化工学报 ›› 2021, Vol. 72 ›› Issue (S1): 430-436.doi: 10.11949/0438-1157.20201539

• 过程系统工程 • 上一篇    下一篇

基于自动特征工程的飞行器轴承故障诊断

张弛1(),李浩1,胡海涛1(),朱翀2,张玉莹2,南国鹏2,舒悦3   

  1. 1.上海交通大学制冷与低温工程研究所,上海 200240
    2.中国商用飞机有限责任公司上海飞机设计研究院,上海 201210
    3.压缩机技术国家重点实验室(压缩机技术安徽省实验室),安徽 合肥 230031
  • 收稿日期:2020-11-01 修回日期:2021-01-25 出版日期:2021-06-20 发布日期:2021-06-20
  • 通讯作者: 胡海涛 E-mail:595723288zc@sjtu.edu.cn;huhaitao2001@sjtu.edu.cn
  • 作者简介:张弛(1997—),男,硕士研究生,595723288zc@sjtu.edu.cn
  • 基金资助:
    国家自然科学基金项目(51976115);上海市科委科技创新行动计划项目(19142203000);压缩机技术国家重点实验室项目(SKL-YSJ201904)

Aircraft bearing fault diagnosis based on automatic feature engineering

ZHANG Chi1(),LI Hao1,HU Haitao1(),ZHU Chong2,ZHANG Yuying2,NAN Guopeng2,SHU Yue3   

  1. 1.Institute of Refrigeration and Cryogenics, Shanghai Jiao Tong University, Shanghai 200240, China
    2.Shanghai Aircraft Design and Research Institute, Commercial Aircraft Corporation of China, Ltd. , Shanghai 201210, China
    3.State Key Laboratory of Compressor Technology (Anhui Laboratory of Compressor Technology), Hefei 230031, Anhui, China
  • Received:2020-11-01 Revised:2021-01-25 Published:2021-06-20 Online:2021-06-20
  • Contact: HU Haitao E-mail:595723288zc@sjtu.edu.cn;huhaitao2001@sjtu.edu.cn

摘要:

针对飞行器轴承信号单一且噪声多、需要针对性特征以及需要高可解释性的问题,开发了涵盖具有自适应噪声的完全集合经验模态分解(CEEMDAN)、自动特征工程以及随机森林的故障诊断模型,模型核心为自动进行特征生成以及提取的特征工程。通过该特征工程能够根据不同对象的信号差异,自动提取出不同对象的有效特征,具备对象间的通用性,且该特征工程可根据样本量的不同调整有效特征的数量,丰富特征空间,具备灵活的可扩展性。验证表明,该涵盖自动特征工程的模型的故障分类准确率为95.32%,可较好地在大样本量下区分压缩机轴承上的不同故障。

关键词: 故障诊断, 算法, 集成, 自动特征工程, 轴承, 模态分解

Abstract:

Aiming at the problems that bearing signals in aircraft are simple and mixed with many noises, which require targeted features and high interpretability, a fault diagnosis model composed of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and automatic feature engineering and random forest was developed. Bearing vibration signal is converted into intrinsic mode functions (IMF) through the decomposition method. The core of the model is the feature engineering that automatically performs feature generation and extraction based on 65 kinds of manually designed structural features. This feature engineering can automatically extract the effective features of different objects according to the signal difference of different objects, which has universality between objects. Besides, it can adjust the number of effective features according to different sample sizes, enrich the feature space, and have flexible scalability. Validation shows that the fault classification accuracy of the model based on automatic feature engineering and random forest classification model is 95.32%, which performs better than common model based on singular value entropy, energy entropy, envelope sample entropy feature engineering and support vector machines classification model. Result shows that automatic feature engineering fault diagnosis model can better distinguish different faults on compressor bearings under a large sample size.

