基于神经网络优化模型的保险公司应对灾害情况的决策安排  

Decision arrangements for insurance company to respond to disaster situations based on neural network optimization model

作　　者：陈翌阳 胥汀然 CHEN Yiyang;XU Tingran(Portland College,Nanjing University of Posts and Telecommunications,Nanjing 210046,China)

机构地区：[1]南京邮电大学波特兰学院,南京210046

出　　处：《计算机应用文摘》2024年第19期176-178,共3页

摘　　要：针对保险公司应对突发环境污染事故的决策安排,文章以BP神经网络为中心,利用WOA算法对网络拓扑结构及BP的权重系数进行了优化,同时采用Cubic混沌映射优化WOA算法的初始种群以避免局部极值,不仅改进了网络预测精度,还得到了预测误差较小的优化模型。以河南省相关环境数据为主要依据进行仿真测试,文章在确定整体模型结构层数的同时减小了误差指标,符合保险公司的决策预期。Regarding the decision-making arrangements for insurance companies to respond to sudden environmental pollution accidents,this article focuses on the BP neural network and uses the WOA algorithm to optimize the network topology and BP weight coefficients.At the same time,the initial population of the WOA algorithm is optimized using the Cubic chaotic mapping to avoid local optima,which not only improves the network prediction accuracy but also obtains an optimized model with smaller prediction errors.Based on relevant environmental data from Henan Province,simulation tests were conducted to determine the overall model structure layers while reducing error indicators,which is in line with the decision-making expectations of insurance companies.

关 键 词：BP神经网络 WOA Cubic混沌映射 保险决策 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]