摘要
为了优化无人驾驶矿卡的能源管理并提高运输效率,基于有效载荷、总阻力、实际速度等关键变量,建立了无人驾驶矿卡油耗预测模型,分析了多元线性回归、人工神经网络和支持向量机3种机器学习模型的油耗预测指标,对无人驾驶系统合理规划行驶策略,提高能源利用效率有重要的意义,并可作为无人驾驶矿卡性能评估的参考依据。基于无人驾驶矿卡实际应用场景,对矿卡柴油消耗建模和评估问题展开研究,采用内蒙古某露天煤矿的30万条实际运行数据,通过决定系数(R^(2))、均方误差(MSE)等指标评估模型效果,人工神经网络模型的预测精度最高(R^(2)=0.9051,MSE=486.32),可为无人驾驶矿卡的节能路径规划与任务调度提供可靠依据。
In order to optimize energy management and enhance transportation efficiency of autonomous mining trucks,this article establishes a fuel consumption prediction model based on key variables including payload,total resistance,and actual speed,analyzez the performance of three machine learning models,multiple linear regression,artificial neural network and support vector machine for fuel consumption prediction.This article holds significant practical value for rationally planning driving strategies of autonomous systems,improving energy utilization efficiency,and serving as a reference for evaluating the performance of autonomous mining trucks.Based on real-world application scenarios,the article investigates the modeling and evaluation of diesel consumption for mining trucks.We utilize a dataset of 300,000 operational records from an open-pit coal mine in Inner Mongolia,the models are evaluated using metrics such as the coefficient of determination(R^(2)),mean squared error(MSE).The ANN model achieves the highest prediction accuracy(R^(2)=0.9051,MSE=486.32),which provide a reliable basis for energy-efficient route planning and task scheduling of autonomous mining trucks.
作者
刘海锋
LIU Haifeng(CHN Energy Zhunge'er Energy Co.,Ltd.,Ordos 010300,China)
出处
《露天采矿技术》
2025年第5期56-61,共6页
Opencast Mining Technology
关键词
无人驾驶矿卡
油耗预测
多元线性回归
人工神经网络
支持向量机
无人驾驶矿卡性能评估
autonomous mining truck
fuel consumption prediction
multiple linear regression
artificial neural network
support vector machine
performance evaluation of autonomous mining truck