Key words: fault diagnosis, algorithm, integration, automatic feature engineering, bearing, mode decomposition

中图分类号: 

  • TH 17

图1

轴承结构"

表1

轴承故障类型及故障程度"

序号类型样本数
1球体轻微故障319
2内圈轻微故障315
3外圈轻微故障1318
4外圈轻微故障2318
5外圈轻微故障3317
6球体中等故障317
7内圈中等故障317
8外圈中等故障317
9球体严重故障317
10内圈严重故障318
11外圈严重故障1317
12外圈严重故障2316
13外圈严重故障3318
14正常635

图2

CEEMDAN 计算流程"

表2

不同的离散特征量"

序号名称计算公式
1平方和i=1Nxi2
2一阶差分绝对值之和i=1N-1xi+1-xi
3最大值位置argmaxxi
4最小值位置argminxi
5自回归系数Xt=ψ0+i=1kψiXt-i+εt
6Ricker小波分析23aπ1/41-x2a2exp(-x22a2)
7傅里叶变换系数Ak=m=0n-1amexp-2πimkn
8平均值1ni=1nxi
9连续两点值的变化的绝对值的平均值1ni=1,...,n-1xi+1-xi
65自相关系数的聚合特征1n-lσ2i=1n-lxi-μxi+l-μ

表3

候选特征量计算"

序号参数名称P
1IMF3的标准差大于0.2[max(x)-min(x)]3.8440×10-69
2IMF1中小于平均值的最长子序列长度1.5204×10-66
3IMF1中大于平均值的最长子序列长度6.7620×10-66
4IMF2中支持10的峰值数量1.5667×10-59
5IMF3中支持10的峰值数量2.2018×10-59
6IMF1中支持5的峰值数量8.0154×10-59
7IMF1的0交叉数量1.5327×10-58
8IMF4的自回归系数1.6436×10-58
18IMF2的复杂性指标1.7666×10-58
19IMF2的最小值1.7772×10-58
20IMF1的最大值1.8096×10-58

图3

随机森林中决策树的结构"

图4

随机森林对于不同故障的分类正确性"

表4

不同特征工程对准确率的影响"

模型组合测试集准确率
CEEMDAN+自动特征工程95.32%
CEEMDAN+奇异值熵92.07%
CEEMDAN+能量熵91.08%
CEEMDAN+{能量熵,奇异熵,包络样本熵}94.52%

表5

不同分类算法的准确率"

