计算机科学 ›› 2022, Vol. 49 ›› Issue (6A): 784-789.doi: 10.11896/jsjkx.210400030
王飞, 黄涛, 杨晔
WANG Fei, HUANG Tao, YANG Ye
摘要： 绝缘栅双极型晶体管(IGBT)器件是一种被广泛应用于工业、通信、计算机、汽车电子等领域的核心技术部件,提高该器件的使用安全性至关重要。近年来,采用机器学习对IGBT器件的寿命进行预测已成为热点的研究问题。然而,普通的神经网络预测仍存在着训练时间长和准确率较低的问题。针对该问题,提出了一种基于Stacking多模型融合的机器学习模型来实现对IGBT的寿命预测,该模型有效地提高了预测的准确率和效率。该算法包含双层结构,融合了4种互补的机器学习算法模型。其中,第一层使用了轻度梯度提升树模型(LGBM)、极端梯度提升树模型(XGBoost)和岭回归模型(Ridge)进行预测,再将预测结果输入第二层进行训练;第二层使用了线性回归模型,经过双层模型训练预测出最终的IGBT寿命。通过实验数据的对比证实,相比常用的长短期记忆神经网络(LSTM)算法模型,基于Stacking多模型融合的机器学习模型对IGBT寿命预测的均方误差平均降低了93%,且模型训练的平均耗时仅为LSTM网络算法模型的13%。
中图分类号:
| [1] BALIGA B J.IGBT devices-physics,design and applications[M].Beijing Machinery Industry Press,2018. [2] CHEN B,LU G,FANG H Z,et al.IGBT health parameter prediction method based on degenerate data and DBN algorithm[J].Computer Measurement and Control,2017,25(5):71-75. [3] SMET V,FOREST F,HUSELSTEIN J J,et al.Ageing andFailure Modes of IGBT Modules in High-Temperature Power Cycling[J].IEEE Transactions on Industrial Electronics,2011,58(10):4931-4941. [4] ALGHASSI A,PERINPANAYAGAM S,SAMIE M.Stochastic RUL Calculation Enhanced With TDNN-Based IGBT Failure Modeling[J].IEEE Transactions on Reliability,2016,65(2):558-573. [5] LI M,ZHU J J,LONG B.Particle Filter Approach for IGBT Remaining Useful Life[J].AMR,2014,981:86-89. [6] WU H W,YE C J,ZHANG Y T,et al.Remaining Useful Life Prediction of an IGBT Module in Electric Vehicles Statistical Analysis[J].Symmetry,2020,12(8):1325. [7] ADLA I,LOTFI S.A New Data-Driven Approach for Power IGBT Remaining Useful Life Estimation Based On Feature Reduction Technique and Neural Network[J].Electronics,2020,9(10):1571. [8] AHSAN M,HON T S,BATUNLU C,et al.Reliability Assessment of IGBT Through Modelling and Experimental Testing[J].IEEE Access,2020,8:39561-39573. [9] LU G Z.Research on Life Prediction Technology of IGBTPower Module[D].Chongqing:Chongqing University,2012. [10] DU X,LI G X,LIU H J,et al.The Influence of Wind Speed Probability Distribution on the Life of Power Devices in Wind Power Converters[J].Journal of Electrotechnical Technology,2015,30(15):109-117. [11] THEBAUD J,WORIGARD E.Strategy for designing accele-rated aging tests to evaluate IGBT power modules lifetime in real operation mode[J].IEEE Transactions on Components and Packaging Technologies,2003,26(2):429-438. [12] LIU B L,LIU D Z,TANG Y,et al.Life prediction and failureanalysis of IGBT module based on accelerated life test[J].Journal of Jiangsu University,2013,34(5):556-563. [13] WANG X C,ZHAO J J.Research on IGBT lifetime based on wavelet neural network[J].Electrotechnical,2020(10):114-116. [14] HAN G G.Research on IGBT fault prediction based on deep learning[D].Beijing:Beijing Jiaotong University,2019. [15] SHI Y Z,GUO B,ZHENG Y J.Research on IGBT lifetime prediction based on LSTM network[J/OL].China Test.http://kns.cnki.net/kcms/detail/51.1714.TB.20200810.1312.006.html. [16] LIU H,LANG B.Machine learning and deep learning methods for intrusion detection systems:A survey[J].Applied Sciences,2019,9(20):4396. [17] YANG R X,SUN C Y,XU L.Prediction of photovoltaic power generation based on stacking model fusion[J].Computer System Application,2020,29(5):36-45. [18] KE G L.Lightgbm:A highly efficient gradient boosting decision tree[J].Advances in Neural Information Processing Systems,2017,30:3146-3154. [19] CHEN T,GUESTRIN C.XGBoost:A Scalable Tree Boosting System [C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco,California,USA,Association