基于PLS的下向进路多参数优化方法

Multiparameter optimization method for downward drift mining based on PLS

为研究下向进路稳定性与多参数间的关系,提出采用正交数值模拟试验法和偏最小二乘法分析下向进路稳定性影响因素,并运用安全系数法和可靠度分析优化下向进路多参数,进而开展工业试验。结果表明:1)影响下向进路稳定性因素依次为:承载层厚度>进路宽度>进路高度>进路侧帮弹模>承载层弹模>充填体泊松比,且前3个因素影响效果显著;2)偏最小二乘法分析对承载层拉应力的拟合和预测效果良好,误差控制在15%以内;3)可靠度分析优化下向进路多参数较安全系数法更为合理,可实现下向进路安全高效经济开采。工业试验效果良好,表明偏最小二乘法优化下向进路多参数具有很好的理论及实践意义。

To study the relationship between multiple parameters and stability of downward drift,orthogonal simulation and partial least squares regression were used to analyze factors affecting the stability of downward drift. Safety coefficient and reliability analysis were applied to optimize these parameters. On the basis of that,an industrial test was conducted. The results show that： 1） The factors affecting tensile stress of the loading layer in a descending sequence in terms of significance are thickness of the loading layer,drift width,drift height,two-sided elastic modulus of the drift,elastic modulus of the loading layer and Poisson ratio of the backfill,and the first three factors are more effective than the others. 2） Satisfactory fitness and forecast were obtained through partial least squares regression with errors controlled within 15%. 3） The reliability analysis is more reasonable than the safety coefficient method in optimizing multiple parameters,which can achieve safer,more efficient and economical downward drift exploitation. The satisfactory results of industrial test indicate that partial least squares regression has theoretical and practical values in optimizing multiple parameters for downward drift mining.