Amidst the swift advancement of new power systems and electric vehicles,inverter-fed machines have progressively materialized as a pivotal apparatus for efficient energy conversion.Stator winding turn insulation failu...Amidst the swift advancement of new power systems and electric vehicles,inverter-fed machines have progressively materialized as a pivotal apparatus for efficient energy conversion.Stator winding turn insulation failure is the root cause of inverter-fed machine breakdown.The online monitoring of turn insulation health can detect potential safety risks promptly,but faces the challenge of weak characteristics of turn insulation degradation.This study proposes an innovative method to evaluate the turn insulation state of inverter-fed machines by utilizing the fractional Fourier transform with a Mel filter(FrFT-Mel).First,the sensitivity of the high-frequency(HF)switching oscillation current to variations in turn insulation was analyzed within the fractional domain.Subsequently,an improved Mel filter is introduced,and its structure and parameters are specifically designed based on the features intrinsic to the common-mode impedance resonance point of the electrical machine.Finally,an evaluation index was proposed for the turn insulation state of inverter-fed machines.Experimental results on a 3kW permanent magnet synchronous machine(PMSM)demonstrate that the proposed FrFT-Mel method significantly enhances the sensitivity of turn insulation state perception by approximately five times,compared to the traditional Fourier transform method.展开更多
In this study,we developed a hollow aerogel fiber out of reduced graphene oxide(rGO),with a hierarchically ordered microstructure through a three-dimensional coaxial printing methodology,that enabled a physicochemical...In this study,we developed a hollow aerogel fiber out of reduced graphene oxide(rGO),with a hierarchically ordered microstructure through a three-dimensional coaxial printing methodology,that enabled a physicochemically cooperative construction process at multiscale.The rGO hollow aerogel fiber was modified by depositing polycaprolactone(PCL)and melatonin(Mel).Attributable to its elaborately designed hierarchical structure and arched alignment of two-dimensional micro-sheets,the rGO/PCL/Mel hybrid aerogel bio-fiber demonstrated remarkable structural robustness in maintaining ordered pathways and high porosity(98.5%±0.24%),which facilitated nerve growth in a complex survival environment in vivo.Furthermore,the excellent combination of properties such as electrical conductivity,biocompatibility,and mechanical properties(elastic modulus:7.06±0.81 MPa to 26.58±4.99 MPa)led to highly efficient regeneration of well-ordered PN tissue.Systematic evaluations of nerve regeneration and muscle function recovery in a Sprague–Dawley rat model with a long nerve defect(15 mm)validated the virtually identical performance of the rGO/PCL/Mel fiber compared to autogenous nerve graft.This study suggests a promising approach to the clinical repair of long PN defects through the combined regulation of rational multiscale structure design and indispensable chemical modification of rGO aerogel-based functional nerve regeneration fibers.展开更多
This article presents an exhaustive comparative investigation into the accuracy of gender identification across diverse geographical regions,employing a deep learning classification algorithm for speech signal analysi...This article presents an exhaustive comparative investigation into the accuracy of gender identification across diverse geographical regions,employing a deep learning classification algorithm for speech signal analysis.In this study,speech samples are categorized for both training and testing purposes based on their geographical origin.Category 1 comprises speech samples from speakers outside of India,whereas Category 2 comprises live-recorded speech samples from Indian speakers.Testing speech samples are likewise classified into four distinct sets,taking into consideration both geographical origin and the language spoken by the speakers.Significantly,the results indicate a noticeable difference in gender identification accuracy among speakers from different geographical areas.Indian speakers,utilizing 52 Hindi and 26 English phonemes in their speech,demonstrate a notably higher gender identification accuracy of 85.75%compared to those speakers who predominantly use 26 English phonemes in their conversations when the system is trained using speech samples from Indian speakers.The gender identification accuracy of the proposed model reaches 83.20%when the system is trained using speech samples from speakers outside of India.In the analysis of speech signals,Mel Frequency Cepstral Coefficients(MFCCs)serve as relevant features for the speech data.The deep learning classification algorithm utilized in this research is based on a Bidirectional Long Short-Term Memory(BiLSTM)architecture within a Recurrent Neural Network(RNN)model.展开更多
