提升机现场数据的载荷预测模型研究  

Research on Load Forecasting Model of Hoist Field Data

作　　者：郑彤 杨兆建[1,2] 杨波 ZHENG Tong;YANG Zhao-jian;YANG Bo(College of Mechanical Engineering,Taiyuan University of Technology,Shanxi Taiyuan 030024,China;Key Laboratory of Fully Mechanized Coal Mining Equipment in Shanxi Province,Shanxi Taiyuan 030024,China)

机构地区：[1]太原理工大学机械工程学院,山西太原030024 [2]煤矿综采装备山西省重点实验室,山西太原030024

出　　处：《机械设计与制造》2021年第5期180-183,188,共5页Machinery Design & Manufacture

基　　金：国家自然科学基金(51475318);山西省“十二五”科技重大专项(20111101040)。

摘　　要：针对目前提升机载荷难以通过直接法测量的问题,以某矿JKM-2.8×6(I)A型多绳摩擦式提升机为研究对象。选取提升机运行过程中的最大启动电流、加速段主电机电流平均值、最大速度、平均加速度等8类2000组数据进行分析,利用多种神经网络(BP、RBF、Elman)的方法建立了载荷预测模型。经过对比分析,表明自适应BP神经网络可作为预测提升机提升载荷的一种有效方法。该方法是基于提升机现场数据进行载荷的预测分析可以为摩擦式提升机载荷监测提供参考,也可以进一步为现场的安全生产与维护提供理论参考依据,非常具有现实指导意义。In view of the problem that the current hoist load is difficult to measure by direct method,this paper takes a mine JKM-2.8×6(I)A multi-rope friction hoist as the research object.Eight types of 2000 sets of data,such as maximum starting current during the operation of the hoist,average current of the main motor of the acceleration section,maximum speed and average acceleration,were selected for analysis,and loads forecast model were established by using various neural networks(BP,RBF,Elman).After comparative analysis,it shows that the adaptive BP neural network can be used as an effective method to predict the lifting load of the hoist.The method based on the hoist field data for predictive analysis of the load can provide reference for the friction hoist load monitoring,and can further provide a theoretical reference for the safety production and maintenance in field,which is very practical and meaningful.

关 键 词：多绳摩擦式提升机 相关性分析 神经网络 载荷识别 

分 类 号：TH16[机械工程—机械制造及自动化] TD534[矿业工程—矿山机电]