论文部分内容阅读
依据某露天矿2006～2007年汽车运输能力统计数据,运用BP神经网络的非线性逼近能力、高度的鲁棒性和容错性及自学习和数据挖掘等特性建立了汽车运输能力时间序列动态预测模型。经过样本数据的训练和检验,表明该模型拟合精度较好,预测结果与实际值吻合度较高,可用于汽车运输能力的预测,为合理有效编制矿山采掘计划、制定经济合理的生产计划及矿山生产过程中采用计算机模拟对汽车运输能力的随机计算提供理论依据,从而提高矿山的经济效益。
According to the statistical data of automobile transportation capacity in a surface mine from 2006 to 2007, the dynamic prediction model of automobile transportation capacity was established based on the characteristics of nonlinear approximation ability, high robustness and fault tolerance of BP neural network and self-learning and data mining. . After the training and testing of the sample data, it shows that the fitting accuracy of the model is good, the prediction result is in good agreement with the actual value, which can be used in the prediction of the automobile transportation capacity. In order to rationally and effectively mine mining plans, formulate economic and reasonable production plans and In the process of mine production, computer simulation is used to provide theoretical basis for stochastic calculation of automobile transportation capacity, so as to improve the economic benefits of the mine.