A Deep Multi-Label Learning Framework for the Intelligent Fault Diagnosis of Machines

Abstract

Deep learning has been applied in intelligent fault diagnosis of machines since it trains deep neural networks to simultaneously learn features and recognize faults. In the intelligent fault diagnosis methods based on deep learning, feature learning and fault recognition are achieved by solving a multi-class classification problem. The multi-class classification, however, has not considered the relationships of fault labels, leading to two weaknesses of these methods. One is that it cannot ensure to learn the correlated features for related faults and the other is that it cannot handle missing label problem. To overcome these weaknesses, we introduce a concept of multi-label classification into intelligent fault diagnosis and propose a deep multilabel learning framework called multi-label convolutional neural network (MLCNN). MLCNN builds the relationship between the labels, and thus it is able to learn the correlated features from mechanical vibration signals and be well trained using the samples with missing labels. A motor bearing diagnosis case and a compound fault diagnosis case are used to verify the proposed method, respectively. The results show that the relationships between features are learned by MLCNN, and the classification accuracies of MLCNN are higher than traditional methods when the missing label problem occurs.

A Novel Method for Predicting Fault Labels of Roller Bearing by Generalized Laplacian Matrix

“…where the upper bound of the loss function H(•, •) is denoted as U . Definition 7 : Assuming that the loss function of the GLLP algorithm is H(u, φ) = (u(c) − d) 2 , then for any ι > 0, when the probability is greater than or equal to 1 − ι, the generalization error limit of GLLP is:…”

“…When faults occur in the system, it is vital to quickly and accurately find the points of faults and the causes of the faults. In actual mechanical systems, the collected fault data often lacks a large amount of label information, which is a fatal blow to most existing fault diagnosis methods based on supervised learning and deep learning [1], [2]. How to accurately classify the fault type using the only incomplete label at hand?…”

2D CNN-Based Multi-Output Diagnosis for Compound Bearing Faults under Variable Rotational Speeds

“…This method requires a large amount of computational resources. In an effort to utilize correlated features in terms of multiple classification tasks, Shen et al [23] proposed a multiple-label framework applied to raw vibration signals to predict single faults with the level of degradation. The simplicity of signal representation made it difficult to ensure stability under conditions of variable rotational speeds and noisy working environments.…”

Bridge Inspection and Defect Recognition with Using Impact Echo Data, Probability, and Naive Bayes Classifiers

“…Zheng et al (2018) used a pretraining process to reduce the overfitting of image classification [21] to improve the performance of their proposed CNN. Training CNN to learn features and recognize faults in data was applied to solve a multiclass problem [22]. The result showed that the connection between features, which were trained by CNN, and the accuracy of classification are higher than conventional training approach [22].…”

“…Training CNN to learn features and recognize faults in data was applied to solve a multiclass problem [22]. The result showed that the connection between features, which were trained by CNN, and the accuracy of classification are higher than conventional training approach [22]. However, none of this information is dedicated to interpret impact echo data.…”