Paper Title
Modelling And Optimization Of Process Parameters Of The Single Point Incremental Forming Of Aluminium 5052 Alloy Sheet Using Genetic Algorithm-Back Propagation Neural Network

Abstract- Dieless incremental sheet metal forming is restricted by different effects. The limited maximum wall angle and a reduced surface quality of the deformed areas are the common issues in single point incremental sheet forming. Using a three-layer back propagation neural network (BPNN) and genetic algorithm (GA), a second order mathematical prediction model is established in this paper to predict and optimise both the wall angle and surface roughness for the material Al5052 alloy sheets in relation with five common SPIF forming parameters: vertical step size, lubrication, spindle speed, tool diameter and feed rate. The main contribution of this work to Single stage SPIF was the successful manufacturing of a Cone shaped parts with almost vertical walls (71.6◦). As a failure criterion for formability prediction in sheet metal forming process, the conventional Forming Limit Diagram (FLD) is often used. To determine the forming limits and the fracture points, FLD is constructed for 27 different parameter combinations.