城市群综合承灾能力评价的RAGA-PP模型

RAGA-PP model for comprehensive disaster-bearing capacity evaluation of urban agglomerations

为解决已有模型普遍存在的难以动态评价非线性寻优的现实问题,引入投影寻踪(PP)模型进行城市群综合承灾能力评价,并运用基于实数编码的加速遗传算法(RAGA)优化辅助多维数据空间拓扑结构的投影方向,对长三角城市群(YRDUA)地区进行实证研究。结果表明:RAGA-PP模型与典型的熵权法(EWM)、灰色关联分析法(GRA)评价结果具有高度一致性,且RAGA-PP评价结果更符合实际,表明RAGA-PP模型具有较强的精确性、稳健性和抗干扰性,不仅能够聚焦于优秀个体的取值区间来实现全局搜索和加速评估,也在较大程度上避免传统方法长期存在的权重设置主观性较强、高维数据不易处理的现实问题;另外,各子系统维度的目标投影值平均水平排序为:抗灾维度>防灾维度>救灾维度>恢复维度,表明抗灾维度指标对综合承灾力影响程度最大。

In order to solve the practical problem that it was difficult to dynamically evaluate the nonlinear optimization of the existing models,the PP model was introduced to evaluate the comprehensive disaster-bearing capacity of YRDUA,and the real coding-based RAGA was used to optimize the projection direction of the auxiliary multidimensional data spatial topology.The results show that the RAGA-PP model is highly consistent with the typical entropy weight method(EWM)and grey relational analysis(GRA)evaluation results,and the evaluation results of RAGA-PP are more in line with the actual situation,indicating that the RAGA-PP model has substantial accuracy,robustness,and anti-interference.It can not only focus on the value interval of excellent individuals to achieve global search and accelerated evaluation,but also to a large extent avoid the high-dimensional data that are difficult to deal with in traditional methods.In addition,the average level of the target projection values of each subsystem dimension is ranked as follows:disaster resistance dimension>disaster prevention dimension>disaster relief dimension>recovery dimension,indicating that the disaster resistance dimension index has the most significant influence on the comprehensive disaster bearing capacity.