【作者】 康波； 吕炳朝；

【Author】 Kang Bo, Lu Bingchao School of Automation Engineering, UESTC, Chengdu, sichuan 610054,China.

【机构】 电子科技大学自动化工程学院；

【摘要】 针对标准遗传算法存在的早熟与收敛速度较慢等问题,利用混沌序列的随机性、遍历性及规律性,提出了一种基于混沌序列进行混沌交叉与混沌变异的改进型遗传算法一混沌遗传算法,并基于组合电路测试生成的神经网络模型,对基于混沌遗传算法的组合电路测试生成方法进行了详细讨论。实验结果表明所提出方法能有效克服标准遗传算法中的局部收敛问题,加快了测试生成过程。更多还原

【Abstract】 Considering the defect of premature and slower convergence speed in genetic algorithm, by taking advantage of the stochastic, ergodic and regular properties of chaotic sequence, a improved genetic algorithm based on chaotic crossover and chaotic mutation, which is called chaos genetic algorithm, is proposed. Based on a neural network model for combinatorial circuit test generation, a test generation approach with chaos genetic algorithm is discussed in detail. The experimental results show that the proposed approach surmounts effectively the local convergence problem of standard genetic algorithm and improves the test generation speed.更多还原