论文部分内容阅读
针对遗传算法(GA)和粒子群优化(PSO)算法优化支持向量机(SVM)存在容易陷入局部最优解、诊断精度相对较低、鲁棒性较差的问题,提出了一种结合GA、PSO、模拟退火算法的GAPSO优化算法,利用这种算法对SVM的参数进行了优化,优化后的算法能够较好地调整算法的全局与局部搜索能力之间的平衡.通过对航空发动机典型故障的诊断研究表明,该方法不仅能够取得良好的分类效果,诊断精度高于BP神经网络、自组织神经网络、标准SVM、GA-SVM,而且有较好的鲁棒性,更适合在故障诊断中应用.
Aiming at the problems of genetic algorithm (GA) and particle swarm optimization (PSO) optimization support vector machine (SVM), which are easy to fall into the local optimal solution, the diagnostic accuracy is relatively low and the robustness is poor, PSO, GAPSO algorithm based on simulated annealing algorithm, the parameters of SVM are optimized by this algorithm, and the optimized algorithm can well adjust the balance between global and local search ability of the algorithm.According to the typical failure of aeroengine Diagnostic studies show that this method not only achieves good classification results, but also has higher diagnostic accuracy than BP neural network, self-organizing neural network, standard SVM and GA-SVM, and has better robustness and is more suitable for fault diagnosis .