In order to prevent and control environmental mass incidents,by comprehensively using literature research,case analysis and logical reasoning method,27 factors influencing environmental mass incidents were selected. A...In order to prevent and control environmental mass incidents,by comprehensively using literature research,case analysis and logical reasoning method,27 factors influencing environmental mass incidents were selected. Among them,15 key influencing factors were screened by Delphi-PCA-frequency analysis composite method. The key influencing factors were analyzed,and corresponding countermeasures were put forward.展开更多
文摘为了解决当前研究中边坡稳定性预测模型计算量大且预测能力不佳的问题,提出了一种基于改进的主成分分析(PCA)和免疫算法优化扩展径向基函数(radial basis function,RBF)支持向量机的边坡安全系数预测方法。首先,在传统的主成分分析方法中引入了线性判别的思想,实现输入空间的降维。此外,利用对称正定矩阵对RBF核函数进行扩展,构建基于ERBF核函数的支持向量机模型,并用免疫算法记性优化。采用均方根误差(root mean squared error,RMSE)、平方和误差(sum of squares for error,SSE)、平均绝对误差(mean absolute error,MAE)、平均绝对百分比误差(mean absolute percentage error,MAPE)和可靠性来验证模型的性能。与网格搜索、粒子群优化算法和遗传算法相比,所提出方法的4种误差分别为0.0226、0.0058、0.0735和0.0121,数值偏差更小,预测结果更接近实际值且可靠性更高。此外,还将以上方法与强度折减法进行了对比,结果表明所提出方法与边坡安全系数计算值最为接近。最后,从边坡安全系数得出的边坡稳定级别也可为相关决策部门在应急响应中提供参考。
基金Supported by the National Natural Science Foundation of China(41001338)Key Projects of Henan Colleges and Universities(15A610012)
文摘In order to prevent and control environmental mass incidents,by comprehensively using literature research,case analysis and logical reasoning method,27 factors influencing environmental mass incidents were selected. Among them,15 key influencing factors were screened by Delphi-PCA-frequency analysis composite method. The key influencing factors were analyzed,and corresponding countermeasures were put forward.