某装备扫雷犁系统的遗传神经网络建模研究  

Neural Network Modeling Based on Genetic Algorithm for Mine Sweeping Plough of a Certain Weapon

作　　者：童仲志[1] 张媛[1] 邢宗义[1] 秦勇[2] 贾利民[2] 

机构地区：[1]南京理工大学机械工程学院,江苏南京210014 [2]北京交通大学交通运输学院,北京100044

出　　处：《兵工学报》2010年第5期650-656,共7页Acta Armamentarii

基　　金：国家自然科学基金资助项目(60674001);南京理工大学紫金之星基金资助项目(2010JX02);南京理工大学科技发展基金资助项目(XKF09003)

摘　　要：提出了一种基于遗传算法的径向基神经网络设计方法,对具有复杂非线性特征的某装备扫雷犁系统进行了建模研究。在神经网络设计过程中,采用遗传算法确定神经网络的中心参数,提高了建模精度,采用最大距离法确定宽度参数和采用最小二乘法确定权值参数,减轻了算法的计算量,从而实现了快速准确的扫雷犁系统的神经网络建模。与其它神经网络建模方法的比较,验证了本文提出方法的有效性。A method for designing the radial basis function neural network based on the genetic algorithm was proposed, a certain mine sweeping plough with complex and nonlinear characteristic was modeled by the method. In order to improve the accuracy of the designed model, a genetic algorithm is used to optimize centers of the neural network. The maximum distance measure is adopted to determine the widths and the least square method is utilized to calculate the weights of the neural network, thus computational burden of the proposed technique is relieved. The comparison between the proposed and the others shows that the proposed modeling method is effective.

关 键 词：人工智能 扫雷犁系统 电液伺服系统 遗传算法 径向基神经网络 

分 类 号：TJ812.5[兵器科学与技术—武器系统与运用工程]