基于改进RBF神经网络的钢构件质量预测研究  

Research of Steel Components Quality Prediction Based on the Improved RBF Neural Network

作　　者：雷兆明[1] 王东泽 花季伟[2] 王军[1] 

机构地区：[1]河北工业大学控制科学与工程学院,天津300130 [2]天津师范大学计算机与信息工程学院,天津300387

出　　处：《自动化与仪表》2015年第9期1-4,46,共5页Automation & Instrumentation

基　　金：河北省科技支撑计划项目(13210307D);天津市高等学校科技发展基金计划项目(20120814)

摘　　要：随着我国国民经济的发展,钢结构在建筑结构中所占比例越来越高,这就对大型钢构件生产过程中的质量问题提出了更高的要求,质量预测在质量控制中也起到至关重要的作用。RBF神经网络算法凭借其无限逼近可微函数的优点在质量预测方面得到了广泛的应用。由于生产过程中影响质量的元素很多,该文将采用遗传算法对RBF神经网络进行优化,使质量预测系统达到最优。With the development of national economy in China,the steel structure building is becoming increasingly commonplace. At the same time the quality problem in the process of producing large steel members is becoming more and more important. Quality prediction also plays a key role in quality control,so the RBF neural network al- gorithm with the advantage of its infinite approximation of differentiable function has been widely used in quality predicting. Due to many elements influencing the quality of production process,this paper adopts genetic algorithm to optimize RBF neural network,and finally achieves the optimum in quality prediction system.

关 键 词：钢结构 质量预测 RBF神经网络 遗传算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]