Deep learning-based prediction of thermal residual stress and melt pool characteristics in laser-irradiated carbon steel

Abstract

Residual stress is a crucial factor that must be managed in laser manufacturing processes. Neglecting it can result in product failure or unsuitability for the intended use. In this article, we present the first surrogate deep learning model based on generative adversarial network that predicts thermal residual stress and melt pool characteristics on the cross-section of laser-irradiated carbon steel. The model was trained using simulation data obtained from the unified momentum equation approach-based numerical model. Our model was designed to predict various aspects of the laser melting process only from three scalar inputs of laser power, beam diameter, and irradiation time at two different points in time (immediately after the laser heating is finished and when the steel is completely cooled down) and successfully predicted the distributions of 12 variables, including residual stress and temperature. Prediction results were not only qualitatively very similar to their ground truth, but also quantitatively accurate with the R2 values ranging from 0.975 to 0.999 and the mean absolute errors between 0.0015 and 0.0126. We demonstrated that complex experiments can be quickly performed using the surrogate model because a single deep learning prediction took only 0.13 s, compared to the 2.5–8 h numerical simulation times.