A temperature-perceptive SFANC (TP-SFANC) approach is proposed that employs a lightweight one-dimensional convolutional neural network (1D CNN) trained using a multi-task learning strategy to dynamically select the optimal control filter.
Abstract
Active noise control (ANC) trim panels offer an effective solution to suppress multi-tonal noise in aircraft. The selective fixed-filter ANC (SFANC) method, characterized by low computational complexity, high robustness and rapid response, is suitable to handle multi-tonal engine noise that varies in frequency due to changes in the rotational speed of the engine shaft. However, real-world conditions introduce variations in lining temperature, altering acoustic and structural paths and degrading noise reduction performance. To address this challenge, a temperature-perceptive SFANC (TP-SFANC) approach is proposed that employs a lightweight one-dimensional convolutional neural network (1D CNN) trained using a multi-task learning strategy. By processing both reference and error signals, the 1D CNN learns frequency and temperature characteristics to dynamically select the optimal control filter. Numerical simulations demonstrate the effectiveness of the proposed method in attenuating multi-tonal noise across varying frequencies and lining temperatures.
This thesis investigates the application of deep learning techniques to overcome the limitations of conventional ANC systems and proposes a novel Stacked Autoencoder (SAE)- based ANC framework, trained to estimate the optimal anti-noise signal required for noise cancellation.
Deep learning-based active noise control (ANC) algorithms demonstrate superior potential over traditional methods in addressing nonlinear distortion. Although recent deep learning approaches incorporating Volterra Neural Networks (VNNs) have been optimized to tackle nonlinearities, there remains room for further improvement: (1) utilizing element-wise addition in skip connections across different feature processing stages increases the risk of feature aliasing or suppression; (2) directly introducing higher-order terms of the Volterra series is prone to causing overfitting; and (3) models trained under a singular nonlinear condition struggle to adapt to real-world scenarios with varying nonlinearities. To address these issues, this letter proposes a novel time-domain ANC framework. While retaining the modeling capabilities of WaveNet and VNNs, the proposed framework integrates the U-shaped structure and incorporates an adaptive gating mechanism for the higher-order Volterra terms. The proposed method is compared with a state-of-the-art deep learning framework. Additionally, the model is evaluated under several controlled nonlinear conditions, and comprehensive ablation studies are conducted. Simulation results demonstrate that the proposed algorithm outperforms existing end-to-end representative Deep Neural Network (DNN) methods, and ablation studies confirm the effectiveness of the proposed modules.
Tianyi Ge, Liang An, Ning Han et al.· IEEE Signal Processing Lette...· 0 citations
A feedback-guided DNN-based controller fusion framework for robust fixed-parameter ANC that combines a causal WaveNet controller with a feedback-guided mixture-of-experts (MoE) module, where a gating network estimates the weights of multiple pre-trained FIR experts according to the current acoustic condition.
Lu Bai, Yiming He, Xiaofeng Nan et al.· 0 citations
The rapid evaluation of interior aerodynamic noise during the Concept A Surface design stage is important for vehicle acoustic development, but conventional methods are limited by high cost and low efficiency. This study proposes a convolutional neural network transformer-based prediction method for vehicle interior wind noise by integrating vehicle styling features and acoustic technical parameters. An optimal Latin hypercube sampling method was used to generate design combinations, and wind tunnel tests were conducted at 120 km/h. Key vehicle styling parameters, including A-pillar geometry, side mirror dimensions, front windscreen angle, side mirror-to-body spacing, and side window inclination, together with glazing material properties, glass thickness, acoustic transfer function, and interior reverberation time, were selected as input features to predict the driver’s left-ear wind noise spectrum. Based on five-fold cross-validation, the proposed model was compared with convolutional neural network (CNN), long short-term memory (LSTM), and transformer models. The CNN-Transformer model achieved the best performance, with mean absolute percentage error (MAPE) and root mean square error (RMSE) values of 2.23% and 0.94 dB, respectively. Compared with the transformer, CNN, and LSTM models, the proposed method reduced MAPE by 24.91%, 36.29%, and 49.59%, and reduced RMSE by 22.95%, 35.17%, and 48.07%, respectively. The model also maintained reliable performance on an independent test set, with MAPE and RMSE values of 4.82% and 1.44 dB. The mean impact value method was further applied to identify the influence of design parameters on interior wind noise, guiding for early vehicle acoustic optimization.
Hongwei Yi, Penghu Li, Jifeng Wang et al.· Sound & Vibration· 0 citations
In this study, a hybrid deep learning architecture is proposed for robust vibration-based fault diagnosis in industrial machinery by jointly modeling time-domain, frequency-domain, and temporal dynamics. In the time domain, convolutional layers combined with an Enhanced Gated Attention (EGA) mechanism emphasize informative signal components while suppressing noise. Temporal evolution is modeled using Neural Ordinary Differential Equations (Neural ODEs), enabling smooth and stable continuous-time feature representations. In parallel, a Fourier Neural Operator (FNO) extracts frequency-domain characteristics, augmented with gated attention to focus on fault-related spectral patterns. Long Short-Term Memory (LSTM) layers capture long-range dependencies, while Squeeze-and-Excitation (SE) blocks adaptively recalibrate channel-wise feature responses. A multi-scale attention-based fusion module integrates domain-specific representations and auxiliary features to enhance discrimination under varying operating conditions. The proposed model is evaluated on the SUBFv1.0 dataset through extensive ablation studies and experiments under multiple noise levels, achieving 98.41% accuracy in noise-free conditions and maintaining performance above 91% even at 5 dB SNR. Unlike existing multi-path approaches that combine heterogeneous features in a loosely coupled or discrete manner, the proposed architecture uniquely integrates multi-domain feature learning with bidirectional attention mechanisms and continuous-time temporal dynamics, enabling coherent cross-domain interaction and robust fault characterization.
Canan Taştimur· Information Technology and C...· 0 citations
This conceptual study provides a thorough explanation of ANC technology spanning more than 90 years of development, from Paul Lueg's early 1936 patent to the most recent deep learning methods, and shows that deep learning approaches are the ANC technology of the future.
M. Qassab, Q. Ali· ITEGAM- Journal of Engineeri...· 0 citations