Condition Monitering of Thrust Bearings Based on Machine Learning with Synthetically Generated Data
Keywords:
Condition monitoring, Thrust bearing, fault detection, Curve fit Algorithm, Machine vision, Deep learning, Artificial Intelligence [AI], Image processing, ThresholdingAbstract
Different approaches to condition monitoring and failure detection are necessary since rolling element bearing problems are a major contributor to total machine failures. Recent developments in machine learning, which reduce the need for planned maintenance, further quicken the effort to increase defect detection accuracy for financial reasons. Difficult issues remain, such as collecting high-quality data to explicitly train an algorithm, and are made harder by the scarcity of historical data. Furthermore, failure data derived from measurements is usually limited to specific equipment components, like Vernier callipers, which offers only round off thrust bearing values. To overcome this, the study works on deep learning, artificial intelligence & Machine vision technologies are introduced with precise measurement values of thrust bearing.
References
[1] Yan X, Jing G, Cao M, Zhang C, Liu Y and Wang X, "Research of Sub- Pixel Inner Diameter Measurement of Workpiece Based on OpenCV", InternationalConference on Robots & Intelligent System (ICRIS), Changsha, China, 2018, pp. 370-373, doi: 10.1109/ICRIS.2018.00098
[2] Han Jian-hai, Zhao Shu-shang and Sun Wei, "Research on subpixel detecting on- line system based on machine vision for inner diameter of bearings", IEEE International Conference on Robotics and Biomimetics (ROBIO), Sanya, 2007, pp. 2049-2052, doi: 10.1109/ROBIO.2007.4522483.
[3] ZHANG Hong-tao, DUAN Fa-jie, “Study on a fast method for subpixel edge detection”. Acta Metrologica Sinica, 2002,23(4), pp.263-266.
[4] Y. Zhao and W. Tang, "Development of Measuring Instrument for Inner and Outer Diameters of Bearing Seal Rings Based on Machine Vision", 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China, 2021, pp.1515-1520, doi: 10.1109/IAEAC50856.2021.9390813.
[5] Q. Chunyang, Z. Liping and L. Tao, "Study on Inner Diameter Measurement of Cannon Barrel Based on Image Processing", First International Conference on Instrumentation, Measurement, Computer, Communication and Control, Beijing, China, 2011, pp. 280-282, doi: 10.1109/IMCCC.2011.77. 41 .
[6] ZHANG Yong-hong, HU De-jin, XU Jun-jie. “Subpixel edge location of Machine parts based on the vision image[J], Chinese Journal of Mechanical Engneering, 2004，40(6), pp.179-182 .
[7] Sub-pixel Edge Detection Based on Curve Fitting XU Guo-Sheng Weifang university, Weifang 261061，China N. Q. Chen, J. J. Wang, L. A. Yu and C. Y. Su, "Sub-pixel Edge Detection of LED Probes Based on Canny Edge Detection and Iterative Curve Fitting," 2014 International Symposium on Computer, Consumer and Control, Taichung, Taiwan, 2014, pp. 131-134, doi: 10.1109/IS3C.2014.45.
[8] Study on Edge Subpixel Location of Ellipse in Computer Vision Measurement Li Baozhang, School of Mechanical and Electronic Engineering, Hebei University of Science and Technology,Shijiazhuang, ChinaStudy on Inner Diameter Measurement of Cannon Barrel
[9] C. Fan and C. Liu, "A novel algorithm for circle curve fitting based on the least square method by the points of the Newton's rings," 2015 International Conference on Computers, Communications, and Systems (ICCCS), Kanyakumari, India, 2015, pp. 256-260, doi: 10.1109/CCOMS.2015.7562911.
[10] Research on Subpixel Detecting on-line System Based on Machine Vision for Inner Diameter of Bearing Han Jian-hai*1, Zhao Shu-shang*1, Sun Wei *2 School of Mechatronics Engineering, Henan University of Science & Technology, Luoyang, China School of Instrument Science & Engineering, Southeast University, Nanjing, China.
[11] X.Q. Xiang, J.Z. Zhou, C.S. Li, et al., Fault diagnosis based on Walsh transform and rough sets, Mech. Syst. Signal Process. Vol.23 (4),pp. 1313–1326, May (2009).
[12] Z.B. Xu, J.P. Xuan, T.L. Shi, et al., A novel fault diagnosis method of bearing based on improved fuzzy ARTMAP and modified distance discriminant technique, Expert Syst. Vol.36 (9), pp.11801–11807, ,November 2009.
[13] Z.B. Xu, J.P. Xuan, T.L. Shi, et al., Application of a modified fuzzy ARTMAP with feature-weight learning for the fault diagnosis of bearing, Expert Syst. Vol.36 (6) ,pp. 9961–9968, August (2009).
[14] T.W. Rauber, F.D. Boldt, F.M. Varejao, Heterogeneous feature models and feature selection applied to bearing fault diagnosis, IEEE Trans. Industr. Electron. 62 (1) ,pp.637–646, January (2015).
[15] X.L. Zhang, X.F. Chen, Z.J. He, An ACO-based algorithm for parameter optimization of support vector machines, Expert Syst. Vol.37 (9),pp.6618–6628, September (2010).
[16] X.L. Zhang, X.F. Chen, Z.J. He, Fault diagnosis based on support vector machines with parameter optimization by an ant colony algorithm, Proc. Instit. Mech. Eng. Part C-J. Mech. Eng. Sci. 224 (C1), pp.217–229, (2010).
[17] J. Demsar, Statistical comparisons of classifiers over multiple data sets, J. Mach. Learn. Res. 7, pp.1–30, May (2009).
