Title :
Nonlinear Inertia Convergence Classification Model of Online Power
Author :
Mei Wang ; Yanan Guo ; Xiaowei Li ; Wei Mo ; Liang Wang
Author_Institution :
Coll. ofElectric & Control Eng., Xi´an Univ. of Sci. & Technol., Xi´an, China
Abstract :
The development and the progress of science and technology of the power industry is faster and faster. Electric power cables are getting more and more widely used in the power system. It plays an extremely important role in industrial production and modern life. To overcome the problem that the kernel parameter and the punishment factor have great influence on the quality of Support Vector Machine (SVM) model, the Particle Swarm Optimization (PSO) is used to optimize the parameters, and then a kind of Hybrid Method Support Vector Machine (HMSVM) is established for fault recognition. Finally, the HMSVM is applied to the recognition of online power cable faults. It is experimentally proved that, the HMSVM is correct and effective for the fault recognition of the online power cable.
Keywords :
electricity supply industry; particle swarm optimisation; power cables; power engineering computing; power system faults; support vector machines; HMSVM; Nonlinear Inertia Convergence Classification Model; PSO; SVM model; electric power cables; hybrid method support vector machine; industrial production; kernel parameter; online power cable fault recognition; particle swarm optimization; power industry; power system; punishment factor; support vector machine; Circuit faults; Convergence; Kernel; Optical sensors; Particle swarm optimization; Power cables; Support vector machines; Fault recognition; Hybrid Model; Particle Swarm Optimization; Support Vector Machines;
Conference_Titel :
Computer, Consumer and Control (IS3C), 2014 International Symposium on
Conference_Location :
Taichung
DOI :
10.1109/IS3C.2014.170
