Litcius/Paper detail

An End-To-End CNN-BiLSTM Attention Model for Gearbox Fault Diagnosis

Xiaoyang Zheng, Jinliang Wu, Zeyu Ye

202023 citationsDOI

Abstract

Existing fault diagnosis methods based on Deep Learning require complicated and cumbersome preprocessing procedures heavily relying on signal processing and manual feature extraction techniques, which fails to maximize the superiority of the adaptive representation capability of Deep Learning. This paper proposes a novel end-to-end fault diagnosis approach combined convolutional neural network (CNN) with Bidirectional Long Short-Term Memory (BiLSTM) and Attention Mechanism. Specifically, one dimensional CNN is utilized to perform local feature extraction and dimension reduction on the input signal data. Then, the BiLSTM network is adopted to extract high-level features from the above results. The miscellaneous features extracted are filtered out by using Attention Mechanism. Finally, the learned features are implemented to train Softmax classifier for identifying fault types. To evaluate the effectiveness of the proposed model, experiments are carried out on two different datasets by using ten-fold cross validation approach. The results demonstrate that the proposed model is capable to learn features adaptively with fewer steps while ensuring higher accuracy compared with other state-of-art fault diagnosis methods.

Topics & Concepts

Softmax functionComputer scienceArtificial intelligenceFeature extractionConvolutional neural networkPreprocessorPattern recognition (psychology)Classifier (UML)Deep learningFeature learningFault (geology)Artificial neural networkMachine learningSeismologyGeologyMachine Fault Diagnosis TechniquesGear and Bearing Dynamics AnalysisAdvanced machining processes and optimization
An End-To-End CNN-BiLSTM Attention Model for Gearbox Fault Diagnosis | Litcius