基于粒子群-向量机的汽车加速噪声评价

以乘用车由50 km/h加速到100 km/h时的噪声信号为评价对象,用成对比较法对车内加速噪声品质偏好性进行主观评价实验,获得每个样本的偏好性评价值。计算各噪声样本的主要心理声学客观参数并进行相关分析。鉴于评价者对非稳态噪声主观评价过程的复杂性,建立支持向量机(Support Vector Machine,SVM)的主客观评价模型,并利用粒子群优化算法(Particle Swarm Optimization,PSO)对模型参数进行优化。为对比优化后预测效果,建立BP神经网络回归模型。结果表明,优化后的粒子群-向量机回归模型用于噪声声品质评价能获得更好的预测效果,可较大程度提高声品质预测精度。

Evaluation of car interior sound quality based on PSO-SVM

The noise signals from passenger car during acceleration from 50km/h to 100km/h were selected as the evaluation objects and Subjective testing is carried out via the paired comparison method to get the annoyance scores. The BK software is used to calculate the main psychoacoustics parameter and then find their Correlation. In view of the complexity of subjective evaluation process to transient noise, this paper use Support Vector Machine model to simulate the process of noise subjective evaluation, and then the input parameters of support vector machines is optimized by the particle swarm optimization. In order to compare the optimized prediction effect, the BP neural network is established at the same time. The results show that the quality evaluation of the acceleration noise can get better prediction effect with pso-svm model, and it could largely improve the predictive accuracy of sound quality evaluation and has reference value for evaluation and analysis of the vehicle noise.