Multi-Objective Optimization of Vortex Disc Process Parameters Based on Neural Network and Genetic Algorithm

In this paper, a multi-objective optimization strategy of production process parameters based on the neural network and genetic algorithm is proposed with an automotive scroll disk as research object. The forging forming numerically simulated by Deform-3D finite element software, billet temperature, die speed variables, load, residual stress, deformation indicators. nonlinear mapping relationship between variables indicators constructed using network, model optimized for dynamic parameters. most suitable solutions finally obtained in Pareto frontier set: temperature: 460°C, mold 220.006°C, speed: 18.4158 mm/s, when values three are smaller. solution was experimentally verified vortex discs were filled to brim no defects, so can be applied actual processing.