摘要
面对资源的日益匮乏、相关法律的陆续出台以及工程机械废旧品数量的不断攀升,工程机械再制造越来越受到企业的重视。与高自动化制造过程不同,工程机械再制造过程中人员效率起到了至关重要的作用,而复杂的再制造环境造就员工频繁的学习——遗忘,使得操作效率起伏不定,故提出了用GABP神经网络预测方法来预测工程机械再制造员工的效率。本文应用统计方法分析影响员工操作时间的因素,剔除无显著相关性的因素;然后应用GABP神经网络算法对员工操作时间进行训练,进而高效准确地获得员工的操作时间;最后通过对样本数据的应用分析,获得了较好的预测效果。
The engineering machinery remanufacturing is becoming increasingly important by many enterprises with the shortage of resources,the relation laws introduced and the number of waste engineering machinery products constantly climbing. Unlike the high autoimmunization manufacturing,the efficiency of workers play a crucial role in the remanufacturing process. The complex remanufacturing environment makes the workers frequent learning and forgetting,which takes the operation efficiency fluctuate. So a GABP neural network algorithm is put forward to forecast the workers' efficiency of engineering machinery remanufacturing. At first,statistical methods is applied to analysis the influence factor on operation time of workers and eliminate the no significant correlation factors in this paper. And then a GABP neural network algorithm is introduced to train and forecast the operation time of workers. At last,a good prediction effect is obtained by applying the example data.
作者
范佳静
曹玉华
曹敏
Fan Jiajing;Cao Yuhua;Cao Min(School of Economics and Management,Zhejiang University of Science and Technology,Hangzhou 310023,China)
出处
《工业技术经济》
CSSCI
北大核心
2018年第8期147-153,共7页
Journal of Industrial Technological Economics
关键词
工程机械
再制造
生产效率
遗传优化
BP神经网络
效率预测
engineering machinery
remanufacturing
production efficiency
GABP neural network algorithm
efficiencyforecast