In order to improve the condition monitoring and fault diagnosis of wind turbines,a stacked noise reduction autoencoding network based on group normalization is proposed in this paper.The network is based on SCADA dat...In order to improve the condition monitoring and fault diagnosis of wind turbines,a stacked noise reduction autoencoding network based on group normalization is proposed in this paper.The network is based on SCADA data of wind turbine operation,firstly,the group normalization(GN)algorithm is added to solve the problems of stack noise reduction autoencoding network training and slow convergence speed,and the RMSProp algorithm is used to update the weight and the bias of the autoenccoder,which further optimizes the problem that the loss function swings too much during the update process.Finally,in the last layer of the network,the softmax activation function is used to classify the results,and the output of the network is transformed into a probability distribution.The selected wind turbine SCADA data was substituted into the pre-improved and improved stacked denoising autoencoding(SDA)networks for comparative training and verification.The results show that the stacked denoising autoencoding network based on group normalization is more accurate and effective for wind turbine condition monitoring and fault diagnosis,and also provides a reference for wind turbine fault identification.展开更多
Underwater shipwreck identification technology, as a crucial technique in the field of marine surveying, plays a significant role in areas such as the search and rescue of maritime disaster shipwrecks. When facing the...Underwater shipwreck identification technology, as a crucial technique in the field of marine surveying, plays a significant role in areas such as the search and rescue of maritime disaster shipwrecks. When facing the task of object detection in shipwreck side-scan sonar images, due to the complex seabed environment, it is difficult to extract object features, often leading to missed detections of shipwreck images and slow detection speed. To address these issues, this paper proposes an object detection algorithm, CSC-YOLO (Context Guided Block, Shared Conv_Group Normalization Detection, Cross Stage Partial with 2 Partial Convolution-You Only Look Once), based on YOLOv8n for shipwreck side-scan sonar images. Firstly, to tackle the problem of small samples in shipwreck side-scan sonar images, a new dataset was constructed through offline data augmentation to expand data and intuitively enhance sample diversity, with the Mosaic algorithm integrated to strengthen the network’s generalization to the dataset. Subsequently, the Context Guided Block (CGB) module was introduced into the backbone network model to enhance the network’s ability to learn and express image features. Additionally, by employing Group Normalization (GN) techniques and shared convolution operations, we constructed the Shared Conv_GN Detection (SCGD) head, which improves the localization and classification performance of the detection head while significantly reducing the number of parameters and computational load. Finally, the Partial Convolution (PConv) was introduced and the Cross Stage Partial with 2 PConv (C2PC) module was constructed to help the network maintain effective extraction of spatial features while reducing computational complexity. The improved CSC-YOLO model, compared with the YOLOv8n model on the validation set, mean Average Precision (mAP) increases by 3.1%, Recall (R) increases by 6.4%, and the F1-measure (F1) increases by 4.7%. Furthermore, in the improved algorithm, the number of parameters decreases by 20%, the computational complexity decreases by 23.2%, and Frames Per Second (FPS) increases by 17.6%. In addition, compared with the advanced popular model, the superiority of the proposed model is proved. The subsequent experiments on real side-scan sonar images of shipwrecks fully demonstrate that the CSC-YOLO algorithm meets the requirements for actual side-scan sonar detection of underwater shipwrecks.展开更多
In this paper, we introduce a practical method for obtaining the structure of thegroup of units for the ring of linear transformations of a vector space over an arbitrary field,and we give a further generalization of ...In this paper, we introduce a practical method for obtaining the structure of thegroup of units for the ring of linear transformations of a vector space over an arbitrary field,and we give a further generalization of the result in [3].展开更多
