Abstract
Equipment condition monitoring and diagnosis is an important means to detect and eliminate mechanical faults in real time, thereby ensuring safe and reliable operation of equipment. This traditional method uses contact measurement vibration signals to perform fault diagnosis. However, a special environment of high temperature and high corrosion in the industrial field exists. Industrial needs cannot be met through measurement. Mechanical equipment with complex working conditions has various types of faults and different fault characterizations. The sound signal of the microphone non-contact measuring device can effectively adapt to the complex environment and also reflect the operating state of the device. For the same workpiece, if it can simultaneously collect its vibration and sound signals, the two complement each other, which is beneficial for fault diagnosis. One of the limitations of the signal source and sensor is the difficulty in assessing the gear state under different working conditions. This study proposes a method based on improved evidence theory method (IDS theory), which uses convolutional neural network to combine vibration and sound signals to realize gear fault diagnosis. Experimental results show that our fusion method based on IDS theory obtains a more accurate and reliable diagnostic rate than the other fusion methods.
Highlights
With the development of intelligent manufacturing, mechanical equipment has become increasingly sophisticated, which makes the production process increasingly complex
The main advantage of the end stacked convolution neural network (ESCNN) model is that the signal is processed in an end-to-end manner, avoiding the difference in model accuracy caused by manual extraction of features
A sound signal was added to the vibration signal to form multi-source information, which overcame the limitations of the single signal and sensor itself
Summary
With the development of intelligent manufacturing, mechanical equipment has become increasingly sophisticated, which makes the production process increasingly complex. Proposed a sound-field feature extraction method based on acoustic information, which was combined with support vector machine to establish the relationship between sound field characteristics and bearing state and realize fault classification. Combined with CNN’s strong recognition capacity, this study takes the gear, which is the most common part of mechanical equipment, as the research object and introduces sound signal on the basis of vibration signals to form multi-source information, which complement each other. To solve the limitation of single signal source, which cannot fully reflect the information of the measured object, the multi-sensor fusion algorithm IDS theory is used to further fuse the diagnosis output of vibration and sound signals, and obtain a more accurate and reliable equipment operation state
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
