基于栈式自动编码器的火箭总装完工时间预测  

Stacked auto-encoder based approach for rocket final assembly cycle time prediction

作　　者：盛夏 赵新明[1] 张朋[1] 张洁 程辉 刘斯琪 张春雨 SHENG Xia;ZHAO Xinming;ZHANG Peng;ZHANG Jie;CHENG Hui;LIU Siqi;ZHANG Chunyu(School of Mechanical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China;College of Mechanical Engineering,Donghua University,Shanghai 201620,China;Shanghai Spaceflight Manufacture,Shanghai 200240,China)

机构地区：[1]上海交通大学机械与动力工程学院,上海200240 [2]东华大学机械工程学院,上海201620 [3]上海航天设备制造总厂,上海200240

出　　处：《计算机集成制造系统》2019年第11期2720-2730,共11页Computer Integrated Manufacturing Systems

基　　金：国家自然科学基金资助项目（U1537110,51435009）~~

摘　　要：针对运载火箭总装过程中由于各种不确定因素和动态事件可能引发的火箭不能按时交付的问题,提出一种基于栈式自动编码器的火箭总装完工时间预测方法。通过逐层训练浅层自动编码器代替传统方法中的特征提取过程,利用无监督学习过程学习完工时间相关因素的非线性压缩特征;通过堆叠浅层自动编码器构成精调网络,利用监督学习过程及参数优化过程精确预测火箭完工时间。通过仿真数据以及上海某航天设备制造厂火箭总装实际数据中的测试数据集,验证了该方法比传统预测方法具有更优秀的泛化性能,能够提升预测精度。To deal with the overdue problem caused by uncertainties and dynamic events during the rocket final assembly process,a novel approach based on Stacked Auto Encoders(SAE)was proposed.By substituting shallow Auto Encoder(AE)for traditional feature extraction process,the condensed non-linear feature of the cycle time s correlative factors was learned with unsupervised layer-wise pretraining.A fine-tuning network was constructed through stacking multiple shallow AE,and the cycle time prediction for rocket final assembly process was predicted accurately with supervised learning and parameter optimization process.Through the test data set generated from both simulation process and actual final assembly process in some spaceflight manufacture in Shanghai,the better generalization performance of proposed method was proved,and the prediction precision had improved compared with traditional prediction approaches.

关 键 词：完工时间预测 栈式自动编码器 火箭总装 精调网络 预测精度 

分 类 号：F42[经济管理—产业经济]