Search for: All records

Abstract Sheet metal stamped and welded assemblies, such as the ones used in automotive body-in-white (BIW) structures, have various sources of manufacturing variations during stamping and assembly processes. One of the major contributors to these variations is the springback on clamping release due to elastic recovery. Mitigating these variations requires expert knowledge of mechanical behavior, tooling, and process design. No analytical models can be used for the variety of geometries. Nonlinear FEA is also being used to predict springback, but it is time-consuming and requires specialized expertise, which makes it difficult to use in design exploration. Machine learning holds the promise of democratizing such complex analyses. This paper presents several case studies for data curation/generation, ML training, and validation. The prediction and quantification of the effects of springback are done on two levels: (i) low granularity, which involves predicting variations in certain parameters that are critical to measuring and understand spring back, and (ii) high granularity, predicting the shape of the component while taking into account the effects of springback and the stresses in the components. The data required to train, test, and validate the ML models were generated previously using an automated, integrated multi-stage simulation approach that was necessary to produce large datasets. Stamping simulations were validated against NUMISHEET benchmarks and also compared to test results published by other researchers. Subsequently, machine learning models were trained on the curated dataset to predict 2D stamped component shapes after springback and stress distributions across these shapes. For the assembly dataset, parameters such as unconstrained planar minimum zone magnitudes, angles between component planes, and twist angles are predicted using machine learning models, including linear and polynomial regression, decision trees, gradient boosting regression, support vector regression, and fully connected neural networks, and compared for their performance using consistent metrics. Hyper-parameter tuning is performed to optimize model performance, with artificial neural networks demonstrating promising capabilities in understanding variations in forming and multi-stage assembly processes. 

Abstract There are many sources of manufacturing variations in sheet metal assemblies, such as automotive bodies. These include non-isotropic material properties from cold rolling, springback in stamping, and distortion from residual stresses when components are clamped and spot welded. FE simulations have been used to predict these variations in order to better design tooling and processes. Such simulations require expertise in complex, multi-stage nonlinear analysis. We are investigating the feasibility of training machine learning algorithms in order to democratize these types of analyses. This requires the curation of large, validated, and balanced data sets. To this end, we have developed a multi-stage finite element simulation workflow encompassing component stamping and joining with a focus on examining deformations due to springback in two-part assemblies. Three connected simulations comprise the workflow: (1) component stamping with capture of springback, (2) assembly clamping, and (3) assembly joining, then release. The workflow utilizes explicit dynamic finite element analysis (FEA) and includes the transfer of intermediate solutions (geometries/stresses), as well as extraction of key geometric parameters of springback from both component- and assembly-level simulations. The NUMISHEET 1993 U-draw/bending benchmark was referenced for its tooling geometry and utilized for verification of the forming process simulation; variations of material and geometry were also simulated. In summary, this work provides a means of generating a design space of flexible two-part assemblies for applications such as dataset generation, design optimization, and machine learning.