for Computing Machinery,2016:785-94. [20] MARQUARDT D W,SNEE R D.Ridge Regression in Practice[J].The American Statistician,1975,29(1):3-20. [21] HUANG H,MAWBY P A.A Lifetime Estimation Technique for Voltage Source Inverters[J].IEEE Transactions on Power Electronics,2013,28(8):4113-4119. [22] CELAYA J,WYSOCKI P,GOBEL K.IGBT accelerated aging data set[J/OL].NASA Ames Prognostics Data Repository,2009.https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/#igbt. [23] SONNENFELD G,KAI G,CELAYA J R,et al.An agile acce-lerated aging,characterization and scenario simulation system for gate controlled power transistors[J].IEEE Autotestcon,2008,6:208-215. |
| [1] | 冷典典, 杜鹏, 陈建廷, 向阳. 面向自动化集装箱码头的AGV行驶时间估计 Automated Container Terminal Oriented Travel Time Estimation of AGV 计算机科学, 2022, 49(9): 208-214. https://doi.org/10.11896/jsjkx.210700028 |
| [2] | 宁晗阳, 马苗, 杨波, 刘士昌. 密码学智能化研究进展与分析 Research Progress and Analysis on Intelligent Cryptology 计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053 |
| [3] | 何强, 尹震宇, 黄敏, 王兴伟, 王源田, 崔硕, 赵勇. 基于大数据的进化网络影响力分析研究综述 Survey of Influence Analysis of Evolutionary Network Based on Big Data 计算机科学, 2022, 49(8): 1-11. https://doi.org/10.11896/jsjkx.210700240 |
| [4] | 李瑶, 李涛, 李埼钒, 梁家瑞, Ibegbu Nnamdi JULIAN, 陈俊杰, 郭浩. 基于多尺度的稀疏脑功能超网络构建及多特征融合分类研究 Construction and Multi-feature Fusion Classification Research Based on Multi-scale Sparse Brain Functional Hyper-network 计算机科学, 2022, 49(8): 257-266. https://doi.org/10.11896/jsjkx.210600094 |
| [5] | 王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011 |
| [6] | 张光华, 高天娇, 陈振国, 于乃文. 基于N-Gram静态分析技术的恶意软件分类研究 Study on Malware Classification Based on N-Gram Static Analysis Technology 计算机科学, 2022, 49(8): 336-343. https://doi.org/10.11896/jsjkx.210900203 |
| [7] | 陈明鑫, 张钧波, 李天瑞. 联邦学习攻防研究综述 Survey on Attacks and Defenses in Federated Learning 计算机科学, 2022, 49(7): 310-323. https://doi.org/10.11896/jsjkx.211000079 |
| [8] | 赵冬梅, 吴亚星, 张红斌. 基于IPSO-BiLSTM的网络安全态势预测 Network Security Situation Prediction Based on IPSO-BiLSTM 计算机科学, 2022, 49(7): 357-362. https://doi.org/10.11896/jsjkx.210900103 |
| [9] | 康雁, 徐玉龙, 寇勇奇, 谢思宇, 杨学昆, 李浩. 基于Transformer和LSTM的药物相互作用预测 Drug-Drug Interaction Prediction Based on Transformer and LSTM 计算机科学, 2022, 49(6A): 17-21. https://doi.org/10.11896/jsjkx.210400150 |
| [10] | 李亚茹, 张宇来, 王佳晨. 面向超参数估计的贝叶斯优化方法综述 Survey on Bayesian Optimization Methods for Hyper-parameter Tuning 计算机科学, 2022, 49(6A): 86-92. https://doi.org/10.11896/jsjkx.210300208 |
| [11] | 赵璐, 袁立明, 郝琨. 多示例学习算法综述 Review of Multi-instance Learning Algorithms 计算机科学, 2022, 49(6A): 93-99. https://doi.org/10.11896/jsjkx.210500047 |
| [12] | 肖治鸿, 韩晔彤, 邹永攀. 基于多源数据和逻辑推理的行为识别技术研究 Study on Activity Recognition Based on Multi-source Data and Logical Reasoning 计算机科学, 2022, 49(6A): 397-406. https://doi.org/10.11896/jsjkx.210300270 |
| [13] | 姚烨, 朱怡安, 钱亮, 贾耀, 张黎翔, 刘瑞亮. 一种基于异质模型融合的 Android 终端恶意软件检测方法 Android Malware Detection Method Based on Heterogeneous Model Fusion 计算机科学, 2022, 49(6A): 508-515. https://doi.org/10.11896/jsjkx.210700103 |
| [14] | 许杰, 祝玉坤, 邢春晓. 机器学习在金融资产定价中的应用研究综述 Application of Machine Learning in Financial Asset Pricing:A Review 计算机科学, 2022, 49(6): 276-286. https://doi.org/10.11896/jsjkx.210900127 |
| [15] | 么晓明, 丁世昌, 赵涛, 黄宏, 罗家德, 傅晓明. 大数据驱动的社会经济地位分析研究综述 Big Data-driven Based Socioeconomic Status Analysis:A Survey 计算机科学, 2022, 49(4): 80-87. https://doi.org/10.11896/jsjkx.211100014 |
|
||
首页