摘要
针对传统的ＢＰ网络学习算法的缺陷，研究一种动态学习算法。依据人工神经网络的一股原理，利用网络的非线性映射功能，实现了综放回采巷道的锚杆支护设计。结果表明，网络的设计结果与现场实际吻合很好。
A new dynamic learning algorithm is proposed to overcome the shortcoming of traditional BP net learning algorithm. Based on the principle of artificial neural network and the proposed algorithm, the bolt support design of mining roadway is made for fully mechanized working face with top-coal caving, and the results keep coincidence well with practical case.
出处
《岩石力学与工程学报》
EI
CAS
CSCD
北大核心
2001年第4期497-501,共5页
Chinese Journal of Rock Mechanics and Engineering
关键词
回采巷道
神经网络
锚杆
支护
设计
Bolts
Learning algorithms
Mining
Neural networks
Structural design