Purpose–The safe operation of the metro power transformer directly relates to the safety and efficiency of the entire metro system.Through voiceprint technology,the sounds emitted by the transformer can be monitored ...Purpose–The safe operation of the metro power transformer directly relates to the safety and efficiency of the entire metro system.Through voiceprint technology,the sounds emitted by the transformer can be monitored in real-time,thereby achieving real-time monitoring of the transformer’s operational status.However,the environment surrounding power transformers is filled with various interfering sounds that intertwine with both the normal operational voiceprints and faulty voiceprints of the transformer,severely impacting the accuracy and reliability of voiceprint identification.Therefore,effective preprocessing steps are required to identify and separate the sound signals of transformer operation,which is a prerequisite for subsequent analysis.Design/methodology/approach–This paper proposes an Adaptive Threshold Repeating Pattern Extraction Technique(REPET)algorithm to separate and denoise the transformer operation sound signals.By analyzing the Short-Time Fourier Transform(STFT)amplitude spectrum,the algorithm identifies and utilizes the repeating periodic structures within the signal to automatically adjust the threshold,effectively distinguishing and extracting stable background signals from transient foreground events.The REPET algorithm first calculates the autocorrelation matrix of the signal to determine the repeating period,then constructs a repeating segment model.Through comparison with the amplitude spectrum of the original signal,repeating patterns are extracted and a soft time-frequency mask is generated.Findings–After adaptive thresholding processing,the target signal is separated.Experiments conducted on mixed sounds to separate background sounds from foreground sounds using this algorithm and comparing the results with those obtained using the FastICA algorithm demonstrate that the Adaptive Threshold REPET method achieves good separation effects.Originality/value–A REPET method with adaptive threshold is proposed,which adopts the dynamic threshold adjustment mechanism,adaptively calculates the threshold for blind source separation and improves the adaptability and robustness of the algorithm to the statistical characteristics of the signal.It also lays the foundation for transformer fault detection based on acoustic fingerprinting.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 51907116in part sponsored by Natural Science Foundation of Shanghai 22ZR1425400sponsored by Shanghai Rising-Star Program 23QA1404000.
文摘Amidst the swift advancement of new power systems and electric vehicles,inverter-fed machines have progressively materialized as a pivotal apparatus for efficient energy conversion.Stator winding turn insulation failure is the root cause of inverter-fed machine breakdown.The online monitoring of turn insulation health can detect potential safety risks promptly,but faces the challenge of weak characteristics of turn insulation degradation.This study proposes an innovative method to evaluate the turn insulation state of inverter-fed machines by utilizing the fractional Fourier transform with a Mel filter(FrFT-Mel).First,the sensitivity of the high-frequency(HF)switching oscillation current to variations in turn insulation was analyzed within the fractional domain.Subsequently,an improved Mel filter is introduced,and its structure and parameters are specifically designed based on the features intrinsic to the common-mode impedance resonance point of the electrical machine.Finally,an evaluation index was proposed for the turn insulation state of inverter-fed machines.Experimental results on a 3kW permanent magnet synchronous machine(PMSM)demonstrate that the proposed FrFT-Mel method significantly enhances the sensitivity of turn insulation state perception by approximately five times,compared to the traditional Fourier transform method.
基金supported by the National Science Fund for Distinguished Young Scholars(No.11925204)the Fundamental Research Funds for Central Universities(Nos.lzujbky-2022-ey02,lzujbky-2023-eyt03)+5 种基金the Science and Technology Program of Gansu(NO.23ZDKA0001)the Fok Ying-Tong Education Foundation for Young Teachers in the Higher Education Institutions of China(No.171107)the National Natural Science Foundation of China(No.82202718)Beijing Natural Science Foundation(No.L212050)the Military Medical Science and Technology Youth Development Program(No.21QNPY112)the China Postdoctoral Science Foundation(No.2019M664007 and 2021T140793).
