We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于深度学习的柴油机气门健康状态评估.
- Authors
白雲杰; 贾希胜; 梁庆海; 白永生
- Abstract
During the operation of a diesel engine, its valve clearance will change with the degradation of its performance state. In order to solve the problems of the traditional health assessment method, the determination of health indicators is difficult and the weight is artificially dependent on human experience. A method for evaluating the health status of diesel engine valves based on deep learning was proposed. Firstly, the diesel engine cylinder head vibration signal was decomposed by wavelet packet decomposition algorithm, and 14 common time-domain features and wavelet packet decomposition signal energy ratio vector were extracted from the decomposed node signals, and a multi-dimensional comprehensive health assessment index vector was constructed. Then build a health evaluation model based on one-dimensional convolutional neural network (1DCNN), and input the obtained health evaluation index vector into the model for training and health evaluation. The effectiveness of the method is verified through the valve degradation simulation experiment carried out on the diesel engine test bench. In addition, compared with the traditional method, it solves the problem of screening health indicators and the influence of subjective experience of people, and has a better health evaluation effect.
- Publication
Science Technology & Engineering, 2022, Vol 22, Issue 10, p3941
- ISSN
1671-1815
- Publication type
Article