Journal of Vibration and Sound

Journal of Vibration and Sound

New Algorithm for Fault Detection of Diesel Engine Injector Nozzle through Vibration Analysis, T Test, and SVM Neural Network

Document Type : research article

Authors
Mahdi Zakizadeh 1
Ali Jamali 2
Mansour Rafeeyan 3
1 Mechanical Engineering Department, giulan University, Iran
2 Mechanical Engineering Department, Guilan University, Iran
3 Mech. Eng./Engineering Faculty/ Yazd University
Abstract
In this study, a new method for the fault detection of the locomotive engine injector nozzle based on vibration analysis and statistical tests, inside artificial neural networks, is presented. For this point, first the under study received vibration signals in the frequency domain is divided into several smaller ranges and the RMS of each range is then extracted as a frequency property and given as an input to the neural network. Because the high selection of the features reduces the accuracy of the neural network, the extracted feature vector with different levels of significance passes through the T-test filters, firstly, and then enters the neural network as an input. Using of this method, the accuracy of the neural network increases from 78.4 to 94.6%, and also help to detect the frequency ranges. According to the results, the fault of the injector nozzle crack increases the intensity of vibrations in the upper band frequencies of 1500 Hz.
Keywords
Condition monitoring
Vibration analysis
Diesel engines
Signal processing
Artificial neural network
Subjects
[1] Jones, N. B., and Yu‐Hua Li., "A review of condition monitoring and fault diagnosis for diesel engines", Tribotest, 2000, Vol.6, no.3, pp.267-291.
[2] F. Gu, W. Li, A. Ball, A. Leung, “The condition monitoring of diesel engines using acoustic measurements” part 1: acoustic characteristics of the engine and representation of the acoustic signals, SAE Technical Paper, 2000.
[3] Branco, C. M., V. Infante, A. Sousa e Brito, and R. F. Martins, "A failure analysis study of wet liners in maritime diesel engines", Engineering Failure Analysis, 2002, Vol.9, no.4, pp.403-421.
[4] Barelli, L., G. Bidini, C. Buratti, and R. Mariani, "Diagnosis of internal combustion engine through vibration and acoustic pressure non-intrusive measurements", Applied Thermal Engineering, 2009, Vol.29, no.8-9, pp.1707-1713.
[5] Klinchaeam, Songpon, Pornchai Nivesrangsan, and Ming Lokitsangthong, "Condition monitoring of a small four-stroke petrol engine using vibration signals", CURRENT APPLIED SCIENCE AND TECHNOLOGY, 2009, Vol.9, no.1, pp.9-17.
[6] Wang, Xia, Changwen Liu, Fengrong Bi, Xiaoyang Bi, and Kang Shao, "Fault diagnosis of diesel engine based on adaptive wavelet packets and EEMD-fractal dimension", Mechanical Systems and Signal Processing, 2013, Vol.41, no.1-2, pp.581-597.
[7] Flett, Justin, and Gary M. Bone, "Fault detection and diagnosis of diesel engine valve trains", Mechanical Systems and Signal Processing, 2016, Vol.72, pp.316-327.
[8] Elamin, Fathi, Fengshou Gu, and Andrew Ball, "Diesel engine injector faults detection using acoustic emissions technique", Modern Applied Science, 2010, Vol.44, no.9, pp.3-13.
[9] Moshou, Dimitrios, Athanasios Natsis, Dimitrios Kateris, Xanthoula-Eirini Pantazi, Ioannis Kalimanis, and Ioannis Gravalos, "Fault detection of fuel injectors based on one-class classifiers", Modern Mechanical Engineering, 2014 (2013).
[10] Ftoutou, Ezzeddine, and Mnaouar Chouchane, "Injection fault detection of a diesel engine by vibration analysis", International Conference Design and Modeling of Mechanical Systems,. Springer, Cham, 2017.
[11] Taghizadeh-Alisaraei, Ahmad, and Alireza Mahdavian, "Fault detection of injectors in diesel engines using vibration time-frequency analysis", Applied Acoustics, 2019, Vol.143, pp.48-58.
[12] Cortes, Corinna, and Vladimir Vapnik, "Support-vector networks", Machine learning, 1995, Vol.20, no.3, pp.273-297.
[13] Wang, Deqing, Hui Zhang, Rui Liu, and Weifeng Lv, "Feature selection based on term frequency and T-test for text categorization", In Proceedings of the 21st ACM international conference on Information and knowledge management, 2012, pp.1482-1486.
[14] Abdulmohsin, Husam Ali, Hala Bahjat Abdul Wahab, and Abdul Mohssen Jaber Abdul Hossen, "A New Hybrid Feature Selection Method Using T-test and Fitness Function", CMC-Computers Materials & Continua, 2021, Vol.68, no.3, pp.3997-4016.
[15] Zhou, Nina, and Lipo Wang, "A modified T-test feature selection method and its application on the HapMap genotype data", Genomics, proteomics & bioinformatics, 2007, Vol.5, no.3-4, pp.242-249.
[16] Devore, J., and R. Peck, "Statistics: The exploration and analysis of data. Duxbury Press", 1997.
[17] H.G. Bramhall Moor Lane, Alstom Maintenance Manual, 2002.
[18] SPM Instrument, Leonova Diamond, User Guide, 2017.