Improving Efficiency of Automotive Coating and Curing Processes Through Deep Learning Algorithms and High-Fidelity CFD Modeling

Abstract

Abstract The automobile industry has relied on computational fluid dynamics (CFD) simulations to analyze and optimize the coating and curing processes, speed up product development, and lower the cost of product development. However, CFD modelings of these processes are computationally expensive due to the complexity of the models and the large number of simulations needed, especially when its used complex sprays such as the nithrothermal electrospray. As a result, more efficient methods must be developed to reduce computing time without compromising accuracy. In this article, we analyze how deep learning techniques can be used to predict coating and curing processes using electrospray CFD simulation. A dataset of 3D Eulerian-Lagrangian CFD simulations of coating and curing processes employing electro-spray for the automotive industry has been used to train different deep-learning models. We investigated how hyperparameters such as batch size and layer count affected deep learning model performance compared to conventional CFD simulations. For this, we evaluated the deep learning models’ efficiency and accuracy in terms of computing time. We also investigated how hyperparameters such as batch size and layer count affected deep learning model performance. Also, we’ve looked at the target’s final droplet deposition, and distribution that is required to accurately estimate the distribution. Furthermore, we studied the percentage of snapshots of the droplet distribution electrospray necessary to predict the target’s final deposition from the Lagrangian distribution. According to our findings, deep learning models can drastically reduce the amount of time needed to run CFD simulations. Depending on the model and hyperparameters applied, we can forecast the whole CFD simulation by utilizing somewhere between 10% and 15% of the initial spray development. Also, we discovered that the use of recurrent cells as an LSTM model outperformed the other models in terms of accuracy and computational efficiency, where the LSTM layers can extract better the features of the input snapshots. Overall, our research demonstrates the potential of deep learning techniques to significantly shorten the computing time of CFD simulations of coating and curing processes for the automotive sector. The results of this study have significant implications for coating and curing process design and optimization in the automobile industry as well as in other industries where CFD simulations are frequently employed.