摘要
为简化模型结构,改善算法全局搜索性能和组卷模型成功率,本研究提出利用QPSO中的全局和局部最优位置优化遗传算法中交叉、变异算子,粒子群编码采用实数编码,交叉、变异操作均在功能块内部进行,目标函数增加了权重系数判定是否更新粒子群,以此建立了智能组卷模型,并进行了相关实验分析。实验结果表明:改进的模型与其他三种组卷模型相比,该模型运行效率、全局搜寻性能、组卷成功率都有较大的提高,说明该组卷模型更稳定有效。
In order to simplify the model structure, improve the algorithm global search performance and the success rate of test paper model, this study proposes to use the global QPSO and local optimal location optimization GA crossover, mutation operator, the real number coding using particle swarm coding, crossover, mutation operation is performed in the inner functional block, the objective function increases the weight coefficient of determination whether to update the particle swarm, establishes the intelligent test paper model, and relevant experimental analysis. The experimental results show that： compared with other three kinds of test paper model, the model efficiency, the global search performance, and the success rate was higher, indicating that the test paper model is more stable and effective.
出处
《电子设计工程》
2016年第13期23-25,共3页
Electronic Design Engineering
基金
2010年云南省高等学校教学改革研究项目(201010)
云南农业大学2013年校级教学改革立项项目(ZNJG201306)
关键词
QPSO
遗传算法
权重系数
智能组卷
模型研究
Quantum-behaved Particle Swarm Optimization（QPSO）
Genetic Algorithm（GA）
weight coefficient
intelligent-paper constructing
model research
