遗传优化的GNNM在瓦斯涌出量预测中的应用

研究矿井瓦斯涌出量准确预测一直是煤矿安全生产中重点关注的问题。煤层瓦斯爆炸因受开发环境、矿层深度、天气等因素的影响,造成与瓦斯涌出量增大而引起的。针对传统预测模型在矿井瓦斯涌出量预测中存在建模困难、收敛速度慢、要求历史数据量大的问题,提出了一种遗传优化的灰色神经网络预测模型。模型利用灰色系统对数据量要求低的特点,将灰色系统理论与神经网络有机结合起来,建立灰色神经网络模型。并采用遗传算法对所建立模型的权值和阈值进行优化。采用模型对矿井瓦斯涌出量进行预测,实验表明,遗传优化的灰色神经网络模型,可以简化系统建模,并能提高瓦斯涌出量预测精度,有一定的实用价值。

Application of GNNM Based on Genetic Optimization for Predicting Amount of Gas Emission in Coal Mine

The prediction of mine gas emission is an important issue in the study on coal mine safety.Aim to the problem of difficult modeling,slow convergence speed,large amount of historical data needed to predict mine gas emission,a gray neural network model based on genetic optimization was proposed in this paper.The gray system,which has the advantage of low requirement for the amount of sample data,was integrated with neural networks model to create gray neural network model.And the genetic algorithms were used to optimize the weights and thresholds of the new model.The model was applied to predict the amount of mine gas emission.The results show that optimized by genetic gray neural network model,the system model can be simplified and improve the prediction accuracy.The results indicate that the new model has certain practical value.