Convolutional Neural Network-Based Detection of Booming Noise in Internal Combustion Engine Vehicles Using Simulated Acoustic Spectrograms
Source abstract
Abstract
In this work, we tested the use of Convolutional Neural Networks (CNNs) to classify booming noise inside vehicles. Instead of relying only on long experimental campaigns, we generated a synthetic dataset from Sound Quality Equivalent (SQE) models that were originally built from real acoustic measurements collected with sensors. By applying smoothing functions and Hann windows, we were able to vary the intensity of the booming effect across different mission profiles. The CNNs were trained on spectrograms derived from these signals, with labels informed by psychoacoustic evaluations. The best model reached about 95.5% accuracy in the binary task (booming vs. no booming) and around 93.3% when using three classes (severe, mild, none). Tests with data from three different car models showed that the method can generalize across platforms. These results suggest that CNNs may become a practical tool for NVH analysis, offering a simpler and cheaper complement to traditional end-of-line testing, and one that could be adapted for real-time embedded systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Vehicle Noise and Vibration Control · Acoustic Wave Phenomena Research · Aerodynamics and Acoustics in Jet Flows
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculdade de Engenharia da Universidade do Porto (FEUP), Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
INEGI—Institute of Science and Innovation in Mechanical and Industrial Engineering, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
Funding
Fundação para a Ciência e Tecnologia
References (33)
Show source-provided references
1. Van de Ponseele, P., Van der Auweraer, H., Janssens, K., Sas, P., Moens, D., and Jonckheere, S. (2012, January 17–19). Source-transfer-receiver approaches: A review of methods. Proceedings of the International Conference on Noise and Vibration Engineering (ISMA2012)/International Conference on Uncertainty in Structural Dynamics (USD2012), Leuven, Belgium.
2. Sound quality analysis of the powertrain booming noise in a diesel passenger car10.1016/j.egypro.2017.08.189 ↗
3. Wellmann, T., Govindswamy, K., and Eisele, G. (2011). Driveline Boom Interior Noise Prediction Based on Multi Body Simulation, SAE International. SAE Technical Papers.10.4271/2011-01-1556 ↗
4. Corbeels, P., Choukri, M., and Bianciardi, F. (2025, December 20). Component-Based Transfer Path Analysis: Guidelines to Predict Component NVH Performance Before the First Vehicle Prototype is Built. Available online: https://www.researchgate.net/publication/344607983_Component-based_transfer_path_analysis_-_Guidelines_to_predict_component_NVH_performance_before_the_first_vehicle_prototype_is_built.
5. Mechanism study and reduction of minivan interior booming noise during acceleration10.1155/2019/2190462 ↗
6. Brunton, S., and Kutz, J. (2019). Linear control theory. Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control, Cambridge University Press.10.1017/9781108380690 ↗
7. A sound quality model for objective synthesis evaluation of vehicle interior noise based on artificial neural network10.1016/j.ymssp.2013.11.001 ↗
8. Sound quality evaluation of the booming sensation for passenger cars10.1016/j.apacoust.2008.03.009 ↗
9. Mitchell, T.M. (1997). Machine Learning, McGraw-Hill.
10. Identification of vehicle booming sound and its objective evaluation using psychoacoustic parameters10.1504/IJVD.2012.045922 ↗
11. Modification of booming level for higher correlation with booming sensation10.1016/S0389-4304(98)00052-6 ↗
12. On an objective measure of the booming sound factor: Modification of the measure for the spectrum pattern and the loudness of the sound
13. Objective prediction of the sound quality of music processed by an adaptive feedback canceller10.1109/TASL.2012.2188513 ↗
14. Kim, D., Jeon, S., Lee, J., Kwak, K., Cho, M., Lee, H., Kim, M., and Chung, J. (2023). Strategies for reducing booming noise generated by the tailgate of an electric sport utility vehicle. Appl. Sci., 13.10.3390/app132413134 ↗
15. Altinsoy, M.E. (2022). The evaluation of conventional, electric and hybrid electric passenger car pass-by noise annoyance using psychoacoustical properties. Appl. Sci., 12.10.3390/app12105146 ↗
16. Acoustic analysis and data-driven control of vehicle NVH: A framework for manufacturing process optimization10.1016/j.apacoust.2025.110618 ↗
17. Chu, H.-C., Zhang, Y.-L., and Chiang, H.-C. (2023). A CNN sound classification mechanism using data augmentation. Sensors, 23.10.3390/s23156972 ↗
18. Tsalera, E., Papadakis, A., and Samarakou, M. (2021). Comparison of pre-trained CNNs for audio classification using transfer learning. J. Sens. Actuator Netw., 10.10.3390/jsan10040072 ↗
19. The use of an artificial neural network for assessing tone perception in electric powertrain noise, vibration and harshness10.1007/s11012-024-01753-x ↗
20. A survey of modern vehicle noise, vibration, and harshness: A state-of-the-art10.1016/j.asej.2024.102957 ↗
21. Blough, J.R., Brown, D.L., and Vold, H. (1997). The Time Variant Discrete Fourier Transform as an Order Tracking Method, SAE International. SAE Technical Paper.10.4271/972006 ↗
22. Sarrazin, M., Colangeli, C., Janssens, K., and Van der Auweraer, H. (2013, January 15–18). Synthesis techniques for wind and tire-road noise. Proceedings of the Internoise 2013, Innsbruckt, Austria.
23. Fast detection and classification of dangerous urban sounds using deep learning
24. Park, J.J., Loia, V., Pan, Y., and Sung, Y. (2021). A study on dropout techniques to reduce overfitting in deep neural networks. Advanced Multimedia and Ubiquitous Engineering, Springer.10.1007/978-981-15-9309-3 ↗
25. Pereira, F., Lopes, H., Pinto, L., Soares, F., Vasconcelos, R., Machado, J., and Carvalho, V. (2025). A novel deep learning approach for yarn hairiness characterization using an improved YOLOv5 algorithm. Appl. Sci., 15.10.3390/app15010149 ↗
26. Pinto, R., Pereira, F., Carvalho, V., Soares, F., and Vasconcelos, R. (2019, January 14–17). Yarn linear mass determination using image processing: First insights. Proceedings of the IECON 2019—45th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal.10.1109/IECON.2019.8926650 ↗
27. Online yarn hairiness–Loop & protruding fibers dataset10.1016/j.dib.2024.110355 ↗
28. 3D Vision Object Identification Using YOLOv8
29. Wang, Y., Li, Y., Song, Y., and Rong, X. (2020). The influence of the activation function in a convolution neural network model of facial expression recognition. Appl. Sci., 10.10.3390/app10051897 ↗
30. Shallow convolutional neural network for image classification10.1007/s42452-019-1903-4 ↗
31. Zafar, A., Aamir, M., Mohd Nawi, N., Arshad, A., Riaz, S., Alruban, A., Dutta, A.K., and Almotairi, S. (2022). A comparison of pooling methods for convolutional neural networks. Appl. Sci., 12.10.3390/app12178643 ↗
32. Yang, Y., Dong, J., Wang, Y., Yu, B., and Yang, Z. (2023). DMAU-Net: An attention-based multiscale max-pooling dense network for the semantic segmentation in VHR remote-sensing images. Remote Sens., 15.10.3390/rs15051328 ↗
33. A review of convolutional neural networks in computer vision10.1007/s10462-024-10721-6 ↗