Based on B-spline wavelet on the interval （BSWI）, two classes of truncated conical shell elements were constructed to solve axisymmetric problems, i.e. BSWI thin truncated conical shell element and BSWI moderately t...Based on B-spline wavelet on the interval （BSWI）, two classes of truncated conical shell elements were constructed to solve axisymmetric problems, i.e. BSWI thin truncated conical shell element and BSWI moderately thick truncated conical shell element with independent slopedeformation interpolation. In the construction of wavelet-based element, instead of traditional polynomial interpolation, the scaling functions of BSWI were employed to form the shape functions through the constructed elemental transformation matrix, and then construct BSWI element via the variational principle. Unlike the process of direct wavelets adding in the wavelet Galerkin method, the elemental displacement field represented by the coefficients of wavelets expansion was transformed into edges and internal modes via the constructed transformation matrix. BSWI element combines the accuracy of B-spline function approximation and various wavelet-based elements for structural analysis. Some static and dynamic numerical examples of conical shells were studied to demonstrate the present element with higher efficiency and precision than the traditional element.展开更多
Artificial intelligence(AI),which has recently gained popularity,is being extensively employed in modern fault diagnostic research to preserve the reliability and productivity of machines.The effectiveness of AI is in...Artificial intelligence(AI),which has recently gained popularity,is being extensively employed in modern fault diagnostic research to preserve the reliability and productivity of machines.The effectiveness of AI is influenced by the quality of the labeled training data.However,in engineering scenarios,available data on mechanical equipment are scarce,and collecting massive amounts of well-annotated fault data to train AI models is expensive and difficult.In response to the inadequacy of training samples,a numerical simulation-based partial transfer learning method for machinery fault diagnosis is proposed.First,a suitable simulation model of critical components in a mechanical system is developed using the finite element method(FEM),and numerical simulation is performed to acquire FEM simulation samples containing different fault types.Second,several synthetic simulation samples are generated to form complete source domain training samples using a generative adversarial network.Subsequently,the partial transfer learning network is trained to extract shared fault characteristics between the simulation and measured samples in the case of class imbalance.Finally,the resulting model is used to diagnose unknown samples from real-world mechanical systems in operation.The proposed method is tested on actual fault samples of bearings and gears obtained from a public dataset and experimental test rig available in our laboratory,achieving average classification accuracy of 99.54%and 99.64%,respectively.Comparison investigations reveal that the proposed method has superior classification and generalization ability when detecting faults in real mechanical systems.展开更多
The existing intelligent fault diagnosis techniques of bevel gear focus on single-sensor signal analysis under the steady operation condition.In this study,a new method is proposed based on ensemble deep transfer lear...The existing intelligent fault diagnosis techniques of bevel gear focus on single-sensor signal analysis under the steady operation condition.In this study,a new method is proposed based on ensemble deep transfer learning and multisensor signals to enhance the fault diagnosis adaptability and reliability of bevel gear under various operation conditions.First,a novel stacked autoencoder(NSAE)is constructed using a denoising autoencoder,batch normalization,and the Swish activation function.Second,a series of source-domain NSAEs with multisensor vibration signals is pretrained.Third,the good model parameters provided by the source-domain NSAEs are transferred to initialize the corresponding target-domain NSAEs.Finally,a modified voting fusion strategy is designed to obtain a comprehensive result.The multisensor signals collected under the different operation conditions of bevel gear are used to verify the proposed method.The comparison results show that the proposed method can diagnose different faults in an accurate and stable manner using only one target-domain sample,thereby outperforming the existing methods.展开更多
The method of constructing any scale wavelet finite element(WFE)based on the one-dimensional or two-dimensional Daubechies scaling functions was presented,and the corresponding WFE adaptive lifting algorithm was given...The method of constructing any scale wavelet finite element(WFE)based on the one-dimensional or two-dimensional Daubechies scaling functions was presented,and the corresponding WFE adaptive lifting algorithm was given.In order to obtain the nested increasing approximate subspaces of multiscale finite element,the Daubechies scaling functions with the properties of multi-resolution analysis were employed as the finite ele-ment interpolating functions.Thus,the WFE could adaptively mesh the singularity domain caused by local cracks,which resulted in better approximate solutions than the traditional finite element methods.The calculations of natural frequencies of cracked beam were used to check the accuracy of given methods.In addition,the results of cracked cantilever beam and engineering application were satisfied.So,the current methods can provide effective tools in the numerical modeling of the fault prognosis of incipient crack.展开更多
A hybrid method is proposed to properly identify multiple damages for plate structures in this work. In the stage of damage localization, singular value decomposition （SVD） is applied to reveal singularities in moda...A hybrid method is proposed to properly identify multiple damages for plate structures in this work. In the stage of damage localization, singular value decomposition （SVD） is applied to reveal singularities in modal shapes, and hence to detect the damage locations. In the stage of damage quantification, based on the detected location information ant colony optimization （ACO） algorithm is introduced to estimate damage severity by searching for damage evaluation database, which reveals the relationship between the natural frequencies and the damage severity. The modal shapes and the natural frequencies required in damage localization and quantification are obtained via the wavelet finite element method. The numerical simulation and experimental investigation are carried out to test the performance of the hybrid method for free aluminum plates with multiple damages. And the results indicate that the proposed method is effective to identify multiple damages of plate structures with reasonable precision.展开更多
基金Project supported by the National Natural Science Foundation of China (Nos. 50335030, 50505033 and 50575171)National Basic Research Program of China (No. 2005CB724106)Doctoral Program Foundation of University of China(No. 20040698026)
文摘Based on B-spline wavelet on the interval （BSWI）, two classes of truncated conical shell elements were constructed to solve axisymmetric problems, i.e. BSWI thin truncated conical shell element and BSWI moderately thick truncated conical shell element with independent slopedeformation interpolation. In the construction of wavelet-based element, instead of traditional polynomial interpolation, the scaling functions of BSWI were employed to form the shape functions through the constructed elemental transformation matrix, and then construct BSWI element via the variational principle. Unlike the process of direct wavelets adding in the wavelet Galerkin method, the elemental displacement field represented by the coefficients of wavelets expansion was transformed into edges and internal modes via the constructed transformation matrix. BSWI element combines the accuracy of B-spline function approximation and various wavelet-based elements for structural analysis. Some static and dynamic numerical examples of conical shells were studied to demonstrate the present element with higher efficiency and precision than the traditional element.