文摘In this study,we developed a hollow aerogel fiber out of reduced graphene oxide(rGO),with a hierarchically ordered microstructure through a three-dimensional coaxial printing methodology,that enabled a physicochemically cooperative construction process at multiscale.The rGO hollow aerogel fiber was modified by depositing polycaprolactone(PCL)and melatonin(Mel).Attributable to its elaborately designed hierarchical structure and arched alignment of two-dimensional micro-sheets,the rGO/PCL/Mel hybrid aerogel bio-fiber demonstrated remarkable structural robustness in maintaining ordered pathways and high porosity(98.5%±0.24%),which facilitated nerve growth in a complex survival environment in vivo.Furthermore,the excellent combination of properties such as electrical conductivity,biocompatibility,and mechanical properties(elastic modulus:7.06±0.81 MPa to 26.58±4.99 MPa)led to highly efficient regeneration of well-ordered PN tissue.Systematic evaluations of nerve regeneration and muscle function recovery in a Sprague–Dawley rat model with a long nerve defect(15 mm)validated the virtually identical performance of the rGO/PCL/Mel fiber compared to autogenous nerve graft.This study suggests a promising approach to the clinical repair of long PN defects through the combined regulation of rational multiscale structure design and indispensable chemical modification of rGO aerogel-based functional nerve regeneration fibers.
文摘This article presents an exhaustive comparative investigation into the accuracy of gender identification across diverse geographical regions,employing a deep learning classification algorithm for speech signal analysis.In this study,speech samples are categorized for both training and testing purposes based on their geographical origin.Category 1 comprises speech samples from speakers outside of India,whereas Category 2 comprises live-recorded speech samples from Indian speakers.Testing speech samples are likewise classified into four distinct sets,taking into consideration both geographical origin and the language spoken by the speakers.Significantly,the results indicate a noticeable difference in gender identification accuracy among speakers from different geographical areas.Indian speakers,utilizing 52 Hindi and 26 English phonemes in their speech,demonstrate a notably higher gender identification accuracy of 85.75%compared to those speakers who predominantly use 26 English phonemes in their conversations when the system is trained using speech samples from Indian speakers.The gender identification accuracy of the proposed model reaches 83.20%when the system is trained using speech samples from speakers outside of India.In the analysis of speech signals,Mel Frequency Cepstral Coefficients(MFCCs)serve as relevant features for the speech data.The deep learning classification algorithm utilized in this research is based on a Bidirectional Long Short-Term Memory(BiLSTM)architecture within a Recurrent Neural Network(RNN)model.
基金the China Academy of Railway Sciences Corporation Limited(2023YJ257).
文摘Purpose–The safe operation of the metro power transformer directly relates to the safety and efficiency of the entire metro system.Through voiceprint technology,the sounds emitted by the transformer can be monitored in real-time,thereby achieving real-time monitoring of the transformer’s operational status.However,the environment surrounding power transformers is filled with various interfering sounds that intertwine with both the normal operational voiceprints and faulty voiceprints of the transformer,severely impacting the accuracy and reliability of voiceprint identification.Therefore,effective preprocessing steps are required to identify and separate the sound signals of transformer operation,which is a prerequisite for subsequent analysis.Design/methodology/approach–This paper proposes an Adaptive Threshold Repeating Pattern Extraction Technique(REPET)algorithm to separate and denoise the transformer operation sound signals.By analyzing the Short-Time Fourier Transform(STFT)amplitude spectrum,the algorithm identifies and utilizes the repeating periodic structures within the signal to automatically adjust the threshold,effectively distinguishing and extracting stable background signals from transient foreground events.The REPET algorithm first calculates the autocorrelation matrix of the signal to determine the repeating period,then constructs a repeating segment model.Through comparison with the amplitude spectrum of the original signal,repeating patterns are extracted and a soft time-frequency mask is generated.Findings–After adaptive thresholding processing,the target signal is separated.Experiments conducted on mixed sounds to separate background sounds from foreground sounds using this algorithm and comparing the results with those obtained using the FastICA algorithm demonstrate that the Adaptive Threshold REPET method achieves good separation effects.Originality/value–A REPET method with adaptive threshold is proposed,which adopts the dynamic threshold adjustment mechanism,adaptively calculates the threshold for blind source separation and improves the adaptability and robustness of the algorithm to the statistical characteristics of the signal.It also lays the foundation for transformer fault detection based on acoustic fingerprinting.
