摘要
针对目前板形模式识别方法存在的问题,以及考虑到现代轧机板形控制手段的多样化和板形控制能力的提高,为了提高板形模式识别模型的精度,本文以1次、2次、3次和4次勒让德正交多项式为板形基本模式,建立了基于量子粒子群-BP算法混合优化神经网络的新型板形模式识别模型。仿真实验表明,该模型抗干扰能力强、识别精度高、速度快,可以为板形控制策略的制定提供可靠依据。
In the light of the problems existed in the present flatness pattern recognition method,and considering the practical situation of modern mills with many different flatness control means and the improvement of flatness control capability,in order to improve the precision of flatness pattern recognition model,in this paper,a new flatness pattern recognition model is established based on QPSO-BP algorithm mix optimization neural network.This model takes linear,quadratic,cubic and biquadratic Legendre orthogonal polynomials as flatness basic patterns.The simulation experiments indicate that this model has strong anti-interference ability,high recognition precision and fast velocity,and can provide reliable basis for the formulation of flatness control strategy.
出处
《燕山大学学报》
CAS
2011年第1期35-39,共5页
Journal of Yanshan University
关键词
板形
模式识别
勒让德多项式
量子粒子群算法
BP神经网络
flatness
pattern recognition
Legendre orthogonal polynomial
QPSO algorithm
BP neural network