基于监督核熵成分分析的发动机磨损故障诊断

doi:10.16182/j.issn1004731x.joss.20-0623

系统仿真学报 ›› 2022, Vol. 34 ›› Issue (1): 45-52.doi: 10.16182/j.issn1004731x.joss.20-0623

基于监督核熵成分分析的发动机磨损故障诊断

祝志超, 吴定会, 岳远昌

江南大学物联网应用技术教育部工程研究中心,江苏无锡 214122

收稿日期:2020-08-24 修回日期:2020-11-24 出版日期:2022-01-18 发布日期:2022-01-14
作者简介:祝志超(1995-)，男，硕士生，研究方向为智能故障诊断。E-mail：549087769@qq.com
基金资助:
国家重点研发计划(2020YFB1711102); 国家自然科学基金(61572237)

Engine Wear Fault Diagnosis Based on Supervised Kernel Entropy Component Analysis

Zhu Zhichao, Wu Dinghui, Yue Yuanchang

Engineering Research Center of internet of Things Technology Applications Ministry of Education, Jiangnan University, Wuxi 214122, China

Received:2020-08-24 Revised:2020-11-24 Online:2022-01-18 Published:2022-01-14

摘要/Abstract

摘要： 针对发动机受工作环境影响,导致油液光谱数据存在大量冗余信息且具有非线性结构,从而影响发动机故障诊断结果的问题,提出监督核熵成分分析(supervised kernel entropy component analysis, SKECA)的特征提取方法;该方法在核熵成分分析基础上引入监督学习算法,提取油液光谱数据的内在几何特征,使提取后的故障特征中包含判别信息,并利用遗传算法(genetic algorithm, GA)寻找参数来优化特征提取的结果,采用支持向量机对故障特征进行分类。结果表明：采用SKECA进行特征提取能够有效提高发动机故障诊断精度。

关键词: 光谱, 故障诊断, 特征提取, 核熵成分分析

Abstract: Focus on the influence of environment on engine operation, which leads to a large amount of redundant information and nonlinear structure in oil spectral data that affects the engine fault diagnosis results, the feature extraction method of SKECA (supervised kernel entropy component analysis) is proposed. A supervised learning algorithm is adopted on the basis of Kernel Entropy Component Analysis, which extracts the inherent geometric features of oil spectrum data to make the extracted fault features include the discriminative information. GA (genetic algorithm) is used to find parameters to optimize the results of feature extraction, and SVM (support vector machine) is used to classify the fault features. Simulation results show that SKECA can effectively improve the accuracy of engine fault diagnosis.

Key words: spectrum, fault diagnosis, feature extraction, kernel entropy component analysis

中图分类号:

TP391.9

祝志超, 吴定会, 岳远昌. 基于监督核熵成分分析的发动机磨损故障诊断[J]. 系统仿真学报, 2022, 34(1): 45-52.

Zhu Zhichao, Wu Dinghui, Yue Yuanchang. Engine Wear Fault Diagnosis Based on Supervised Kernel Entropy Component Analysis[J]. Journal of System Simulation, 2022, 34(1): 45-52.

