Based on the analysis of the principle and structure of the convolutionalneuralnetwork (CNN) model in a deep learning theory system, an intelligent method for judging the flashover of a porcelain insulator with ultr...
详细信息
Based on the analysis of the principle and structure of the convolutionalneuralnetwork (CNN) model in a deep learning theory system, an intelligent method for judging the flashover of a porcelain insulator with ultraviolet discharge is proposed. In this method, the porcelain insulator chip was subjected to power frequency flashover testing, and the ultraviolet spectra of different discharge states without discharge, weak coronal discharge, and strong spark discharge were captured by FILIN UV imager. The Alexnet deep convolution neuralnetworkmodel was used to predict the discharge state of the UV spectrum for classification training and identification assessment. The new method doesn't use UV imaging to detect flashover warnings. It is necessary to extract the characteristics of the UV spectra and leakage current parameters manually. The multi-layer combination of UV imaging method with end-to-end autonomous learning with deep learning training and the adopted test method provided classification identification, through a large number of UV images in the deep CNN training. This allowed flashover evaluation of abstract feature parameters of the independent extraction. The results show that this method has the advantages of high accuracy, and provides a new idea for the intelligent detection of UV flashover.
Visual-based technologies are very useful and meaningful to driver's fatigue detection. In this study, the authors present a multi-task hierarchical CNN scheme for fatigue detection system and propose a convolutio...
详细信息
Visual-based technologies are very useful and meaningful to driver's fatigue detection. In this study, the authors present a multi-task hierarchical CNN scheme for fatigue detection system and propose a convolutionalneuralnetwork (CNN) model with multi-scale pooling (MSP-Net). Multi-task' includes three tasks: face detection, eye and mouth state detection and fatigue detection. First, they use a pre-trained network - multi-task CNN for face detection extracting eye and mouth regions. Then, the main work of this study, eye and mouth state detection is processed by MSP-Net, which can fit multi-resolution input images captured from variant cameras excellently. For the third step, the percentage of eyelid closure over the pupil over time (PERCLOS) parameters and the frequency of open mouth (FOM) parameters are used to detect fatigue, and the FOM parameters are proposed by ourselves. Besides, they successfully port the system to the embedded platform (the NVIDIA JETSON TX2 development board) and test on real driving scene. The results show that their system performs well and is robust to complex environments and is in line with the demand of real-time system.
Dynamic security assessment (DSA) is widely used in dispatching operation systems, and the small signal stability is one of the DSA's most time-consuming calculation methods. In this article, a fast method is prop...
详细信息
Dynamic security assessment (DSA) is widely used in dispatching operation systems, and the small signal stability is one of the DSA's most time-consuming calculation methods. In this article, a fast method is proposed aiming to predict the small signal stability metrics of designated oscillation mode, for example frequency or damping ratio. The method is much faster than the simulation and suitable for the online application. First, the t-distributed stochastic neighbour embedding (t-SNE) algorithm is performed which can create a mapping from the power system components to 2D coordinate depending on the electrical distance of each other;then, it will be transformed into a grid structure by meshing operation, on which the convolutionalneuralnetwork (CNN) model can be run properly. Finally, with a large amount of simulation samples, the CNN model can be well trained using static quantities as its input and small signal stability metrics as its prediction target. While a new operation mode needs to be evaluated, the result will be obtained by CNN directly. The validity of proposed method is verified using online data of State Grid Corp of China. It is proved that the method meets the requirements for speed and accuracy of online analysis system.
The traffic sign recognition system inside the vehicle plays an important role and could guarantee the safety of human life on the road since it feedbacks road information to the driver in time. Benefited from learnin...
详细信息
ISBN:
(纸本)9781538633540
The traffic sign recognition system inside the vehicle plays an important role and could guarantee the safety of human life on the road since it feedbacks road information to the driver in time. Benefited from learning features of the traffic sign, the convolutionalneuralnetwork (CNN) has been widely used in traffic sign recognition with a high accuracy. However, the different kinds of traffic signs appear to distinctive features. A deep and high complexity neuralnetwork with a larger number of parameters is usually required to adapt the distinctive features, while it tends to be time-consuming and can not meet real-time requirement. In this paper, we firstly divide traffic signs into hierarchal structure according to the types of features, and then use a combined CNNs (CCNN) to adapt the hierarchical traffic signs, where the probabilities of superclass and subclass the sign belongs to are calculated using two CNNs with a simple network. Finally, classifying of the sign can be achieved by the weighted output of the two CNNs, and a low complexity sign recognition system could be obtained. Simulation results on the GTSRB database show that the proposed method achieves comparable accuracy and less time-consuming to the state-of-the-art methods.
Deep neuralnetworkmodels have achieved considerable success in a wide range of fields. Several architectures have been proposed to alleviate the vanishing gradient problem, and hence enable training of very deep net...
详细信息
ISBN:
(纸本)9781510833135
Deep neuralnetworkmodels have achieved considerable success in a wide range of fields. Several architectures have been proposed to alleviate the vanishing gradient problem, and hence enable training of very deep networks. In the speech recognition area, convolutionalneuralnetworks, recurrent neuralnetworks, and fully connected deep neuralnetworks have been shown to be complimentary in their modeling capabilities. Combining all three components, called CLDNN, yields the best performance to date. In this paper, we extend the CLDNN model by introducing a highway connection between LSTM layers, which enables direct information flow from cells of lower layers to cells of upper layers. With this design, we are able to better exploit the advantages of a deeper structure. Experiments on the GALE Chinese Broadcast Conversation/News Speech dataset indicate that our model outperforms all previous models and achieves a new benchmark, which is 22.41% character error rate on the dataset.
暂无评论