论文部分内容阅读
深井煤层底板突水是一个复杂的水文地质力学系统,各影响因素共同作用、彼此关联和相互耦合.在“九因素学说”的基础上,笔者通过隶属函数和隶属度实现各因素数据的规范处理,选取相对保守合适的参数建立神经网络模型.选取深井回采面突水实例验证模糊神经模型,得到输入层、隐含层和输出层之间的权值系数矩阵,最终以绝对影响性系数衡量各个主控因素的贡献权重.其中,水文地质条件和煤层开采条件是造成深井煤层底板突水风险程度高的主要原因.结果表明,这种方法能够有效消除人为影响和显著增强模型动态,具有一定的研究价值和较高的实际意义.
The water inrush of deep coal seam floor is a complicated system of hydrogeology and mechanics, all the influencing factors work together, are related to each other and are coupled to each other.On the basis of “nine factors theory ”, the author realizes the data of each factor through the membership function and membership degree The neural network model is selected based on the relatively conservative and appropriate parameters.Finally, the fuzzy neural model is verified by using the example of water inrush from deep well, and the weight coefficient matrix between input layer, hidden layer and output layer is obtained. Finally, the absolute coefficient of influence Which is the main reason for the high risk of water inrush from deep coal seam floor.The results show that this method can effectively eliminate the human influence and significantly enhance the dynamic state of the model, Certain research value and higher practical significance.