Abstract
Fault diagnosis is an important technology to ensure the safe and reliable operation of equipment. Deep learning driven by big data brings new opportunities for fault diagnosis. Due to the diversity and complexity of the actual fault data distribution, a fault diagnosis algorithm based on non-negative sparse constrained deep neural networks (NSCDNN) and Dempster-Shafer theory (DST) is proposed in this paper. The deep neural network is trained by non-negative constraint and sparse constraint, which can learn part-based representation of fault data. The improved DST is combined with the classification confidence and accuracy of NSCDNN model, which can deal with the uncertainty of information from different sensors. Experimental results of the data provided by Case Western Reserve University Bearing Data Center show that the proposed NSCDNN-DST algorithm can improve the accuracy of fault diagnosis effectively.
Highlights
The safety and reliability of modern equipment operations directly affect the economic and social characteristics of industrial systems [1]
In order to enhance fault feature variability and deal with the uncertainty of information, we propose a fault diagnosis algorithm based on non-negative sparse constrained deep neural networks (NSCDNN) and improved Dempster-Shafer theory (DST)
A NEW FAULT DIAGNOSIS METHOD BASED ON NSCDNN-DST MODEL In order to improve the feature expression ability of the traditional SAE model and fuse fault information from different sensors, this paper proposes a new fault diagnosis method based on NSCDNN-DST model
Summary
The safety and reliability of modern equipment operations directly affect the economic and social characteristics of industrial systems [1]. Large rotating machinery such as fans, compressors and steam turbines are key production tools in modern enterprises such as petroleum, chemical, metallurgical and electric power [2]. An effective fault feature of a rotating machinery is that the machine is accompanied by abnormal vibration and noise during operation, and its vibration signal reflects the machine fault information in real time from the amplitude domain, the frequency domain and the time domain [3]. Extracting fault features of the rotating mechanical signal and performing in-depth analysis is an important meanses of fault diagnosis.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call