Prediction and Optimization of Vehicle Interior Noise Sound Quality Based on XGBoost Algorithm
2022-01-0373
03/29/2022
- Event
- Content
- In the subjective evaluation of noise, it is often necessary for experienced people to listen to a certain number of sound samples and score and evaluate it, which is time-consuming and labor-intensive, and it is easy to cause hearing fatigue and even lead to inaccurate evaluation results. In the past research on sound quality prediction models, multiple linear regression models, support vector machine models, neural network models, etc. were mostly used for prediction. In this paper, psychoacoustic objective parameters such as loudness, sharpness, roughness, speech intelligibility, and A-weighted sound pressure level are selected for objective evaluation and used as the input value of the prediction model. A grade scoring method was used to evaluate 68 samples of vehicle interior noise. Finally, the arithmetic average of the subjective scores of 20 people was calculated and used as the output value of the subsequent prediction model. Based on the XGBoost algorithm, a prediction model of the vehicle interior noise sound quality is constructed. Compared with multiple linear regression models and neural network models, it has more accurate results. Then, the sound absorption performance and sound insulation performance of several acoustic package materials were determined through acoustic tests, loaded to the corresponding positions and then re-collected test data. Finally, the A-weighted sound level is reduced the most, which is 0.96dB(A), followed by loudness, which is 1.83 sone. According to the prediction results of the XGBoost model, the subjective evaluation result after optimization is significantly better than the original case.
- Citation
- OU, J., Liu, J., ZHANG, Y., and YANG, E., "Prediction and Optimization of Vehicle Interior Noise Sound Quality Based on XGBoost Algorithm," SAE Technical Paper 2022-01-0373, 2022, .