分类算法测试集准确率
逻辑回归90.18%
SVM92.54%
单隐层神经网络89.70%
决策树93.81%
XGBoost95.42%
1 卢浩贤, 肖彪, 何林, 等. 制冷空调系统中压缩机缺氟可靠性的试验研究[J]. 环境技术, 2018, 36(2): 55-59, 81.
Lu H X, Xiao B, He L, et al. Research on reliability experiment of compressor refrigerant leakage for air conditioning system [J]. Environmental Technology, 2018, 36(2): 55-59, 81.
2 王录雁, 王强, 张梅军, 等. 基于EMD的滚动轴承故障灰色诊断方法[J]. 振动与冲击, 2014, 33(3): 197-202.
Wang L Y, Wang Q, Zhang M J, et al. A grey fault diagnosis method for rolling bearings based on EMD [J]. Journal of Vibration and Shock, 2014, 33(3): 197-202.
3 陈俊洵, 程龙生, 胡绍林, 等. 基于EMD的改进马田系统的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(5): 151-156.
Chen J X, Cheng L S, Hu S L, et al. Fault diagnosis of rolling bearings using modified Mahalanobis-Taguchi system based on EMD [J]. Journal of Vibration and Shock, 2017, 36(5): 151-156.
4 潘洋洋, 何伟, 朱丹宸. 基于CEEMD与IMCKD的滚动轴承故障诊断方法[J]. 机电工程技术, 2019, 48(10): 98-102.
Pan Y Y, He W, Zhu D C. Fault diagnosis method for rolling bearings based on CEEMD and IMCKD [J]. Mechanical & Electrical Engineering Technology, 2019, 48(10): 98-102.
5 卓仁雄, 肖金凤. 基于改进的集合经验模态分解的电动机滚动轴承故障诊断研究[J]. 机械制造与自动化, 2019, 48(1): 36-39.
Zhuo R X, Xiao J F. Research on fault diagnosis method of motor bearing based on improved EEMD and SVM [J]. Machine Building & Automation, 2019, 48(1): 36-39.
6 Kong Y, Wang T Y, Chu F L. Meshing frequency modulation assisted empirical wavelet transform for fault diagnosis of wind turbine planetary ring gear [J]. Renewable Energy, 2019, 132: 1373-1388.
7 Torres M E, Colominas M A, Schlotthauer G, et al. A complete ensemble empirical mode decomposition with adaptive noise [C]// 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2011: 4144-4147.
8 The Case Western Reserve University Bearing Data Center Website. Bearing Data Center Seeded Fault Test Data [DB/OL]. [2001-11-12]. .
9 Paquet C, Lavieille M, Schuster W. Aircraft supplemental cooling system noise propagation and radiation: comparisons between acoustics numerical modeling and testing [C]// 17th AIAA/CEAS Aeroacoustics Conference (32nd AIAA Aeroacoustics Conference). AIAA, 2011.
10 Deng M Q, Deng A D, Zhu J, et al. Bandwidth Fourier decomposition and its application in incipient fault identification of rolling bearings [J]. Measurement Science and Technology, 2020, 31(1): 015012.
11 Wang L C, Der S Z, Nasrabadi N M. Automatic target recognition using a feature-decomposition and data-decomposition modular neural network [C]// Proc. SPIE3307, Applications of Artificial Neural Networks in Image Processing Ⅲ. 1998, 3307: 2-13.
12 Lilliefors H W. On the Kolmogorov-Smirnov test for normality with mean and variance unknown [J]. Journal of the American Statistical Association, 1967, 62(318): 399-402.
