Fault Diagnosis Method of Diesel Engine Based on Improved Structure Preserving and K-NN Algorithm

被引：0
|
作者：
Li, Yu [1 ]
Han, Min [1 ]
Han, Bing [2 ]
Le, Xinyi [3 ]
Kanae, Shunshoku [4 ]
机构：
[1] Dalian Univ Technol, Fac Elect Informat & Elect Engn, Dalian 116023, Peoples R China
[2] Shanghai Ship & Shipping Res Inst, State Key Lab Nav & Safety Technol, Shanghai 200135, Peoples R China
[3] Shanghai Jiao Tong Univ, Sch Mech Engn, Shanghai 200240, Peoples R China
[4] Junshin Gakuen Univ, Dept Med Engn, Fac Hlth Sci, Fukuoka, Fukuoka, Japan
来源：
ADVANCES IN NEURAL NETWORKS - ISNN 2018 | 2018年 / 10878卷
基金：
中国国家自然科学基金;
关键词：
Diesel engine fault diagnosis; Feature extraction; Kernel Principal Component Analysis; Locality structure preserving; Modified K-NN;
D O I：
10.1007/978-3-319-92537-0_75
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
The diesel engine fault data is nonlinear and it's difficult to extract the characteristic information. Kernel Principal Component Analysis (KPCA) is used to extract features of nonlinear data, only considering global structure. Kernel Locality Preserving Projection (KLPP) considers the local feature structure. So an improved algorithm for global and local structure preserving is proposed to extract the feature of data. The improved feature extraction algorithm combining KPCA and KLPP, avoids the loss of information considering the global and local feature structure and then uses the modified K-NN algorithm for fault classification. In this paper, the software AVL BOOST is used to simulate the faults of diesel engine. The simulation experiments indicate the proposed method can extract the feature vectors effectively, and shows good classification performance.
引用
收藏
页码：656 / 664
页数：9
相关论文
共 50 条
  • [1] An Improved Fingerprint Method Based on K-NN Algorithm for Indoor Multiple Object Tracking
    Rahmadini, Asti Putri
    Kristalina, Prima
    Sudarsono, Amang
    [J]. 2017 INTERNATIONAL ELECTRONICS SYMPOSIUM ON ENGINEERING TECHNOLOGY AND APPLICATIONS (IES-ETA), 2017, : 239 - 244
  • [2] The Improved Text Classification Method Based on Bayesian and k-NN
    Tao, Wang
    Liang, Huo
    Liu, Yang
    [J]. PROCEEDINGS OF THE 2012 INTERNATIONAL CONFERENCE OF MODERN COMPUTER SCIENCE AND APPLICATIONS, 2013, 191 : 57 - +
  • [3] An Improved Feature-Weighted Method Based on K-NN
    Gao Yunlong
    Liu Yixiao
    [J]. PROCEEDINGS OF THE 35TH CHINESE CONTROL CONFERENCE 2016, 2016, : 6950 - 6956
  • [4] Research of liver cancer detection based on improved K-NN algorithm
    Liu, Jianhua
    Wang, Jianwei
    Bu, Wenjuan
    [J]. Journal of Chemical and Pharmaceutical Research, 2014, 6 (05) : 360 - 367
  • [5] An improved k-NN algorithm for localization in multipath environments
    Yang Zhao
    Kaihua Liu
    Yongtao Ma
    Zhuo Li
    [J]. EURASIP Journal on Wireless Communications and Networking, 2014
  • [6] Diesel Engine Fault Diagnosis Method Based on Optimized VMD and Improved CNN
    Zhan, Xianbiao
    Bai, Huajun
    Yan, Hao
    Wang, Rongcai
    Guo, Chiming
    Jia, Xisheng
    [J]. PROCESSES, 2022, 10 (11)
  • [7] An improved k-NN algorithm for localization in multipath environments
    Zhao, Yang
    Liu, Kaihua
    Ma, Yongtao
    Li, Zhuo
    [J]. EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING, 2014, : 1 - 10
  • [8] A K-NN algorithm based fault locating system for HVDC transmission lines
    Flih, Abdelhak
    Souag, Slimane
    Ghomri, Leila
    [J]. PRZEGLAD ELEKTROTECHNICZNY, 2023, 99 (11): : 104 - 108
  • [9] A case based method to predict optimal k value for k-NN algorithm
    Yang Zhongguo
    Li Hongqi
    Zhu Liping
    Liu Qiang
    Ali, Sikandar
    [J]. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2017, 33 (01) : 55 - 65
  • [10] Induction motor fault diagnosis based on the k-NN and optimal feature selection
    Nguyen, Ngoc-Tu
    Lee, Hong-Hee
    [J]. INTERNATIONAL JOURNAL OF ELECTRONICS, 2010, 97 (09) : 1071 - 1081
12345