蚁群神经网络在变压器故障诊断中的应用

针对蚁群算法收敛速度慢的问题, 提出了一种改进方法, 通过为蚁群算法增加一种收敛因子, 使其在信息素的全局更新中为每次迭代产生的最优路径赋予额外的信息素增量, 降低了算法陷入局部最优解的可能性。分析了改进蚁群算法的收敛性, 并对其寻优能力进行了测试, 结果表明, 改进蚁群算法具有较强的寻优能力和较快的收敛速度。用改进蚁群算法优化神经网络并将其应用于变压器的故障诊断, 与BP神经网络诊断结果对比, 蚁群算法优化神经网络具有更快的收敛速度和更高的诊断精度。

Application of Ant Colony Neural Network in Transformer Fault Diagnosis

To solve the problem of slow convergent speed of ACA （Ant Colony Algorithm）, an improved method is proposed. One kind of convergence factor is added to ACA to guarantee that the best route produced in each iteration would be given additional pheromone increment during the pheromone global u Therefore, the possibility of algorithm trapped in local optimal solution is reduced. The pdating procedure. convergence of the improved ACA is proved and its optimizing ability is tested. The simulation results show that the improved ACA has higher optimizing ability and faster convergent speed in contrast with the basic ACA. The improved ACA is used to optimize neural network, and the optimized neural network is applied in the diagnosis of transformer fault. The results show that the optimized neural network based on the improved ACA has higher convergent speed and diagnostic accuracy in contrast with BP neural network.