Industrial robots are currently used in light milling operations for their low cost and large workspace compared with CNC machine tools. However, milling robots are prone to vibration instabilities (chatter) and process deviations since they are significantly less stiff than machine tools. As a result, robot dynamic response depends on its posture which represents a major challenge. This paper presents a direct method to update any multibody model, enclosing flexible rotational/translational or virtual joints with minimal tuning. The novel method allows determining the elastic parameters of the model based on a curve fitting of the frequency response functions measured at the tool tip. Fitting is fast and efficient as it occurs in the frequency domain without the need to transform the measured data into the model parameter space. It relies on a genetic algorithm followed by a deterministic procedure to ensure a refined solution of the identified global minimum. The method is firstly demonstrated and validated on a simulated flexible manipulator with three rotational joints. Its multibody model is built using minimal coordinates with known elastic parameters that the method recovers accurately. The new fitting algorithm is eventually applied to an actual industrial robot (KUKA KR90 R3100 robotic arm) resulting in the proper fit of its critical resonances. Posture dependency can also be tackled by considering multiple measurements in different poses within the same fitting procedure. Updating procedure was programmed in Matlab and made public so that it can be easily adapted to identify elastic parameters of other flexible mechanical systems.

与CNC机床相比，工业机器人目前在轻铣削操作中具有低成本和大工作空间的特点。但是，铣削机器人的刚性明显低于机床，因此容易出现振动不稳（颤动）和过程偏差。结果，机器人的动态响应取决于其姿势，这是一个重大挑战。本文提出了一种直接方法来更新任何多体模型，并以最少的调整来封闭柔性旋转/平移或虚拟关节。该新颖方法允许基于在工具尖端处测量的频率响应函数的曲线拟合来确定模型的弹性参数。拟合快速高效，因为它发生在频域中，而无需将测量数据转换到模型参数空间中。它依赖于遗传算法，然后是确定性过程，以确保对确定的全局最小值进行精确求解。该方法首先在具有三个旋转关节的模拟柔性机械手上得到了证明和验证。它的多体模型是使用具有已知弹性参数的最小坐标建立的，该方法可以准确地恢复。新的拟合算法最终应用于实际的工业机器人（KUKA KR90 R3100机械臂），从而使其临界共振得以正确拟合。姿势依赖性也可以通过考虑在同一拟合过程中以不同姿势进行的多次测量来解决。更新程序在Matlab中进行了编程，并公开发布，因此可以轻松地进行修改，以识别其他柔性机械系统的弹性参数。