In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dime...In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dimensional batch normalization visual geometry group(3D-BN-VGG)and long short-term memory(LSTM)network is designed.In this network,3D convolutional layer is used to extract the spatial domain features and time domain features of video sequence at the same time,multiple small convolution kernels are stacked to replace large convolution kernels,thus the depth of neural network is deepened and the number of network parameters is reduced.In addition,the latest batch normalization algorithm is added to the 3-dimensional convolutional network to improve the training speed.Then the output of the full connection layer is sent to LSTM network as the feature vectors to extract the sequence information.This method,which directly uses the output of the whole base level without passing through the full connection layer,reduces the parameters of the whole fusion network to 15324485,nearly twice as much as those of 3D-BN-VGG.Finally,it reveals that the proposed network achieves 96.5%and 74.9%accuracy in the UCF-101 and HMDB-51 respectively,and the algorithm has a calculation speed of 1066 fps and an acceleration ratio of 1,which has a significant predominance in velocity.展开更多
Let G be a finite group. It is proved that any class-preserving Coleman automorphism of G is an inner automorphism whenever G belongs to one of the following two classes of groups： （1） CN-groups, i.e., groups in wh...Let G be a finite group. It is proved that any class-preserving Coleman automorphism of G is an inner automorphism whenever G belongs to one of the following two classes of groups： （1） CN-groups, i.e., groups in which the centralizer of any element is nilpotent; （2） CIT-groups, i.e., groups of even order in which the centralizer of any involution is a 2-group. In particular, the normalizer conjecture holds for both CN-groups and CIT-groups. Additionally, some other results are also obtained.展开更多
For the stratified shallow water with a lossy bottom, the distribution and asymptotic behavior of mode eigenvalues in the complex plane are discussed on the basis of the Pekeris cut. The analysis shows that even in th...For the stratified shallow water with a lossy bottom, the distribution and asymptotic behavior of mode eigenvalues in the complex plane are discussed on the basis of the Pekeris cut. The analysis shows that even in the shallow water with a low-speed lossy bottom there may be the proper modes which satisfy the radiation condition at infinite depth. It is also shown that when the ratio between the densities of the seawater and seabottom is close to one, there exist only a finite number of improper modes . An iterative method for evaluating the complex eigenvalues and group velocities of normal modes is presented and some numerical results are given.展开更多
基金the National Natural Science Foundation of China(51767014),2018–2021.
文摘In order to improve the condition monitoring and fault diagnosis of wind turbines,a stacked noise reduction autoencoding network based on group normalization is proposed in this paper.The network is based on SCADA data of wind turbine operation,firstly,the group normalization(GN)algorithm is added to solve the problems of stack noise reduction autoencoding network training and slow convergence speed,and the RMSProp algorithm is used to update the weight and the bias of the autoenccoder,which further optimizes the problem that the loss function swings too much during the update process.Finally,in the last layer of the network,the softmax activation function is used to classify the results,and the output of the network is transformed into a probability distribution.The selected wind turbine SCADA data was substituted into the pre-improved and improved stacked denoising autoencoding(SDA)networks for comparative training and verification.The results show that the stacked denoising autoencoding network based on group normalization is more accurate and effective for wind turbine condition monitoring and fault diagnosis,and also provides a reference for wind turbine fault identification.
基金supported in part by the Hainan Provincial Natural Science Foundation(Grant No.420CXTD439)Sanya Science and Technology Special Fund(Grant No.2022KJCX83)+1 种基金Institute and Local Cooperation Foundation of Sanya in China(Grant No.2019YD08)National Natural Science Foundation of China(Grant No.61661038).
