基于人工神经网络的瓦斯涌出量预测

由于影响瓦斯涌出量的因素很多并且它们之间存在着复杂的非线性关系，用传统方法很难对其进行准确预测，神经网络算法简单，学习收敛速度快，具有线性、非线性逼近精度高等特性，适合对瓦斯涌出量进行建模，针对对波动性较大的数据预测结果不理想的问题，在对监测数据分析的基础上，提出了用数据预处理的方法弱化数据波动性，然后进行神经网络建模的瓦斯涌出量预测模型，试验证明取得到了比较理想的结果。

Mine Gas Gushing Forecasting Based on Artificial Neural Network

Traditional methods are hard to accurately calculate because there are a lot of facts that affect Mine Gas gushing. And among these facts there is a complicated and nonlinear relationship. Neural network is a simple algorithm with high speed learning process and excellent characteristics in the linear or nonlinear accurate approximation, which is suitable for modeling the Mine Gas gushing. The result of previous research on fluctuating data is not satisfactory, based on analysis of the data, we use data preprocessing method to weaken its fluctuation, then use neural network to forecast the Mine Gas gushing. Experiment shows the result is satisfactory,