In sheet metal industries, predicting and avoiding failures, such as necking, fracture, and wrinkling, is important. Thus, working within a safe region to avoid these failures is important. The forming limit diagram (FLD) is the most appropriate tool to obtain the safe strain region for every sheet metal in different conditions. Forming Limit Diagram of perforated sheet metal can be affected by its mechanical properties like Yield Strength, Sheet thickness, Anisotropy value, Ultimate Tensile Strength, Strain Hardening exponent, and total elongation. In this project, the mechanical properties of aluminium and steel metal sheets are correlated with their forming limit diagram at room temperature. Various models based on machine learning and deep learning have been introduced to reveal the forming limit diagram of various metal sheets and then the accuracy of different models was compared to select the best model. The effect of each mechanical property on the FLD was also studied and analysed. After using experimental data to train and validate the various models, the models were applied to the test data for the prediction of forming limit diagrams.
deep0505sharma / formability-analysis-of-sheet-metals-using-machine-learning Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License