Turn-Milling Combined NC machine tool is different from traditional machine tools in structure and process realization. As an important means in the design stage, the analysis method of geometric accuracy error is also different from the traditional method. The actual errors and the error compensation values are a pair of "symmetry" data sets which are connected by the movement of machine tools. The authors try to make them more consistent through this work. The geometric error terms were firstly determined by topological structure analysis, then based on homogeneous coordinate transformation and multibody system theory, the geometric error model was established. With the interval theory, the function rule of sensitivity of geometric error sources to spatial errors was analyzed in detail, and the global maximum interval sensitivity of nine geometric error sources was extracted, providing a theoretical basis for error compensation and precision distribution. The geometric error sensitivity analysis method proposed in this paper can accurately evaluate the influence weights of each error term on the machining accuracy, and identify the important sensitive error terms with great influence on the machining accuracy from many error terms.

Open access peer-reviewed chapter

In the process of human–robot collaborative assembly, robots need to recognize and predict human behaviors accurately, and then perform autonomous control and work route planning in real-time. To support the judgment of human intervention behaviors and meet the need of real-time human–robot collaboration, the Fast Spatial–Temporal Transformer Network (FST-Trans), an accurate prediction method of human assembly actions, is proposed. We tried to maximize the symmetry between the prediction results and the actual action while meeting the real-time requirement. With concise and efficient structural design, FST-Trans can learn about the spatial–temporal interactions of human joints during assembly in the same latent space and capture more complex motion dynamics. Considering the inconsistent assembly rates of different individuals, the network is forced to learn more motion variations by introducing velocity–acceleration loss, realizing accurate prediction of assembly actions. An assembly dataset was collected and constructed for detailed comparative experiments and ablation studies, and the experimental results demonstrate the effectiveness of the proposed method.

Li P.; Lin, L., and Chen Y., 2018. A SROD algorithm based accurate detection method for surface rust spots in ocean ship. In: Liu, Z.L. and Mi, C. (eds.), Advances in Sustainable Port and Ocean Engineering. Journal of Coastal Research, Special Issue No. 83, pp. 921–926. Coconut Creek (Florida), ISSN 0749-0208. A new spot detection method is proposed to improve the detection accuracy of the surface rust. Aimed at the features of variable size and random distribution of rust spots, the rough criteria condition of the spot, based on the SROD algorithm, is improved. With proposed method, the adaptive threshold is used to identify the number of spots. The location and area size of the rust spot are accurately determined by the adaptive spot boundary calibration. The experimental results show that the advantage of proposed method is that it reduces the misidentification probability of the inherent surface structure, and improves precision of spot centroid and the area of the irregular rust. With proposed method, both detection rate and range are better than that with traditional methods.