Bearing Fault Diagnosis with DDCNN Based on Intelligent Feature Fusion Strategy in Strong Noise

作     者：Chaoqian He Runfang Hao Kun Yang Zhongyun Yuan Shengbo Sang Xiaorui Wang 

作者机构：College of Electronic Information and Optical EngineeringTaiyuan University of TechnologyTaiyuan030024China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of EducationTaiyuan030024China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第77卷第12期

页      面：3423-3442页

核心收录：

学科分类：08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0838[工学-公安技术] 

基　　金：supported by the Key Research and Development Plan of Shanxi Province(Grant No.202102030201012) 

主　　题：Fault diagnosis dual-data dual-channel feature fusion noise-resistance 

摘      要：Intelligent fault diagnosis in modern mechanical equipment maintenance is increasingly adopting deep learning ***,conventional bearing fault diagnosis models often suffer from low accuracy and unstable performance in noisy environments due to their reliance on a single input ***,this paper proposes a dual-channel convolutional neural network(DDCNN)model that leverages dual data *** DDCNN model introduces two key ***,one of the channels substitutes its convolution with a larger kernel,simplifying the structure while addressing the lack of global information and shallow ***,the feature layer combines data from different sensors based on their primary and secondary importance,extracting details through small kernel convolution for primary data and obtaining global information through large kernel convolution for secondary *** experiments conducted on two-bearing fault datasets demonstrate the superiority of the two-channel convolution model,exhibiting high accuracy and robustness even in strong noise ***,it achieved an impressive 98.84%accuracy at a Signal to Noise Ratio(SNR)of−4 dB,outperforming other advanced convolutional models.