CAE Acceleration With Machine Learning For Results Prediction

Industries are following a tedious product development cycle for developing their product. In product development major steps includes design ideas, Drawings, CAD, CAE, Testing and design improvement cycle. This is a monotonous process and takes time which impacts on its time to deliver product and cost on development. Now a days industries are fast growing and targeting to reduce development cycle time and cost. AIML is impacting almost all areas in the industry and significantly reducing efforts time and cost. To make use of AIML in CAE, Altair Physics AI is an effective tool. To ensure the design of product traditional way is to develop a CAD of the product, develop, perform CAE and analyze performance. If we consider CAE procedure it is time consuming process which includes FEA model build, applying boundary conditions, running simulation and analyzing results which could take minutes to hours. By using ML with Physics AI we can make predictions on new design of the product in seconds and significantly save time and cost. To demonstrate the CAE acceleration process with physic AI we have solved two case studies. The first case study is head impact on hood where ML tool will predict deformation contour of the hood, acceleration and displacement curve of the impactor. The second case study is Tube crush analysis where prediction of tube deformation pattern, force and energy curve for different tube length and impact velocity is carried out. For both Case studies we have used TCS inhouse data to train test and prediction of the ML model. For Head impact case study, it gives lower training loss with more than 90 percent prediction accuracy. Similarly for tube crush study it gives good accuracy and predicts comparable behavior patten with CAE results. Physic AI ML tool accelerates the design and development cycle and can be utilized in different product development. Implementation of ML accelerates the CAE process in design and development of products. It saves a lot of time in multiple design iteration study. Similar method can be implemented for different CAE cases