转向架参数测定试验台位姿正解

Forward Kinematics of Test Bench for Bogie Parameters

并联机构位姿正解求解运用的Newton-Raphson迭代法对初值有很强依赖性,且收敛速度较慢,无法满足实时性要求.为此文中提出基于Levenberg-Marquardt(L-M)算法的改进BP分类神经网络结构模型和高阶收敛改进Newton-Raphson迭代法(HMNR)相结合求解并联机构位姿正解.以转向架参数测定试验台为例,借助位姿反解将轨道谱路谱转化成试验台作动器的伸缩量指令,将其给定到液压系统中,驱动试验台耦合运动模拟车体或转向架在该路谱线路上的运行状态.运用大量实际运行样本数据作为训练数据,实现了试验台位姿正解的初值求解,并与常用的基于拟牛顿算法(BFGS)的神经网络模型和量化共轭梯度(SCG)算法的神经网络模型进行对比分析.结果表明,L-M算法模型在误差性能分析上明显优于BFGS与SCG算法模型,且预测角度值误差均小于4×10^(-7),位移值误差均小于8×10^(-4).将预测值作为HMNR法的初值,进行迭代计算,较之Newton-Raphson(NR)法迭代次数减少41%,迭代时间缩短23%.将此混合策略用于试验台,进行实际相邻车端相对位姿测量试验,进一步验证了该策略的有效性.

The existing Newton-Raphson iterative method used for the forward kinematics of parallel mechanismshas a strong dependency on the initial value with a slow iteration convergence speed, and thnot be satisfied. In order to solve these problems,a combinatorial method of a new improved BP Neural Networkmodel based on the Levenberg-lMarquardt algorithm and the high-order modified Newton-Raphson （HMNR） itera-tion method is proposed to achieve the forward kinematics of Redundancy parallel mechatest bench for bogie parameters （TBBP） as the example, the track spectrum is actuator with the help of the invert kinematics. Hydraulic system received the instruction of displacement to propelthe test bench’s coupling motion,which is used to simulate the running status of the real vehicle or bogie on real tracks. By using a mass of actual data as the training material, the initial value of the forward kinematics of the test bench is thus determined, which is then compared with those obtained through the netively based on the quasi-Newton algorithm BFGS and the scaled conjugate gradient （SCG） algorittal results show that the L-Ml algorithm model is obviously superior to the BFGS algorithm model and the SCG algo-rithm model in terms of the error performance analysis, with a predicted angle value of less than 4 Xplacement error of less than 8 x 10 4. In addition, the predicted value is taken as the initial value of the HMNR method to perform an iterative calculation, which causes a 4 1 % reduction in the required iterations and a 2 3 % re-duction in the iteration time in comparison with the Newton-Raphson （NR） method. Finally, by applying the hy-brid strategy on the TBBP for testing the relative position and attitude of adjacent vehiclhybrid strategy is further validated.