The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR...The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR） approach is developed for the quality prediction of nonlinear and multiphase batch processes. After the collected data is preprocessed through batchwise unfolding, the hidden Markov model （HMM） is applied to identify different operation phases. A GLDA algorithm is also presented to extract the appropriate process variables highly correlated with the quality variables, decreasing the complexity of modeling. Besides, the multiple local GPR models are built in the reduced- dimensional space for all the identified operation phases. Furthermore, the HMM-based state estimation is used to classify each measurement sample of a test batch into a corresponding phase with the maximal likelihood estimation. Therefore, the local GPR model with respect to specific phase is selected for online prediction. The effectiveness of the proposed prediction approach is demonstrated through the multiphase penicillin fermentation process. The comparison results show that the proposed GLDA-GPR approach is superior to the regular GPR model and the GPR based on HMM （HMM-GPR） model.展开更多
Efficient bolted joint design is an essential part of designing the minimum weight aerospace structures, since structural failures usually occur at connections and interface. A comprehensive numerical study of three-d...Efficient bolted joint design is an essential part of designing the minimum weight aerospace structures, since structural failures usually occur at connections and interface. A comprehensive numerical study of three-dimensional(3D) stress variations is prohibitively expensive for a large-scale structure where hundreds of bolts can be present. In this work, the hybrid composite-to-metal bolted connections used in the upper stage of European Ariane 5ME rocket are analyzed using the global-local finite element(FE) approach which involves an approximate analysis of the whole structure followed by a detailed analysis of a significantly smaller region of interest. We calculate the Tsai-Wu failure index and the margin of safety using the stresses obtained from ABAQUS. We find that the composite part of a hybrid bolted connection is prone to failure compared to the metal part. We determine the bolt preload based on the clamp-up load calculated using a maximum preload to make the composite part safe. We conclude that the unsuitable bolt preload may cause the failure of the composite part due to the high stress concentration in the vicinity of the bolt. The global-local analysis provides an efficient computational tool for enhancing 3D stress analysis in the highly loaded region.展开更多
A continuous wavelet transform(CWT)and globallocal feature(GLF)extraction-based signal classificationalgorithm is proposed to improve the signal classification accuracy.First,the CWT is utilized to generate the timefr...A continuous wavelet transform(CWT)and globallocal feature(GLF)extraction-based signal classificationalgorithm is proposed to improve the signal classification accuracy.First,the CWT is utilized to generate the timefrequency scalogram.Then,the GLF extraction method is proposed to extract features from the time-frequency scalogram.Finally,a classification method based on the support vector machine(SVM)is proposed to classify the extracted features.Experimental results show that the extended binary phase shift keying(EBPSK)bit error rate(BER)of the proposed classification algorithm is1.3x10_5under the environment of additional white Gaussian noise with the signal-to-noise ratio of-3dB,which is24times lower than that of the SVM-based signal classification method.Meanwhile,the BER using the GLF extraction method is13times lower than the one using the global feature extraction method and24times lower than the one using the local feature extraction method.展开更多
A global-local finite element modeling technique is employed in this paper to predict the separation in steel cord-rubber composite materials of radial truck tires. The local model uses a finite element analysis in co...A global-local finite element modeling technique is employed in this paper to predict the separation in steel cord-rubber composite materials of radial truck tires. The local model uses a finite element analysis in conjunction with a glob-al-local technique in ABAQUS. A 3-dimensional finite element local model calculates the maximum cyclic shear strain of an interface between steel cord and rubber materials at the carcass ply shoulder region. It is found that the maximum cyclic shear strain is reliable as a result of the analysis of carcass ply separation in radial truck tires. Using the analysis of the local model, a study of the cyclic shear strain is performed in the shoulder region and used to deter-mine the carcass ply separation. The effect of the change of carcass ply design on the separation in steel cord-rubber composite materials of radial truck tires is discussed.展开更多
