Artificial neural network for modeling and investigating the effects of forming tool characteristics on the accuracy and formability of thin aluminum alloy blanks when using SPIF

Abstract Incremental Sheet Forming (ISF) has attracted attention due to its flexibility as far forming process and complexity in the deformation mode are concerned. Single Point (SPIF) is one of major types ISF, which also constitutes simplest type ISF. If sufficient quality accuracy without defects desired, for production an ISF component, optimal parameters should be selected. In order do that, initial prediction formability geometric helps researchers select proper when components using SPIF. this process, selected tool materials shapes. As evidenced by earlier studies, multiple tests with different have been conducted experimentally explore such With regard range these parameters, scope study, influence material, shape, tool-end corner radius, surface roughness ( Ra / Rz ) were investigated on SPIF components: studied factors include formed parts. produce a well-established appropriate modeling was needed. To end, help adopting data collected from 108 SPIF, Artificial Neural Network (ANN) used determine geometry tools: thus, ANN applied predict output. Process input created relying actual values obtained experimental components. addition, analytical equation generated each output based extracted weight bias best network prediction. Compared approach, equations enable researcher estimate parameter within relatively short time practicable way. Also, Relative Importance (RI) (generated partitioning method) concerning expected presented study. One key findings that characteristics play essential role all predictions fundamentally impact final products.