Sound quality evaluation of electronic expansion valve using Gaussian restricted Boltzmann machines based DBN

Abstract

The operational noise of electronic expansion valve (EEV) is the main component of noise source for the indoor unit of the air conditioner. The sound quality of EEV noise directly influences the consumer’s perceptions. Based on deep belief network (DBN) technique, an objective model has been conducted to evaluate the sound quality of EEV. Gaussian Restricted Boltzmann Machines (GRBM) provides the capability of modeling continuous data and has been used to develop a DBN model in this paper. The interior noise of 46 EEVs under working conditions were measured and corresponding subjective evaluation were implemented. A linear regression-based DBN (LR-DBN) is proposed with 6 psychoacoustic metrics and 26 Mel-frequency cepstral coefficients (MFCC) as input features. The performance of LR-DBN was validated against an ordinary DBN, a multiple linear regression (MLR) and a back-propagation neural network (BPNN). The results show that the LR-DBN has higher correlation coefficient and lower prediction error with human perception compared to the other considered methods. In addition, LR-DBN shows better stability than the other models. This present method may be a reliable approach for evaluating EEV sound.