检索结果-内蒙古大学图书馆

pattern-recognition OF PARTIAL DISCHARGE IN XLPE CABLES USING A NEURAL NETWORK

IEEE TRANSACTIONS ON ELECTRICAL INSULATION 1992年第3期27卷 543-549页

作者： SUZUKI, H ENDOH, T Power System Laboratory Hitachi Cable Limited Hitachi Japan

This paper describes an experimental study of pattern recognition of partial discharge (PD) in a crosslinked polyethylene (XLPE) cable by using a neural network (NN) system. The NN system was a three-layer artificial neural system with feedforward connections, and its learning method was a back-propagation algorithm incorporating an external teacher signal. Input information for the NN was a combination of the discharge magnitude, the number of pulse counts and the phase angle of applied voltage in which PD is produced. PD measurement was carried out using a PD pulse recorder for a 66 kV XLPE cable with an artificial defect under a 38 kV ac applied voltage. After learning 30 typical input patterns, the NN discriminated unknown patterns with 90% correct responses. The time duration including measuring time required for the NN to discriminate PD signal was approximately 30 s. In a long-term performance test of a 66 kV XLPE cable with an artificial defect, the NN-based alarm processor was able to recognize the presence of PD 1 h before breakdown of the cable, and successfully alerted the operator.

关键词： alarm systems cable insulation computerised pattern recognition high-voltage engineering insulation testing neural nets organic insulating materials partial discharges polymers power cables power engineering computing 66 kV XLPE cables alarm processor applied voltage artificial defect backpropagation algorithm discharge magnitude external teacher signal feedforward connections long-term performance test neural network number of pulse counts partial discharge phase angle Artificial neural networks Backpropagation algorithms Cables Learning systems Neural networks Partial discharges pattern recognition Polyethylene Pulse measurements Voltage

来源：评论

学校读者我要写书评

暂无评论

PARTIAL DISCHARGE DIAGNOSIS USING STATISTICAL OPTIMIZATION ON A PC-BASED SYSTEM

引用

IEEE TRANSACTIONS ON ELECTRICAL INSULATION 1992年第1期27卷 93-98页

作者： KRANZ, HG KRUMP, R Gesamthochschule Wuppertal Eergische Universität Germany

Personal computer (PC) aided PD evaluation needs high-speed electronic devices for on-line measurement and digital conversion of PD signals. This paper includes quantities to be measured to evaluate PD signals, which are characterized by a statistical scatter of magnitude and duration and are additionally influenced by noise and a complex time behavior. Using the correct algorithms and parameters the PC gains some intelligence to discriminate unknown defects. Artificial sample defects, representing sources of PD, have been implanted into a GIS system. By performing a statistical analysis of charge, energy and phase angle on the measured signals, it is possible to solve the diagnosis problem by a noise resistant software solution. The final diagnosis is carried out by pattern recognition, using a specially calculated identification data set, which is compared to reference patterns measured earlier. The strategy takes into account the fundamental differences in the physics of discernible defects.

关键词： charge measurement computerised instrumentation computerised pattern recognition fault location insulation testing microcomputer applications partial discharges statistical analysis switchgear testing GIS system PC-based system artificial sample defects defect discrimination digital conversion high-speed electronic devices identification data set noise resistant software solution partial discharge diagnosis pattern recognition phase angle signal charge signal energy statistical analysis statistical optimization Artificial intelligence Geographic Information Systems High-speed electronics Microcomputers Noise measurement Partial discharge measurement Partial discharges Performance evaluation Scattering Time measurement

来源：评论

学校读者我要写书评

暂无评论

HARDWARE REQUIREMENTS FOR NEURAL NETWORK pattern CLASSIFIERS - A CASE-STUDY AND IMPLEMENTATION

引用

IEEE MICRO 1992年第1期12卷 32-40页

作者： BOSER, BE SACKINGER, E BROMLEY, J LECUN, Y JACKEL, LD AT&T BELL LABS HOLMDELNJ 07733

A special-purpose chip, optimized for computational needs of neural networks, performs over 2,000 multiplications and additions simultaneously. Its data path is suitable particularly for the convolutional architectures typical in pattern classification networks but can also be configured for fully connected or feedback topologies. A development system permits rapid prototyping of new applications and analysis of the impact of the specialized hardware on system performance. We demonstrate the power and flexibility of the processor with a neural network for handwritten character recognition containing over 133,000 connections.

