scholarly journals Power Cable Fault Recognition Based on an Annealed Chaotic Competitive Learning Network

Algorithms ◽  
2014 ◽  
Vol 7 (4) ◽  
pp. 492-509 ◽  
Author(s):  
Xuebin Qin ◽  
Mei Wang ◽  
Jzau-Sheng Lin ◽  
Xiaowei Li
Keyword(s):  
Competitive Learning ◽  
Power Cable ◽  
Learning Network ◽  
Fault Recognition

Cable Fault Recognition Based on the Wavelet Energy Spectrum of Mode Components

2013 ◽  
Vol 427-429 ◽  
pp. 834-837
Author(s):  
Mei Wang ◽  
Jing Wu
Keyword(s):  
Energy Spectrum ◽  
High Frequency ◽  
Transient Current ◽  
Power Cable ◽  
Two Phase ◽  
High Frequencies ◽  
Wavelet Energy ◽  
Fault Recognition ◽  
Frequency Components ◽  
Independent Mode

When a fault appeared in a power cable transmission line, the transient current with high frequencies would be produced in the system. Three independent mode components could be obtained by applying the phase mode transformation to the transient current. For different types of the faults, the three independent mode components have different features. Based on wavelet energy spectrum of mode components, a method for cable fault recognition is developed in this paper. First, the fault current is decomposed by using Karenbaue transformation matrix. Then, wavelet transformation is uses to obtain the coefficients of the high frequency components which reflect the original signal high frequency energy. Finally, based on the wavelet energy spectrum method and the detailed coefficient manipulation, the equivalent norms of the mode components are obtained. Compared with the traditional fault recognition method, the new method depends less on zero mode component in two-phase short to ground state, and it can recognize the fault class in the cases of different fault positions, different fault path resistances and different inception angles.

A COMPARATIVE STUDY OF CLUSTERING METHODS FOR MOLECULAR DATA

2007 ◽  
Vol 17 (06) ◽  
pp. 447-458 ◽  
Author(s):  
LIN WANG ◽  
MINGHU JIANG ◽  
YINGHUA LU ◽  
MINFU SUN ◽  
FRANK NOE
Keyword(s):  
Hierarchical Cluster ◽  
Molecular Data ◽  
Competitive Learning ◽  
Clustering Methods ◽  
Learning Network ◽  
Large Size ◽  
Cluster Distance ◽  
Standard Deviation Range ◽  
Multi Level ◽  
Distance Relation

The research aim is to use three clustering technologies for establishing molecular data model of large size sets by comparison between low energy samples (LES) and local molecular samples (LMS). Hierarchical cluster of multi-level tree distance relation, competitive learning network of similar inputs falling into the same cluster and topological SOM are used to analyze 6242 LES and 5000 LMS. Our experiments show that in SOM, there are 24 to 25 Davies-Boulding clustering index and color map cluster units in the LES more than 10 to 12 in the LMS, which is consistent with the results of hierarchical cluster and competitive learning network in the rough. The hierarchical cluster reflects the biggest inter-cluster distance about 30 for the LES is far larger than that of LMS about 10. The intra-cluster distance of LES about 15 is also far bigger than that of LMS about 3. In SOM, there are more cluster borders of high values (black) reflecting large distance and more clusters in the D-matrix and U-matrix of LES than that of LMS, due to the biggest standard deviation range from -8 to 10 of samples feature of the LES is bigger than that of LMS from -2.5 to 2.5.

A methodology to carry out voting classification tasks using a particle swarm optimization-based neuro-fuzzy competitive learning network

2016 ◽  
Vol 8 (1) ◽  
pp. 49-69 ◽  
Author(s):  
Androniki Tamvakis ◽  
George E. Tsekouras ◽  
Anastasios Rigos ◽  
Christos Kalloniatis ◽  
Christos-Nikolaos Anagnostopoulos ◽  
...  
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Competitive Learning ◽  
Swarm Optimization ◽  
Learning Network ◽  
Neuro Fuzzy ◽  
Classification Tasks

Power Cable Fault Recognition Using the Improved PSO-SVM Algorithm

2013 ◽  
Vol 427-429 ◽  
pp. 830-833 ◽  
Author(s):  
Mei Wang ◽  
Xiao Wei Li
Keyword(s):  
Function Parameter ◽  
Support Vector ◽  
Power Cable ◽  
Power Cables ◽  
Simulation Experiments ◽  
Training Time ◽  
Fault Recognition ◽  
Svm Algorithm ◽  
Improved Pso

Power cables are increasingly popular in daily life and industrial production. The long-term use will make various cable faults. To reduce the losses caused by the faults, the cable faults should be recognized correctly and timely. In this paper, we developed an improved particle swarm optimization and support vector machine (IPSO-SVM) algorithm to recognize the power cable faults. The algorithm used the improved PSO to optimize the SVM kernel function parameter and the penalty parameter simultaneously. Two advantages were illustrated by the simulation experiments. The first one is the recognition accuracy which was increased from 81.8% to 90.9%; the second advantage is the SVM training time which decreased from 0.0247 second to 0.0202 second.

Branching Competitive Learning Network: A Novel Self-Creating Model

2004 ◽  
Vol 15 (2) ◽  
pp. 417-429 ◽  
Author(s):  
H. Xiong ◽  
M.N.S. Swamy ◽  
M.O. Ahmad ◽  
I. King
Keyword(s):  
Competitive Learning ◽  
Learning Network
Sign in / Sign up

Export Citation Format

Share Document