| 袁泽宇,刘利生,彭晴晴,杨凯,郭冲,崔方舒.融合NBEATS模型的IGBT寿命预测[J].电子测量与仪器学报,2025,39(10):232-242 |
| 融合NBEATS模型的IGBT寿命预测 |
| IGBT lifetime prediction based on NBEATS fusion model |
| |
| DOI： |
| 中文关键词: IGBT 寿命预测 变分模态分解 高斯过程回归 NBEATS |
| 英文关键词:IGBT lifetime prediction variational mode decomposition Gaussian process regression neural basis expansion analysis for time series |
| 基金项目:山西省基础研究计划(202303021222084)项目资助 |
|
|
| Author | Institution |
| Yuan Zeyu | School of Semiconductor and Physics, North University of China, Taiyuan 030051, China |
| Liu Lisheng | Shanxi Zhongbei Measurement and
Control Co., Ltd., Taiyuan 030051, China |
| Peng Qingqing | North Automatic Control Technology Institute, Taiyuan 030006, China |
| Yang Kai | Space Long
March Rocket Technology Co., Ltd., Beijing 100076, China |
| Guo Chong | Beijing Institute of Astronautical Systems Engineering, Beijing
100094, China |
| Cui Fangshu | School of Computer Science and Technology, North University of China, Taiyuan 030051, China |
|
| 摘要点击次数: 608 |
| 全文下载次数: 452 |
| 中文摘要: |
| 作为电力电子系统的核心器件,绝缘栅双极型晶体管（IGBT）在实际应用中易受电 热应力影响而发生性能退化和失效,因此对其剩余寿命的准确预测具有重要意义。针对IGBT寿命预测中单一模型预测精度不足的问题，研究了多模型融合的剩余寿命预测方法。首先采用变分模态分解（VMD）将IGBT寿命预测关键特征参数集电极 发射极瞬态尖峰电压分解为多个本征模态分量,其中低频趋势分量应用高斯过程回归模型预测,高频波动分量使用神经基扩展分析（NBEATS）网络建模,最后将各分量预测结果进行重构融合得到最终预测值。在NASA提供的IGBT加速老化实验数据上进行验证,所用融合模型较最优的单一VMD-NBEATS模型,均方根误差降低70%,平均绝对误差减少232%,决定系数提升至0.97以上。改变模型训练集和测试集的比例,融合模型在不同比例下仍表现出最优性能,验证了多尺度分解与差异化模型的稳定性和泛化性,为电力电子设备的健康监测与预防性维护提供了新的方案。 |
| 英文摘要: |
| As a core component of power electronic systems, insulated gate bipolar transistors （IGBT） are susceptible to performance degradation and failure due to electro-thermal stress during practical applications, making accurate remaining useful life prediction crucial. To address the insufficient prediction accuracy of single models in insulated gate bipolar transistors lifetime prediction, this paper investigates a multi-model fusion approach for remaining useful life prediction. The method first employs variational mode decomposition （VMD） to decompose the collector-emitter transient peak voltage, a key characteristic parameter for insulated gate bipolar transistors lifetime prediction, into multiple intrinsic mode components. The low-frequency trend component is predicted using a Gaussian process regression model, while the high-frequency fluctuation components are modeled using neural basis expansion analysis for time series (NBEATS) network. The final prediction is obtained by reconstructing and fusing the predictions of all components. Validation using NASA’s IGBT accelerated aging experimental data shows that the proposed fusion model achieves a 70% reduction in root mean square Error, a 23.2% decrease in mean absolute error, and an improvement in the coefficient of determination to above 0.97 compared to the best single VMD-NBEATS model. By varying the ratio between training and testing sets, the fusion model consistently demonstrates superior performance across different proportions, validating the stability and generalizability of the multi-scale decomposition and differentiated modeling approach. This work provides a novel solution for health monitoring and preventive maintenance of power electronic devices. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
