电子测量与仪器学报

佐磊,胡小敏,何怡刚,孙洪凯,李兵.灰色双重残差修正的多芯片组件寿命预测[J].电子测量与仪器学报,2020,34(5):82-88

灰色双重残差修正的多芯片组件寿命预测

Double residual correction for life prediction of multi-chip module

DOI：

中文关键词: 多芯片组件小子样灰色模型双重残差修正马尔科夫-尾段残差灰色模型寿命预测

英文关键词:multi-chip module small samples grey model double residual correction Markov-tail residual gray model life prediction

基金项目:装备预先研究重点项目(41402040301)、国家重点研发计划(20l6YFF0102200)、国家自然科学基金重点项目(51637004)、国家自然科学基金(51777050,51577046)资助项目

作者	单位
佐磊	1. 合肥工业大学电气与自动化工程学院，2. 可再生能源接入电网技术国家地方联合工程实验室(合肥工业大学)
胡小敏	1. 合肥工业大学电气与自动化工程学院
何怡刚	1. 合肥工业大学电气与自动化工程学院，2. 可再生能源接入电网技术国家地方联合工程实验室(合肥工业大学)，3. 武汉大学电气与自动化学院
孙洪凯	1. 合肥工业大学电气与自动化工程学院
李兵	1. 合肥工业大学电气与自动化工程学院，2. 可再生能源接入电网技术国家地方联合工程实验室(合肥工业大学)

Author	Institution
Zuo Lei	1. School of Electrical Engineering and Automation, Hefei University of Technology，2. National Local Joint Engineering Laboratory of Renewable Energy Access to Power Grid Technology (Hefei University of Technology)
Hu Xiaomin	1. School of Electrical Engineering and Automation, Hefei University of Technology
He Yigang	1. School of Electrical Engineering and Automation, Hefei University of Technology，2. National Local Joint Engineering Laboratory of Renewable Energy Access to Power Grid Technology(Hefei University of Technology)，3. School of Electrical Engineering and Automation, Wuhan University
Sun Hongkai	1. School of Electrical Engineering and Automation, Hefei University of Technology
Li Bing	1. School of Electrical Engineering and Automation, Hefei University of Technology，2. National Local Joint Engineering Laboratory of Renewable Energy Access to Power Grid Technology(Hefei University of Technology)

摘要点击次数: 524

全文下载次数: 979

中文摘要:

针对利用传统灰色模型进行多芯片组件寿命预测时存在的精度不足,以及预测精度随时间跨度增加而显著降低的问题,提出马尔科夫-尾段双重残差修正的多芯片组件寿命灰色预测方法。将在灰色 GM(1,1)模型预测值基础上经马尔科夫法优化后的残差作为尾段灰色残差模型的输入值,实现双重残差修正。以对热循环加速试验条件下得到少量试验数据的影响多芯片组件寿命的电阻值进行寿命预测为例,试验结果表明,相较于传统灰色模型和神经网络预测方法,所提出方法在小样本条件下平均残差分别减小了 80. 469%和 68. 53%,预测精度得以提高,结果更加可靠,能够更准确地预测多芯片组件的寿命。

英文摘要:

Aiming at the problems of inadequate accuracy in the prediction of multi-chip module life using traditional gray model and the significant decrease in prediction accuracy with the increase of time span, a Markov-tail double residual correction method for multi-chip component life prediction based on grey model is proposed. Based on the predicted value of grey GM ( 1,1) model, the residual optimized by Markov method is used as the input value of the tail segment grey residual model to achieve double residual correction. An example is given to predict the life of multi-chip module by using resistance values which influence the life of multi-chip module with a small amount of test data obtained under the condition of accelerated thermal cycle test. The experimental results show that compared with the traditional grey model and neural network prediction methods, the average residuals of the proposed method are reduced by 80. 469% and 68. 53% under the small samples condition, the prediction accuracy is improved, the result is more reliable and the life prediction of multi-chip modules can be more accurate.

查看全文查看/发表评论下载PDF阅读器