Feasibility study of data-driven wall interference correction framework for subsonic wind tunnel

Although the classical method is widely used for wall interference correction in wind tunnel testing, its reliability and accuracy for complex and unconventional geometries are rather limited. Studies on the evaluation of wall interference and the improvement of correction methods are desirable to enhance the reliability and generality for various geometric configurations. This study proposes a wall interference correction framework based on a deep neural network (DNN) ensemble using data obtained from the numerical panel method. The panel method is validated by comparing the results with those of Reynolds-averaged Navier-Stokes simulations. An automated process was established to generate a large amount of training data, and 600,000 datasets were generated based on the geometric parameters of the wind tunnel, test model, and angles of attack. The input variables of the DNN were determined through sensitivity analysis of the data. To alleviate the randomness of the initial weights and data distribution in the generation process of the DNN model, 20 DNNs with the same multi-layer perceptron structure were trained, and a DNN ensemble model was constructed using five ensemble members with high predictability. The accuracy of the DNN-ensemble based correction models were evaluated by comparing the correction results for the testing data.