基于免疫编程的无量纲指标构建

摘要

In order to solve the problem of premature convergence in the genetic programming using conventional artificial immu -nity algorithm,a novel dimensionless parameters construction based on immune programming is proposed .Combining cloning ,hy-permutation and replacement operator ,the antibody affinity is defined by the ratio of inter-class scatter to the intra-class scatter . Finally the clonal selection optimal algorithm is obtained with excellent classification performance .Experimental result shows that the optimum dimensionless parameter can achieve accurate classification of rotating machinery fault .%针对使用传统人工免疫算法进行多项式组合优化易陷入局部优化解的不足，提出一种基于免疫编程的无量纲指标构建算法，利用克隆、变异和更新等机制实现抗体的优化，采用类内、类间散布距离进行抗体亲和度衡量，最终获得具有最佳分类能力的新无量纲指标。实验结果表明该无量纲指标能够对旋转机械故障进行准确分类。