基于粒子群优化算法神经网络在开采沉陷中的应用

PSO-based Neural Network Applications in Open Mining Subsidence

考虑BP网络存在收敛速度慢、局部极值等缺点,引入线性下降惯性权重粒子群优化(LWPSO)算法,建立基于线性下降惯性权重粒子群优化(LWPSO)算法的人工神经网络模型,在分析抚顺发电有限责任公司厂区地表下沉的实际观测资料的基础上,对厂区的任意点,任意时刻进沉陷预测研究。

Considering the shortcomings of BP network such as slow convergence, the local minimum, the linear decrease inertia weight particle swarm optimization （LWPSO） algorithm is introduced to establish artificial neural network model which is based on the linear decrease inertia weight particle swarm optimization （LWPSO） algorithm. By analyzing the observed data of Fushun Power Generation Co. Ltd＇ s plant surface subsidence, any point of plant surface subsidence can be predicted at any time.