College of Engineering, Pune

About: College of Engineering, Pune is a based out in . It is known for research contribution in the topics: Sliding mode control & Control theory. The organization has 4264 authors who have published 3492 publications receiving 19371 citations. The organization is also known as: COEP.

Resistance Spot Welding Behavior of Automotive Steels

Abstract: In present-day automobiles, new high-strength steel grades are being extensively utilized, which have different alloy concentration, microstructure and properties, and results in different spot welding behavior. In the present work, the effect of weld current was studied on four widely used automotive grades, such as IF 270, TRIP 690, DP 780 and TRIP 980, in a laboratory welding machine. The welding current was varied between 5 and 15 kA. Weld quality was assessed based on tensile shear, mode of failure, weld nugget diameter, metallographic observations and hardness tests. Experimental results showed that weld strength increased with an increase in base metal tensile strength but with a drop at the point of expulsion. Variation in hardness along the cross section was found to be higher in high-strength steels. The initial microstructure and phase transformation during cooling affected the final properties. Critical currents for peak strength, expulsion, sticking and failure mode transition were determined for each grade for industrial applications. This study helped in determining the criterion-based optimized welding parameters for specific applications of these automotive-grade steels.

Modeling of solar photovoltaic module using system identification

Abstract: For gaining clean and free energy from the sun, solar photovoltaic (PV) systems are used. The main input to PV system is solar insolation which is uncontrollable variable. To optimize the energy gain from this system good models of system dynamics are required. System identification methods are often either highly specialized for the application or require an extensive amount of data, especially when the dynamics studied are nonlinear. This paper shows that by application of system identification technique, a solar PV module system can be modeled with very good accuracy, without modifying the model structure.

Survey of Different Feature Selection Algorithms for Diabetes Mellitus Prediction

Abstract: Diabetes Mellitus is a non-communicable diseases and it is a major health hazard in the world today. There is a huge data of diabetes in health care industry which is chaotic (not structured). Hence to structure and emphasize the size of this huge diabetic data is very necessary for better and accurate prediction results. The major task in this prediction is to select the relevant features for prediction. With the help of feature selection algorithm we can achieve better prediction of diabetes. In this paper we are discussing some feature selection algorithms like-K Nearest Neighbor, K means, branch and bound algorithm, etc. We are considering a common diabetic dataset and analyzing each algorithm for its performance and accuracy and selecting best algorithm among them.

Recognition of Devanagari Scene Text Using Autoencoder CNN

Abstract: Scene text recognition is a well-rooted research domain covering a diverse application area Recognition of scene text is challenging due to the complex nature of scene images Various structural characteristics of the script also influence the recognition process Text and background segmentation is a mandatory step in the scene text recognition process A text recognition system produces the most accurate results if the structural and contextual information is preserved by the segmentation technique Therefore, an attempt is made here to develop a robust foreground/background segmentation(separation) technique that produces the highest recognition results A ground-truth dataset containing Devanagari scene text images is prepared for the experimentation An encoder-decoder convolutional neural network model is used for text/background segmentation The model is trained with Devanagari scene text images for pixel-wise classification of text and background The segmented text is then recognized using an existing OCR engine (Tesseract) The word and character level recognition rates are computed and compared with other existing segmentation techniques to establish the effectiveness of the proposed technique