基于行程时间实时预测的露天矿调度服务研究

发布时间：2019-06-03 19:54

【摘要】：GNNS/GIS和无线通讯技术降低了露天矿调度系统的成本，，也减少了员工和系统的交互障碍。本文应用智能交通行程时间预测的概念和方法，在分析露天矿车辆-路径行程时间变化规律的基础上，对比研究BP神经网络和支持向量机在行程时间预测上的结果，选择基于SVM的预测模型对露天矿车辆-路径行程时间进行预测，获得调度时刻下一阶段车辆-路径的行程时间预测，作为参数改进动态调度模型，进一步提高了动态调度模型的准确和可靠度；同时通过减少动态调度引起的车辆-路径变化频率，提高运输效率和安全。分析了露天矿调度系统的多层服务结构和主要的调度服务契约。基于工作流理论利用Petri网描述了露天矿调度系统业务流程和车辆终端业务流程，并利用等价计算理论计算露天矿调度业务流程的时间耗费，实现定量分析露天矿调度系统业务流程的改进效果。
[Abstract]:GNNS/GIS and wireless communication technology reduce the cost of open pit dispatching system, and also reduce the interaction between employees and the system. In this paper, the concept and method of intelligent transportation travel time prediction are applied, and on the basis of analyzing the variation law of vehicle-path travel time in open pit mine, the results of BP neural network and support vector machine in travel time prediction are compared and studied. The prediction model based on SVM is selected to predict the vehicle-path travel time of open pit mine, and the travel time prediction of vehicle-path in the next stage of scheduling time is obtained as a parameter to improve the dynamic scheduling model. The accuracy and reliability of the dynamic scheduling model are further improved. At the same time, the transportation efficiency and safety can be improved by reducing the frequency of vehicle-path change caused by dynamic scheduling. The multi-layer service structure and main dispatching service contract of open pit dispatching system are analyzed. Based on workflow theory, Petri net is used to describe the business process of open pit dispatching system and vehicle terminal business process, and the equivalent calculation theory is used to calculate the time consumption of open pit dispatching business process. The improvement effect of business process of open pit dispatching system is realized quantitatively.
【学位授予单位】：中国矿业大学（北京）
【学位级别】：博士
【学位授予年份】：2014
【分类号】：TD65;P208

【参考文献】