Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Author: search.filters.author.Vardhan, H.Subject: search.filters.subject.Neural networks

Search Results

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    A critical review on estimation of rock properties using sound levels produced during rotary drilling
    (CAFET INNOVA Technical Society cafetinnova@gmail.com 1-2-18/103, Mohini Mansion, Gagan Mahal Road, Domalguda, Hyderabad 500029, 2012) Masood; Vardhan, H.; Mangalpady, M.; Rajesh Kumar, B.
    This paper summarizes the critical review on estimation of rock properties using sound levels produced during rotary drilling. In this paper an overall emphasis has been made to summarize the importance of sound level produced during drilling by considering various parameters like drill bit speed, penetration rate, drill bit diameter, type of drill bit and equivalent sound level produced during drilling for the estimation of rock properties. Further an attempt has also made to include the application of ANN modeling and acoustic emission in estimating rock properties. © 2012 CAFET-INNOVA TECHNICAL SOCIETY.
  • No Thumbnail Available
    Item
    Prediction of penetration rate and sound level produced during percussive drilling using regression and artificial neural network
    (2012) Kivade, S.B.; Murthy, C.S.N.; Vardhan, H.
    The main objective of this investigation is to develop a general prediction model and to study the effect of predictor variables such as uniaxial compressive strength, air pressure and thrust on penetration rate and sound level produced during percussive drilling of rocks. The experiment was carried out using three levels Box-Behnken design with full replication in 15 trials. Modeling was done using artificial neural network (ANN) and multipleregression analysis (MRA). These techniques can be utilized for the prediction of process parameters. Comparison of artificial neural network and multiple linear regression models was made and found that error rate was smaller in ANN than that predicted by MRA in terms of sound level and penetration rate. © 2012 CAFET-INNOVA TECHNICAL SOCIETY.
  • No Thumbnail Available
    Item
    ANN Models for Prediction of Sound and Penetration Rate in Percussive Drilling
    (Springer India sanjiv.goswami@springer.co.in, 2015) Kivade, S.B.; Murthy, C.S.N.; Vardhan, H.
    In the recent years, new techniques such as; Artificial Neural Network (ANN) were employed for developing of the predictive models to estimate the needed parameters. Soft computing techniques are now being used as alternate statistical tool. In this study, ANN models were developed to predict rock properties of sedimentary rock, by using penetration and sound level produced during percussive drilling. The data generated in the laboratory investigation was utilized for the development of ANN models for predicting rock properties like, uniaxial compressive strength, abrasivity, tensile strength, and Schmidt rebound number using air pressure, thrust, bit diameter, penetration rate and sound level. Further, ANN models were also developed for predicting penetration rate and sound level using air pressure, thrust, bit diameter and rock properties as input parameters. The constructed models were checked using various prediction performance indices. ANN models were more acceptable for predicting rock properties. © 2015, The Institution of Engineers (India).
  • No Thumbnail Available
    Item
    Design and fabrication of optimized magnetic roller for permanent roll magnetic separator (PRMS): Finite element method magnetics (FEMM) approach
    (Elsevier B.V., 2021) Mohanraj, G.T.; Rahman, M.R.; Joladarashi, S.; Hanumanthappa, H.; Shanmugam, B.K.; Vardhan, H.; Rabbani, S.A.
    In the present work, an attempt has been made to develop a PRMS in a cost effective and environmental friendly way through FEMM analysis of magnetic roller (active part of PRMS). The FEMM analysis indicates that, the optimized magnetic roller having magnet-to-steel disk thickness ratio of 5 mm: 2.5 mm was proved to be gainful in beneficiating paramagnetic minerals due to the best magnetic field value from the roller surface that is, 0.89 to 2.59 T. Prediction analysis was performed on FEMM data using artificial neural network (ANN) modelling technique. Further, the design calculations of lab scale PRMS in terms of power requirements and belt tensions were addressed. The fabricated PRMS was tested on paramagnetic mineral (hematite ore) assayed 51.24% of Fe, 10.20% of SiO2, and 2.98% of Al2O3 for different roller speeds and the belt thickness. The result showed that, at 0.5 mm belt thickness with 180 rpm roller speed the fabricated lab scale PRMS works well in terms of improvement in the Fe content up to 59.5% at the concentrate along with the Fe recovery of 71.41%. The obtained results suggest that, the FEMM analysis is more suitable to optimize the effective magnetic roller for the PRMS. © 2021 The Society of Powder Technology Japan
  • No Thumbnail Available
    Item
    ANN modeling and residual analysis on screening efficiency of coal in vibrating screen
    (Taylor and Francis Ltd., 2022) Shanmugam, B.K.; Vardhan, H.; Raj, M.G.; Kaza, M.; Sah, R.; Hanumanthappa, H.
