Full
Outline
Aimed at the health status of insulated gate bipolar transistors (IGBTs) and the problem of evaluation on their remaining useful life (RUL), the aging parameter of IGBTs was predicted based on an adaptive recurrent neural network (AdaRNN) transfer learning model. First, the failure mechanism of IGBTs was analyzed, and the on-state collector-emitter voltage was selected as the aging parameter to evaluate the health status of IGBTs. Then, an IGBT aging test bench was set up to collect the aging parameter online. Finally, based on the acquired aging parameter, the AdaRNN model was used to predict the IGBT aging parameter. Results show that when the same IGBT aging parameter was used as the training and test sets, the accuracy and speed of prediction results of the traditional time series model and AdaRNN model were similar. When the aging parameters of two sets of different IGBTs were used as the training and test sets, the AdaRNN model can solve the problem of aging parameter difference caused by device difference, and the prediction accuracy was obviously higher than that of the traditional time series model, indicating the strong generalization capability and robustness of the new model.
40
4
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
