基于改进粒子群优化SVM的通风机故障诊断

Fault Diagnosis of Ventilator Based on SVM Optimized by Improved PSO

针对支持向量机在故障诊断中参数的选取问题,提出一种改进的粒子群优化算法,对支持向量机的惩罚因子与核参数进行优化。为了克服传统粒子群算法前期收敛快、后期易陷入局部最优的缺陷,提出一种惯性权重自适应调整的粒子群优化算法,建立基于粒子群和支持向量的通风机故障诊断模型,通过样本数据对模型进行训练与测试,实现了通风机故障的识别,结果表明该模型对通风机故障的诊断是可靠的。

Aimed at the problem of parameters selection of support vector machine（SVM） in fault diagnosis,put forward an improved particle swarm optimization（PSO） algorithm to optimize the penalty factor of SVM and the kernel parameter. A particle swarm optimization algorithm with adaptive inertia weight adjustment was proposed in order to overcome the defects of converges fast in early stage and easy to fall into local optimum in later stage for traditional particle swarm algorithm. The fault diagnosis model of mine ventilator was established based on particle swarm and support vector machine. After training and testing through the sample data the model can identify the fault of mine ventilator accurately, the results show that the model of ventilator fault diagnosis is reliable.