Blade-vortex interaction (BVI) noise is a significant source of rotor noise. In recent years, active flap control (AFC) has been used successfully to control BVI by adding a trailing edge flap to the blade. However, due to the rotor’s complex shape and motion in AFC, the accurate simulation of the motion and unsteady flow field is challenging. Therefore, studies of noise control by AFC have mostly focused on experimental methods. Few numerical simulations were conducted on the noise reduction mechanism. In order to understand the noise reduction mechanism of the AFC clearly, this paper establishes a computational fluid dynamics (CFD) method based on an overset grid and tries to simulate the AFC airfoil flow field with the artificial vortex interaction. The noise characteristics are obtained from an acoustic analogy method based on the Farassat 1A (F1A) equation. By parameter analysis study and by testing the airfoil load and vertical interference distance, the results show that the proposed active control method exactly reduces the airfoil-vortex interaction noise. A maximum noise reduction of 1.56 dB is observed, and the most critical control parameter is the deflection phase of the trailing edge. When the vortex core passes over the airfoil, the load fluctuation and the interaction noise can be reduced by an upward deflection of the trailing edge. The flapping of the trailing edge significantly changes the vortex core’s path, which can further control the downstream airfoil-vortex interaction and achieve noise reduction.

Conventional methods for solving Navier–Stokes (NS) equations to analyze flow fields and aerodynamic forces of airfoils with trailing edge flaps (TEFs) are known for their significant time cost. This study presents a Multi-Task Swin Transformer (MT-Swin-T) deep learning framework tailored for swift prediction of velocity fields and aerodynamic coefficients of TEF-equipped airfoils. The proposed model combines a Swin Transformer (Swin-T) for flow field prediction with a multi-layer perceptron (MLP) dedicated to lift coefficient prediction. Both networks undergo gradient updates through the shared encoder component of the Swin Transformer. Such a trained network model for computational fluid dynamics simulations is both effective and robust, significantly improving the efficiency of complex aerodynamic shape design optimization and flow control. The study further investigates the impact of integrating multi-task learning loss functions, skip connections, and the network’s structural design on prediction accuracy. Additionally, the effectiveness of deep learning in improving the aerodynamic simulation efficiency of airfoils with TEF is examined. Results demonstrate that the multi-task deep learning approach provides accurate predictions for TEF airfoil flow fields and lift coefficients. The strategic combination of these tasks during network training, along with the optimal selection of loss functions, significantly enhances prediction accuracy compared with the single-task network. In a specific case study, the MT-Swin-T model demonstrated a prediction time that was 1/7214 of the time necessitated by CFD simulation.

Reducing rotor aerodynamic noise is an important challenge in helicopter design. Active flap control (AFC) on rotors is an effective noise reduction method. It changes the segment airfoil shape, aerodynamic load distribution, and the wake path of the rotor flow by adding trailing edge flaps (TEFs). Although AFC noise reduction control is easily simulated, the relevant experiments have not been widely conducted due to test technical problems and limited financial support. The acoustic characteristics of the AFC-equipped rotor, such as the placement of TEFs for noise reduction and whether multiple winglets can provide a better effect than single winglets, have not been verified in previous experiments. In this work, an AFC-equipped rotor with two TEFs was designed, and its acoustic properties were tested in the FL-17 acoustic wind tunnel with microphone arrays in the far field. The results showed that the noise reduction effect of AFC was closely related to the control frequency and phase. Increasing the control phase could move the reduction region toward the azimuth-decreasing region for far-field noise. The noise reduction in a single outboard TEF was better than that in a single inboard TEF, while the dual-TEF model performed better. In this experiment, the average noise reduction in the observation point at the lower front of the rotor could be more than 3 dB, and the maximum noise reduction could be 6.2 dB.