The Journal of Engine Research

The Journal of Engine Research

Development of Machine Vision System to Track Movement of an Engine Timing Belt Tensioner Based on Deep Neural Network

Document Type : Original Article

Authors
Ali Reza Hosseini 1
Ashkan Moosavian 2
Saeed Javan 3
Shahriar B. Shokouhi 4
1 B.Sc. Student, School of Electrical Engineering, Iran University of Science and Technology (IUST), Tehran, Iran
2 Assistant Professor, Department of Agricultural Engineering, Technical and Vocational University (TVU), Tehran, Iran
3 Engine Labs Unit, Irankhodro Powertrain Company (IPCo)
4 Associate Professor, School of Electrical Engineering, Iran University of Science and Technology (IUST), Tehran, Iran
10.22034/er.2022.697916
Abstract
Belt tensioner is one of the main components in timing mechanism of IC engines. This component has an angular motion to adjust the timing belt tension and ensure the continuous connection between crankshaft and camshafts. This angular motion is one of the important parameters in design of the belt tensioner, which is evaluated during validation tests. The present paper, with the aim of using in modern validation tests, presents a new method for measuring the kinetic characteristics of the belt tensioner. The proposed method is a machine vision system that uses a deep neural network to track the movement of the belt tensioner indicator and then obtain its motion characteristics including angular displacement, velocity and acceleration. To this end, the engine test was designed and performed so that the belt travels its entire stroke. Simultaneously the movement of the belt tensioner was captured with a camera. The results showed that the tensioner indicator was correctly tracked with about 80% accuracy during the whole test. The maximum angular displacement of this component reached 14 degrees at the end of the test. The results also showed that the belt tensioner under study moved with the maximum angular speed and acceleration of 1 rad/s and 61 rad/s2. In addition, it was found that the frequency of the belt tensioner movement reached about 10 Hz. The results showed that the proposed method could be an appropriate alternative to conventional methods to measure the tensioner movement. 
Keywords
Belt Tensioner
Deep Neural Network
IC Engine
Machine vision
Timing Mechanism
[1] T. Koyama, K.M. Marshek, Toothed belt drives—past, present and future, Mechanism and Machine Theory, Vol. 23, pp. 227-241, 1988
[2] R. Perneder, I. Osborne, Handbook timing belts: principles, calculations, applications, Springer Science & Business Media, 2012
[3] N. Paul, C. Chung, Application of HDR algorithms to solve direct sunlight problems when autonomous vehicles using machine vision systems are driving into sun, Computers in Industry, Vol. 98, pp. 192-196, 2018
[4] H.A. Williams, M.H. Jones, M. Nejati, M.J. Seabright, J. Bell, N.D. Penhall, J.J. Barnett, M.D. Duke, A.J. Scarfe, H.S. Ahn, Robotic kiwifruit harvesting using machine vision, convolutional neural networks, and robotic arms, Biosystems Engineering, Vol. 181, pp. 140-156, 2019
[5] E. Pechenina, V. Pechenin, M. Bolotov, Neural network training procedure for machine vision systems in aerospace industries,  AIP Conference Proceedings, AIP Publishing LLC, pp. 040014, 2021
[6] A. Martín, R. Lara-Cabrera, F. Fuentes-Hurtado, V. Naranjo, D. Camacho, EvoDeep: a new evolutionary approach for automatic deep neural networks parametrisation, Journal of Parallel and Distributed Computing, Vol. 117, pp. 180-191, 2018
[7] H. Yaşar, G. Çağıl, O. Torkul, M. Şişci, Cylinder Pressure Prediction of An HCCI Engine Using Deep Learning, Chinese Journal of Mechanical Engineering, Vol. 34, pp. 1-8, 2021
[8] N. Audebert, B. Le Saux, S. Lefèvre, Segment-before-detect: Vehicle detection and classification through semantic segmentation of aerial images, Remote Sensing, Vol. 9, pp. 368, 2017
[9] X. Wang, W. Zhang, X. Wu, L. Xiao, Y. Qian, Z. Fang, Real-time vehicle type classification with deep convolutional neural networks, Journal of Real-Time Image Processing, Vol. 16, pp. 5-14, 2019
[10] M.A. Rafique, W. Pedrycz, M. Jeon, Vehicle license plate detection using region-based convolutional neural networks, Soft Computing, Vol. 22, pp. 6429-6440, 2018
[11] J. Li, X. Shi, J. Wang, M. Yan, Adaptive road detection method combining lane line and obstacle boundary, IET Image Processing, Vol. 14, pp. 2216-2226, 2020
[12] S. Capela, R. Silva, S.R. Khanal, A.T. Campaniço, J. Barroso, V. Filipe, Engine Labels Detection for Vehicle Quality Verification in the Assembly Line: A Machine Vision Approach,  Portuguese Conference on Automatic Control, Springer, pp. 740-751, 2020
[13] J. Rochussen, P. Kirchen, Robust image segmentation for feature extraction from internal combustion engine in-cylinder images, Measurement Science and Technology, Vol. 32, pp. 015302, 2020
[14] R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation,  Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580-587, 2014
[15] J. Redmon, S. Divvala, R. Girshick, A. Farhadi, You only look once: Unified, real-time object detection, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788, 2016
[16] G. Jocher, A. Stoken, J. Borovec, NanoCode012, ChristopherSTAN, L, Changyu, Laughing, tkianai, A. Hogan, lorenzomammana, yxNONG, AlexWang1900, L. Diaconu, Marc, wanghaoyang0106, ml5ah, Doug, F. Ingham, Frederik, Guilhen, Hatovix, J. Poznanski, J. Fang, L. Yu, changyu98, M. Wang, N. Gupta, O. Akhtar, PetrDvoracek, and P. Rai,“ultralytics/yolov5: v3, 1 2020
[17] J.A. Kim, J.Y. Sung, S.H. Park, Comparison of Faster-RCNN, YOLO, and SSD for real-time vehicle type recognition, 2020 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), IEEE, pp. 1-4, 2020
[18] T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, C.L. Zitnick, Microsoft coco: Common objects in context, European conference on computer vision, Springer, pp. 740-75, 2014.
The Journal of Engine Research
Volume 67, Issue 67
Spring 2022
Pages 16-23

  • Receive Date 04 February 2022
  • Revise Date 19 May 2022
  • Accept Date 19 May 2022