摘要
依据含水率进行洒水是抑制煤炭转运过程中扬尘的一种有效方式,但是目前皮带机物料含水率监测系统无法识别皮带振动引起的异常点,导致预测模型无法满足精度和范围要求。因此,本文提出一种基于机器学习的动态场景下含水率监测系统方案,利用SVM算法对皮带速度、横向振动量进行异常识别,采用3次样条插值算法替换异常点的高度和微波数据,然后构建XGBoost回归模型,预测煤炭含水率。结果表明:相对于第一代线性模型,系统可检测煤炭含水率的范围由8.1%~12.3%提升为8%~27%,模型平均绝对误差(MAE)由0.86下降至0.53,均方误差(MSE)由0.93缩减到0.87,模型拟合度(R2)由0.1828上升为0.9735。实际监测75车次、14种煤炭,其含水率预测值的相对误差基本在±5%以内。
Sprinkling water according to the moisture content is an effective way to suppress dust during coal transportation.However,at present,the moisture content monitoring system of materials in the belt conveyor cannot identify the abnormal points caused by belt vibration.As a result,the predictive model cannot meet the accuracy and range requirements.Therefore,a scheme of moisture content monitoring system in dynamic scenes based on machine learning is proposed.SVM algorithm is used to identify the belt speed and transverse vibration,the 3rd spline interpolation algorithm is used to replace the height and microwave data of the outliers,and then the XCBoost regression model is constructed to predict the moisture content of coal.The results show that,compared with the first generation linear model,the detectable range of coal moisture content is increased from 8.1%~12.3%to 8%~27%,the mean absolute error(MAE)of the model is reduced from 0.86 to 0.53,the mean square error(MSE)is reduced from 0.93 to 0.87,and the model fitting degree(R°)is increased from 0.1828 to 0.9735.In the actual monitoring of 75 trains and 14 kinds of coal,the relative error of the predicted value of moisture content is basically within±5%.
作者
贾若帆
周伟
付博宣
柳海涛
齐跃峰
JIA Ruofan;ZHOU Wei;FU Boxuan;LIU Haitao;QI Yuefeng(Yanshan University College of Information Science and Engineering,Qinhuangdao 066004,Hebei,China;Yanshan University The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province,Qinhuangdao 066004,Hebei,China;The Ninth Port Branch of Qinhuangdao Port Co.,Ltd.,Qinhuangdao 066004,Hebei,China)
出处
《烧结球团》
北大核心
2023年第2期72-77,共6页
Sintering and Pelletizing
基金
国家自然科学基金资助项目(61735011)
河北省重点研发计划资助项目(19251703D)。
作者简介
贾若帆(1997-),男,硕士研究生,从事煤炭含水率实时监测方面的研究;通信作者:周伟(1997-),男,从事港口煤炭无人化自动装卸系统关键技术方面的研究。