13 Thissen D, Steinberg L, Kuang D. Quick and easy implementation of the Benjamini-Hochberg procedure for controlling the false positive rate in multiple comparisons [J]. Journal of Educational and Behavioral Statistics, 2002, 27(1): 77-83.
14 刘晓婉. 基于CEEMDAN模糊熵和SVM的滚动轴承故障诊断[J]. 现代制造技术与装备, 2019, (9): 178-179.
Liu X W. Fault diagnosis of rolling bearing based on CEMDAN fuzzy entropy and SVM [J]. Modern Manufacturing Technology and Equipment, 2019, (9): 178-179.
15 Friedl M A, Brodley C E. Decision tree classification of land cover from remotely sensed data [J]. Remote Sensing of Environment, 1997, 61(3): 399-409.
16 Liaw A, Wiener M. Classification and regression by RandomForest [J]. R News, 2002, 2(3): 18-22.
[1] 王兆奇, 李孟山, 胡海涛, 魏文建. 双排对折型微通道换热器仿真模型开发[J]. 化工学报, 2021, 72(S1): 113-119.
[2] 徐健玮, 梁颖宗, 罗向龙, 陈健勇, 杨智, 陈颖. 液化天然气深冷-膜蒸馏海水淡化系统集成与分析[J]. 化工学报, 2021, 72(S1): 437-444.
[3] 梁坤峰, 王莫然, 高美洁, 吕振伟, 徐红玉, 董彬, 高凤玲. 纯电动车集成热管理系统性能的热力学分析[J]. 化工学报, 2021, 72(S1): 494-502.
[4] 朱轶林, 张新敬, 徐玉杰, 丁捷, 郭欢, 陈海生. 基于遗传算法-综合计算法的生物质热解气化优化分析[J]. 化工学报, 2021, 72(9): 4910-4920.
[5] 蒋迎花, 韩儒松, 康丽霞, 刘永忠. 厂际氢气网络多周期集成的分步优化方法[J]. 化工学报, 2021, 72(9): 4816-4829.
[6] 郭金玉, 李文涛, 李元. 在线压缩KECA的自适应算法在故障检测中的应用[J]. 化工学报, 2021, 72(8): 4227-4238.
[7] 韩正恒, 崔国民, 赵倩倩, 肖媛, 张冠华. RWCE算法中采用单元重构策略激励换热网络结构优化[J]. 化工学报, 2021, 72(6): 3316-3327.
[8] 谢昊源, 黄群星, 林晓青, 李晓东, 严建华. 基于图像深度学习的垃圾热值预测研究[J]. 化工学报, 2021, 72(5): 2773-2782.
[9] 王龙洋, 蒙西, 乔俊飞. 基于改进集合经验模态分解和深度信念网络的出水总磷预测[J]. 化工学报, 2021, 72(5): 2745-2753.
[10] 孙浩然, 吕中原, 吴成云, 胡海涛. 机载补气增焓制冷系统动态仿真模型[J]. 化工学报, 2021, 72(5): 2484-2492.
[11] 贾小平, 石磊, 杨友麒. 工业园区生态化发展的挑战与过程系统工程的机遇[J]. 化工学报, 2021, 72(5): 2373-2391.
[12] 赵杨, 熊伟丽. 基于多策略自适应差分进化算法的污水处理过程多目标优化控制[J]. 化工学报, 2021, 72(4): 2167-2177.
[13] 王东亮, 谢江鹏, 周怀荣, 孟文亮, 杨勇, 李德磊. 基于MDEA的烟气SO2捕集过程工艺参数和能量集成分析[J]. 化工学报, 2021, 72(3): 1521-1528.
[14] 李勇, 钱锋, 宋育梅. 基于特征选择的常减压装置模型及在计划优化中的应用[J]. 化工学报, 2021, 72(3): 1419-1429.
[15] 顾俊发, 许明阳, 马方圆, 林治宇, 纪成, 王璟德, 孙巍. 基于MIC的支持向量回归及其在化工过程中的应用[J]. 化工学报, 2021, 72(3): 1480-1486.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 叶树明, 蒋凯, 蒋春跃, 潘勤敏. 聚合物系动态超临界流体脱挥[J]. CIESC Journal, 2005, 13(6): 732 -735 .
[2] HUANGLixin,KurichiKumar,A.S.Mujumdar. 干燥室中不同液体的喷雾蒸发对流动、传热、传质性能的影响[J]. CIESC Journal, 2004, 12(6): 737 -743 .
[3] 马璐, 李浩然, 王从敏, 韩世钧. α-蒎烯+顺式蒎烷+正已醇体系的等温等压汽液平衡[J]. CIESC Journal, 2004, 12(1): 92 -95 .
[4] 蒋国强, 朱德权, 昝佳, 丁富新. 电致孔经皮给药:表面活性剂对孔道存在时间和药物传输的影响[J]. CIESC Journal, 2007, 15(3): 397 -402 .
[5] 朱建华, 沈复. 酯化反应蒸馏过程的模型化及模拟研究[J]. CIESC Journal, 2003, 11(6): 736 -739 .
[6] 刘先桥, 官月平, 邢建民, 马志亚, 刘会洲. 带环氧基的超顺磁性高分子微球的制备及其性能表征[J]. CIESC Journal, 2003, 11(6): 731 -735 .
[7] 吉远辉, 吉晓燕, 冯新, 刘畅, 吕玲红, 陆小华. CO2-H2O和CO2-H2O-NaCl 体系的相平衡研究进展[J]. CIESC Journal, 2007, 15(3): 439 -448 .
[8] 赵锁奇, 许志明, 王仁安. 超临界流体萃取制备脱沥青油与沥青微粒[J]. CIESC Journal, 2003, 11(6): 691 -695 .
[9] 曹维良, 王泽, 张敬畅. 影响纳米碳酸钙制备过程的因素分析[J]. CIESC Journal, 2003, 11(5): 589 -593 .
[10] 刘伯潭, 刘春江. 精馏塔板液相流场三维模拟[J]. CIESC Journal, 2002, 10(5): 517 -521 .