改进人工鱼群算法优化小波神经网络在矿用变压器故障诊断中的应用

Application of Improved Artificial Fish Swarm Algorithm to Optimize Wavelet Neural Network in Fault Diagnosis of Mining Transformer

为有效克服人工鱼群算法容易陷入局部最优的影响,通过视野和步长的优化,促使在迭代次数增加的过程中,从全局搜索逐步转向精细搜索,避免算法出现部分最优的情况。仿真实验证明了这种改进人工鱼群算法优化小波神经网络可以有效地提升矿用变压器故障诊断的精度,提高了诊断效率。

Aiming at the problem that the artificial fish swarm algorithm is easy to fall into the local optimum, the visual field and the step size are optimized to promote the gradual shift from the global search to the fine search in the process of increasing the number of iterations, so as to avoid partial optimality of the algorithm. Simulation experiments show that this improved artificial fish swarm algorithm to optimize wavelet neural network can be effectively applied to the mining transformer fault diagnosis and improve the diagnostic efficiency.