论文部分内容阅读
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。
Aiming at the selection of parameters in fault diagnosis of support vector machines, an improved Particle Swarm Optimization (PSO) algorithm is proposed to optimize the penalty factors and kernel parameters of SVM. In order to overcome the shortcomings of the traditional particle swarm optimization algorithm such as fast convergence in the early period and easy fall-in in the local optimum, a particle swarm optimization algorithm based on inertia weight adaptive adjustment is proposed. Based on the particle swarm optimization and support vector, The model is trained and tested, and the fan fault identification is realized. The results show that the model is reliable for the diagnosis of fan fault.