中文摘要：

针对传统BP算法易陷入局部极小、遗传算法（GA）易于早熟的问题,提出了一种基于免疫遗传BP算法的小波神经网络模型。算法将BP算法嵌入免疫遗传算法中,利用BP算法对遗传算法定位的解空间进行局部的同步搜索,充分利用遗传算法的全局寻优能力和BP算法的局部搜索能力,优化小波神经网络参数,并将优化的网络应用于企业绩效的评价中,通过与基于遗传算法与BP算法的结果比较,表明基于免疫遗传BP算法的小波神经网络模型的精度有较大的提高,网络计算的准确性有很大的改进。

英文摘要：

For the trend of failing into local minimum of BP algorithm and the premature convergence of simple genetic algorithm, an improved wavelet neural network model based on immune genetic and BP algorithm （IGA-BP） is presented, which takes full advantage of the global optimization ahilky of genetic algorithm and the local search ability of BP algorithm. BP algorithm is incorporated into immune genetic algorithm to optimize the parameters of wavelet neural network by local synchronized searching in the solution space that the genetic algorithm has searched out. The improved algorithm is used to corporate performance evaluation and the results show that the algorithm has higher accuracy than the genetic algorithm and the BP algorithm.