数据驱动的加工产线生产周期预测研究  

Data-Driven Production Line Cycle Time Prediction Study

作　　者：张翔宇 李想[1,2,4] 王伟[1,2,4] 杨旭[1,2,4] ZHANG Xiangyu;LI Xiang;WANG Wei;YANG Xu(Shenyang Institute of Automation Chinese Academy of Sciences,Shenyang 110016,China;Research Institutes of Robotics and Intelligent Equipment,Chinese Academy of Sciences,Shenyang 110169,China;不详)

机构地区：[1]中国科学院沈阳自动化研究所,沈阳110016 [2]中国科学院机器人与智能制造创新研究院,沈阳110169 [3]中国科学院大学,北京100049 [4]辽宁省智能检测与装备技术重点实验室,沈阳110169

出　　处：《组合机床与自动化加工技术》2024年第3期182-186,共5页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：中央引导地方科技发展资金计划项目(2022JH6/100100061);辽宁省应用基础研究计划项目(2022JH2/101300199)。

摘　　要：针对生产周期中的不可控时间、生产线数据结构复杂和构成变化的问题,提出一种以异构数据融合驱动的生产线周期预测方法。基于隶属函数和动态规整算法在三角特征构型下建立异构数据融合算法,将异构数据统一;以深度置信网络为主建立周期预测模型进行生产周期预测,通过确定因素求解生产周期中的不可控时间,用改进方程沟通粒子群算法和神经网络,每次迭代优化神经网络的同时还会反馈改进粒子群算法。以某航空企业加工产线为例,优化后神经网络正确率提升9%,粒子群训练时间减少5%,预测模型实现了生产周期的预测,且模型能够适应产线构成的变化。In order to solve the problems of uncontrollable time in the cycle time,complex data composition and change of production line composition,a production line cycle time prediction method driven by heterogeneous data is proposed.Based on the membership function and the dynamic time warping,the heterogeneous data fusion algorithm is established under the triangular characteristic configuration,in this way unify heterogeneous data under the same structure.The deep belief networks is used to establish the cycle time prediction model,solve the uncontrollable time composition of the cycle time by certain factors,communicate the particle swarm optimization algorithm and the neural network through the improved equation,which could get neural network optimized iteratively every time and use the feedback to improve the particle swarm optimization algorithm.Taking an aviation processing production line as an example,the optimized neural network accuracy increases by 9%,the particle swarm training time decreases by 5%,and the prediction model can predict the cycle time,also adapt to the changes of production line composition.

关 键 词：特征融合 粒子群算法 深度置信网络 生产周期预测 

分 类 号：TH166[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]