关键词： Neural Nets computerised pattern recognition Handwritten Character recognition Neural Network pattern Classifiers Special Purpose Chip Data Path Convolutional Architectures pattern Classification Networks Development System Rapid Prototyping Neural Network Hardware Neural Networks Computer Networks Computer Architecture pattern Classification Neurofeedback Network Topology Prototypes Performance Analysis System Performance

来源：评论

学校读者我要写书评

暂无评论

HARDWARE TO SUPPORT RUNTIME INTELLIGENCE

引用

COMPUTER 1992年第5期25卷 63-66页

作者： ROBINSON, IN Hewlett-Packard Lab. Palo Alto CA

An associative memory system that is specialized to support the syntax and associated pattern-matching rules common to declarative expression is discussed. A coprocessor board based on an array of custom VLSI chips that combine both logic and memory is described. It is shown how this hardware supports a number of popular intelligent-system architectures. Application to querying a dynamic database is considered

关键词： VLSI associative memory system computerised pattern recognition content-addressable storage coprocessor board custom VLSI chips database management systems declarative expression dynamic database knowledge based systems memory architecture pattern-matching rules popular intelligent-system architectures querying runtime intelligence syntax

来源：评论

学校读者我要写书评

暂无评论

DISCRIMINATION OF PARTIAL DISCHARGE patternS USING A NEURAL NETWORK

引用

IEEE TRANSACTIONS ON ELECTRICAL INSULATION 1992年第3期27卷 550-556页

作者： HOZUMI, N OKAMOTO, T IMAJO, T Yokosuka Research Laboratory Central Research Institute of Electric Power Industry Nagasaka Japan

This paper describes the application of the neural network algorithm to the perception of partial discharge patterns. Needle shaped void samples, made from epoxy resin, were used to generate an electrical tree under ac voltage. The partial discharge patterns before and after the tree initiation were learned by the neural network using the back-propagation method. After the learning process was over, unknown discharge patterns were put into the network. It was shown that the network discriminates the tree initiation well. For the stable discrimination of tree initiation, it was required that the tree length be larger than the length of the void.

关键词： cable insulation computerised pattern recognition high-voltage engineering insulation testing neural nets partial discharges power cables power engineering computing AC voltage back-propagation method cable insulation electrical tree epoxy resin needle shaped void samples neural network partial discharge patterns pattern recognition stable discrimination Dielectrics and electrical insulation Electric breakdown Epoxy resins Helium Needles Neural networks Partial discharges Testing Trees - insulation Voltage

来源：评论

学校读者我要写书评

暂无评论

MASSIVELY PARALLEL MODEL-MATCHING - GEOMETRIC HASHING ON THE CONNECTION MACHINE

引用

COMPUTER 1992年第2期25卷 33-42页

作者： RIGOUTSOS, I HUMMEL, R NYU COMP SCINEW YORKNY 10003

The parallelizability of geometric hashing is explored, and two algorithms are presented. Geometric hashing uses the collection of models in a preprocessing phase (executed off line) to build a hash table data structure. The data structure encodes the model information in a highly redundant, multiple-viewpoint way. During the recognition phase, when presented with a scene and extracted features, the hash table data structure indexes geometric properties of the scene features to candidate models. The first uses: parallel hypercube techniques to route information through a series of maps and building-block parallel algorithms. The second algorithm uses the Connection Machine's large memory resources and achieves parallelism through broadcast facilities from the front end. The discussion is confined to the problem of recognizing dot patterson embedded in a scene after they have undergone translation, rotation, and scale changes

关键词： Connection Machine broadcast facilities building-block parallel algorithms computational geometry computerised pattern recognition data structures dot patterson extracted features geometric hashing geometric properties hash table data structure model information multiple-viewpoint parallel algorithms parallel hypercube techniques parallel machines parallel programming preprocessing phase recognition phase

来源：评论

学校读者我要写书评

暂无评论

POSTAL ADDRESS BLOCK LOCATION IN REAL-TIME

引用

COMPUTER 1992年第7期25卷 34-42页

作者： PALUMBO, PW SRIHARI, SN SOH, J SRIDHAR, R DEMJANENKO, V SUNY BUFFALO DEPT COMP SCIBUFFALONY 14260

The CEDAR real-time address block location system, which determines candidates for the location of the destination address from a scanned mail piece image, is described. For each candidate destination address block (DAB), the address block location (ABL) system determines the line segmentation, global orientation, block skew, an indication of whether the address appears to be handwritten or machine printed, and a value indicating the degree of confidence that the block actually contains the destination address. With 20-MHz Sparc processors, the average time per mail piece for the combined hardware and software system components is 0.210 seconds. The system located 89.0% of the addresses as the top choice. Recent developments in the system include the use of a top-down segmentation tool, address syntax analysis using only connected component data, and improvements to the segmentation refinement routines. This has increased top choice performance to 91.4%

关键词： CEDAR real-time address block location system address syntax analysis block skew computer vision computerised pattern recognition computerised picture processing destination address block global orientation line segmentation real-time systems segmentation refinement routines top-down segmentation tool

