期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到3篇文章
< 1 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Phased microphone array for sound source localization with deep learning 认领 引用 被引量：6
1
作者 Wei Ma Xun Liu 《Aerospace Systems》 2019年第2期71-81,共11页
To phased microphone array for sound source localization,algorithm with both high computational efficiency and high precision is a persistent pursuit until now.In this paper,convolutional neural network(CNN)a kind of ... To phased microphone array for sound source localization,algorithm with both high computational efficiency and high precision is a persistent pursuit until now.In this paper,convolutional neural network(CNN)a kind of deep learning is preliminarily applied as a new algorithm.The input of CNN is only cross-spectral matrix,while the output of CNN is source distribution.With regard to computing speed in applications,CNN once trained is as fast as conventional beamforming,and is significantly faster than the most famous deconvolution algorithm DAMAS.With regard to measurement accuracy in applications,at high frequency,CNN can reconstruct the sound localizations with up to 100%test accuracy,although sidelobes may appear in some situations.In addition,CNN has a spatial resolution nearly as that of DAMAS and better than that of the conventional beamforming.CNN test accuracy decreases with frequency decreasing;however,in most incorrect samples,CNN results are not far away from the correct results.This exciting result means that CNN perfectly finds source distribution directly from cross-spectral matrix without given propagation function and microphone positions in advance,and thus,CNN deserves to be further explored as a new algorithm. 展开更多
关键词 Microphone arrays Beamforming Deep learning CNN
Fault diagnosis of aeroengine fan based on generative adversarial network and acoustic features 认领 引用 被引量：3
2
作者 Haoyuan Dong Liu Xun Wei Ma 《Aerospace Systems》 2022年第4期567-575,共9页
Aeroengine fan is an important component of aeroengine,and its reliability is very important for aircraft.Therefore,the fault diagnosis and fault analysis of aeroengine fan are of great significance to aircraft safety... Aeroengine fan is an important component of aeroengine,and its reliability is very important for aircraft.Therefore,the fault diagnosis and fault analysis of aeroengine fan are of great significance to aircraft safety.This paper proposes a fault diagnosis method of aeroengine fan based on generative adversarial network and acoustic features.First,referring to Mel frequency cepstral coefficients,the features of the collected original signal are extracted,and the first-order and second-order difference parameters to form a three-dimensional feature vector are also extracted.Then,the neural network model is used to build generator and discriminator,and the training is carried out through a generative adversarial network model.Finally,the public rotating machinery data set is used to construct training set and test set to verify the recognition effect of the model.Compared with the recognition results of the model using the same neural network architecture and the same data set,it is verified that the model has different degrees of improvement in terms of training efficiency,robustness and accuracy.Using data sequences at different speeds,it is verified that the model is stable in various states of aeroengine. 展开更多
关键词 Aeroengine fan Generative adversarial network Fault diagnosis Feature extraction
Analysis of error induced by the Doppler effect in the ROSI beamforming for rotating sound source identification 认领 引用
3
作者 Yuxi Wang Ce Zhang +1 位作者 Xun Liu Wei Ma 《Aerospace Systems》 2022年第2期323-330,共8页
Identifications of rotating sound sources are of interest in many industrial applications.Nowadays,ROSI is still the unique widely recognized beamforming for arraywith arbitrarymicrophone configuration to identify rot... Identifications of rotating sound sources are of interest in many industrial applications.Nowadays,ROSI is still the unique widely recognized beamforming for arraywith arbitrarymicrophone configuration to identify rotating sound source.Recently,there are some researchers found that ROSI cannot completely compensate the Doppler effect.Ghost contribution in ROSI will be induced at other grids at side band frequencies to the fundamental frequency with a modulation frequency equal to the rotation speed.However,there is no article to investigate how much the error induced by the Doppler effect in the ROSI beamforming is.This paper is devoted to analyze this error of ROSI beamforming at side band frequencies due to the Doppler effect.As the order of frequency shift increases,the error of ROSI beamforming decreases.This error cannot be neglected when we use ROSI beamforming for rotating sound source identification and it can be compensated as much as possible by constructing a suitable microphone array in the future research. 展开更多
关键词 Microphone arrays Beamforming ROSI Doppler effect
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