返回
Learning-based dispatching system with trajectory optimisation for autonomous mining transportation
DOI:10.1080/17480930.2025.2486316.png)
摘要
En 中文
本研究通过将车队管理表述为多智能体强化学习(MARL)问题,并将深度Q网络(DQN)调度系统与动态规划(DP)速度优化相结合来应对这一挑战。利用基于真实矿山参数的事件驱动采矿模拟器,所提出的方法在8小时模拟中,相较于常规基线方法,实现了每吨平均能耗降低10%,总产量增加3,000吨。该方法确保了更公平的任务分配和资源利用率的提升。此外,该策略在无需重新训练的情况下,能够在不同车队规模(20-25辆卡车)下保持稳健性能,确保在动态运营环境中的一致效率。
Keyword:
Energy consumption
fleet management
learning-based method
mining and sustainability
transportation efficiency
word
期刊
IF:
2.6
论文数:
67
被引数:
1.2K
机构
引用论文
Deep Reinforcement Learning based real-time open-pit mining truck dispatching system基于深度强化学习的露天矿卡车实时调度系统
Multi-objective Velocity Trajectory Optimization Method for Autonomous Mining Vehicles自主采矿车多目标速度轨迹优化方法
A Computationally Efficient and Hierarchical Control Strategy for Velocity Optimization of On-Road Vehicles一种计算高效的分层控制策略,用于道路车辆的速度优化
Reinforcement Learning-Based Fleet Dispatching for Greenhouse Gas Emission Reduction in Open-Pit Mining Operations基于强化学习的露天矿作业温室气体减排车队调度
The Use of a Machine Learning Method to Predict the Real-Time Link Travel Time of Open-Pit Trucks利用机器学习方法预测露天矿卡车的实时路段行程时间
Fuel-Optimal Cruising Strategy for Road Vehicles With Step-Gear Mechanical Transmission具有步进齿轮机械变速器的道路车辆的燃油最优巡航策略
Prediction of fuel consumption of mining dump trucks: A neural networks approach矿用自卸车油耗预测的神经网络方法
APPLIED ENERGY
IF11

