Yiming Du
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yiming Du has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
Guohua Long
Electric Power Research Institute of State Grid Jiangxi Electric Power Co., Ltd. , Nanchang
1 shared publicationMengying Cheng
Electric Power Research Institute of State Grid Jiangxi Electric Power Co., Ltd. , Nanchang
1 shared publicationTao Han
Nanchang University School of Advanced Manufacturing Nanchang
1 shared publication- Yicun Tang
School of Advanced Manufacturing, Nanchang University
1 shared publication
Latest Publications
- 6 November 2026
- Published by Emerald Publishing in World Journal of Engineering
- p. 1-12
Multi-physics coupled simulation of a 110 kV three-phase gas-insulated switchgear busbar and its temperature-rise prediction based on machine learning
Purpose: The purpose of this study is to investigate the temperature distribution of a 110 kV three-phase gas-insulated switchgear (GIS) busbar by multi-physics coupled numerical simulation. This study analyses the influences of different factors on the temperature field of the busbar. The study aims to provide an efficient formula to predict the temperature rise of the contact area based on the numerical results through machine learning. The findings can be used for the over-temperature warning of the hot spot in the GIS busbar equipment. Design/methodology/approach: A multi-physics coupled numerical simulation is performed in the ANSYS software, which aims to study the effects of different factors, such as the contact resistance, solar radiation and ambient temperature, on the temperature field of the busbar. Based on the data set from the simulation, an empirical formula is fitted to quickly predict the contact temperature. In addition, the Random Forest (RF) algorithm is used for the training of the obtained temperature data set, which is used for the over-temperature prediction. Findings: The results reveal that the temperature of the contact area is mainly affected by the contact resistance, while the temperature of the GIS enclosure is more sensitive to the solar radiation and the ambient temperature. The fitted empirical formula can quickly predict the contact temperature, which has a prediction accuracy of 0.97°C. The temperature prediction accuracy by machine learning is better, which is 0.0165°C. Originality/value: This study provides an original investigation into the temperature rise prediction of the contact area in a GIS busbar through multi-physics coupled simulation and machine learning, which is scarcely addressed in previous studies. By systematically considering different influencing factors, this work offers a quick estimation of the inner temperature of the contact area, which provides efficient and valuable guidelines for the over-temperature warning of the GIS equipment.
- 6 November 2026
- Published by Emerald Publishing in World Journal of Engineering
- p. 1-12
Multi-physics coupled simulation of a 110 kV three-phase gas-insulated switchgear busbar and its temperature-rise prediction based on machine learning
Purpose: The purpose of this study is to investigate the temperature distribution of a 110 kV three-phase gas-insulated switchgear (GIS) busbar by multi-physics coupled numerical simulation. This study analyses the influences of different factors on the temperature field of the busbar. The study aims to provide an efficient formula to predict the temperature rise of the contact area based on the numerical results through machine learning. The findings can be used for the over-temperature warning of the hot spot in the GIS busbar equipment. Design/methodology/approach: A multi-physics coupled numerical simulation is performed in the ANSYS software, which aims to study the effects of different factors, such as the contact resistance, solar radiation and ambient temperature, on the temperature field of the busbar. Based on the data set from the simulation, an empirical formula is fitted to quickly predict the contact temperature. In addition, the Random Forest (RF) algorithm is used for the training of the obtained temperature data set, which is used for the over-temperature prediction. Findings: The results reveal that the temperature of the contact area is mainly affected by the contact resistance, while the temperature of the GIS enclosure is more sensitive to the solar radiation and the ambient temperature. The fitted empirical formula can quickly predict the contact temperature, which has a prediction accuracy of 0.97°C. The temperature prediction accuracy by machine learning is better, which is 0.0165°C. Originality/value: This study provides an original investigation into the temperature rise prediction of the contact area in a GIS busbar through multi-physics coupled simulation and machine learning, which is scarcely addressed in previous studies. By systematically considering different influencing factors, this work offers a quick estimation of the inner temperature of the contact area, which provides efficient and valuable guidelines for the over-temperature warning of the GIS equipment.