANZOS A. One-class Convex Hull-based Algorithm for Classification in Distributed Environments［J］. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2017, 50(2):386-396.
［14］FERNNDEZ-FRANCOS D, MARTNEZ-REGO D, FONTENLA-ROMERO O, et al. Automatic Bearing Fault Diagnosis Based on One-class ν-SVM［J］. Computers & Industrial Engineering, 2013, 64(1):357-365.
［15］SAARI J, STRMBERGSSON D, LUNDBERG J, et al. Detection and Identification of Windmill Bearing Faults Using a One-class Support Vector Machine (SVM)［J］. Measurement, 2019, 137:287-301.
［16］SHIN H J, EOM D H, KIM S S. One-class Support Vector Machines—an Application in Machine Fault Detection and Classification［J］. Computers & Industrial Engineering, 2005, 48(2):395-408.
［17］WANG Q, LIU X, WEI B, et al. Online Incipient Fault Detection Method Based on Improved 1 Trend Filtering and Support Vector Data Description［J］. IEEE Access, 2021, 9:30043-30059.
［18］ZENG M, YANG Y, LUO S, et al. One-class Classification Based on the Convex Hull for Bearing Fault Detection［J］. Mechanical Systems and Signal Processing, 2016, 81:274-293.
［19］NEZ I, JOVE E, CASTELEIRO-ROCA J L, et al. Hybrid Approximate Convex Hull One-class Classifier for an Industrial Plant［C］∥Computational Intelligence in Security for Information Systems Conference. Cham, 2019:282-292.
［20］YI J, WU L, ZHOU W, et al. ASparse Dimensionality Reduction Approach Based on False Nearest Neighbors for Nonlinear Fault Detection［J］. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2019, 51(8):4980-4992.
［21］SONG X, ZHANG Y, GONG D, et al. FeatureSelection Using Bare-bones Particle Swarm Optimization with Mutual Information［J］. Pattern Recognition, 2021, 112:107804.
［22］INCE T, MALIK J, DEVECIOGLU O C, et al. EarlyBearing Fault Diagnosis of Rotating Machinery by 1d Self-organized Operational Neural Networks［J］. IEEE Access, 2021, 9:139260-139270.

[1]	张龙, 胡燕青, 赵丽娟, 张号. 多通道信息融合与深度迁移学习的旋转机械故障诊断[J]. 中国机械工程, 2023, 34(08): 966-975.
[2]	姜万录, 李满, 张培尧, 赵亚鹏, 张淑清. 基于全矢增强深度森林的旋转设备智能故障诊断方法[J]. 中国机械工程, 2022, 33(11): 1324-1335.
[3]	蒋佳炜, 胡以怀, 方云虎, 张陈, 芮晓松, 汪猛. 基于多尺度时域平均分解和模糊熵的船用风机故障诊断方法[J]. 中国机械工程, 2022, 33(10): 1178-1188.
[4]	石明宽, 赵荣珍. 基于局部平衡判别投影的旋转机械故障诊断方法[J]. 中国机械工程, 2021, 32(14): 1653-1658,1668.
[5]	李锋1;程阳洋1,2;陈勇1;汤宝平3. 用于旋转机械状态趋势预测的量子注意力循环编码解码神经网络[J]. 中国机械工程, 2020, 31(21): 2573-2582.
[6]	杨宇;李鑫;潘海洋;程军圣. 基于非线性模式分解的旋转机械复合故障特征提取方法[J]. 中国机械工程, 2018, 29(24): 2947-2953.
[7]	陈换过, 陈培, 陈文华, 蔡丽, 沈建洋, 吴建伟, 吴明建, . 采样频率对聚合经验模态分解的影响研究[J]. 中国机械工程, 2016, 27(18): 2472-2476.
[8]	陈宏, 雷文平, 陈磊, 韩捷. 一种转子动态不对中量计算方法[J]. 中国机械工程, 2016, 27(17): 2379-2383.
[9]	时培明, 苏翠娇, 赵娜, 韩东颖. 基于解析模态分解的机械故障诊断方法[J]. 中国机械工程, 2016, 27(05): 674-679.
[10]	罗颂荣, 程军圣, Hunglinh A O. 基于人工化学反应优化的SVM及旋转机械故障诊断[J]. 中国机械工程, 2015, 26(10): 1306-1312.
[11]	孟宗, 闫晓丽, 王亚超. 基于LMD和HMM的旋转机械故障诊断[J]. 中国机械工程, 2014, 25(21): 2942-2946,2951.
[12]	张颖, 刘占生, 苏宪章. 旋转机械参数图形多尺度多结构元边缘检测[J]. 中国机械工程, 2013, 24(23): 3176-3180.
[13]	时培明;李庚;韩东颖. 基于改进EMD的旋转机械耦合故障诊断方法研究[J]. 中国机械工程, 2013, 24(17): 2367-2372.
[14]	任达千1, 2, 杨世锡1, 吴昭同1, 严拱标1. LMD时频分析方法的端点效应在旋转机械故障诊断中的影响[J]. 中国机械工程, 2012, 23(8): 951-956.
[15]	张玉存, 马睿, 付献斌, 孔涛. 基于拓扑传递的耦合机械故障特征提取方法 [J]. 中国机械工程, 2012, 23(4): 435-438.

SPCA和OCHD相结合的旋转机械早期微弱故障检测方法

Early Weak Fault Detection Method of Gear Rotating Machinery by Combining SPCA and OCHD

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics