Research device structure upon suppressing impress and wrinkling about three-dimensional numerical control bending machine.3D ship curved-surface outside plate automatic forming process is always the difficult part in the field of domestic and international shipbuilding. Analyzing the problems in existing processing methods ,for example, line heating technology has the defects of poor production conditions, large labor intensity, not environmental friendly and cold bending forming method may result in indentation, wrinkling or rebound phenomenon.Presents the forming process of a ship hull plate based on square head adjustable die curved surface forming device. By setting the non pressure and a plurality of planar head to replace the traditional integral die method, the paper will illustrate the composition and working principles of the process at the same time try to implement effective control of indentation and wrinkle phenomenon followed by verification through experiments.

In the process of three-dimensional curved hull plate forming, springback caused serious influence on the forming accuracy, in order to ensure the forming quality of the asymmetric multiple pressure heads CNC bending machine of ship hull 3D surface plate, to achieve the automatic processing, it is necessary to solve the problem of springback in the hull plate forming process. It is rarely to see the research on the cold bending springback problem of middle-thickness hull plate now. To established nonlinear model of plate parameters and springback amount based on BP neural network, accurately analyzing the prediction of springback, and getting the sptringback prediction model based on the BP neural network in the Matlab programming.

Accurate prediction and effective control springback has a great significance to the plate cold bending forming. Based on the analysis of the support vector machine method principle and structure, Study on support vector machine prediction process based on MATLAB and prediction models about radius and resilience is set up. And the results predicted were compared with BP neural network prediction results to verify the accuracy.To provide an effective method for the accurate prediction springback.

According to the characteristics of high-speed liners, the multi-objective scheduling optimization mathematical model of high speed liners is established from the greenness angle. And the quantitative indicators and qualitative indicators were organic combined. The integer linear programming method was adopted to optimize analysis. Finally verify the feasibility of this optimal dispatch model through an example. Thus a scientific, reasonable way is provided for the high-speed liners scheduling arrangement.