摘要
维修间隔是维修策略中最为主要的指标之一。传统的预防性维护方法通常运用统计学原理来预测维修间隔。这种传统维修思想的局限性在于缺乏灵活性,不能根据设备的实际情况动态调整时间间隔,容易造成维修不足或维修过剩。为了达到个性化维护的目的,本文采用BP神经网络来动态预测某个设备的维修间隔。其具体做法是:首先提取历史维修数据中的维修模式,再利用这些模式来训练BP神经网络,最后根据某个特定设备的维护模式来预测下一次的维修间隔。这种方法得到的维修间隔不仅考虑了过去维护因素对特定设备的影响,而且能得到较为优化的维修间隔。本文利用这种方法对真实的电梯维修数据进行了分析。实验证明,其预测平均模式相对误差为27.1%。这种动态的维修间隔可以为制定个性化的设备维护策略提供科学依据。
Maintenance interval is one of the most important index in maintenance strategy.In the traditional planned maintenance strategy,maintenance interval is often predicted by making use of statistical theory.This method lacks flexibility and can not adjust maintenance intervals according to the actual situation of the maintenance,it will easily lead to under-maintenance or over-maintenance.In order to carry out individual maintenance,in this paper,we use BP Neural Network to predict dynamically maintenance intervals.At first,we extract a lot of maintenance models that exist in the historical maintenance data,and then use these models to train the BP neural network,finally use the trained BP neural network to predict the maintenance interval according to the equipment maintenance model.This method considered the past maintenance factors and made maintenance interval better.The experiment shows that this method achieved 27.1% model average relative error.The dynamic maintenance interval makes the amendment of maintenance interval more scientific for individual strategy.
出处
《微计算机信息》
2010年第28期107-109,87,共4页
Control & Automation
基金
上海市国防科工办国防科研项目资助
上海市重点学科建设项目(J50103)
关键词
BP神经网络
维修间隔
维修策略
维修模式
BP neural network
Maintenance interval
Maintenance strategy
Maintenance pattern