参考文献

[1] 张全德, 陈果, 郑宏光, 等. 一种基于油液分析数据挖掘的航空发动机磨损故障诊断知识获取方法[J]. 润滑与密封, 2019, 44(3): 128-134.
Zhang Quande, Chen Guo, Zheng Hongguang, et al.A Knowledge Acquisition Method of Aero Engine Wear Fault Diagnosis Based on Oil Analysis Data Mining[J]. Lubrication Engineering, 2019, 44(3): 128-134.
[2] 李婧, 田洪祥, 刘韬, 等. 因子分析法在船舶柴油机润滑油发射光谱数据挖掘中的应用[J]. 润滑与密封, 2019, 44(7): 107-111.
Li Jing, Tian Hongxiang, Liu Tao, et al.Application of Factor Analysis for Mining the AE Spectrum Data of Marine Diesel Engine Oil[J]. Lubrication Engineering, 2019, 44(7): 107-111.
[3] Wang G, Jiao J, Yin S.Efficient Nonlinear Fault Diagnosis Based on Kernel Sample Equivalent Replace- ment[J]. IEEE Transactions on Industrial Informatics (S1551-3203), 2019, 15(5): 2682-2690.
[4] Xiao Y Q, Feng L G.A Novel Neural-network Approach of Analog Fault Diagnosis Based on Kernel Discriminant Analysis and Particle Swarm Optimization[J]. Applied Soft Computing (S1568-4946), 2012, 12(2): 904-920.
[5] Zhou H D, Shi T L, Liao G L, et al.Weighted Kernel Entropy Component Analysis for Fault Diagnosis of Rolling Bearings[J]. Sensors (S1424-8220), 2017, 17(3): 625.
[6] 孙明明. 流形学习理论与算法研究[D]. 南京: 南京理工大学, 2007.
Sun Mingming.Study on Theories and Algorithms in Manifold Learning[D]. Nanjing: Nanjing University of Science and Technology, 2007.
[7] 张赟, 林学森, 王琳, 等. 采用监督局部切空间排列算法的航空发动机磨损故障诊断[J]. 西安交通大学学报, 2020, 54(4): 179-185.
Zhang Yun, Lin Xuesen, Wang Lin, et al.Aero-Engine Wear Fault Diagnosis with Super-Vised Locally Tangent Space Alignment[J]. Journal of Xi'an Jiaotong University, 2020, 54(4): 179-185.
[8] Jenssen R.Kernel Entropy Component Analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2010, 32(5): 847-860.
[9] 齐咏生, 张二宁, 高胜利, 等. 基于EEMD-KECA的风电机组滚动轴承故障诊断[J]. 太阳能学报, 2017, 38(7): 1943-1951.
Qi Yongsheng, Zhang Erning, Gao Shengli, et al.Wind Turbine Rolling Bearings Fault Diagnosis Based on EEMD-KECA[J]. Acta Energiae Solaris Sinica, 2017, 38(7): 1943-1951.
[10] 余绍斌, 丁强, 江爱朋, 等. 基于KECA-IGKDE的离心式冷水机组故障检测[J]. 测控技术, 2019, 38(11): 68-72, 80.
Yu Shaobin, Ding Qiang, Jiang Aipeng, et al.Centrifugal Chiller Fault Detection Based on KECA-IGKDE Method[J]. Measurement & Control Technology, 2019, 38(11): 68-72, 80.
[11] 周宏娣. 基于核熵成分分析的滚动轴承状态识别方法研究[D]. 武汉: 华中科技大学, 2017.
Zhou Hongdi.Research on Condition Recognition Methods of Rolling Bearings Based on Kernel Entropy Component Analysis[D]. Wuhan: Huazhong University of Science and Technology, 2017.
[12] Izquierdo-Verdiguier E, Laparra V, Jenssen R, et al.Camps-Valls. Optimized Kernel Entropy Components[J]. IEEE Transactions on Neural Networks and Learning Systems (S2162-237X), 2017, 28(6): 1466-1472.
[13] Renyi A.On measures of entropy and information[C]// 4th Berkeley Symposium on Mathematical Statistics and Probability. California, USA: University of California Press, 1961: 547-561.
[14] Jenssen R.Information Theoretic Learning and Kernel Methods[M]. Information Theory and Statistical Learning. Boston, MA: Springer, 2009: 209-230.
[15] He X, Niyogi P.Locality preserving projections[C]// Advances in Neural Information Processing Systems. Vancouver, Canada: Neural Information Processing Systems Foundation, 2003: 585-591.
[16] 韩敏, 李宇, 韩冰. 基于改进结构保持数据降维方法的故障诊断研究[J/OL]. 自动化学报[2020-08-13].https: //doi.org/10.16383/j.aas.c180138.
Han Min, Li Yu, Han Bing.Research on Fault Diagnosis of Data Dimension Reduction Based on Improved Structure Preserving Algorithm[J/OL]. Acta Automatica Sinica[2020-08-13].https://doi.org/10.16383/j.aas. c180138.
[17] 王绵斌, 安磊, 李芬花, 等. 基于遗传算法的耦合隐马尔科夫模型的故障诊断方法[J]. 机械设计与制造, 2018(12): 195-198.
Wang Mianbin, An Lei, Li Fenhua, et al.Fault Diagnosis Method Based on GA-CHMM[J]. Machinery Design & Manufacture, 2018(12): 195-198.
[18] 刘学坤. 基于支持向量机和油液检测的船舶发动机故障诊断研究[D]. 大连: 大连海事大学, 2013.
Liu Xuekun.The Research of Marine Diesel Engine Fault Diagnosis Based on SVM and Oil Monitoring[D]. Dalian: Dalian Maritime University, 2013.

