摘要
本研究采用机器学习算法构建AGB组合预测模型,提高煤矿机电设备运行状态的智能预测精度。实验采用单一预测模型,包括GM(1,1)灰色模型、ARIMA模型和BP神经网络模型,并在此基础上建立AGB预测模型。通过煤矿采煤机冷却水压力的实际数据,对4种模型预测结果进行分析对比。结果显示,AGB模型在模拟实际数据方面表现出高度一致性,并在预测精度上具有显著优势,预测精度进一步提高。本研究成果可用于煤矿机电设备的状态预测,为煤矿安全运行提供科学依据。
Machine learning algorithms is adopted to construct an AGB combination prediction model in order to improve the intelligent prediction accuracy of the operation status of coal mine electromechanical equipment.The experiment uses a single prediction model,including GM(1,1)grey model,ARIMA model,and BP neural network model,and establishes an AGB prediction model.The predicted results of four models based on the actual data of cooling water pressure in coal mining machines are analyzed and compared.The results show that the AGB model exhibits high consistency in simulating actual data and has significant advantages in prediction accuracy,thus further improving prediction accuracy.
作者
闫建飞
YAN Jianfei(Shanxi Yangquan Yinying Coal Industry Co.,Ltd.,Yangquan 045011,China)
出处
《陕西煤炭》
2025年第7期175-179,共5页
Shaanxi Coal
关键词
煤矿机电设备
运行状态
机器学习
ARIMA模型
coal mine electromechanical equipment
operating status
machine learning
ARIMA model
