Measuring the pre-breakdown current of long sparks in air is important for investigating the discharge mechanism.Since the breakdown of long air gaps is conducted by a series of streamer-leader processes,the correspon...Measuring the pre-breakdown current of long sparks in air is important for investigating the discharge mechanism.Since the breakdown of long air gaps is conducted by a series of streamer-leader processes,the corresponding current signals cover a bandwidth of 0 to more than 20 MHz.Measurement accuracy of the current from the high voltage side is affected by the displacement current and impulse electromagnetic interference.In this paper,a coaxial current sensor with a DC bandwidth of 74.45 MHz is developed.A displacement current-restrained electrode structure is proposed to reduce the equivalent capacitance between the current sensor and the ground over 30 times.Combined with the digital optical fiber synchronous acquisition unit,a current measurement system for long air gap discharge is established.For the purpose of the UHV system’s external insulation optimization design,the discharge current waveform of a 6 m rod-plane air gap under positive switching impulse voltage with 250µs and 1000µs time to crest is obtained.Discharge images and stressed voltage are combined to analyze the continuous feature of a current waveform under critical time to crest impulse and discontinuous feature under long front duration impulse.For the purposes of a lightning protection study,the current waveform of a 10 m rod-plane air gap is subjected to negative switching impulse.Finally,the pulse characteristics of the current corresponding to the single channel and branching stepped negative leader are discussed.展开更多
Text sentiment analysis is a common problem in the field of natural language processing that is often resolved by using convolutional neural networks(CNNs).However,most of these CNN models focus only on learning local...Text sentiment analysis is a common problem in the field of natural language processing that is often resolved by using convolutional neural networks(CNNs).However,most of these CNN models focus only on learning local features while ignoring global features.In this paper,based on traditional densely connected convolutional networks(DenseNet),a parallel DenseNet is proposed to realize sentiment analysis of short texts.First,this paper proposes two novel feature extraction blocks that are based on DenseNet and a multiscale convolutional neural network.Second,this paper solves the problem of ignoring global features in traditional CNN models by combining the original features with features extracted by the parallel feature extraction block,and then sending the combined features into the final classifier.Last,a model based on parallel DenseNet that is capable of simultaneously learning both local and global features of short texts and shows better performance on six different databases compared to other basic models is proposed.展开更多
基金supported by the Fund of the National Basic Research of China(2011CB 209403).
文摘Measuring the pre-breakdown current of long sparks in air is important for investigating the discharge mechanism.Since the breakdown of long air gaps is conducted by a series of streamer-leader processes,the corresponding current signals cover a bandwidth of 0 to more than 20 MHz.Measurement accuracy of the current from the high voltage side is affected by the displacement current and impulse electromagnetic interference.In this paper,a coaxial current sensor with a DC bandwidth of 74.45 MHz is developed.A displacement current-restrained electrode structure is proposed to reduce the equivalent capacitance between the current sensor and the ground over 30 times.Combined with the digital optical fiber synchronous acquisition unit,a current measurement system for long air gap discharge is established.For the purpose of the UHV system’s external insulation optimization design,the discharge current waveform of a 6 m rod-plane air gap under positive switching impulse voltage with 250µs and 1000µs time to crest is obtained.Discharge images and stressed voltage are combined to analyze the continuous feature of a current waveform under critical time to crest impulse and discontinuous feature under long front duration impulse.For the purposes of a lightning protection study,the current waveform of a 10 m rod-plane air gap is subjected to negative switching impulse.Finally,the pulse characteristics of the current corresponding to the single channel and branching stepped negative leader are discussed.
基金supported by the National Natural Science Foundation of China(82070261,82170251,and 82200386)the National Key Research and Development Program of China(2021YFA1100501)+4 种基金the Chinese Postdoctoral Science Foundation of China(2022M712590)the Science and Technology Research and Development Program of Shaanxi Province,China(2022JQ881,2021SF-324,and 2022SF-091)the Youth Innovation Team of Shaanxi Universitiesthe Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University(CX2022068)the Seed Foundation of Innovation and Creation for Graduate Students in Northwestern Polytechnical University(CX202065)。
基金This work was supported by the National Key R&D Program of China under Grant Number 2018YFB1003205by the National Natural Science Foundation of China under Grant Numbers U1836208,U1536206,U1836110,61602253,and 61672294+3 种基金by the Startup Foundation for Introducing Talent of NUIST(1441102001002)by the Jiangsu Basic Research Programs-Natural Science Foundation under Grant Number BK20181407by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fundby the Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET)fund,China.
文摘Text sentiment analysis is a common problem in the field of natural language processing that is often resolved by using convolutional neural networks(CNNs).However,most of these CNN models focus only on learning local features while ignoring global features.In this paper,based on traditional densely connected convolutional networks(DenseNet),a parallel DenseNet is proposed to realize sentiment analysis of short texts.First,this paper proposes two novel feature extraction blocks that are based on DenseNet and a multiscale convolutional neural network.Second,this paper solves the problem of ignoring global features in traditional CNN models by combining the original features with features extracted by the parallel feature extraction block,and then sending the combined features into the final classifier.Last,a model based on parallel DenseNet that is capable of simultaneously learning both local and global features of short texts and shows better performance on six different databases compared to other basic models is proposed.
