This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Research on Vehicle State Segmentation and Failure Prediction Based on Big Data
Technical Paper
2022-01-0223
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Vehicle failure prediction technology is an important part of PHM (Prognostic and Health Management) technology, which is of great significance to the safety of vehicles and to improve driving safety. Based on the vehicle operating data collected by the on-board terminal (T-box) of the telematics system, the research on the state of vehicle failure is conducted. First, this paper conducts statistical analysis on vehicle historical fault data. Preprocessing procedures such as cleaning, integration, and protocol are performed to group the data set. Then, three indexes including recency (R) frequency (F), and days (D) are selected to construct a vehicle security status subdivision system, and K -Means algorithm is utilized to divide different vehicle categories from the perspective of vehicle value. Labeled information of vehicles in different security status are further established. Moreover, taking engine faults as an example, this paper uses gray correlation analysis method to extract key fault characteristic parameters. Based on self-organizing mapping network theory (SOM), the fault prediction model is built. And, by learning the fault data of the vehicles and obtaining the characteristic differences between different states, the prediction of fault and evaluation of vehicle condition is completed. Finally, test data is selected to verify the prediction accuracy of the model.
Recommended Content
Authors
- Zheng Lu - Nanjing University of Science and Technology
- Jingxing Liu - Nanjing University of Science and Technology
- Xiaojun Zou - Southeast University
- Hong Zhong - Nanjing University of Science and Technology
- Ailei Zhang - Nanjing Iveco Automobile Co. Ltd.
- Liangmo Wang - Nanjing University of Science and Technology
Citation
Lu, Z., Liu, J., Zou, X., Zhong, H. et al., "Research on Vehicle State Segmentation and Failure Prediction Based on Big Data," SAE Technical Paper 2022-01-0223, 2022, https://doi.org/10.4271/2022-01-0223.Also In
References
- Johnson , S. , Gormley , T. , Kessler , S. et al. System Health Management with Aerospace Applications John Wiley & sons, Inc. 2011
- Nickerson , B. , and Lally , R. Development of a Smart Wireless Networkable Sensor for Aircraft Engine Health Management Proceeding of Aerospace Conference 2001 3255 3262
- Ding , B. 2011
- Jiang , X. , Fu , X. , and Yang , Z. Application of RBF Neural Network Analysis Method in Remote Monitoring System of Vehicle State Automotive Practical Technology 3 2011 23 26
- Li , H. and Xiao , D. Overview of Fault Diagnosis Methods Based on Data-Driven Control and Decision 26 1 2011 1 9
- Virk , S. , Muhammad , A. , and Martinez-Enriquez , A. Fault Prediction Using Artificial Neural Network and Fuzzy Logic IEEE Computer Society 2008
- Li , H. Function and Application of Vehicle State Analysis Software based on On-Board Data Urban Rail Transit Research 18 6 2015 150 152
- Marko , K. , James , J. , Dosdall , J. , et al. Automotive Control System Diagnostics Using Neural Nets for Rapid Pattern Classification of Large Data Sets International Joint Conference on Neural Networks 2009
- Sharkey , A. , Sharkey , N. , and Chandroth , G. Diverse Neural Net Solutions to a Fault Diagnosis Problem Neural Computing & Applications 4 4 2012 218 227
- Zhang , K. , Lu , D. , Song , L. et al. Research on Engine Fault Diagnosis Based on Support Vector Machine Digital Technology and Application 3 2011 50 51
- Li , X. Research and Development of Hydraulic Press Fault Diagnosis Expert System based on Rough Set Neural Network Hefei University of Technology 2012
- Bai , W. Comparison of RBF Neural Network and BP Neural Network in Engine Fault Diagnosis Science and Technology Outlook 26 2017
- Shao , Z. Research on Engine Fault Diagnosis based on Data Stream Modern Vocational Education 5 2017 36 36
- Shi , N. , Zhu , X. , Yuan , P. , et al. 2015 2431 2435
- Wu , C. , Wu , Z. , Zang , C. , Deng , Z. et al. Improving Customer Value Index and Consumption Forecasts Using a Weighted RFM Model and Machine Learning Algorithms Journal of Global Information Management 30 3 2021 1 23 10.4018/JGIM.20220701.OA1
- Yin , S. , Wang , T. , Xie , F. , and Liu , L. Clustering Result Evaluation Method Based on Mutual Information and Contour Coefficient Journal of Ordnance Equipment Engineering 41 08 2020
- Werbos , P. Backpropagation: Past and Future IEEE International Conference on Neural Network 1988 343 353
- Aboemagd , N. , Rashad , S. , Ahmed , O. et al. INS/GPS Data Fusion Technique Utilizing Radial Basis Function Neural Network IEEE 2 2004 280 284
- Chang , B. Research on Artificial Neural Network Forecast of Railway Freight Volume Based on Economic Cycle Hunan Central South University 2010
- Ge , Y. and Wang , L. Application of Self-Organizing Competitive Artificial Neural Network in Color Selection Computer System Application 01 2010 137 139
- Midenet , S. and Grumbach , A. Learning Associations by Self-Organization: The LASSO Model Neurocompition 6 1994 343 361
- Wang , M. , Xu , X. , Yan , Z. et al. An Online Optimization Method for Extracting Parameters of Multi-Parameter PV Module Model Based on Adaptive Levenberg-Marquardt Algorithm Energy Conversion and Management 245 2021 10.1016/J.ENCONMAN.2021.114611