Deep convolutional tree-inspired network: a decision-tree-structured neural network for hierarchical fault diagnosis of bearings

Abstract

The fault diagnosis of bearings is crucial in ensuring the reliability of rotating machinery. Deep neural networks have provided unprecedented opportunities to condition monitoring from a new perspective due to the powerful ability in learning fault-related knowledge. However, the inexplicability and low generalization ability of fault diagnosis models still bar them from the application. To address this issue, this paper explores a decision-tree-structured neural network, that is, the deep convolutional tree-inspired network (DCTN), for the hierarchical fault diagnosis of bearings. The proposed model effectively integrates the advantages of convolutional neural network (CNN) and decision tree methods by rebuilding the output decision layer of CNN according to the hierarchical structural characteristics of the decision tree, which is by no means a simple combination of the two models. The proposed DCTN model has unique advantages in 1) the hierarchical structure that can support more accuracy and comprehensive fault diagnosis, 2) the better interpretability of the model output with hierarchical decision making, and 3) more powerful generalization capabilities for the samples across fault severities. The multiclass fault diagnosis case and cross-severity fault diagnosis case are executed on a multicondition aeronautical bearing test rig. Experimental results can fully demonstrate the feasibility and superiority of the proposed method.

Twins transformer: rolling bearing fault diagnosis based on cross-attention fusion of time and frequency domain features

“…However, such methods lack the ability to learn and struggle with highly complex nonlinear signals, thus being unable to effectively handle industrial big data [5]. In contrast, machine learning-based fault diagnosis methods utilize shallow learning models, such as decision trees [6], random forests [7] and support vector machines [8], to learn the statistical features of original signals and achieve fault classification. Nonetheless, the decision-making capability of these models still depends on the extraction and selection of statistical features of faults and fully intelligent diagnosis has not yet been achieved.…”

Lightweight bearing fault diagnosis method based on cross-scale learning transformer under imbalanced data*

“…Secondly, the samples of different fault types are often imbalanced, resulting in a decline in model performance [3]. Shallow neural networks and machine learning algorithms based on feature extraction, such as random forests [4], decision trees [5], and support vector machines [6], have been found to inadequately mine the latent information within monitoring signals. In recent years, the advancements in deep learning have furnished the fault diagnosis domain with novel perspectives and methodologies.…”

A comprehensive review of mechanical fault diagnosis methods based on convolutional neural network

“…Compared with the traditional algorithm, their accuracy rate is up to 95.397 %. Wang et al [16] proposed an AdaBoost algorithm based on Decision Tree. Compared with the conventional algorithm, it has better generalization performance and fewer iterations with the same accuracy.…”