来源：评论

学校读者我要写书评

暂无评论

A ROBUST recognition SYSTEM FOR A DRAWING SUPERIMPOSED ON A MAP

引用

COMPUTER 1992年第7期25卷 56-59页

作者： SHIMOTSUJI, S HORI, O ASANO, M SUZUKI, K HOSHINO, F ISHII, T TOKYO ELECT POWER CO LTD COMP & COMMUN RES CTRTOKYO 104JAPAN TOSHIBA CO LTD CTR RES & DEVINFORMAT SYST LABKAWASAKI 210JAPAN

A robust and efficient drawing recognition system that is based on a representation technique using accurate shape and topological line information for an input drawing image is described. This representation supports primitive decomposition and object extraction that enable accurate automatic interpretation even for low-quality drawings. The system, which is adapted to an underground electric cable diagram, has been implemented on a workstation

关键词： automatic interpretation computerised pattern recognition computerised picture processing drawing input drawing image map object extraction primitive decomposition representation technique robust recognition system topological line information underground electric cable diagram

来源：评论

学校读者我要写书评

暂无评论

READING HANDWRITTEN DIGITS - A ZIP CODE recognition SYSTEM

引用

COMPUTER 1992年第7期25卷 59-63页

作者： MATAN, O BAIRD, HS BROMLEY, J BURGES, CJC DENKER, JS JACKEL, LD LECUN, Y PEDNAULT, EPD SATTERFIELD, WD STENARD, CE THOMPSON, TJ AT&T BELL LABS ADV INFORMAT SYST ENGN GRPHOLMDELNJ 07733 AT&T BELL LABS ADV INFORMAT SYST DEV GRPTECH STAFFHOLMDELNJ 07733 AT&T BELL LABS ADAPT SYST RES DEPTHOLMDELNJ 07733 AT&T BELL LABS MACHINE PERCEPT RES DEPTTECH STAFFHOLMDELNJ 07733 AT&T BELL LABS COMP SCI RES CTRTECH STAFFHOLMDELNJ 07733

A neural network algorithm-based system that reads handwritten ZIP codes appearing on real US mail is described. The system uses a recognition-based segmenter, that is a hybrid of connected-components analysis (CCA), vertical cuts, and a neural network recognizer. Connected components that are single digits are handled by CCA. CCs that are combined or dissected digits are handled by the vertical-cut segmenter. The four main stages of processing are preprocessing, in which noise is removed and the digits are deslanted, CCA segmentation and recognition, vertical-cut-point estimation and segmentation, and directly lookup. The system was trained and tested on approximately 10000 images, five- and nine-digit ZIP code fields taken from real mail

关键词： ZIP code recognition system character recognition computerised pattern recognition computerised picture processing connected-components analysis directly lookup handwritten digits reading neural nets neural network algorithm-based system neural network recognizer recognition-based segmenter vertical cuts vertical-cut-point estimation

来源：评论

学校读者我要写书评

暂无评论

ON PIECEWISE-LINEAR CLASSIFICATION

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 1992年第7期14卷 782-786页

作者： HERMAN, GT YEUNG, KTD Dept. of Radiol. Pennsylvania Univ. Philadelphia PA USA

If two sets of vectors (in N-dimensional real Euclidean space R(N)) do not have an element in common, then they can always be separated from each other by using a series of N - 1 dimensional hyperplanes in R(N). In piecewise-linear classification, one finds such a series of hyperplanes using a training set containing elements from both classes. Efficient methods to find such a piecewise-linear separation for the training sets have been proposed in the literature. However, since complete separation of the training set fits the "noise" as well as the "signal" in the training set, the desirability of such a complete separation depends on the nature of the data. In this paper, we make use of a real data set (containing 9-D measurements of fine needle aspirates of a patient's breast for the purpose of classifying a tumor's malignancy) for which early stopping in the generation of the separating hyperplanes is not appropriate. We compare a piecewise-linear classification method (both with complete separation on the training set and with separation using only seven hyperplanes) with classification based on a single (but in a statistical sense optimal) linear separator. A precise methodology for comparing the relative efficacy of two classification methods for a particular task (including a way of providing the statistical significance of the results) is described and is applied to the comparison on the breast cancer data of the relative performances of the two versions of the piecewise-linear classifier and the classification based on an optimal linear separator. It is found that for this data set, the piecewise-linear classifier that uses all the hyperplanes needed to separate the training set outperforms the other two methods and that these differences in performance are significant at the 0.001 level. There is no statistically significant difference between the performance of the other two methods. We discuss the relevance of these results for this and other application

关键词： Piecewise linear techniques Vectors Particle separators Needles Breast cancer Medical diagnosis pattern recognition Performance evaluation Biomedical image processing Radiology INSPEC: Controlled Indexing patient diagnosis computerised pattern recognition medical computing INSPEC: Non-Controlled Indexing breast cancer data tumor malignancy classification patient diagnosis pattern recognition piecewise-linear classification hyperplanes

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：