Vibration-based identification of engine valve clearance using a convolutional neural network

Maciej Tabaszewski; Grzegorz M. Szymański; Tomasz Nowakowski

doi:10.5604/01.3001.0015.8254

Authors

Maciej Tabaszewski Poznan University of Technology, Institute of Applied Mechanics, Poznań Author https://orcid.org/0000-0001-6215-8485
Grzegorz M. Szymański Poznan University of Technology, Institute of Transport, Poznań Author https://orcid.org/0000-0002-2784-9149
Tomasz Nowakowski Poznan University of Technology, Institute of Transport, Poznań Author https://orcid.org/0000-0001-5415-7052

DOI:

https://doi.org/10.5604/01.3001.0015.8254

Keywords:

combustion engine, diagnostics, vibration, machine learning, convolutional network

Abstract

Contemporary operation-related requirements for combustion engines force the necessity of ongoing assessment of their in operation technical condition (e.g. marine engines). The engine efficiency and durability depend on a variety of parameters. One of them is valve clearance. As has been proven in the paper, the assessment of the valve clearance can be based on vibration signals, which is not a problem in terms of signal measurement and processing and is not invasive into the engine structure. The authors described the experimental research aiming at providing information necessary to develop and validate the proposed method. Active experiments were used with the task of valve clearance and registration of vibrations using a three-axis transducer placed on the engine cylinder head. The tests were carried out during various operating conditions of the engine set by 5 rotational speeds and 5 load conditions. In order to extract the training examples, fragments of the signal related to the closing of individual valves were divided into 11 shorter portions. From each of them, an effective value of the signal was determined. Obtained total 32054 training vectors for each valve related to 4 classes of valve clearance including very sensitive clearance above 0.8 mm associated with high dynamic interactions in cylinder head. In the paper, the authors propose to use a convolutional network CNN to assess the correct engine valve clearance. The obtained results were compared with other methods of machine learning (pattern recognition network, random forest). Finally, using CNN the valve clearance class identification error was less than 1% for the intake valve and less than 3.5% for the exhaust valve. Developed method replaces the existing standard methods based on FFT and STFT combined with regression calculation where approximation error is up to 10%. Such results are more useful for further studies related not only to classification, but also to the prediction of the valve clearance condition in real engine operations.

References

Arroyo, J., Muñoz, M., Moreno, F., Bernal, N., Monné, C. (2013). Diagnostic method based on the analysis of the vibration and acoustic emission energy for emergency diesel generators in nuclear plants. Applied Acoustics, 74(4), 502–508. https://doi.org/10.1016/j.apacoust.2012.09.010.

Aslan, M. F., Sabanci, K., Durdu, A., Unlersen, M. F. (2022). COVID-19 diagnosis using state-of-the-art CNN architecture features and Bayesian Optimization. Computers in Biology and Medicine, 142, 105244. https://doi.org/10.1016/j.compbiomed.2022.105244.

Babu, A. K., Raj, V., Govindaraj, K. (2016). Misfire detection in a multi-cylinder diesel engine: A machine learning approach. Journal of Engineering Science and Technology, 11, 278–295.

Badawy, T., Shrestha, A., Henein, N. (2012). Detection of combustion resonance using an ion current sensor in diesel engines. Journal of Engineering for Gas Turbines and Power, 134(5), 1–9. https://doi.org/10.1115/1.4004840.

Ben Fredj, H., Bouguezzi, S., Souani, C. (2021). Face recognition in unconstrained environment with CNN. Visual Computer, 37(2), 217–226. https://doi.org/10.1007/s00371-020-01794-9.

Bilal, A., Sun, G., Li, Y., Mazhar, S., Latif, J. (2022). Lung nodules detection using grey wolf optimization by weighted filters and classification using CNN. Journal of the

Chinese Institute of Engineers, Transactions of the Chinese Institute of Engineers, Series A. https://doi.org/10.1080/02533839.2021.2012525.

Boulila, W., Ghandorh, H., Khan, M. A., Ahmed, F., Ahmad, J. (2021). A novel CNN-LSTM-based approach to predict urban expansion. Ecological Informatics, 64, 101325. https://doi.org/https://doi.org/10.1016/j.ecoinf.2021.101325.

Brzeziński, K. (2011). Active - Passive: On Preconceptions of Testing. Journal of Telecommunications and Information Technology, nr 3, 63–73.

Cai, Y., Li, A., He, Y., Wang, T., Zhao, J. (2010). Application of wavelet packets and GA-BP algorithm in fault diagnosis for diesel valve gap abnormal fault. 2010 2nd International Conference on Advanced Computer Control, 4, 621–625. https://doi.org/10.1109/ICACC.2010.5487142.

Delvecchio, S., Bonfiglio, P., Pompoli, F. (2018). Vibro-acoustic condition monitoring of Internal Combustion Engines: A critical review of existing techniques. Mechanical Systems and Signal Processing, 99, 661–683. https://doi.org/10.1016/j.ymssp.2017.06.033.

