DE 算法主要用于求解连续变量的全局优化问题，其主要工作步骤与其他进化算法基本一致，主要包括变异(Mutation)、交叉(Crossover)、选择(Selection)三种操作。算法的基本思想是从某一随机产生的初始群体开始，利用从种群中随机选取的两个个体的差向量作为第三个个体的随机变化源，将差向量加权后按照一定的规则与第三个个体求和而产生变异个体，该操作称为变异。然后，变异个体与某个预先决定的目标个体进行参数混合，生成试验个体，这一过程称之为交叉。如果试验个体的适应度值优于目标个体的适应度值，则在下一代中试验个体取代目标个体，否则目标个体仍保存下来，该操作称为选择。在每一代的进化过程中，每一个体矢量作为目标个体一次，算法通过不断地迭代计算，保留优良个体，淘汰劣质个体，引导搜索过程向全局最优解逼近。-DE primarily used for global optimization problem for continuous variables, whose main work steps consistent with other evolutionary algorithms, including variation (Mutation), crossover (Crossover),　(Selection) three operations. The basic idea of the algorithm is　a randomly generated initial population began using the difference vector of two individuals randomly selected　the population as a source of the third random variations in individuals, in accordance with certain rules and third after the weighted difference vector individuals summing the individual mutation, the operation is called mutation. Then, the individual variation with a predetermined target individual mixing parameters to generate the individual test, this process is called cross. If the value of individual fitness test than target individual fitness value, then in the next generation self-test replace the target individual, otherwise the target individual is still preserved, the operation is called selection. In