Springback is an inevitable problem in the local bending process of hull plates, which leads to low processing efficiency and affects the assembly accuracy. Therefore, the prediction of the springback effect, as a result of the local bending of hull plates, bears great significance. In total, four springback prediction models, based on genetic and back propagation neural network (GA-BPNN) algorithms and the improved particle swarm optimization (PSO)-BPNN algorithms, are established.

In this paper, a high-rigidity screw-type tip-inserting mechanism with a good centering effect is designed. The structural characteristics and working principle of the inserting mechanism are introduced, the stiffness model of the new-type pipetting device is established and its stiffness and axial deformation are calculated. Finally, a multi-station high-throughput automatic pipette produced by a company was used as an example to optimize and improve it and conduct a prototype test.

Non-circular grinding is used in the grinding of crankshafts. In this study, an equation for detecting the angle error in non-circular grinding is established. Previous studies did not exclusively detect the errors caused by bending deformation and torsional deformation. However, the established equation detects these errors separately. The angle error was found to be up to 0.44 arcsec, which is 5 % of the angle error obtained from previous studies.

The paper proposed a normal contact stiffness model considering 3D topography and elastic–plastic contact of rough surfaces. The proposed model is validated using experimental tests conducted on two types of specimens and is compared with published theoretical models. The proposed model can provide a tool for efficient calculation of the contact force, deformation, and contact stiffness in engineering surfaces.

In this paper, the typical mechanical joint surface is taken as the research object. Through the combination of theoretical analysis and experimental analysis, the dynamic characteristics of typical joint surface parameters with different surface textures and the influence of texture parameters on the dynamic characteristics of the joint surface are studied.

Due to the time-consuming and inefficient traditional tool selection method based on the human experience, we apply transfer learning to CNC tool selection issue in the field of industrial manufacturing. A unified expression of expert experience and process case is given in a more complex environment and then we improve the algorithm. The results show that the method we proposed can facilitate tool selection.

Temperature fields evolving during metal cutting processes have been of major interest. Temperatures in the tool influence the wear behaviour and hence costs, temperatures in the work-piece are directly responsible for later product quality. Due to the high significance of temperatures, many modelling attempts for temperature fields have been conducted, however failed to deliver satisfying results. The present paper describes an analytical model using complex functions based on potential theory.