Guowen Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Guowen Su has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Haotian Zhang
Master of Engineering in Control Engineering, Civil Aviation University of China, Tianjin, China
1 shared publication - Hongxu Zhao
Civil Aviation University of China
1 shared publication Xudong Shi
College of Information Engineering and Automation, Civil Aviation University of China, Tianjin, China
1 shared publication
Latest Publications
- 19 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electromagnetic Compatibility
- Vol. 65 (1) , 114-125
Defect Diagnosis Method of Cable Shielding Layer Based on Frequency Domain Reflection Coefficient Spectrum
In this article, the genetic algorithm-variational mode decomposition-reflection coefficient spectrum (RCS) method is proposed based on frequency domain RCS to detect and locate the weak defects of the cable shielding layer more precisely. In this method, variational mode decomposition (VMD) algorithm is applied on the RCS to extract defect information, and genetic algorithm based on envelope entropy and kurtosis is adopted to optimize the number of decomposed intrinsic mode functions and penalty factor of the VMD. In addition, with 40 groups of data, support vector machine algorithm is engaged to identify the types of different shielding layer defects. The experimental results show that the proposed method can detect and locate weak defects, such as one-strand fractures and holes, and meanwhile identify the types of defects accurately.
- 19 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electromagnetic Compatibility
- Vol. 65 (1) , 114-125
Defect Diagnosis Method of Cable Shielding Layer Based on Frequency Domain Reflection Coefficient Spectrum
In this article, the genetic algorithm-variational mode decomposition-reflection coefficient spectrum (RCS) method is proposed based on frequency domain RCS to detect and locate the weak defects of the cable shielding layer more precisely. In this method, variational mode decomposition (VMD) algorithm is applied on the RCS to extract defect information, and genetic algorithm based on envelope entropy and kurtosis is adopted to optimize the number of decomposed intrinsic mode functions and penalty factor of the VMD. In addition, with 40 groups of data, support vector machine algorithm is engaged to identify the types of different shielding layer defects. The experimental results show that the proposed method can detect and locate weak defects, such as one-strand fractures and holes, and meanwhile identify the types of defects accurately.