The stress distribution surrounding the fastener hole in thick laminate mechanical joints is complex. It is time-consuming to analyze the distribution using finite element method. To accurately and efficiently obtain ...The stress distribution surrounding the fastener hole in thick laminate mechanical joints is complex. It is time-consuming to analyze the distribution using finite element method. To accurately and efficiently obtain the stress state around the fastener hole in multi-bolt thick laminate joints, a global-local approach is introduced. In the method, the most seriously damaged zone is 3D modeled by taking the displacement field got from the 2D global model as boundary conditions. Through comparison and analysis there are the following findings: the global-local finite element method is a reliable and efficient way to solve the stress distribution problem; the stress distribution around the fastener hole is quite uneven in through-the-thickness direction, and the stresses of the elements close to the shearing plane are much higher than the stresses of the elements far away from the shearing plane; the out-of-plane stresses introduced by the single-lap joint cannot be ignored due to the delamination failure; the stress state is a useful criterion for further more complex studies involving failure analysis.展开更多
Objective: A global-local processing task was adapted to be used in an event- related potential paradigm in order to examine the effects of positive emotion on
In recent years,semantic segmentation on 3D point cloud data has attracted much attention.Unlike 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and...In recent years,semantic segmentation on 3D point cloud data has attracted much attention.Unlike 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and inherently sparse.Therefore,it is very difficult to extract long-range contexts and effectively aggregate local features for semantic segmentation in 3D point cloud space.Most current methods either focus on local feature aggregation or long-range context dependency,but fail to directly establish a global-local feature extractor to complete the point cloud semantic segmentation tasks.In this paper,we propose a Transformer-based stratified graph convolutional network(SGT-Net),which enlarges the effective receptive field and builds direct long-range dependency.Specifically,we first propose a novel dense-sparse sampling strategy that provides dense local vertices and sparse long-distance vertices for subsequent graph convolutional network(GCN).Secondly,we propose a multi-key self-attention mechanism based on the Transformer to further weight augmentation for crucial neighboring relationships and enlarge the effective receptive field.In addition,to further improve the efficiency of the network,we propose a similarity measurement module to determine whether the neighborhood near the center point is effective.We demonstrate the validity and superiority of our method on the S3DIS and ShapeNet datasets.Through ablation experiments and segmentation visualization,we verify that the SGT model can improve the performance of the point cloud semantic segmentation.展开更多
基金The Fundamental Research Funds for the Central Universities(No.JUDCF12027,JUSRP51323B)the Scientific Innovation Research of College Graduates in Jiangsu Province(No.CXLX12_0734)
文摘The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR） approach is developed for the quality prediction of nonlinear and multiphase batch processes. After the collected data is preprocessed through batchwise unfolding, the hidden Markov model （HMM） is applied to identify different operation phases. A GLDA algorithm is also presented to extract the appropriate process variables highly correlated with the quality variables, decreasing the complexity of modeling. Besides, the multiple local GPR models are built in the reduced- dimensional space for all the identified operation phases. Furthermore, the HMM-based state estimation is used to classify each measurement sample of a test batch into a corresponding phase with the maximal likelihood estimation. Therefore, the local GPR model with respect to specific phase is selected for online prediction. The effectiveness of the proposed prediction approach is demonstrated through the multiphase penicillin fermentation process. The comparison results show that the proposed GLDA-GPR approach is superior to the regular GPR model and the GPR based on HMM （HMM-GPR） model.
基金Project(282522)supported by the European Union's Research and Innovation Funding Programme
文摘Efficient bolted joint design is an essential part of designing the minimum weight aerospace structures, since structural failures usually occur at connections and interface. A comprehensive numerical study of three-dimensional(3D) stress variations is prohibitively expensive for a large-scale structure where hundreds of bolts can be present. In this work, the hybrid composite-to-metal bolted connections used in the upper stage of European Ariane 5ME rocket are analyzed using the global-local finite element(FE) approach which involves an approximate analysis of the whole structure followed by a detailed analysis of a significantly smaller region of interest. We calculate the Tsai-Wu failure index and the margin of safety using the stresses obtained from ABAQUS. We find that the composite part of a hybrid bolted connection is prone to failure compared to the metal part. We determine the bolt preload based on the clamp-up load calculated using a maximum preload to make the composite part safe. We conclude that the unsuitable bolt preload may cause the failure of the composite part due to the high stress concentration in the vicinity of the bolt. The global-local analysis provides an efficient computational tool for enhancing 3D stress analysis in the highly loaded region.
