DeepForge: Leveraging AI for Microstructural Control in Metal Forming via Model Predictive Control
This addresses quality control in metal forging processes, offering an incremental improvement by integrating AI for better microstructure management.
The study tackled microstructure control in closed die hot forging by developing DeepForge, a machine learning model that predicts microstructure changes from surface temperature measurements with a mean absolute error of 0.4±0.3%, and used Model Predictive Control to adjust inter-stroke wait times to achieve a target grain size of less than 35 microns in a specific region.
This study presents a novel method for microstructure control in closed die hot forging that combines Model Predictive Control (MPC) with a developed machine learning model called DeepForge. DeepForge uses an architecture that combines 1D convolutional neural networks and gated recurrent units. It uses surface temperature measurements of a workpiece as input to predict microstructure changes during forging. The paper also details DeepForge's architecture and the finite element simulation model used to generate the data set, using a three-stroke forging process. The results demonstrate DeepForge's ability to predict microstructure with a mean absolute error of 0.4$\pm$0.3%. In addition, the study explores the use of MPC to adjust inter-stroke wait times, effectively counteracting temperature disturbances to achieve a target grain size of less than 35 microns within a specific 2D region of the workpiece. These results are then verified experimentally, demonstrating a significant step towards improved control and quality in forging processes where temperature can be used as an additional degree of freedom in the process.