针对模式识别中协同方法存在的问题，提出了一种协同神经网络中序参量重构的方法，该方法是利用遗传算法的全局最优搜索能力，通过对训练样本集的学习，然后再通过在序参量的构建参数空间进行全局搜索来获得最优重构参数。利用实际采样得到的样本对新算法进行的测试表明，新方法确定能找到一组序参量重构参数，并能使识别性能有较大提高。

A novel method of reconstruction of order parameters in synergetic neural network is presented in this paper, Considering the neural network has the self learning ability, so we construct this linear transformantion using this ability. Additionally, considering the genetic algorithm has the globally optimal searching ability, so we can achieve these reconstruction parameters using genetic algorithm. The new method trained the synergetic neural network using genetic algorithm on the training samples set, after the convergence of genetic algorithm, the reconstruction parameters can be got. In the theory, genetic algorithm can achieve the globally optimal reconstruction parameters after infinite computation, which can be guaranteed by itself theory. So this method completely solves the construction of reconstruction parameters on the theory. The test on the samples from real applications shows:new method really can find a group of reconstruction parameters which improves the performance of synergetic neural network greatly.