论文部分内容阅读
针对矿井涌水系统的复杂性和随机性,提出采用神经网络修正灰色残差模型对矿井涌水量进行预测,既利用GM(1,1)模型能较好预测涌水量发展趋势的特点,又利用神经网络对于复杂非线性系统的优越性,保证了模型的精度,克服了单个模型所存在的不足。结果表明,该模型方法在矿井涌水量的预测中是可行的。
In view of the complexity and randomness of mine gushing system, this paper proposes to use neural network to correct the gray residual model to forecast the mine water inflow, which not only can predict the development trend of gush water with GM (1,1) The advantages of the network for complex nonlinear systems ensure the accuracy of the model and overcome the shortcomings of a single model. The results show that this model method is feasible in predicting mine water inflow.