聚类优化RBF网络在锅炉燃烧中的应用

Clustering Optimization RBF Network in the Application of The Boiler Combustion

为了提高径向神经网络的训练精度,提出一种混合优化算法.算法将基于萤火虫算法的模糊聚类,应用到径向神经网络基函数中心向量的计算中,利用萤火虫算法良好的全局寻优能力来优化搜索基函数中心,提高了获取网络类中心的稳定性.锅炉燃烧优化的实例表明,混合优化算法达到了预期效果,提升了锅炉燃烧效率.

In order to improve the training accuracy of radial basis neural network, this paper proposes a hybrid optimization algorithm and applied to boiler combustion efficiency optimization. The fuzzy clustering of Glowworm Swarm Optimization is applied to the radial nerve network class centre vector calculation, based on the firefly algorithm with good global search optimization ability to optimize clustering center, improve the accuracy of access network class center. Boiler combustion optimization examples show that the hybrid optimization algorithm to achieve the desired effect, achieve the purpose of the boiler combustion efficiency.