Desbazeille, M., Randall, R. B., Guillet, F., El Badaoui, M., Hoisnard, C. (2010). Model-based diagnosis of large diesel engines based on angular speed variations of the crankshaft. Mechanical Systems and Signal Processing, 24(5), 1529–1541. https://doi.org/10.1016/j.ymssp.2009.12.004.

Devraj Mudgal, Rohit Nikam, Trupti Nikumbh, M. K. (2021). Traffic sign detection and recognition using CNN and Keras. International Research Journal of Engineering and Technology, 8(5), 2333–2335.

Dey, D., Chatterjee, B., Dalai, S., Munshi, S., Chakravorti, S. (2017). A deep learning framework using convolution neural network for classification of impulse fault patterns in transformers with increased accuracy. IEEE Transactions on Dielectrics and Electrical Insulation, 24, 3894–3897.

Dolatabadi, N., Theodossiades, S., Rothberg, S. J. (2015). On the identification of piston slap events in internal combustion engines using tribodynamic analysis. Mechanical Systems and Signal Processing, 58, 308–324. https://doi.org/10.1016/j.ymssp.2014.11.012.

Figlus, T., Gnap, J., Skrúcaný, T., Šarkan, B., Stoklosa, J. (2016). The use of denoising and analysis of the acoustic signal entropy in diagnosing engine valve clearance. Entropy, 18(7). https://doi.org/10.3390/e18070253.

Figlus, T., Liščák, Š., Wilk, A., Łazarz, B. (2014). Condition monitoring of engine timing system by using wavelet packet decomposition of a acoustic signal. Journal of Mechanical Science and Technology, 28(5), 1663–1671. https://doi.org/10.1007/s12206-014-0311-3.

Galkin, A. (2017). Urban environment influence on distribution part of logistics systems. Archives of Transport, 42(2), 7–23. https://doi.org/10.5604/01.3001.0010.0522.

Gao, F., Huang, T., Wang, J., Sun, J., Hussain, A., Yang, E. (2017). Dual-branch deep convolution neural network for polarimetric SAR image classification. Applied Sciences, 7(5). https://doi.org/10.3390/app7050447.

Gao, F., Lv, J. (2016). Fault Diagnosis for Engine Based on Single-Stage Extreme Learning Machine. Mathematical Problems in Engineering, 2016, 7939607. https://doi.org/10.1155/2016/7939607.

Gawande, S. H., Navale, L. G., Nandgaonkar, M. R., Butala, D. S., Kunamalla, S. (2012). Fault Detection of Inline Reciprocating Diesel Engine: A Mass and Gas-Torque Approach. Advances in Acoustics and Vibration, 2012, 314706. https://doi.org/10.1155/2012/314706.

Géron, A. (2017). Hands-On Machine Learning with Scikit-Learn and TensorFlow. O’Reilly Media.

Goswami, T., Javaji, S. R. (2021). CNN model for American sign language recognition. In A. Kumar and S. Mozar (Eds.), ICCCE 2020 (pp. 55–61). Springer Singapore.

Huang, X., Li, Y., Chai, Y. (2021). Intelligent fault diagnosis method of wind turbines planetary gearboxes based on a multi-scale dense fusion network. Frontiers in Energy Research, 9. https://doi.org/10.3389/fenrg.2021.747622.

Khumaidi, A., Yuniarno, E. M., Purnomo, M. H. (2017). Welding defect classification based on convolution neural network (CNN) and Gaussian kernel. 2017 International Seminar on Intelligent Technology and Its Applications (ISITIA), 261–265.

Krishnaswamy Rangarajan, A., Ramachandran, H. K. (2022). A fused lightweight CNN model for the diagnosis of COVID-19 using CT scan images. Automatika, 63(1), 171–184. https://doi.org/10.1080/000 51144.2021.2014037.

Leclere, Q., Pezarat, C., Laulagent, B., Polac, L. (66 C.E.). Application of multi-channel spectral analysis to identify the source of a noise amplitude modulation in a diesel engine operating at idle. Applied Acoustics, 7(7), 779–798.

Lekha, S., M, S. (2018). Real-time non-invasive detection and classification of diabetes using modified convolution neural network. IEEE Journal of Biomedical and Health Informatics, 22(5), 1630–1636. https://doi.org/10.1109/JBHI.2017.2757510.

Lin, J., Yao, Y., Ma, L., Wang, Y. (2018). Detection of a casting defect tracked by deep convolution neural network. The International Journal of Advanced Manufacturing Technology, 97, 573–581.

Liu, Y., Pei, S., Fu, W., Zhang, K., Ji, X., Yin, Z. (2017). The discrimination method as applied to a deteriorated porcelain insulator used in transmission lines on the basis of a convolution neural network. IEEE Transactions on Dielectrics and Electrical Insulation, 24(6), 3559–3566. https://doi.org/10.1109/TDEI.2017.006840.

Lu, J., Ye, Y., Xu, X., Li, Q. (2019). Application research of convolution neural network in image classification of icing monitoring in power grid. EURASIP Journal on Image and Video Processing, 2019(1), 49. https://doi.org/10.1186/s13640-019-0439-2.

