The perception of vehicle interior sound quality is important for passengers. In this paper, a feature fusion process for extracting the characteristics of vehicle interior noise is studied, and an improved deep belief network (DBN) that uses continuous restricted Boltzmann machines (CRBMs) to model continuous data is proposed. Six types of vehicles are used for recording interior noise under different working conditions, and a corresponding subjective evaluation is implemented. Psychoacoustic metrics and energy-based criteria using the wavelet transform (WT), wavelet packet transform (WPT), empirical mode decomposition (EMD), critical-band-based pass filter, and Mel-scale-based triangular filer approaches have been applied to extract interior noise features and then develop a fusing feature set combining psychoacoustic metrics and critical band energy based on comparisons. Using the obtained fusion feature set, a CRBM-based DBN (CRBM-DBN) model is developed through experiments. The newly developed model is verified by comparing its performance relative to multiple linear regression (MLR), backpropagation neural network (BPNN), and support vector machine (SVM) models. The results show that the proposed CRBM-DBN model has a lower prediction error and higher correlation coefficient with human perception compared to the other considered methods. In addition, CRBM-DBN outperforms

The sound quality of vehicle interior noise strongly influences passengers' psychological and physiological perceptions. To predict the sound quality of interior noise, a vehicle road test with four compact cars has been conducted. All recorded interior noise signals have been denoised via a discrete wavelet transform (DWT) denoising procedure and subsequently evaluated subjectively through the anchor semantic differential (ASD) test by a jury. In addition, a novel prediction method, namely, regression-based deep belief networks (DBNs), which substitute the support vector regression (SVR) layer for the linear softmax classification layer at the top of the general DBN's structure, has been proposed to predict the interior sound quality. The parameter selection of the DBN model has been compared and studied using a grid search. In addition, four conventional machine-learning-based methods have been introduced to enable a comparison of the performance with the newly developed DBNs. Furthermore, the feature fusion ability of DBNs has been studied by varying the amount of information that the dataset offers. The results show the following: 1) The accuracy and robustness of the proposed DBN-based sound quality prediction approach are better than those of the 4 other referenced

No abstract

Squeak and rattle (S&R) Wavelet packet transform (WPT) Wavelet packet energy (WPE) Wavelet packet sample entropy (WPSE) Genetic algorithm (GA) Support vector machine (SVM) a b s t r a c tThe squeak and rattle (S&R) noise of a vehicle's suspension shock absorber substantially influences the psychological and physiological perception of passengers. In this paper, a state-of-the-art method, specifically, a genetic algorithm-optimized support vector machine (GA-SVM), which can select the most effective feature subsets and optimize the model's free parameters, is proposed to identify this specific noise. A vehicular road test and a shock absorber rig test are conducted to investigate the relationship between these features, and then an approach for quantifying the shock absorber S&R noise is given. Pre-processed signals are decomposed through a wavelet packet transform (WPT), and two criteria, namely, the wavelet packet energy (WPE) and wavelet packet sample entropy (WPSE), are introduced as the feature extraction methods. Then, the two extracted feature sets are compared based on this genetic algorithm. Another advanced method, known as the genetic algorithm-optimized back propagation neural network (GA-BPNN), is introduced for comparison to illustrate the superiority of the newly developed GA-SVM model. The result shows that the WPSE can extract more useful features than the WPE and that the GA-SVM is more effective and efficient than the GA-BPNN. The proposed approach could be retrained and extended to address other fault identification problems.