In order to extract the fault feature of the bearing effectively and prevent the impact components caused by bearing damage being interfered with by discrete frequency components and background noise,a method of fault...In order to extract the fault feature of the bearing effectively and prevent the impact components caused by bearing damage being interfered with by discrete frequency components and background noise,a method of fault feature extraction based on cepstrum pre-whitening(CPW)and a quantitative law of symplectic geometry mode decomposition(SGMD)is proposed.First,CPW is performed on the original signal to enhance the impact feature of bearing fault and remove the periodic frequency components from complex vibration signals.The pre-whitening signal contains only background noise and non-stationary shock caused by damage.Secondly,a quantitative law that the number of effective eigenvalues of the Hamilton matrix is twice the number of frequency components in the signal during SGMD is found,and the quantitative law is verified by simulation and theoretical derivation.Finally,the trajectory matrix of the pre-whitening signal is constructed and SGMD is performed.According to the quantitative law,the corresponding feature vector is selected to reconstruct the signal.The Hilbert envelope spectrum analysis is performed to extract fault features.Simulation analysis and application examples prove that the proposed method can clearly extract the fault feature of bearings.展开更多
Owing to the harsh conditions,wind turbine bearings are prone to faults,and the resulting fault information is easily submerged by strong noise disturbance,making conventional diagnosis challenging.Therefore,this stud...Owing to the harsh conditions,wind turbine bearings are prone to faults,and the resulting fault information is easily submerged by strong noise disturbance,making conventional diagnosis challenging.Therefore,this study presents an innovative bearing fault diagnosis approach predicated on Parameter⁃Optimized Symplectic Geometry Mode Decomposition(POSGMD)and Improved Convolutional Neural Network(ICNN).Firstly,assisted by the relative entropy⁃based adaptive selection of embedding dimension,a POSGMD is presented to adaptively decompose the collected bearing vibration signals into various Symplectic Geometry Components(SGC),which can solve the problem of manual selection of the embedding dimension in the raw Symplectic Geometry Mode Decomposition(SGMD).Meanwhile,the signal reconstruction on the decomposed SGC is conducted based on kurtosis⁃weighted principle to obtain the reconstructed signals.Subsequently,the Continuous Wavelet Transform(CWT)of the reconstructed signals is calculated to generate the corresponding time⁃frequency images as sample set.Finally,an ICNN is introduced for model training and automatic recognition of bearing faults.Two case studies are used to validate the presented methods efficacy.Comparing the presented method with traditional fault diagnosis methods,experimental results show that it can achieve greater identification accuracy and superior anti⁃noise resilience.This work provides a practical and effective solution for fault diagnosis in wind turbine bearings,contributing to the timely detection of faults and the reliable operation of wind turbines or other rotational machinery in industrial applications.展开更多
Incomplete fault signal characteristics and ease of noise contamination are issues with the current rolling bearing early fault diagnostic methods,making it challenging to ensure the fault diagnosis accuracy and relia...Incomplete fault signal characteristics and ease of noise contamination are issues with the current rolling bearing early fault diagnostic methods,making it challenging to ensure the fault diagnosis accuracy and reliability.A novel approach integrating enhanced Symplectic geometry mode decomposition with cosine difference limitation and calculus operator(ESGMD-CC)and artificial fish swarm algorithm(AFSA)optimized extreme learning machine(ELM)is proposed in this paper to enhance the extraction capability of fault features and thus improve the accuracy of fault diagnosis.Firstly,SGMD decomposes the raw vibration signal into multiple Symplectic geometry components(SGCs).Secondly,the iterations are reset by the cosine difference limitation to effectively separate the redundant components from the representative components.Additionally,the calculus operator is performed to strengthen weak fault features and make them easier to extract,and the singular value decomposition(SVD)weighted by power spectrum entropy(PSE)can be utilized as the sample feature representation.Finally,AFSA iteratively optimized ELM is adopted as the optimized classifier for fault identification.The superior performance of the proposed method has been validated by various experiments.展开更多
Understanding the effect of source-receiver geometry on sound propagation in surface ducts can improve the performance of near-surface sonar in deep water. The Lloyd-mirror and normal mode theories are used to analyze...Understanding the effect of source-receiver geometry on sound propagation in surface ducts can improve the performance of near-surface sonar in deep water. The Lloyd-mirror and normal mode theories are used to analyze the features of surface-duct propagation in this paper. Firstly, according to the Lloyd-mirror theory, a shallow point source generates directional lobes, whose grazing angles are determined by the source depth and frequency. By assuming a part of the first lobe to be just trapped in the surface duct, a method to calculate the minimum cutoff frequency （MCF） is obtained. The presented method is source depth dependent and thus is helpful for determining the working depth for sonar. Secondly, it is found that under certain environments there exists a layer of low transmission loss （TL） in the surface duct, whose thickness is related to the source geometry and can be calculated by the Lloyd-mirror method. The receiver should be placed in this layer to minimize the TL. Finally, the arrival angle on a vertical linear array （VLA） in the surface duct is analyzed based on normal mode theory, which provides a priori knowledge of the beam direction of passive sonar.展开更多
基金The National Natural Science Foundation of China(No.52075095).
