基于模糊神经网络和证据理论的瓦斯突出评判策略

针对影响煤矿瓦斯突出因素的不确定性和复杂的非线性关系,不能够利用经典的数学理论建立精确的预测模型,将模糊神经网络和D-S证据理论有机结合,提出了基于模糊神经网络和D-S证据理论的煤矿瓦斯突出危险等级评判策略.首先对传感器采集的待评判采掘面参数进行预处理,使用模糊神经网络得出第一步的融合结果,并将其进行归一化处理,归一化函数作为基本概率赋值函数,然后将归一化之后的数值作为基本概率分配值,再用D-S证据理论进行第二次数据融合,作出最终评判.实验结果表明,该方法具有良好的适应性并能得到准确性较高的评判结果.

Evaluation Strategy of Gas Outburst Based on Fuzzy Neural Network and Evidence Theory

Because of the complicated non-linear relation between the coalmine gas outburst and its affecting factors,it is difficult to establish an accurate detection model with traditional mathematical method.The fuzzy neural network and D-S evidence theory were organically combined to suggest an evaluation strategy for the coalmine gas outburst risk level.After perprocessing the evaluation parameters data flow,the first-step fused result was obtained by using fuzzy neural network and normalized as a basic probability assignment function.Each output value was taken as the basic belief assignment value,then through D-S evidence theory fusion to get the second fused result.The simulation results show that the model is reliable and precise and the security level can be accurately predicted with the proposed method.