Realtime vision-based surface defect inspection of steel balls

Abstract

In the proposed system for online inspection of steel balls, a diffuse illumination is developed to enhance defect appearances and produce high quality images. To fully view the entire sphere, a novel unfolding method is put forward based on geometrical analysis, which only requires one-dimensional movement of the balls and a pair of cameras to capture images from different directions. Moreover, a realtime inspection algorithm is customized to improve both accuracy and efficiency. The precision and recall of the sample set were 87.7% and 98%, respectively. The average time cost on image processing and analysis for a steel ball was 47 ms, and the total time cost was less than 200 ms plus the cost of image acquisition and balls’ movement. The system can sort 18 000 balls per hour with a spatial resolution higher than 0.01 mm.

Keywords

machine vision / steel ball / defect inspection / image processing

References

[1] Li Y, Billington S, Zhang C, et al. Dynamic prognostic prediction of defect propagation on rolling element bearings[J]. Tribology Transactions, 1999, 42(2): 385-392.

[2] Kotzalas M N, Harris T A. Fatigue failure and ball bearing friction[J]. Tribology Transactions, 2000, 43(1): 137-143.

[3] Halme J, Andersson P. Rolling contact fatigue and wear fundamentals for rolling bearing diagnostics-State of the art[J]. Journal of Engineering Tribology, 2010, 224(4): 377-393.

[4] Gereg C V. Eddy Current Bearing Ball Flaw Detector: US, 1984.

[5] Johnson W L, Norton S J, Bendec F, et al. Ultrasonic spectroscopy of metallic spheres using electromagneticacoustic transduction[J]. The Journal of the Acoustical Society of America, 1992, 91(5): 2637-2642.

[6] Deneuville F, Duquennoy M, Ouaftouh M, et al. Coupled analysis of high and low frequency resonant ultrasound spectroscopy: Application to the detection of defects in ceramic balls[J]. Review of Scientific Instruments, 2009, 80(5): 054903

[7] Tandon N, Choudhury A. A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings[J]. Tribology International, 1999, 32(8): 469-480.

[8] Pandya D H, Upadhyay S H, Harsha S P. Fault diagnosis of rolling element bearing with intrinsic mode function of acoustic emission data using APF-KNN[J]. Expert Systems with Applications, 2013, 40(10): 4137-4145.

[9] Papaelias M P, Roberts C, Davis C L. A review on nondestructive evaluation of rails: State-of-the-art and future development[J]. Journal of Rail and Rapid Transit, 2008, 222(4): 367-384.

[10] Wang P, Zhao Y L, Liu X L, et al. The key technology research for vision inspecting instrument of steel ball surface defect[J]. Key Engineering Materials, 2008, 392–394: 816-820.

[11] Nonoyama T, Inazaki N. Rolling Device for Inspecting Spheres: JP, 2013.

[12] Ng T W. Optical inspection of ball bearing defects[J]. Measurement Science and Technology, 2007, 18(9): N73-N76.

[13] Do Y, Lee S, Kim Y. Vision-based surface defect inspection of metal balls[J]. Measurement Science and Technology, 2011, 22(10): 107001

[14] Martin D, Guinea D M, García-Alegre M C, et al. Multimodal defect detection of residual oxide scale on a cold stainless steel strip[J]. Machine Vision and Applications, 2010, 21(5): 653-666.

[15] Yun J P, Choi S, Seo B, et al. Real-time vision-based defect inspection for high-speed steel products[J]. Optical Engineering, 2008, 47(7): 077204

[16] Shen H, Li S, Gu D, et al. Bearing defect inspection based on machine vision[J]. Measurement, 2012, 45(4): 719-733.

[17] Li Q, Ren S. A real-time visual inspection system for discrete surface defects of rail heads[J]. IEEE Transactions on Instrumentation and Measurement, 2012, 61(8): 2189-2199.

[18] Fawcett T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2006, 27(8): 861-874.