Kongu Engineering College

About: Kongu Engineering College is a based out in . It is known for research contribution in the topics: Computer science & Cluster analysis. The organization has 2001 authors who have published 1978 publications receiving 16923 citations.

Fault Diagnosis and Asset Management of Power Transformer Using Adaptive Boost Machine Learning Algorithm

Abstract: Dissolved Gas Analysis (DGA) data of liquid insulation used to find the incipient faults such as partial discharge, thermal faults of various temperatures, discharge of high and low energy faults, combination of electrical and thermal faults in transformers. The conventional approaches of DGA namely Gas Ratio method, Duval triangle method and the Neural Network seems to be time consuming and sometimes yield erroneous results. In this paper, Adaptive BOOST machine learning algorithm is proposed, which is effective in classifying the transformer incipient faults. The results of proposed algorithm is compared with the results of different other machine learning algorithms such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree, Ensembler algorithm for the same set of transformers data. From the comparison, it is evident that ADABOOST machine learning algorithm performs well.

Simulation and emulation of induction motor faults

Abstract: The efficiency of induction motor depends on the condition of the motor. Condition monitoring of the induction motor relies on the detection of difference between healthy and faulty motors. The Motor Current Signature Analysis (MCSA) is the most reliable method as it does not require any sensors for its functioning. The major faults like broken rotor bar, eccentricity, stator unbalance and stator coil short circuit faults can be diagnosed by using the MCSA method. In this paper we propose a system that could simulate and emulate the major faults in induction motor.

Probabilistic approach based optimal placement of phasor measurement units via the estimation of dynamic vulnerability assessment

Abstract: This paper aims in presenting the optimal placement of the Phasor Measurement Unit (PMU) of an IEEE-5 bus system. In this paper a simplest scheme for dynamic vulnerability assessment based on Power System Loss Index has been proposed for Optimal PMU placement and which is compared against the Multi Criteria Decision Making (MCDM) Techniques namely Analytical Hierarchy Process (AHP), Fuzzy AHP approach and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) approach. MCDM helps in finding the best solution among the multiple alternatives for the placement of PMU which is based on the weighing factor. But this MCDM has neglected the dynamic operation of the system. In the proposed scheme, the probabilistic nature of network dynamics is performed by Monte Carlo Simulation to iteratively evaluate the system performance for probable input parameter variations such as load variation, generation variation and list of credible contingencies to assess the vulnerability index of the system. Newton — Raphson load flow analysis is performed for each contingency and the power system losses in various parts of the networks are observed. The vulnerability Index is calculated based on total Power System Loss (PSL). Based on the index, the vulnerable regions in the power system network are identified and clustered with the help of Data clustering algorithm. The PMUs have to be located in the most vulnerable regions to prevent the system from blackouts and to take corrective control actions. This proposed simple approach is tested on IEEE-5 Bus test systems. The test result shows that PSL index is effective in identifying the vulnerable regions for optimal PMU placement. The findings of the PMU location are compared against MCDM techniques.

Automatic irrigation and worm detection for peanut field using Raspberry pi with OpenCV

Abstract: Crop productivity in agriculture is in great demand. To increase or to achieve better production, detection of worms at an early stage and better irrigation is to be done. In earlier days irrigation process is done by sensors by monitoring the soil moisture in the field. It seems to be inaccurate, and varies for different areas such as top layer and inner layer of the soil. In order to avoid this problem, Automatic irrigation system and worm detection at early stage is being done. In automatic irrigation system, Web camera is placed in the field to monitor the dry peanut leaves which will turn upside down when it is dried and shrink if it is half dried (leaves). The Captured leaves are compared with the database images using color and edge histogram correlation method. If it is found dry it sends the information to the control room to turn ON the motor. This reduces the manpower needed for monitoring continuously. Meanwhile, detecting the worm in leaves by edge detection method is done which informs the people to be aware and take preventive actions at the earliest. By doing this Crop yield can be increased and can reduce the wastages of plants.