文摘Underwater shipwreck identification technology, as a crucial technique in the field of marine surveying, plays a significant role in areas such as the search and rescue of maritime disaster shipwrecks. When facing the task of object detection in shipwreck side-scan sonar images, due to the complex seabed environment, it is difficult to extract object features, often leading to missed detections of shipwreck images and slow detection speed. To address these issues, this paper proposes an object detection algorithm, CSC-YOLO (Context Guided Block, Shared Conv_Group Normalization Detection, Cross Stage Partial with 2 Partial Convolution-You Only Look Once), based on YOLOv8n for shipwreck side-scan sonar images. Firstly, to tackle the problem of small samples in shipwreck side-scan sonar images, a new dataset was constructed through offline data augmentation to expand data and intuitively enhance sample diversity, with the Mosaic algorithm integrated to strengthen the network’s generalization to the dataset. Subsequently, the Context Guided Block (CGB) module was introduced into the backbone network model to enhance the network’s ability to learn and express image features. Additionally, by employing Group Normalization (GN) techniques and shared convolution operations, we constructed the Shared Conv_GN Detection (SCGD) head, which improves the localization and classification performance of the detection head while significantly reducing the number of parameters and computational load. Finally, the Partial Convolution (PConv) was introduced and the Cross Stage Partial with 2 PConv (C2PC) module was constructed to help the network maintain effective extraction of spatial features while reducing computational complexity. The improved CSC-YOLO model, compared with the YOLOv8n model on the validation set, mean Average Precision (mAP) increases by 3.1%, Recall (R) increases by 6.4%, and the F1-measure (F1) increases by 4.7%. Furthermore, in the improved algorithm, the number of parameters decreases by 20%, the computational complexity decreases by 23.2%, and Frames Per Second (FPS) increases by 17.6%. In addition, compared with the advanced popular model, the superiority of the proposed model is proved. The subsequent experiments on real side-scan sonar images of shipwrecks fully demonstrate that the CSC-YOLO algorithm meets the requirements for actual side-scan sonar detection of underwater shipwrecks.
基金Supported by the NSF of Educational Department of Henan Province(200510482001)
文摘In this paper, we introduce a practical method for obtaining the structure of thegroup of units for the ring of linear transformations of a vector space over an arbitrary field,and we give a further generalization of the result in [3].
基金the National Natural Science Foundation of China(No.61772417,61634004,61602377)Key R&D Program Projects in Shaanxi Province(No.2017GY-060)Shaanxi Natural Science Basic Research Project(No.2018JM4018).
文摘In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dimensional batch normalization visual geometry group(3D-BN-VGG)and long short-term memory(LSTM)network is designed.In this network,3D convolutional layer is used to extract the spatial domain features and time domain features of video sequence at the same time,multiple small convolution kernels are stacked to replace large convolution kernels,thus the depth of neural network is deepened and the number of network parameters is reduced.In addition,the latest batch normalization algorithm is added to the 3-dimensional convolutional network to improve the training speed.Then the output of the full connection layer is sent to LSTM network as the feature vectors to extract the sequence information.This method,which directly uses the output of the whole base level without passing through the full connection layer,reduces the parameters of the whole fusion network to 15324485,nearly twice as much as those of 3D-BN-VGG.Finally,it reveals that the proposed network achieves 96.5%and 74.9%accuracy in the UCF-101 and HMDB-51 respectively,and the algorithm has a calculation speed of 1066 fps and an acceleration ratio of 1,which has a significant predominance in velocity.
基金Supported by the National Natural Science Foundation of China （71571108）, Projects of International （Regional） Cooperation and Exchanges of NSFC （71611530712, 61661136002）, Specialized Research Fund for the Doctoral Program of Higher Education of China （20133706110002）, Natural Science Foundation of Shandong Province （ZR2015GZ007） Project Funded by China Postdoctoral Science Foundation （2016M590613）, Specialized Fund for the Postdoctoral Innovative Research Program of Shandong Province （201602035）, Project of Shandong Province Higher Educational Science and Technology Program （J14LI10） and Project of Shandong Province Higher Edu- cational Excellent Backbone Teachers for International Cooperation and Training.
文摘Let G be a finite group. It is proved that any class-preserving Coleman automorphism of G is an inner automorphism whenever G belongs to one of the following two classes of groups： （1） CN-groups, i.e., groups in which the centralizer of any element is nilpotent; （2） CIT-groups, i.e., groups of even order in which the centralizer of any involution is a 2-group. In particular, the normalizer conjecture holds for both CN-groups and CIT-groups. Additionally, some other results are also obtained.
文摘For the stratified shallow water with a lossy bottom, the distribution and asymptotic behavior of mode eigenvalues in the complex plane are discussed on the basis of the Pekeris cut. The analysis shows that even in the shallow water with a low-speed lossy bottom there may be the proper modes which satisfy the radiation condition at infinite depth. It is also shown that when the ratio between the densities of the seawater and seabottom is close to one, there exist only a finite number of improper modes . An iterative method for evaluating the complex eigenvalues and group velocities of normal modes is presented and some numerical results are given.
