Engine Wear Fault Diagnosis Based on Supervised Kernel Entropy Component Analysis

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

Abstract

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

CLC Number:

TP391.9

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.

References

[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.