Ma, X., Yan, W. Q. (2021). Banknote serial number recognition using deep learning. Multimedia Tools and Applications, 80(12), 18445–18459. https://doi.org/10.1007/s11042-020-10461-z.

Merkisz-Guranowska, A., Pielecha, J. (2014). Passenger cars and heavy duty vehicles exhaust emissions under real driving conditions. Archives of Transport, 31(3), 47–59. https://doi.org/10.5604/08669546.1146986.

Merkisz, J., Jacyna, M., Merkisz-Guranowska, A., Pielecha, J. (2014). The parameters of passenger cars engine in terms of real drive emission test. Archives of Transport, 32(4), 43–50. https://doi.org/10.5604/08669546.1146998.

Nakjai, P., Katanyukul, T. (2019). Hand sign recognition for thaifinger spelling: an application of convolution neural network. J. Signal Process. Syst., 91(2), 131–146. https://doi.org/10.1007/s11265-018-1375-6.

Nowakowski, T., Komorski, P. (2021). Diagnostics of the drive shaft bearing based on vibrations in the high-frequency range as a part of the vehicle’s self-diagnostic system. Eksploatacja i Niezawodnosc – Maintenance and Reliability, 24(1), 70–79. https://doi.org/10.17531/ein.2022.1.9.

Omar, F. K., Selim, M. Y. E., Emam, S. A. (2017). Time and frequency analyses of dual-fuel engine block vibration. Fuel, 203, 884–893. https://doi.org/https://doi.org/10.1016/j.fuel.2017.05.034.

Pham, M.-T., Kim, J.-M., Kim, C.-H. (2021). 2D CNN-based multi-output diagnosis for compound bearing faults under variable rotational speeds. Machines, 9(9). https://doi.org/10.3390/machines9090199.

Ramaiyan, A., Dnvsls, I., Lanka, D. (2021). Acoustic based Scene Event Identification Using Deep Learning CNN. Turkis Journal of Computer and Mathematics Education (TURCOMAT), 12, 1398–1405.

Ren, L., Sun, Y., Wang, H., Zhang, L. (2018). Prediction of bearing remaining useful life with deep convolution neural network. IEEE Access, PP, 1. https://doi.org/10.1109/ACCESS.2018.2804930.

Sannasi Chakravarthy, S. R., Bharanidharan, N., Rajaguru, H. (2022). Multi-Deep CNN based Experimentations for Early Diagnosis of Breast Cancer. IETE Journal of Research, 1-16. https://doi.org/10.1080/03772063.2022.2028584.

Sarker, G. (2018). Some studies on convolution neural network. International Journal of Computer Applications, 182(21), 13–22. https://doi.org/10.5120/ijca2018917965.

Szymański, G.M. (2005). Analysis possibilities application of characteristic of vibration signal for diagnostic of internal combustion engine (in Polish). Poznan University of Technology.

Szymański, Grzegorz M., Tomaszewski, F. (2016). Diagnostics of automatic compensators of valve clearance in combustion engine with the use of vibration signal. Mechanical Systems and Signal Processing, 68–69, 479–490. https://doi.org/10.1016/j.ymssp.2015.07.015.

Szymański, Grzegorz M, Tabaszewski, M. (2020). Engine valve clearance diagnostics based on vibration signals and machine learning methods. Maintenance and Reliability, 22(2), 331–339. https://doi.org/10.17531/ein.2020.2.16.

Wang, Z., Liu, T. (2022). Two-stage method based on triplet margin loss for pig face recognition. Computers and Electronics in Agriculture, 194, 106737. https://doi.org/10.1016/j.compag.2022.106737.

Wong, P. K., Zhong, J., Yang, Z., Vong, C. M. (2016). Sparse Bayesian extreme learning committee machine for engine simultaneous fault diagnosis. Neurocomput., 174(PA), 331–343. https://doi.org/10.1016/j.neucom.2015.02.097.

Wu, H., Chen, J., Liu, X., Xiao, Y., Wang, M., Zheng, Y., Rao, Y. (2019). One-Dimensional CNN-Based Intelligent Recognition of Vibrations in Pipeline Monitoring With DAS. Journal of Lightwave Technology, 37(17), 4359–4366. https://doi.org/10.1109/jlt.2019.2923839.

Ye, F., Zhai, X. (2019). Research on energy management strategy of diesel hybrid electric vehicle based on decision tree CART algorithm. IOP Conference Series: Materials Science and Engineering, 677(3). https://doi.org/10.1088/1757-899X/677/3/032 076.

Zhang, P., Gao, W., Li, Y., Wei, Z. (2021). Combustion parameter evaluation of diesel engine via vibration acceleration signal. International Journal of Engine Research, July. https://doi.org/10.1177/14680874211030878.

Zhao, Y. P., Song, F. Q., Pan, Y. T., Li, B. (2017). Retargeting extreme learning machines for classification and their applications to fault diagnosis of aircraft engine. Aerospace Science and Technology, 71(October), 603-618. https://doi.org/10.1016/j.ast.2017.10.004.