    In this paper, coal screening in vibrating screen was carried out with the size ranges of ?6 mm + 4 mm, ?4 mm + 2 mm, and ?2 mm + 0.5 mm. The vibrating screen was newly designed with flexibility in angle and frequency. The vibrating screen experimentation was carried out by varying screen mesh, angle, and screen frequency. During the screening, the angle was kept constant, and frequency was varied to obtain each size range’s screening efficiency. The experimental results of screening efficiency were evaluated for each size fraction range of coal. The maximum efficiency for screening coal with ?6 mm+4 mm, ?4 mm+2 mm, and ?2 mm+0.5 mm size range obtained was 87.60%, 80.93%, and 62.96%, respectively. Further, the prediction model was developed for each size range using a feed-backward artificial neural network (ANN) to consider the back-propagation error technique. For each screening condition, 10 ANN models were developed with the variation in 1–10 different neurons. ANN has provided mathematical models with a 99.9% regression coefficient for predicting each size range’s screening efficiency. Furthermore, the residuals of each optimal ANN model were analyzed using a normal probability plot and histogram. The ANN model’s accuracy was obtained from the residual analysis by evaluating four different model conditions, i.e., independence, homoscedasticity, normality, and mean error. © 2021 Taylor & Francis Group, LLC.
  • No Thumbnail Available
    Item
    Numerical approach for optimization of magnetic roller and evaluating the performance of permanent magnet roller separator through design of experiment
    (Elsevier B.V., 2022) Mohanraj, G.T.; Joladarashi, S.; Hanumanthappa, H.; Shanmugam, B.K.; Vardhan, H.; Naik, G.M.; Bhat Panemangalore, B.P.; Rahman, M.R.
    The present study is focused on numerical analysis of magnetic roller (Mr) using finite element method magnetics (FEMM) software for different magnet disc-to-steel disc (MD-to-SD) width ratios. The numerical (FEMM) results reveal that, the optimized Mr with the MD-to-SD width ratio of 5 mm: 2.5 mm was proved advantageous because of the effective magnetic field (Mf) value of 0.89–2.59 T. The artificial neural network (ANN) modelling technique was used for the prediction analysis of obtained numerical results. Furthermore, by using optimized Mr, the lab-scale permanent magnet roller separator (PMRS) was developed and parametric optimization has been carried out using Taguchi-based L27 orthogonal array design. The significance of parameters on the overall quality of the product has also been evaluated quantitatively by the analysis of variance (ANOVA) method. It was found that the belt thickness was the most influential factor in the product of desired Fe grade and recovery %. The obtained regression coefficient (i.e., R2 = 87.13 and 91.69% for Fe grade and Fe recovery %, respectively) and normal probability plot show the highest correlation between the experimented and predicted data. The results suggested that the numerical approach was suitable for designing optimized Mr for the processing of paramagnetic minerals. © 2022 Faculty of Engineering, Alexandria University
  • No Thumbnail Available
    Item
    An Artificial Neural Network-Based Approach to Predict Blast-Induced Ground Vibrations in Open Cast Coal Mine— A Case Study
    (Pleiades Publishing, 2025) Ravikumar, A.; Vardhan, H.; Shankar, M.U.
    Abstract: This study aims to assess and predict blast-induced ground vibrations of opencast coal mine. The analysis was carried out using two methods i.e. the widely employed empirical vibration predictor known as the USBM (United States Bureau of Mines) equation, and a machine learning model called the artificial neural network (ANN). A dataset including 38 blast vibration recordings was collected and used for the development of an ANN model. Additionally, these datasets were employed to evaluate the site determination constants of the empirical vibration predictor. A total of 27 recordings of blast-induced ground vibrations were gathered from the same opencast coal mine in order to assess the effectiveness of both models. The output (dependent variable) for both models is the peak particle velocity. The effectiveness of the prediction model was evaluated by using commonly used statistical measures, namely the coefficient of determination (). Consequently, the ANN model that was built exhibited more precision in comparison to the existing empirical model. The ANN model exhibited a strong positive relationship between the observed and anticipated peak particle velocity values, as shown by the coefficient of determination (). © Pleiades Publishing, Ltd. 2025.