Rapid Inspection Technique for Conveyor Belt Deviation

Author(s): 
X. Z. Mei†‡, C. Y. Miao†*, Y. L. Yang†, & X. G. Li†

Affiliation(s): 

†School of Electronics and Information Engineering, Tianjin Polytechnic University, Tianjin 300387, China, 
‡College of Mechanical Engineering, Inner Mongolia University of Technology, Hohhot 010051, China
Cite this paper
X. Z. Mei, C. Y. Miao, Y. L. Yang, X. G. Li, “Rapid Inspection Technique for Conveyor Belt Deviation”, Journal of Mechanical Engineering Research and Developments, vol. 39, no. 3, pp. 653-662, 2016. DOI: 10.7508/jmerd.2016.03.006

ABSTRACT: In view of the problems of the existing conveyor belt deviation detection system, such as high false alarm rate and missing alarm rate, a rapid detection method of deviation fault based on machine vision is proposed. According to the consistency of the light intensity induced by the images in the same column collected by the linear array camera, a segmentation method that could rapidly extract the edges of the conveyor belt is adopted to restrain the effects of the large noise and uneven illumination of the conveyor belt image. Moreover, the offset of conveyor belt center and runway center, change rate of variance between columns of the edges of conveyor belt, and the twist angle are utilized to identify the belt deviation fault. Research results show that the method proposed in this paper could meet the requirements of timeliness, accuracy, and anti-noise property of the overall deviation within ±15% width of the belt and the twist deviation detection within ±10°.

Keywords : Conveyor belt; Deviation; Machine vision; Image processing

References
[1] H. W. Ma, Q. H. Mao, and X. H. Zhang, “Intelligent monitoring technology study process for steel cord conveyor belt in coal mine”, Journal of Vibration, Measurement and Diagnosis, vol. 36, no. 2, pp. 213-219, February 2016.
[2] A. Grincova, M. Andrejiova, and D. Marasova, “Failure analysis of conveyor belt in terms of impact loading by means of the damping coefficient”, Engineering Failure Analysis, vol. 68, no. 4, pp. 210-221, April 2016.
[3] T. Healy and W. D. Lange. “Reliability of geomorphic indicators of littoral drift: examples from the bay of plenty, New Zealand”, Journal of Coastal Research, vol. 30.2, pp. 301-318, 2005.
[4] J. Li and C. Y. Miao, “The conveyor belt longitudinal tear on-line detection based on improved SSR algorithm”, Optik, vol. 127, no. 19, pp. 7395-8202, October 2016.
[5] Y. L. Yang, C. Y. Miao, and X. G. Li, “On-line conveyor belts inspection based on machine vision”, Optik, vol. 125, no. 19, pp. 5803-5807, October 2014.
[6] X. Z. Mei, C. Y. Miao, and Y. L. Yang, “Automatic detection method for mine conveyor belt surface damage”, Journal of the China Coal Society, vol. 41, no. S1, pp. 259-265, December 2016.
[7] H. B. Liu and Z. L. Liu, “Recycling utilization patterns of coal mining waste in China”, Resources Conservation and Recycling, vol. 54, no. 12, pp. 1331-1340, 2010.
[8] K. Hu, S. Wang, and Y. C. Guo, “Analysis of lateral force and deviation of permanent magnetic levitation belt conveyor”, Journal of System Simulation, vol. 28, no. 5, pp. 1173-1178, May 2016.
[9] Z. L. Liu, “Environmental kuznets curve: A new computational test and modeling”, International Journal of Advancements in Computing Technology, vol. 5, no. 5, pp. 551-558, 2013. doi:10.4156/ijact.
[10] M. Zhang, H. L. Gao, and Y. Zhang, “Analysis and dispose of deviation of mine belt conveyor”, Applied Mechanics and Materials, vol. 28, no. 5, pp. 685-688, May 2014.
[11] S. K. Lu, “Analysis on belt deviation prevention device of mine belt conveyor”, Coal Engineering, vol. 46, no. 7, pp. 124-127, July 2014.
[12] Y. B. Li, “Discussion and analysis of the underground belt transport condition monitoring system in coal mine”, Shandong Coal Science and Technology, no. 6, pp. 110-113, June 2016.
[13] M. Priyanka and B. C. Bidyut, “A survey of the hough transform”, Pattern Recognition, vol. 48, no. 8, pp. 993-1010, August 2015.
[14] J. B. Burns, A. R. Hanson, and E. M. Riseman, “Extracting straight lines”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, no. 4, pp. 425-455, April 1986.
[15] R. G. Von Gioi, J. Jakubowicz, and J. M. Morel, “LSD: A fast line segment detector with a false detection control”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 4, pp. 722-732, April 2010.
[16] C. Akinlar and E. D. Topal, “Lines: A real-time line segment detector with a false detection control”, Pattern Recognition Letters, vol. 32, no. 13, pp. 1633-1642, July 2011.
[17] V. Patraucean, P. Gurdjos, and R. G. Von Gioi, “A parameterless line segment and elliptical arc detector with enhanced ellipse fitting”, in Computer Vision-ECCV 2012. Berlin: Springer, 2012, pp. 572-585.
[18] H. Xu, Z. B. Li, and Y. Y. Jiang, “Research of automatic detection algorithm of conveying belt deviation based on OpenCV”, Industry and Mine Automation, vol. 40, no. 9, pp. 48-52, September 2014.
[19] A. C. Zhu, G. Hua, and Y. X. Wang, “The research on the detection method of belt deviation by video in coal mine”, in 2011 International Conference on Mechatronic Science, Electric Engineering and Computer, 2011, pp. 430-433.
[20] Y. L. Yang, C. Y. Miao, and K. Kang, “Machine vision inspection technique for conveyor belt deviation”, Journal of North University of China(Natural Science Edition), vol. 33, no. 6, pp. 667-671, June 2012.
[21] T. Y. Li, J. Wang, and J. P. Li, “An effective correction method for uneven illumination images”, Journal of University of JiNan(Sci.&Tech.), vol. 29, no. 6, pp. 401-405, June 2015.
[22] L. N. Han, “The algorithm of correcting uneven illumination pavement image based on statistical properties”, Science Technology and Engineering, vol. 13, no. 26, pp. 7875-7879, December 2013.
[23] L. Zhu, R. L. Bai, and F. Ji, “Local threshold segmentation based on grayscale wave for uneven illumination image”, Computer Engineering and Applications, vol. 51, no. 12, pp. 144-149, December 2015.
[24] X. Fu, J. Zhang, and W. Wang, “A new local threshold segmentation algorithm”, Computer Applications and Software, vol. 32, no. 4, pp. 195-197, April 2015.
[25] C. P. Soo, Z. H. Yu, T. Z. Mary, and J. C. Feng, “Uneven illumination removal and image enhancement using empirical mode decomposition”, Journal of Electronic Imaging, vol. 22, no. 4, pp. 043037, April 2013.
[26] S. Pankaj and K. Kashif Khan, “Image denoising using local contrast and adaptive mean in wavelet transform domain”, International Journal of WaveletsMultiresolution and Information Processing, vol. 12, no. 6, pp. 1450038, June 2014.
[27] R. G. Von Gioi, J. Jakubowicz, and J. M. Morel, “LSD: a line segment detector”, Image Processing On Line, no. 2, pp. 35-55, February 2012.