A Novel Fault Diagnosis Method for Analog Circuits Based on Conditional Variational Neural Networks
- PDF / 1,646,221 Bytes
- 25 Pages / 439.37 x 666.142 pts Page_size
- 37 Downloads / 183 Views
A Novel Fault Diagnosis Method for Analog Circuits Based on Conditional Variational Neural Networks Tianyu Gao1 · Jingli Yang1
· Shouda Jiang1 · Ge Yan2
Received: 17 April 2020 / Revised: 31 October 2020 / Accepted: 4 November 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract To enhance the reliability of analog circuits in complex electrical systems, a novel fault diagnosis method based on conditional variational neural networks (CVNN) is presented in this paper. The CVNN model is constructed by adding a sampling layer to the multi-layer perceptron. The latent variable which has the same distribution with the original signal of the analog circuit is obtained in the sampling layer, where the noise is introduced to improve the generalization performance of the model. The output features of the sampling layer are achieved by resampling on the latent variable, and the variational inference is adopted to estimate unknown parameters of the model. To address the overfitting issue of the CVNN model, the Dropout algorithm and the scaled exponential linear unit function are applied to the hidden layers. Furthermore, the features compressed by the second hidden layer are input into the Softmax classifier for training, and then the trained fault diagnosis model is utilized to identify the fault classes of the analog circuit. The method is fully evaluated with the three typical analog circuits, and the experimental results demonstrate that the fault diagnosis method based on CVNN can achieve better diagnosis accuracy and generalization performance than other typical fault diagnosis methods for analog circuits. Keywords Analog circuits · Fault diagnosis · Conditional variational neural networks · Sampling layer · Latent variable
B
Jingli Yang [email protected] Tianyu Gao [email protected] Shouda Jiang [email protected] Ge Yan [email protected]
1
Department of Automatic Test and Control, Harbin Institute of Technology, Harbin 150001, China
2
China Institute of Marine Technology and Economy, Beijing 100081, China
Circuits, Systems, and Signal Processing
1 Introduction Analog circuits are widely applied in many fields, including aerospace, military, communications, and industrial control. However, analog circuit failures affect system functions and even cause catastrophic accidents. To improve system reliability and security, enhanced technology associated with fault diagnosis of analog circuits is of urgently needed [2,6]. In general, analog circuit failures include hard faults and soft faults. The hard faults (e.g., short or open circuit faults), which are easier to identify, are caused by substrate rupture, resistance film burning, lead cap falling off, and capacitor breakdown. Due to the influence of the surrounding environment (e.g., temperature, humidity, and pressure), the parameters of passive components in analog circuits always deviate from the allowable range, which will result in the soft faults with a high frequency of occurrence. For example, the conductive materials w
Data Loading...
