Intelligent fault diagnosis of medical equipment based on long short term memory network.
10.7507/1001-5515.201912019
- Author:
Xiangjun LIU
1
;
Lang LANG
1
;
Shihui ZHANG
1
;
Jingjing XIAO
1
;
Liping FAN
1
;
Jianchuan MA
1
;
Yinbao CHONG
1
Author Information
1. Department of medical engineering, The Second Affiliate Hospital of Army Medical University, Chongqing 400037, P.R.China.
- Publication Type:Journal Article
- Keywords:
fault diagnosis;
feature fusion;
feature screening;
long short term memory network;
no circuit drawing
- MeSH:
Algorithms;
Electricity;
Memory, Short-Term;
Neural Networks, Computer
- From:
Journal of Biomedical Engineering
2021;38(2):361-368
- CountryChina
- Language:Chinese
-
Abstract:
In order to solve the current problems in medical equipment maintenance, this study proposed an intelligent fault diagnosis method for medical equipment based on long short term memory network(LSTM). Firstly, in the case of no circuit drawings and unknown circuit board signal direction, the symptom phenomenon and port electrical signal of 7 different fault categories were collected, and the feature coding, normalization, fusion and screening were preprocessed. Then, the intelligent fault diagnosis model was built based on LSTM, and the fused and screened multi-modal features were used to carry out the fault diagnosis classification and identification experiment. The results were compared with those using port electrical signal, symptom phenomenon and the fusion of the two types. In addition, the fault diagnosis algorithm was compared with BP neural network (BPNN), recurrent neural network (RNN) and convolution neural network (CNN). The results show that based on the fused and screened multi-modal features, the average classification accuracy of LSTM algorithm model reaches 0.970 9, which is higher than that of using port electrical signal alone, symptom phenomenon alone or the fusion of the two types. It also has higher accuracy than BPNN, RNN and CNN, which provides a relatively feasible new idea for intelligent fault diagnosis of similar equipment.