基金The National Key Technology R&D Program(No.2012BAH15B00)the Scientific Innovation Research of College Graduates in Jiangsu Province(No.KYLX150076)
文摘A continuous wavelet transform(CWT)and globallocal feature(GLF)extraction-based signal classificationalgorithm is proposed to improve the signal classification accuracy.First,the CWT is utilized to generate the timefrequency scalogram.Then,the GLF extraction method is proposed to extract features from the time-frequency scalogram.Finally,a classification method based on the support vector machine(SVM)is proposed to classify the extracted features.Experimental results show that the extended binary phase shift keying(EBPSK)bit error rate(BER)of the proposed classification algorithm is1.3x10_5under the environment of additional white Gaussian noise with the signal-to-noise ratio of-3dB,which is24times lower than that of the SVM-based signal classification method.Meanwhile,the BER using the GLF extraction method is13times lower than the one using the global feature extraction method and24times lower than the one using the local feature extraction method.
文摘A global-local finite element modeling technique is employed in this paper to predict the separation in steel cord-rubber composite materials of radial truck tires. The local model uses a finite element analysis in conjunction with a glob-al-local technique in ABAQUS. A 3-dimensional finite element local model calculates the maximum cyclic shear strain of an interface between steel cord and rubber materials at the carcass ply shoulder region. It is found that the maximum cyclic shear strain is reliable as a result of the analysis of carcass ply separation in radial truck tires. Using the analysis of the local model, a study of the cyclic shear strain is performed in the shoulder region and used to deter-mine the carcass ply separation. The effect of the change of carcass ply design on the separation in steel cord-rubber composite materials of radial truck tires is discussed.
文摘The stress distribution surrounding the fastener hole in thick laminate mechanical joints is complex. It is time-consuming to analyze the distribution using finite element method. To accurately and efficiently obtain the stress state around the fastener hole in multi-bolt thick laminate joints, a global-local approach is introduced. In the method, the most seriously damaged zone is 3D modeled by taking the displacement field got from the 2D global model as boundary conditions. Through comparison and analysis there are the following findings: the global-local finite element method is a reliable and efficient way to solve the stress distribution problem; the stress distribution around the fastener hole is quite uneven in through-the-thickness direction, and the stresses of the elements close to the shearing plane are much higher than the stresses of the elements far away from the shearing plane; the out-of-plane stresses introduced by the single-lap joint cannot be ignored due to the delamination failure; the stress state is a useful criterion for further more complex studies involving failure analysis.
文摘Objective: A global-local processing task was adapted to be used in an event- related potential paradigm in order to examine the effects of positive emotion on
基金supported in part by the National Natural Science Foundation of China under Grant Nos.U20A20197,62306187the Foundation of Ministry of Industry and Information Technology TC220H05X-04.
文摘In recent years,semantic segmentation on 3D point cloud data has attracted much attention.Unlike 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and inherently sparse.Therefore,it is very difficult to extract long-range contexts and effectively aggregate local features for semantic segmentation in 3D point cloud space.Most current methods either focus on local feature aggregation or long-range context dependency,but fail to directly establish a global-local feature extractor to complete the point cloud semantic segmentation tasks.In this paper,we propose a Transformer-based stratified graph convolutional network(SGT-Net),which enlarges the effective receptive field and builds direct long-range dependency.Specifically,we first propose a novel dense-sparse sampling strategy that provides dense local vertices and sparse long-distance vertices for subsequent graph convolutional network(GCN).Secondly,we propose a multi-key self-attention mechanism based on the Transformer to further weight augmentation for crucial neighboring relationships and enlarge the effective receptive field.In addition,to further improve the efficiency of the network,we propose a similarity measurement module to determine whether the neighborhood near the center point is effective.We demonstrate the validity and superiority of our method on the S3DIS and ShapeNet datasets.Through ablation experiments and segmentation visualization,we verify that the SGT model can improve the performance of the point cloud semantic segmentation.
