LSTM网络在采煤机摇臂齿轮箱寿命预测中的应用  

Application of LSTM Network in Life Prediction of Shearer Rocker Gearbox

作　　者：刘文广[1] 杨兰柱 秦波[1] Liu Wenguang;Yang Lanzhu;Qin Bo(School of Mechanical Engineering,Inner Mongolia University of Science and Technology,Baotou,Inner Mongolia 014010,China;Engineering Training Center,Inner Mongolia University of Science and Technology,Baotou,Inner Mongolia 014010,China)

机构地区：[1]内蒙古科技大学机械工程学院,内蒙古包头014010 [2]内蒙古科技大学工程训练中心,内蒙古包头014010

出　　处：《机电工程技术》2020年第11期168-170,共3页Mechanical & Electrical Engineering Technology

基　　金：内蒙古自然科学基金面上项目(编号:2017MS0509)。

摘　　要：作为机械化采煤的主要设备,保证滚筒式采煤机稳定运行的重点是摇臂齿轮箱的可靠性。利用深度学习中的长短时记忆模型(Long short-term memory neural network,LSTM)对实际工程环境下的摇臂齿轮箱寿命进行了预测。实验所用数据集采集于内蒙古西部某矿场采煤机摇臂齿轮箱,包含了采煤机摇臂齿轮箱主齿由初始状态到齿面发生较大磨损的全部数据。实验表明,该网络在摇臂齿轮箱寿命预测中效果较好,具有一定的可行性。As the main equipment of mechanized coal mining,the key to ensure the stable operation of drum shearer is the reliability of rocker gear box.The long short term memory neural network(LSTM)was used to predict the life of rocker gear box in practical engineering environment.The data set used in the experiment was collected from a coal mine in the west of Inner Mongolia.It contains all the data of the main teeth of the shearer′s rocker gear box from the initial state to the large wear of the tooth surface.The experiment shows that the network is effective and feasible in the life prediction of rocker gear box.

关 键 词：采煤机 摇臂齿轮箱 LSTM网络 寿命预测 

分 类 号：TD421[矿业工程—矿山机电]