毕凤荣¹, 李琳², 张剑¹, 马腾¹
AuthorsHTML:毕凤荣¹, 李琳², 张剑¹, 马腾¹
AuthorsListE:Bi Fengrong¹, Li Lin², Zhang Jian¹, Ma Teng¹
AuthorsHTMLE:Bi Fengrong¹, Li Lin², Zhang Jian¹, Ma Teng¹
Unit:1. 天津大学内燃机燃烧学国家重点实验室，天津 300072；2. 天津大学机械工程学院，天津 300072
Unit_EngLish:1．State Key Laboratory of Engines, Tianjin University, Tianjin 300072, China
2．School of Mechanical Engineering, Tianjin University, Tianjin 300072, China
Abstract_Chinese:为了预测柴油机辐射噪声品质, 采用基于集总经验模态分解(EEMD)、希尔伯特变换(HT)与最小二乘支持向量机(LSSVM)相结合的柴油机辐射噪声品质预测方法．该方法先采集柴油机辐射噪声信号, 进行滤波和EEMD, 再用HT得到相应的特征模态函数(IMF)分量的瞬时频率并对其进行临界频率带计权, 最后计算其能量得到声音信号特征作为输入; 用等级评分法对柴油机辐射噪声进行主观评价试验, 把主观评价值作为输出; 利用LSSVM训练得到预测模型．同时, 以心理声学客观参数作为LSSVM的输入, 建立另一个预测模型．分别用两个预测模型进行预测, 结果表明基于EEMD-HT与LSSVM的柴油机辐射噪声品质预测模型具有更高的声品质预测精度, 即更加接近人的主观感受．
Abstract_English:In order to predict the diesel engine radiated noise quality，a sound quality prediction method for diesel engine radiated noise is proposed in this paper based on the combination of ensemble empirical mode decomposition(EEMD)，Hilbert transform(HT)and the least squares support vector machine(LSSVM). At first，the sound signals of diesel engine were sampled，filtered，decomposed by EEMD and transformed by HT; Then the corresponding intrinsic mode function(IMF)components were weighted by critical frequency band with the instantaneous frequency，their energies were calculated as the features of sound signals; What is more，a subjective evaluation test on the diesel engine radiated sound quality of sample engines was conducted using level score method; Finally，by using LSSVM for training with the features of sound signals as input and the subjective evaluation values as output，a sound quality prediction model for diesel engine radiated noise was obtained. Meanwhile another prediction model for sound quality based psychology parameters was also built with psychology parameters as LSSVM input. The results of predictions on the diesel engine radiated noise with two models respectively show that compared with psychology parameters-based model，the model put forward in this paper get a higher accuracy，meaning it has much closer to subject feeling of people.
Keyword_Chinese:辐射噪声; 声品质; 集总经验模态分解; 希尔伯特变换; 最小二乘支持向量机; 预测模型
Keywords_English:radiated noise; sound quality; ensemble empirical mode decomposition; Hilbert transform; least squares support vector machine; prediction model

PDF全文下载地址:http://xbzrb.tju.edu.cn/#/digest?ArticleID=5761