基于监督核熵成分分析的发动机磨损故障诊断

Engine Wear Fault Diagnosis Based on Supervised Kernel Entropy Component Analysis

PDF (PC)

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

本文评价

[1]	李元, 耿泽伟. 基于LLE与K均值聚类算法的工业过程故障诊断[J]. 系统仿真学报, 2021, 33(9): 2066-2073.
[2]	王印松, 孙天舒. 基于二分类NMF网络的执行器故障状态评估[J]. 系统仿真学报, 2021, 33(8): 1882-1891.
[3]	位晶晶, 刘勤明, 叶春明, 李冠林. 基于GA-SVR的小样本数据缺失下的设备故障诊断[J]. 系统仿真学报, 2021, 33(6): 1342-1349.
[4]	吴定会, 祝志超, 韩欣宏. 基于BO-SDAE多源信号的风电机组轴承故障诊断[J]. 系统仿真学报, 2021, 33(5): 1148-1156.
[5]	刘轩, 李向阳, 何芳, 赵建伟, 张峰干. 基于空谱特征融合的高光谱RX异常检测方法[J]. 系统仿真学报, 2021, 33(12): 2891-2900.
[6]	宋晓瑞, 邹玲, 吴玲达, 徐万朋. 基于背景重建的高光谱图像异常检测[J]. 系统仿真学报, 2020, 32(7): 1287-1293.
[7]	李炜, 周丙相, 蒋栋年. 基于深度学习序贯检验的电源车故障诊断方法[J]. 系统仿真学报, 2020, 32(4): 638-648.
[8]	樊名鲁, 王艳, 纪志成. 基于特征生成的轴承不均衡数据故障诊断[J]. 系统仿真学报, 2020, 32(12): 2438-2448.
[9]	车辚辚, 孔英会, 陈智雄. 基于最大方差展开法的电能质量扰动识别[J]. 系统仿真学报, 2019, 31(8): 1702-1710.
[10]	李炜, 葛振福, 申富媛, 龚建兴. 基于FDRE的3D威亚编码器故障检测与容错控制[J]. 系统仿真学报, 2019, 31(4): 740-749.
[11]	曹京亚, 韩绍坤, 夏文泽, 王亮. 一种条纹管多光谱激光三维成像系统的仿真算法[J]. 系统仿真学报, 2019, 31(2): 283-293.
[12]	王天润, 苏中, 刘宁, 李超, 付国栋. 跌倒检测的时频特征提取方法研究[J]. 系统仿真学报, 2019, 31(12): 2600-2605.
[13]	贺梦嘉, 吴迎年, 杨睿. 基于改进深度回归网络的无创血糖检测算法研究[J]. 系统仿真学报, 2019, 31(11): 2492-2498.
[14]	贾立山, 刘喆, 孙毅. 基于RMBP神经网络的飞机电气故障智能诊断[J]. 系统仿真学报, 2018, 30(9): 3493-3501.
[15]	沈艳霞, 苗贝贝. 三电平逆变器的开关管开路故障诊断策略[J]. 系统仿真学报, 2018, 30(8): 3058-3065.