A5068072369- Engineering and Test Systems
- Advanced Decision-Making Techniques
- Integrated Circuits and Semiconductor Failure Analysis
- Software Testing and Debugging Techniques
- Industrial Vision Systems and Defect Detection
- Smart Grid and Power Systems
- Software Engineering Research
- VLSI and Analog Circuit Testing
- Image Processing Techniques and Applications
- Software Reliability and Analysis Research
Shandong University of Technology
2022-2024
To accurately locate faulty components in analog circuits, an circuit fault diagnosis method based on Tunable Q-factor Wavelet Transform(TQWT) and Convolutional Neural Network (CNN) is proposed this paper. Firstly, the Grey Wolf algorithm (GWO) used to improve TQWT. The improved TQWT can adaptively determine parameters decomposition level. Secondly, signal decomposed, single-branch reconstruction conducted with facilitate adequate feature extraction. Thirdly, capture time-frequency features...
A soft fault in an analog circuit is a symptom where the parameter range of component exists symmetrically to left and right its nominal value exceeds specific range. The proposed method uses Grey Wolf Optimization (GWO) optimized tunable Q-factor wavelet transform (TQWT) algorithm for feature refinement, Inception model extraction, SVM diagnosis. First, make it more compatible with signal. Second, signal decomposed, single-branch reconstruction performed using TQWT extract features...
When the number of parameters or values systems under test is large, combinatorial cases increases dramatically. All will take up a lot time and resources. Prioritization technology can find system faults as early possible improve efficiency. Most existing prioritization methods rely on prior knowledge, but in many it difficult to obtain random results are lower fault detection rates. In this paper, method based small sample tests proposed. Firstly, weights value combinations suspected...