Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be improved.Specifically,approaches using normalizing flows can accurately ...Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be improved.Specifically,approaches using normalizing flows can accurately evaluate sample distributions,mapping normal features to the normal distribution and anomalous features outside it.Consequently,this paper proposes a Normalizing Flow-based Bidirectional Mapping Residual Network(NF-BMR).It utilizes pre-trained Convolutional Neural Networks(CNN)and normalizing flows to construct discriminative source and target domain feature spaces.Additionally,to better learn feature information in both domain spaces,we propose the Bidirectional Mapping Residual Network(BMR),which maps sample features to these two spaces for anomaly detection.The two detection spaces effectively complement each other’s deficiencies and provide a comprehensive feature evaluation from two perspectives,which leads to the improvement of detection performance.Comparative experimental results on the MVTec AD and DAGM datasets against the Bidirectional Pre-trained Feature Mapping Network(B-PFM)and other state-of-the-art methods demonstrate that the proposed approach achieves superior performance.On the MVTec AD dataset,NF-BMR achieves an average AUROC of 98.7%for all 15 categories.Especially,it achieves 100%optimal detection performance in five categories.On the DAGM dataset,the average AUROC across ten categories is 98.7%,which is very close to supervised methods.展开更多
The failure behavior of metal materials under strong dynamic loading such as explosive and impact loading has important applications in the fields of defense industry and civil security. In this study, a novel coupled...The failure behavior of metal materials under strong dynamic loading such as explosive and impact loading has important applications in the fields of defense industry and civil security. In this study, a novel coupled bidirectional weighted mapping method between Lagrange particles and Euler meshes is proposed to numerically simulate the dynamic response and failure process of steel structure under explosive loading. In this method, the Lagrange particles and Euler meshes are used to describe the materials that need to be accurately tracked and can more accurately characterize the deformation history and failure process of the material. A comparison between the numerical results and experimental data shows that this method can be used to solve large deformation problem of multi-medium materials and the failure problems of complex structures under strong impact loading.展开更多
基金This work was supported in part by the National Key R&D Program of China 2021YFE0110500in part by the National Natural Science Foundation of China under Grant 62062021in part by the Guiyang Scientific Plan Project[2023]48-11.
文摘Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be improved.Specifically,approaches using normalizing flows can accurately evaluate sample distributions,mapping normal features to the normal distribution and anomalous features outside it.Consequently,this paper proposes a Normalizing Flow-based Bidirectional Mapping Residual Network(NF-BMR).It utilizes pre-trained Convolutional Neural Networks(CNN)and normalizing flows to construct discriminative source and target domain feature spaces.Additionally,to better learn feature information in both domain spaces,we propose the Bidirectional Mapping Residual Network(BMR),which maps sample features to these two spaces for anomaly detection.The two detection spaces effectively complement each other’s deficiencies and provide a comprehensive feature evaluation from two perspectives,which leads to the improvement of detection performance.Comparative experimental results on the MVTec AD and DAGM datasets against the Bidirectional Pre-trained Feature Mapping Network(B-PFM)and other state-of-the-art methods demonstrate that the proposed approach achieves superior performance.On the MVTec AD dataset,NF-BMR achieves an average AUROC of 98.7%for all 15 categories.Especially,it achieves 100%optimal detection performance in five categories.On the DAGM dataset,the average AUROC across ten categories is 98.7%,which is very close to supervised methods.
基金the National Natural Science Foundation of China(Grant No.11902036)the China Postdoctoral Science Foundation(Grant No.2020T130057)。
文摘The failure behavior of metal materials under strong dynamic loading such as explosive and impact loading has important applications in the fields of defense industry and civil security. In this study, a novel coupled bidirectional weighted mapping method between Lagrange particles and Euler meshes is proposed to numerically simulate the dynamic response and failure process of steel structure under explosive loading. In this method, the Lagrange particles and Euler meshes are used to describe the materials that need to be accurately tracked and can more accurately characterize the deformation history and failure process of the material. A comparison between the numerical results and experimental data shows that this method can be used to solve large deformation problem of multi-medium materials and the failure problems of complex structures under strong impact loading.