基金supported by the National Natural Science Foundation of China (Grant No.U1909217)the Zhejiang Natural Science Foundation of China (Grant No.LD21E050001)the Wenzhou Major Science and Technology Innovation Project of China (Grant No.ZG2020051)。
文摘Artificial intelligence(AI),which has recently gained popularity,is being extensively employed in modern fault diagnostic research to preserve the reliability and productivity of machines.The effectiveness of AI is influenced by the quality of the labeled training data.However,in engineering scenarios,available data on mechanical equipment are scarce,and collecting massive amounts of well-annotated fault data to train AI models is expensive and difficult.In response to the inadequacy of training samples,a numerical simulation-based partial transfer learning method for machinery fault diagnosis is proposed.First,a suitable simulation model of critical components in a mechanical system is developed using the finite element method(FEM),and numerical simulation is performed to acquire FEM simulation samples containing different fault types.Second,several synthetic simulation samples are generated to form complete source domain training samples using a generative adversarial network.Subsequently,the partial transfer learning network is trained to extract shared fault characteristics between the simulation and measured samples in the case of class imbalance.Finally,the resulting model is used to diagnose unknown samples from real-world mechanical systems in operation.The proposed method is tested on actual fault samples of bearings and gears obtained from a public dataset and experimental test rig available in our laboratory,achieving average classification accuracy of 99.54%and 99.64%,respectively.Comparison investigations reveal that the proposed method has superior classification and generalization ability when detecting faults in real mechanical systems.
基金the National Natural Science Foundation of China(Grant No.51905160)the Natural Science Foundation of Hunan Province(Grant No.2020JJ5072)the Fundamental Research Funds for the Central Universities(Grant No.531118010335)。
文摘The existing intelligent fault diagnosis techniques of bevel gear focus on single-sensor signal analysis under the steady operation condition.In this study,a new method is proposed based on ensemble deep transfer learning and multisensor signals to enhance the fault diagnosis adaptability and reliability of bevel gear under various operation conditions.First,a novel stacked autoencoder(NSAE)is constructed using a denoising autoencoder,batch normalization,and the Swish activation function.Second,a series of source-domain NSAEs with multisensor vibration signals is pretrained.Third,the good model parameters provided by the source-domain NSAEs are transferred to initialize the corresponding target-domain NSAEs.Finally,a modified voting fusion strategy is designed to obtain a comprehensive result.The multisensor signals collected under the different operation conditions of bevel gear are used to verify the proposed method.The comparison results show that the proposed method can diagnose different faults in an accurate and stable manner using only one target-domain sample,thereby outperforming the existing methods.
基金This work was supported by the National Basic Research Program of China(Grant No.2005CB724100)the National Natural Science Foundation of China(Grant Nos.50335030,50505033 and 50575171)the Doctor Program Foundation of University of China(Grant No.20040698026).
文摘The method of constructing any scale wavelet finite element(WFE)based on the one-dimensional or two-dimensional Daubechies scaling functions was presented,and the corresponding WFE adaptive lifting algorithm was given.In order to obtain the nested increasing approximate subspaces of multiscale finite element,the Daubechies scaling functions with the properties of multi-resolution analysis were employed as the finite ele-ment interpolating functions.Thus,the WFE could adaptively mesh the singularity domain caused by local cracks,which resulted in better approximate solutions than the traditional finite element methods.The calculations of natural frequencies of cracked beam were used to check the accuracy of given methods.In addition,the results of cracked cantilever beam and engineering application were satisfied.So,the current methods can provide effective tools in the numerical modeling of the fault prognosis of incipient crack.
基金supported by the National Natural Science Foundation of China(Grant No.51475356)the National Key Basic Research Program of China(Grant No.2015CB057400)the Wenzhou Technologies R&D Program of China(Grant No.G20140047)
文摘A hybrid method is proposed to properly identify multiple damages for plate structures in this work. In the stage of damage localization, singular value decomposition （SVD） is applied to reveal singularities in modal shapes, and hence to detect the damage locations. In the stage of damage quantification, based on the detected location information ant colony optimization （ACO） algorithm is introduced to estimate damage severity by searching for damage evaluation database, which reveals the relationship between the natural frequencies and the damage severity. The modal shapes and the natural frequencies required in damage localization and quantification are obtained via the wavelet finite element method. The numerical simulation and experimental investigation are carried out to test the performance of the hybrid method for free aluminum plates with multiple damages. And the results indicate that the proposed method is effective to identify multiple damages of plate structures with reasonable precision.
