摘要
针对最小二乘支持向量机(LSSVM)在故障诊断过程中的模型参数选择问题,提出了利用全局寻优能力强、收敛速度快的量子遗传算法(QGA)对模型参数进行参数寻优,把LSSVM参数选择问题转化为优化问题。该算法克服了遗传算法优化过程中陷入局部极值的问题,提高了优化性能。利用UCI数据库的数据进行分类验证,相比遗传优化的LSSVM和交叉验证的LSSVM,基于QGA优化的LSSVM模型提高了分类精度。最后,把该模型应用于风力发电机齿轮箱故障诊断中,取得了良好的效果。
Quantum genetic algorithm（ QGA） has excellent global optimization characteristics and fast convergence speed. To solve the parameter selection problems,a fault diagnosis model using least squares support vector machine（ LSSVM） is proposed. The method converts the LSSVM model parameter selection into an optimization problem. It solves the problem that genetic algorithm is easy to fall into local optimum,and improves the optimization performance. Experiments are carried out on the data sets from the UCI database. Compared with genetic algorithm LSSVM and cross-validation LSSVM,the classification accuracy is improved. Finally,this model is applied to the wind turbine gearbox diagnosis with a good result.
出处
《上海电机学院学报》
2014年第3期158-163,共6页
Journal of Shanghai Dianji University
基金
上海市科学技术委员会科技攻关项目资助(11dz1200207
13dz0511300)
关键词
最小二乘支持向量机
量子遗传算法
故障诊断
参数优化
least squares support vector machine（LSSVM）
quantum genetic algorithm（QGA）
parameters optimization
fault diagnosis
