Abstract:

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.

Key words: comprehensive disaster bearing capacity, real coding based accelerating genetic algorithm(RAGA), projection pursuit(PP), projection direction, Yangtze River Delta urban agglomeration(YRDUA)