基于RELS方法的激光焊接过程非线性辨识

Nonlinear identification of laser welding process based on recursive extended least squares method

激光焊接过程是一个很复杂的非线性系统,用机理建模法很难得到系统的数学模型,通常采用基于输入输出数据的系统辨识方法。考虑到实际系统通常伴随着有色噪声,本文采用递推增广最小二乘法(RELS)辨识。这种方法考虑了噪声模型,可以得到模型参数的无偏最小方差估计。试验数据和模型仿真的拟合效果表明,递推增广最小二乘法是激光焊接过程非线性辨识的一种行之有效的方法。

Laser welding process was a complicated nonlinear system.It was very difficult to obtain the mathematical model of the system by mechanism.Systems identification method was usually adopted to get the model by using input-output data.Considering the system was usually subject to colored noises,this paper used the recursive extended least squares to identify the model.The method considered the noise model and could get an unbiased estimation of the model parameters.The fitting results between the experimental data and model simulation showed that recursive extended least squares was an effective nonlinear identification approach for laser welding process.