In the field of data-driven bearing fault diagnosis,convolutional neural network(CNN)has been widely researched and applied due to its superior feature extraction and classification ability.However,the convolutional o...In the field of data-driven bearing fault diagnosis,convolutional neural network(CNN)has been widely researched and applied due to its superior feature extraction and classification ability.However,the convolutional operation could only process a local neighborhood at a time and thus lack the ability of capturing long-range dependencies.Therefore,building an efficient learning method for long-range dependencies is crucial to comprehend and express signal features considering that the vibration signals obtained in a real industrial environment always have strong instability,periodicity,and temporal correlation.This paper introduces nonlocal mean to the CNN and presents a 1D nonlocal block(1D-NLB)to extract long-range dependencies.The 1D-NLB computes the response at a position as a weighted average value of the features at all positions.Based on it,we propose a nonlocal 1D convolutional neural network(NL-1DCNN)aiming at rolling bearing fault diagnosis.Furthermore,the 1D-NLB could be simply plugged into most existing deep learning architecture to improve their fault diagnosis ability.Under multiple noise conditions,the 1D-NLB improves the performance of the CNN on the wheelset bearing data set of high-speed train and the Case Western Reserve University bearing data set.The experiment results show that the NL-1DCNN exhibits superior results compared with six state-of-the-art fault diagnosis methods.展开更多
An improved method based on the Tikhonov regularization principle and the precisely known reference station coordinate is proposed to design the regularized matrix. The ill-conditioning of the normal matrix can be imp...An improved method based on the Tikhonov regularization principle and the precisely known reference station coordinate is proposed to design the regularized matrix. The ill-conditioning of the normal matrix can be improved by the regularized matrix. The relative floating ambiguity can be computed only by using the data of several epochs. Combined with the LAMBDA method, the new approach can correctly and quickly fix the integer ambiguity and the success rate is 100% in experiments. Through using measured data sets from four mediumlong baselines, the new method can obtain exact ambiguities only by the Ll-frequency data of three epochs. Compared with the existing methods, the improved method can solve the ambiguities of the medium-long baseline GPS network RTK only using L1-frequency GPS data.展开更多
Network RTK (Real-Time Kinematic) is a technology that is based on GPS (Global Positioning System) or more gener-ally on GNSS (Global Navigation Satellite System) measurements to achieve centimeter-level accuracy posi...Network RTK (Real-Time Kinematic) is a technology that is based on GPS (Global Positioning System) or more gener-ally on GNSS (Global Navigation Satellite System) measurements to achieve centimeter-level accuracy positioning in real-time. Reference station placement is an important problem in the design and deployment of network RTK systems as it directly affects the quality of the positioning service and the cost of the network RTK systems. This paper identifies a new reference station placement for network RTK, namely QoS-aware regional network RTK reference station placement problem, and proposes an algorithm for the new reference station placement problem. The algorithm can always produce a reference station placement solution that completely covers the region of network RTK.展开更多
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supported by the State Key Laboratory of Traction Power,Southwest Jiaotong University (TPL2104)the National Natural Science Foundation of China (61833002).
文摘In the field of data-driven bearing fault diagnosis,convolutional neural network(CNN)has been widely researched and applied due to its superior feature extraction and classification ability.However,the convolutional operation could only process a local neighborhood at a time and thus lack the ability of capturing long-range dependencies.Therefore,building an efficient learning method for long-range dependencies is crucial to comprehend and express signal features considering that the vibration signals obtained in a real industrial environment always have strong instability,periodicity,and temporal correlation.This paper introduces nonlocal mean to the CNN and presents a 1D nonlocal block(1D-NLB)to extract long-range dependencies.The 1D-NLB computes the response at a position as a weighted average value of the features at all positions.Based on it,we propose a nonlocal 1D convolutional neural network(NL-1DCNN)aiming at rolling bearing fault diagnosis.Furthermore,the 1D-NLB could be simply plugged into most existing deep learning architecture to improve their fault diagnosis ability.Under multiple noise conditions,the 1D-NLB improves the performance of the CNN on the wheelset bearing data set of high-speed train and the Case Western Reserve University bearing data set.The experiment results show that the NL-1DCNN exhibits superior results compared with six state-of-the-art fault diagnosis methods.
文摘An improved method based on the Tikhonov regularization principle and the precisely known reference station coordinate is proposed to design the regularized matrix. The ill-conditioning of the normal matrix can be improved by the regularized matrix. The relative floating ambiguity can be computed only by using the data of several epochs. Combined with the LAMBDA method, the new approach can correctly and quickly fix the integer ambiguity and the success rate is 100% in experiments. Through using measured data sets from four mediumlong baselines, the new method can obtain exact ambiguities only by the Ll-frequency data of three epochs. Compared with the existing methods, the improved method can solve the ambiguities of the medium-long baseline GPS network RTK only using L1-frequency GPS data.
文摘Network RTK (Real-Time Kinematic) is a technology that is based on GPS (Global Positioning System) or more gener-ally on GNSS (Global Navigation Satellite System) measurements to achieve centimeter-level accuracy positioning in real-time. Reference station placement is an important problem in the design and deployment of network RTK systems as it directly affects the quality of the positioning service and the cost of the network RTK systems. This paper identifies a new reference station placement for network RTK, namely QoS-aware regional network RTK reference station placement problem, and proposes an algorithm for the new reference station placement problem. The algorithm can always produce a reference station placement solution that completely covers the region of network RTK.
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.
