基于演化算法的约束区域均匀仿真实验设计方法

Uniform Experimental Design of Constrained Region Based on Evolutionary Algorithm

仿真系统通常依赖实验设计来产生仿真参数。面对约束区域下均匀实验设计存在的设计难度大、计算代价高的问题,改进了一种两段差分演化算法。将抽象的实验设计问题建模为一个约束优化问题。设计了一种融合分布估计和差分演化的求解策略;并提出了一种删点迭代的方法,降低优化种群均匀性的时间复杂度。采用标准测试题和工程应用问题进行实验分析。实验结果表明:新算法在求解性能、算法稳定性、以及计算复杂度上都优于原算法。

The parameters of a simulation system are usually generated by the experimental design. Aiming at high design difficulty and computational cost of the uniform experimental design, of the constraint region, a two-stage differential evolutionary algorithm is further improved. The design is modeled as a constrained optimization problem. A strategy combining distribution estimation algorithm(EDA) and differential evolution(DE) is adopted. A point-deletion method is proposed to reduce the time complexity of optimizing the population uniformity. To demonstrate the advantages, the test instances and engineering applications are used in experimental analysis. The experimental results show that the performance, stability, and computational complexity of the proposed algorithm are better than those of the original algorithm.