An intelligent design methodology for multi-stage loading paths of variable parameters during large-scale electric upsetting process

Abstract

It is a great challenge to design the multi-stage loading path of variable parameters to obtain the component with smooth shape and fine-grained microstructures during the electric upsetting process of large-scale valves. To achieve this, an intelligent design methodology was developed and applied in an electric upsetting process of Ni80A alloy. The methodology integrates backpropagation neural network (BP neural network), case-based reasoning (CBR), and parameter self-feedback adjustment coupling with finite element (FE). Firstly, a BP neural network model was developed based on the basic database to predict the initial processing parameters of components (upsetting force, current, and pre-heating time). Secondly, utilizing the CBR method, the suitable design schemes were identified by retrieving similar components, and then the multi-stages loading paths for upsetting force and current were devised. Thirdly, a subroutine of self-feedback adjustment to fine-tune the loading paths was developed and implanted into the multi-field and multi-scale coupling FE model. Finally, the optimal loading paths was obtained using the FE model until the deformed component meets the requirements of shape and grain size. The results indicated that the surface contour of component was smoother and without macroscopic defects under the optimal loading paths, with the maximum grain size refined to 103.9 μm. To further improve the automation level of the parameters design process, an expert system was developed based on the designed methodology. This work contributes to the intelligent design of processing parameters for the electric upsetting process, which provides a design framework of processing parameter in other manufacturing technologies.