Kelo S.,Ram Meghe Institute of Technology and Research |
Dudul S.,Sant Gadge Baba Amravati University
International Journal of Electrical Power and Energy Systems | Year: 2012
In this paper, a novel combination of wavelet and Elman network as a recurrent neural network is proposed to predict 1-day-ahead electrical power load under the influence of temperature. Using wavelet multi-resolution analysis, the load series are decomposed to different sub-series, showing different frequency characteristics of the load. Elman network (EN) is optimally designed and trained using static back propagation algorithm based on the optimization of performance measures such as mean square error, correlation coefficient and mean absolute percentage error on test prediction dataset. Feasibility of Daubechies wavelet at different scales with suitable number of decomposition levels is investigated to choose the best order for different seasonal load series. The estimated models are evaluated over different temperature and humidity in order to examine their impact on accurate load prediction. The reliability and consistency in prediction by the adopted technique is maintained even in the presence of controlled Gaussian noise to the predicted temperature series. © 2012 Elsevier Ltd. All rights reserved.
Mohod S.W.,Ram Meghe Institute of Technology and Research |
Mohod S.W.,Visvesvaraya National Institute of Technology |
Aware M.V.,Visvesvaraya National Institute of Technology
2010 IEEE International Conference on Sustainable Energy Technologies, ICSET 2010 | Year: 2010
The wind energy generation, utilization and its grid penetration in electrical grid is increasing world wide. The wind generated power is always fluctuating due to its time varying nature and causing stability problem. This weak interconnection of wind generating source in the electrical network affect the power quality and reliability. The localized energy storages shall compensate the fluctuating power and support to strengthen the wind generator in the power system. In this paper, it is proposed to control the voltage source inverter (VSI) in current control mode with energy storage, that is, batteries across the dc bus. The generated wind power can be extracted under varying wind speed and stored in the batteries. This energy storage maintains the stiff voltage across the dc bus of the voltage source inverter. The propose scheme enhances the stability and reliability and maintain unity power factor as well as operated in stand alone mode in the power system. The power exchange across the wind generation and the load under dynamic situation is feasible while maintaining the power quality norms at the common point of coupling , strengthen the weak grid in the power system. This control strategy is evaluated on the test system under dynamic condition by using simulation. ©2010 IEEE.
Chitlange M.R.,Government Polytechnic |
Bang R.S.,Government Polytechnic |
Pajgade P.S.,Ram Meghe Institute of Technology and Research
Journal of the Institution of Engineers (India): Civil Engineering Division | Year: 2010
Conventionally concrete is a mixture of cement, sand and aggregate. The large variation in the strength of concrete is due to the variation in the strength of aggregates used. There'is a scarcity of natural sand due to heavy demand in the growing construction activities. This necessitates that a suitable substitute be found. The cheapest substitute for natural sand is obtained by crushing natural stone to get artificial sand of desired size and grade, which would be free from all impurities. This paper presents the feasibility of using artificial sand obtained by crushing basalt, over natural sand considering the technical, environmental and commercial factors. For the purpose of experimentation concrete mixes were designed for M20, M30 and M40 grades with 100% replacement of natural sand by artificial sand. The compressive, flexural and spilt tensile tests were conducted to study the strength of concrete using artificial sand and the results are compared with that of natural sand concrete.
Kshirsagar S.V.,NBN Sinhgad Technical Institute Campus |
Bhuyar L.B.,Ram Meghe Institute of Technology and Research
International Journal of Applied Engineering Research | Year: 2011
In this paper, a novel approach to the crack detection in cantilever beam by vibration signature analysis is established. The crack detection method is based on the vibration analysis under harmonic excitation. An experimental setup is designed in which a cracked cantilever beam is excited by an exciter and the signature is obtained using an accelerometer attached to the beam. To avoid non-linearity, it is assumed that the crack is always open. Natural frequencies obtained from modal analysis as a criterion for crack detection has been extensively used in the last decades due to its simplicity. However the online crack detection and condition monitoring using vibration signature is not straightforward. An efficient technique is necessary to obtain significant results. To identify the crack, contours of the normalized frequency in terms of the normalized crack depth and location are plotted. The intersection of contours with the constant damage index planes is used to relate the crack location and depth. The proposed method is based on the change in natural frequencies extracted from vibration signature of the beam. © Research India Publications.
Gupta S.R.,Ram Meghe Institute of Technology and Research
Proceedings - International Conference on Electronic Systems, Signal Processing, and Computing Technologies, ICESC 2014 | Year: 2014
Because of increase in social networking, more and more people are connected. The people use to share information using these sites and also through the personal blogs. This information sharing is done globally. As the Internet Technology is becoming reliable, people feel safe while sharing the information. Other than messages and photos, this information also includes opinions, experiences and feedbacks regarding any product. These opinions and feedbacks are very important for the organizations that are selling or manufacturing the products, which can be used for changing designs, personalization and better understanding of product. This information is very useful for people or customer for buying the product. But for a customer, it is very difficult to review all the opinions or feedbacks available on net for a particular product. So, data mining approaches are used to mine the opinions, perform summarization of reviews for a particular product based on features or any other category. Most of the existing methods are processing the reviews in terms of positive and negative comments. But this approach is not enough for a customer to make decision about product. The proposed approach not only finding the positive and negative comments for any product or product features, but also rating them in the order of positivity and negativity. Also, the proposed approach gives the degree of comparisons for a particular product and product features. © 2014 IEEE.