基于最小二乘法的自动钻铆工时预测研究

Study on Prediction of Man-hour of Automatic Drilling and Riveting Based on Least Square Method

为了提高企业的管理效率,降低生产成本,需要对工时信息进行准确的掌握,并实时通过工时管理系统进行更新。针对过去工时管理并没有统一的概念,且多依靠经验进行预测等问题,提出了基于最小二乘法对工时进行预测。通过对采集到的历史数据进行分析和挖掘,求解出相应工时预测模型,并以自动钻铆工序的工时为例进行预测说明。针对自动钻铆过程中影响因素众多、影响因子之间关系复杂、影响因子单位不统一等特点,对样本数据中不同单位的工时数据进行了归一化处理,建立了基于最小二乘法的工时预测模型,解决了工时预测靠经验判断、工时管理低效的问题。分析了基于最小二乘法的预测误差,并与根据经验判断允许的误差进行了对比,证明了预测的有效性,这为后续工时管理系统的开发提供了理论支撑依据。

In order to improve the management efficiency of enterprise and reduce the production cost,it is necessary to accurately master the man-hour information and update it through the man-hour management system in real time.In order to solve the problem that there is no unified concept of man-hour management in the past,and it relies on experience to predict working hour,we propose the least square method to predict man-hour.Through the analysis and mining of the collected historical data,the corresponding man-hour prediction model is solved,and the man-hour of automatic drilling and riveting process is taken as an example to predict and explain.In view of the characteristics of many influencing factors,complex relations among influencing factors and different units of influencing factors in the process of automatic drilling and riveting,the man-hour data of different units in the sample data are normalized,and a man-hour prediction model based on least square method is established.The problems of man-hour forecast relying on experience judgment and low efficiency of man-hour management are solved.The prediction error based on least square method is analyzed and compared with the allowable error based on experience.The validity of the prediction is proved,which provides a theoretical basis for the development of the subsequent man-hour management system.