Measurement Method of Flexible Component Pose based on Discrete Motion Actuators

Abstract In order to address the limitations of traditional large discrete motion actuator mechanisms in realizing high-precision inter-axis relationship calibration in manufacturing environments, this paper proposes a new convolutional neural network-based attitude mapping estimation method, CPCNN. The method implicitly encodes the inter-axis relation matrix into the weight parameters of the training neural network, which results in a high degree of integration with existing large discrete motion actuator mechanisms. The CPCNN-based method directly obtains the attitude change of the adjustment cabin by reading the change of each axis of the current motion actuator mechanism in its own coordinate system. This method can overcome the limitations of the experimental process in the traditional calibration methods and improve the accuracy of attitude mapping under the influence of self-weight by selecting better motion parameters through redundant degrees of freedom. The application of this new method will provide an effective solution for the high-precision inter-axis relationship calibration of large discrete motion actuator mechanisms in manufacturing environments, offering new possibilities for improving production efficiency and product quality.