Semi-supervised deep rule-based approach for the classification of wagon bogie springs condition

Abstract

The wagons are submitted to stressing cycles with heavy loads, increasing their bogie defects through springs fatigue, then, the capacity to detect critical freight cars conditions enables to guarantee the safety production and high productivity of transportation systems. The image processing and computational intelligence techniques are increasingly participating in the solution for this scenario, especially human interpretable and self-evolve models which can learn new classes actively without human experts’ involvement to self-evolve and perform classification on out-of-sample images. In this sense, this dissertation presents a new approach model for the classification of wagon bogie springs condition through images acquired by a wayside equipment. As such, we are discussing the application of a semi-supervised learning approach based on a deep rules-based (DRB) classifier learning approach to achieve a high classification of a bogie, and check if they either have spring problems or not. We use a pre-trained VGG19 deep convolutional neural network to extract the attributes from images to be used as input to the Fuzzy Rule Based (FRB) layer of the semi-supervised DRB (SSDRB) classifier and evaluated with euclidean, cosine, manhattan, minkowski, chebyshev distance measures. The performance is calculated based on the dataset composed of images provided by a Brazilian railway company which covers the two spring condition : normal condition (no elastic reserve problems) and bad condition (with elastic reserve problems). Also, an additive Gaussian noise levels, Cauchy noise and Laplace noise are applied to the images to challenge the proposed model and to represent possible problems on image acquisition. Finally, we discuss the performance analysis of the semi-supervised DRB (SSDRB) classifier and its distinctive characteristics with each distance measure compared with other classifiers. The reported results demonstrate a relevant performance of the SSDRB classifier applied to the questions raised as well the importance of evaluation of distance measure to achieve a high classification