Detection of DC Voltage Fault in SRM Drives Using K-Means Clustering and Classification with SVM
Journal Title: International Journal of Modern Engineering Research (IJMER) - Year 2014, Vol 4, Issue 1
Abstract
This paper presents a new method of detection of DC voltage fault in SRM drives based on K Means Clustering technique. Also the range of fault is classified using Support Vector Machines (SVM). Switched reluctance motors are very popular in these days, because of ease in manufacturing and operation. Though an electronic circuit can detect the fault like under voltage and over voltage but, the classification cannot be done effectively with electronic circuitry. More over an intelligent method can easily identify the fault and classify and hence the root cause of the fault may be guessed and rectified using this method of classification. The information used to include this intelligence in the system are just torque waveforms. Moreover, the early detection minimizes the faulty operation time and ensures the plant stability and saves the life of motor too. Hence a system to detect such fault under a simulation model has been proposed in this study
Authors and Affiliations
V. Chandrika
Keywords
Related Articles
- EP ID EP88140
- DOI -
- Views 150
- Downloads 0
Energy Aware and Link Quality Based Routing in Wireless Sensor Networks under TinyOS-2.x
Abstract: In WSN the size of sensor node is too small and in future it will become smaller and energy is one of the constraints in sensor node in WSN. In sensor node energy required to process data,transmitting dat...
On some locally closed sets and spaces in Ideal Topological Spaces
In this paper we introduce and characterize some new generalized locally closed sets known as δˆ s-locally closed sets and spaces are known as δˆ s-normal space and δˆ s-connected space and discussed some of their proper...
A Review of Techniques used in spoken-word Recognition System
Humans feel most comfortable to interact among themselves via speech, rather than any other medium such as gestures, text. Computers have become an important part of the world today and we humans need to interact w...
Development of a Thermoelectric Micro generation based on Seebeck Effect
This paper presents a study of the national electric power, showing the Brazil consumes electricity in a year and how much you could save if thermoelectric modules were used in some industries and new cars and plan...
Cluster computing performance in the context of non extensive statistics
This work presents the problem of clusters computing performance in the context of nonextensive statistics. Simulation studies have demonstrated that the cluster computing process is self-similar or long-range dependent...