文摘In order to extract the fault feature of the bearing effectively and prevent the impact components caused by bearing damage being interfered with by discrete frequency components and background noise,a method of fault feature extraction based on cepstrum pre-whitening(CPW)and a quantitative law of symplectic geometry mode decomposition(SGMD)is proposed.First,CPW is performed on the original signal to enhance the impact feature of bearing fault and remove the periodic frequency components from complex vibration signals.The pre-whitening signal contains only background noise and non-stationary shock caused by damage.Secondly,a quantitative law that the number of effective eigenvalues of the Hamilton matrix is twice the number of frequency components in the signal during SGMD is found,and the quantitative law is verified by simulation and theoretical derivation.Finally,the trajectory matrix of the pre-whitening signal is constructed and SGMD is performed.According to the quantitative law,the corresponding feature vector is selected to reconstruct the signal.The Hilbert envelope spectrum analysis is performed to extract fault features.Simulation analysis and application examples prove that the proposed method can clearly extract the fault feature of bearings.
基金Jiangsu Association for Science and Technology Youth Talent Support Project(Grant No.JSTJ-2024-031)National Natural Science Foundation of China(Grant No.52005265)Natural Science Fund for Colleges and Universities in Jiangsu Province(Grant No.20KJB460002)。
文摘Owing to the harsh conditions,wind turbine bearings are prone to faults,and the resulting fault information is easily submerged by strong noise disturbance,making conventional diagnosis challenging.Therefore,this study presents an innovative bearing fault diagnosis approach predicated on Parameter⁃Optimized Symplectic Geometry Mode Decomposition(POSGMD)and Improved Convolutional Neural Network(ICNN).Firstly,assisted by the relative entropy⁃based adaptive selection of embedding dimension,a POSGMD is presented to adaptively decompose the collected bearing vibration signals into various Symplectic Geometry Components(SGC),which can solve the problem of manual selection of the embedding dimension in the raw Symplectic Geometry Mode Decomposition(SGMD).Meanwhile,the signal reconstruction on the decomposed SGC is conducted based on kurtosis⁃weighted principle to obtain the reconstructed signals.Subsequently,the Continuous Wavelet Transform(CWT)of the reconstructed signals is calculated to generate the corresponding time⁃frequency images as sample set.Finally,an ICNN is introduced for model training and automatic recognition of bearing faults.Two case studies are used to validate the presented methods efficacy.Comparing the presented method with traditional fault diagnosis methods,experimental results show that it can achieve greater identification accuracy and superior anti⁃noise resilience.This work provides a practical and effective solution for fault diagnosis in wind turbine bearings,contributing to the timely detection of faults and the reliable operation of wind turbines or other rotational machinery in industrial applications.
基金supported by National Key Research and Development Project (2020YFE0204900)National Natural Science Foundation of China (Grant Numbers 62073193,61873333)Key Research and Development Plan of Shandong Province (Grant Numbers 2019TSLH0301,2021CXGC010204).
文摘Incomplete fault signal characteristics and ease of noise contamination are issues with the current rolling bearing early fault diagnostic methods,making it challenging to ensure the fault diagnosis accuracy and reliability.A novel approach integrating enhanced Symplectic geometry mode decomposition with cosine difference limitation and calculus operator(ESGMD-CC)and artificial fish swarm algorithm(AFSA)optimized extreme learning machine(ELM)is proposed in this paper to enhance the extraction capability of fault features and thus improve the accuracy of fault diagnosis.Firstly,SGMD decomposes the raw vibration signal into multiple Symplectic geometry components(SGCs).Secondly,the iterations are reset by the cosine difference limitation to effectively separate the redundant components from the representative components.Additionally,the calculus operator is performed to strengthen weak fault features and make them easier to extract,and the singular value decomposition(SVD)weighted by power spectrum entropy(PSE)can be utilized as the sample feature representation.Finally,AFSA iteratively optimized ELM is adopted as the optimized classifier for fault identification.The superior performance of the proposed method has been validated by various experiments.
基金Project supported by the National Natural Science Foundation of China(Grant No.11174235)the Science and Technology Development Project of Shaanxi Province,China(Grant No.2010KJXX-02)+1 种基金the Science and Technology Innovation Foundation of Northwestern Polytechnical University of Chinathe Doctorate Foundation of Northwestern Polytechnical University,China(Grant No.CX201226)
文摘Understanding the effect of source-receiver geometry on sound propagation in surface ducts can improve the performance of near-surface sonar in deep water. The Lloyd-mirror and normal mode theories are used to analyze the features of surface-duct propagation in this paper. Firstly, according to the Lloyd-mirror theory, a shallow point source generates directional lobes, whose grazing angles are determined by the source depth and frequency. By assuming a part of the first lobe to be just trapped in the surface duct, a method to calculate the minimum cutoff frequency （MCF） is obtained. The presented method is source depth dependent and thus is helpful for determining the working depth for sonar. Secondly, it is found that under certain environments there exists a layer of low transmission loss （TL） in the surface duct, whose thickness is related to the source geometry and can be calculated by the Lloyd-mirror method. The receiver should be placed in this layer to minimize the TL. Finally, the arrival angle on a vertical linear array （VLA） in the surface duct is analyzed based on normal mode theory, which provides a priori knowledge of the beam direction of passive sonar.
