The panel-type structures used in aerospace engineering can be subjected to severe highfrequency acoustic loadings in service. This paper evaluates the frequency-dependent random fatigue of panel-type structures made ...The panel-type structures used in aerospace engineering can be subjected to severe highfrequency acoustic loadings in service. This paper evaluates the frequency-dependent random fatigue of panel-type structures made of ceramic matrix composites（CMCs） under acoustic loadings. Firstly, the high-frequency random responses from the broadband random excitation will result in more stress cycles in a deinite period of time. The probability density distributions of stress amplitudes will be different in different frequency bandwidths, though the peak stress estimations are identical. Secondly, the fatigue properties of CMCs can be highly frequency-dependent. The fatigue evaluation method for the random vibration case is adopted to evaluate the fatigue damage of a representative stiffened panel structure. The frequency effect through S-N curves on random fatigue damage is numerically veriied. Finally, a parameter is demonstrated to characterize the mean vibration frequency of a random process, and hence this parameter can further be considered as a reasonable loading frequency in the fatigue tests of CMCs to obtain more reliable S-N curves.Therefore, the inluence of vibration frequency can be incorporated in the random fatigue model from the two perspectives.展开更多
Passive acoustic monitoring(PAM)technology is increasingly becoming one of the mainstream methods for bird monitoring.However,detecting bird audio within complex natural acoustic environments using PAM devices remains...Passive acoustic monitoring(PAM)technology is increasingly becoming one of the mainstream methods for bird monitoring.However,detecting bird audio within complex natural acoustic environments using PAM devices remains a significant challenge.To enhance the accuracy(ACC)of bird audio detection(BAD)and reduce both false negatives and false positives,this study proposes a BAD method based on a Dual-Feature Enhancement Fusion Model(DFEFM).This method incorporates per-channel energy normalization(PCEN)to suppress noise in the input audio and utilizes mel-frequency cepstral coefficients(MFCC)and frequency correlation matrices(FCM)as input features.It achieves deep feature-level fusion of MFCC and FCM on the channel dimension through two independent multi-layer convolutional network branches,and further integrates Spatial and Channel Synergistic Attention(SCSA)and Multi-Head Attention(MHA)modules to enhance the fusion effect of the aforementioned two deep features.Experimental results on the DCASE2018 BAD dataset show that our proposed method achieved an ACC of 91.4%and an AUC value of 0.963,with false negative and false positive rates of 11.36%and 7.40%,respectively,surpassing existing methods.The method also demonstrated detection ACC above 92%and AUC values above 0.987 on datasets from three sites of different natural scenes in Beijing.Testing on the NVIDIA Jetson Nano indicated that the method achieved an ACC of 89.48%when processing an average of 10 s of audio,with a response time of only 0.557 s,showing excellent processing efficiency.This study provides an effective method for filtering non-bird vocalization audio in bird vocalization monitoring devices,which helps to save edge storage and information transmission costs,and has significant application value for wild bird monitoring and ecological research.展开更多
基金supports from the National Natural Science Foundation of China (No. 11572086 , No. 11402052 )the New Century Excellent Talent in University (NCET-11-0086)+3 种基金the Natural Science Foundation of Jiangsu province (No. BK20140616 )the Fundamental Research Funds for the Central Universities and the Scientiic Research Innovation Program of Jiangsu Province College Postgraduates (KYLX_0093, KYLX15_0092)the China Scholarship Council ( 201506090047 )the Ministry of Education, Science and Technological Development of Republic of Serbia ( TR 35011 and ON 74001 )
文摘The panel-type structures used in aerospace engineering can be subjected to severe highfrequency acoustic loadings in service. This paper evaluates the frequency-dependent random fatigue of panel-type structures made of ceramic matrix composites（CMCs） under acoustic loadings. Firstly, the high-frequency random responses from the broadband random excitation will result in more stress cycles in a deinite period of time. The probability density distributions of stress amplitudes will be different in different frequency bandwidths, though the peak stress estimations are identical. Secondly, the fatigue properties of CMCs can be highly frequency-dependent. The fatigue evaluation method for the random vibration case is adopted to evaluate the fatigue damage of a representative stiffened panel structure. The frequency effect through S-N curves on random fatigue damage is numerically veriied. Finally, a parameter is demonstrated to characterize the mean vibration frequency of a random process, and hence this parameter can further be considered as a reasonable loading frequency in the fatigue tests of CMCs to obtain more reliable S-N curves.Therefore, the inluence of vibration frequency can be incorporated in the random fatigue model from the two perspectives.
基金supported by the Beijing Natural Science Foundation(5252014)the National Natural Science Foundation of China(62303063)。
文摘Passive acoustic monitoring(PAM)technology is increasingly becoming one of the mainstream methods for bird monitoring.However,detecting bird audio within complex natural acoustic environments using PAM devices remains a significant challenge.To enhance the accuracy(ACC)of bird audio detection(BAD)and reduce both false negatives and false positives,this study proposes a BAD method based on a Dual-Feature Enhancement Fusion Model(DFEFM).This method incorporates per-channel energy normalization(PCEN)to suppress noise in the input audio and utilizes mel-frequency cepstral coefficients(MFCC)and frequency correlation matrices(FCM)as input features.It achieves deep feature-level fusion of MFCC and FCM on the channel dimension through two independent multi-layer convolutional network branches,and further integrates Spatial and Channel Synergistic Attention(SCSA)and Multi-Head Attention(MHA)modules to enhance the fusion effect of the aforementioned two deep features.Experimental results on the DCASE2018 BAD dataset show that our proposed method achieved an ACC of 91.4%and an AUC value of 0.963,with false negative and false positive rates of 11.36%and 7.40%,respectively,surpassing existing methods.The method also demonstrated detection ACC above 92%and AUC values above 0.987 on datasets from three sites of different natural scenes in Beijing.Testing on the NVIDIA Jetson Nano indicated that the method achieved an ACC of 89.48%when processing an average of 10 s of audio,with a response time of only 0.557 s,showing excellent processing efficiency.This study provides an effective method for filtering non-bird vocalization audio in bird vocalization monitoring devices,which helps to save edge storage and information transmission costs,and has significant application value for wild bird monitoring and ecological research.
