摘要
针对煤炭企业高频备件的消耗量特点,提出一种基于改进的人工神经网络预测模型.首先,建立的RBF神经网络实现了备件消耗预测.然后利用马尔科夫模型修正相对误差残值,可使修正后的预测值更加接近实际消耗值.结果表明,基于改进的人工神经网络模型能够较好地提高神华某煤炭公司备件消耗预测的准确度.
According to the consumption characteristics of high-frequency spare parts of coal enterprises,a prediction model based on the improved artificial neural network was proposed.First,the prediction of spare parts consumption was realized using the established RBF neural network.Then,the Markov model was adopted to correct the relative error residual value,which can make the revised predicted value closer to the actual consumption value.The results show that the improved artificial neural network model can better improve the accuracy of spare parts consumption prediction of a coal company in Shenhua.
作者
段军
张雪妮
宋广宇
辛立伟
DUAN Jun;ZHANG Xueni;SONG Guangyu;XIN Liwei(Mining Research Institute, Inner Mongolia University of Science and Technology, Baotou 014010, China;Information Engineering school, Inner Mongolia University of Science and Technology, Baotou 014010, China;Baotou Lianfang Information Automation Co., Ltd., Baotou 014010, China)
出处
《内蒙古科技大学学报》
CAS
2020年第3期261-265,共5页
Journal of Inner Mongolia University of Science and Technology
基金
包头市稀土高新区科技创新服务载体基金资助项目(20191213)。
