基于神经网络的弹性连杆机构广义刚度可靠性仿真  

Numerical Simulation of Random-fuzzy Reliability of Elastic Linkage Mechanism Stiffness Based on Artificial Neural Network

作　　者：拓耀飞[1] 陈建军[1] 陈永琴[1] 张驰江[1] 

机构地区：[1]西安电子科技大学机电工程学院

出　　处：《系统仿真学报》2007年第5期1138-1140,1156,共4页Journal of System Simulation

基　　金：国防预研基金(51421060505DZ0155);陕西省自然科学基金(2002A14)

摘　　要：将弹性连杆机构的杆长、截面尺寸均视为随机变量,并考虑机构安全的极限状态的模糊性,建立了弹性连杆机构广义刚度可靠性分析模型。针对进行可靠性数值模拟时求解机构动力响应过程的复杂性和耗时性,构建了基于BP网络的动力响应分析模型。从而可以明显减少可靠性仿真时求解动力响应的时间开支,提高仿真效率。最后,通过仿真实例验证了方法的可行性和有效性。The random-fuzzy reliability model was built by taking the bar length, interception parameters as random variables and taking the fuzziness of safety state into consideration. Then a dynamic analysis model based on BP （Back-propagation） Network was established in accordance with the complexity and time-consuming character of the dynamic analysis in the reliability simulation of elastic linkage mechanism. It can decrease the simulation time and increase calculation efficiency obviously. Finally, the results of the numerical simulations show that the method is practicable and effective.

关 键 词：弹性连杆机构 神经网络 数值仿真 刚度 广义可靠性 

分 类 号：TP302.7[自动化与计算机技术—计算机系统结构] TH112.5[自动化与计算机技术—计算机科学与技术]