Performance Evaluation of Automatic Labeling System of Crack Length at Tooth Root and Examination of Erroneous Detection
In this paper, a semi-automatic labeling system of crack lengths at the tooth root of plastic gears is developed. Captured side-view images of plastic gears by a high-speed camera have been manually labeled with the quantity of crack lengths. Based on the large amount of labelled image data obtained from previous research, the developed system using a deep neural network classifies the side-view images superadded by endurance tests of plastic gears according to the crack length, automatically. The system employs a pre-learned popular convolutional neural network called VGG16, which has 1000 classification ability. The system was modified to fit a four classifications problem related to the crack length (“no crack”, “~ 40%”, “~ 70%” or “~ 100%”), and the weight of two layers, which were close to the output layer, were relearned with transfer learning. As a result of the learning, the classification accuracy of the unknown images was about 90%, Finally, misclassified images were investigated, and the hard-to-classify images were revealed.
KeywordsPlastic gears Crack detection Classification of crack length Convolutional Neural Network Transfer learning Automatic labeling
Unable to display preview. Download preview PDF.
- 1.Iba, D., Ohmori, S., Hongu, J., Nakamura, M., Moriwaki, I.: Failure detection of plastic gears based on a comparison of fourier coefficients of a gear mesh vibration model by rec- tangle pulse train and frequency analysis of acceleration response, Trans. of the japan soci- ety of mechanical engineers, Series C, Vol. 79, Issue 808, pp.5138-5148, (2013).Google Scholar
- 2.Ishii, Y., Iba, D., Miyamoto, S., Miura, N., Iizuka, T., Masuda, A., Sone, A., Moriwaki, I.: Automatic acquisition system of meshing vibration data and image pictures of crack propa- gation, The proceedings of the machine design and tribology division meeting in JSME, Vol. 2018.18 1B1-6, pp.1-4, (2018).Google Scholar
- 3.Krizhevsky, A., Sutskever, I.: ImageNet classification with deep convolutional neural net- works, Advances in information processing system, pp.1097-1105, (2012).Google Scholar
- 4.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Proceedings of ICLR 2015, pp.1-14, (2015).Google Scholar