Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
8 results
Search Results
Item Sparsity inspired pan-sharpening technique using multi-scale learned dictionary(Elsevier B.V., 2018) Gogineni, R.; Chaturvedi, A.The significant issues in remote sensing image fusion are enhancing the spatial details and preserving the essential spectral information. The classical pan-sharpening methods often incur spectral distortion and still striving to produce the fused images with prominent spatial and spectral attributes. Motivated by the desirable results of sparse representation (SR) theory, a novel pan-sharpening method is developed based on SR of high frequency (HF) components over a multi-scale learned dictionary (MSLD). MSLD technique acquires the capability of extracting the intrinsic characteristics of images, wherein, it possess the features of both multi-scale representation and learned dictionaries. In this paper, the dictionaries are adaptively learned from HF sub-images derived from the two versions of panchromatic image, realized at different spatial resolutions. A fast and computationally efficient algorithm is used for dictionary learning. The notion of SR together with patch recurrence over different scales is incorporated to estimate the high frequency details. The fused image is reconstructed by injecting the band specific spatial details into the up-sampled multi-spectral images. The performance of the proposed method is appraised with the datasets from different satellite sensors namely, QuickBird, IKONOS, WorldView-2 and Pléiades. The observations inferred from visual perception and quality indices analysis manifest the efficiency of proposed method over several well-known methods for the datasets considered at reduced-scale and full-scale resolutions. Further, the quantitative analysis of obtained performance measures confirms the efficacy of the proposed method for the reduced-scale and full-scale data sets. Especially, at a reduced-scale, proposed method yields an optimal value of Correlation coefficient, Structural similarity and Q4. In a comparative sense, usage of the proposed method at full-scale results in 4% and 2.56% improvement in the Spatial distortion index for QuickBird and WorldView-2 data respectively contrary to the best reported outcome obtained from Sparse Representation of injected details (SR-D) scheme. Invariably, for full-scale data, the QNR attains its optimal value. © 2018 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS)Item Application ANN Tool for Validation of LHD Machine Performance Characteristics(Springer, 2020) Balaraju, B.; Raj, G.R.; Murthy, C.S.Survival of industries has become more critical in the present global competitive business environment unless they produce their projected production levels. The accomplishment of this can be possible only by maintaining the men and machinery in an efficient and effective manner. Hence, it is more essential to estimate the performance of utilized equipment for reaching/achieving future goals. The present study focuses on the estimation of underground mining machinery such as the load–haul–dump machine performance characteristics using ‘Isograph Reliability Workbench 13.0’ software. The allocation of best-fit/goodness-of-fit distribution was made by utilizing the Kolmogorov–Smirnov test (K–S) test. The parameters were recorded based on the best-fitted results using the maximum likelihood estimate test. Further, a feed-forward-back-propagation artificial neural network (ANN) tool has been used to develop the models of reliability, availability and preventive maintenance time intervals. The number of neurons was selected with the Levenberg–Marquardt learning algorithm in the hidden layer as the optimal value. The output responses were predicted corresponding to the optimal values. Further, an attempt has been made to validate the computed results with ANN predicted responses. The recommendations are suggested to the industry based on the results for the improvement of system performance. © 2020, The Institution of Engineers (India).Item Optimal design of inverted rotary MR brake with waveform boundary using a novel combined magnetostatic approach(IOP Publishing Ltd, 2020) Saini, R.S.T.; Kumar, H.; Chandramohan, S.In the present work, an inverted rotary drum magneto rheological (MR) brake with waveform arc boundary suitable for prosthetic knee application is optimally designed. Often, the magnetostatic analysis is performed assuming linear magnetic systems and solving a lumped parametric equivalent magnetic model (EMM). Although, this reduces the computational time but compromises the accuracy of the solution. On the other hand, finite element magnetostatic (FEMS) analysis combined with a search-based optimization technique requires more time and effort. In this work, an approach combining the EMM and FEMS methods is proposed to optimally design the MR brake. This method requires the optimization algorithm to maintain an external repository so that individuals which are non-dominated at each generation get stored in the repository and only those individuals are allowed to use FEMS method. This approach reduces the number of function calls made to FEMS method and thus reduces the computational time substantially. A recently proposed multi-objective particle swarm optimization (MOPSO) which evaluates the global best using minimum distance of point of line (MDPL) method is implemented with the proposed combined magnetostatic method. While FEMS method alone resulted in an average computational time of 7.25 h, the proposed method evaluated a similar Pareto front solution in 38 min. Finally, the optimal design is compared to other prosthetic knee MR brakes from the literature. © 2020 IOP Publishing Ltd.Item Design of bypass rotary vane magnetorheological damper for prosthetic knee application(SAGE Publications Ltd, 2021) Saini, R.S.T.; Chandramohan, S.; Sujatha, S.; Kumar, H.Semi-active systems using magnetorheological fluids have been realized in many novel devices such as linear dampers, rotary dampers, brakes, and so on. Rotary vane-type magnetorheological damper is one such device that uses magnetorheological fluid as a hydraulic medium and a controllable magnetorheological valve to generate variable resistance. This device, due to its limited angle motion, lends itself to a natural application for prosthetic knee joint. In this article, a bypass rotary vane-type magnetorheological damper suitable for prosthetic knee device is designed. In the proposed design, the rotary vane chamber and the bypass magnetorheological valve are connected using hydraulic cables and ports. The design of rotary cylinder is implemented based on the largest possible dimensions within the envelope of a healthy human knee, while the magnetorheological valve is designed optimally using a multi-objective genetic algorithm optimization. Off-state braking torque, induced on-state braking torque and mass of the valve are selected as three objectives. The torque and angular velocity requirements of the normal human knee are used as design limits. The optimal solution is chosen from the obtained Pareto fronts by prioritizing the objective of weight reduction of magnetorheological valve. The optimal solution is capable of producing a damping torque of 73 Nm at a design speed of 8.4 rpm and current supply of 1.9 A. Potential benefits offered by this design when compared with multi-plate magnetorheological brake are flow mode operation, large clearance gap, and fewer design components, thus reducing the manufacturing complexity. © The Author(s) 2020.Item Generation of microholes on GFRP composite using ES-µ-ECDM system(Elsevier Ltd, 2022) Bhargav, K.V.J.; Shanthan, P.; Balaji, P.S.; Sahu, R.K.; Sahoo, S.K.Microfeatures fabrication on FRPs is very essential nowadays because of its growing demand in various industries like aerospace, automobile, space, marine, etc. Glass fiber reinforced plastic (GFRP) composite is one among the FRPs that has many potential applications with extraordinary physical, chemical and mechanical properties. Generation of microholes on GFRP composite has gained its pace in recent years because of its applications in circuit boards and filters in biomedical applications. This study focuses on the generation of microholes in GFRP composite using an in-house developed electrolyte-sonicated micro-electrochemical discharge machining (ES-µ-ECDM) system. The process parameters voltage (V), concentration (wt%), and feed rate (µm/s) are selected at three levels for performing experiments using FCC-RSM modeling. The machining responses material removal rate (MRR) and overcut (OC) are analyzed. A RSM-based regression model is developed, and a multi-objective optimization using the MOJAYA algorithm is employed to obtain a set of non-dominated Pareto optimal solutions. The Pareto optimal solution set showed a feed rate of 5 µm/s should be employed for better MRR and OC. The SEM micrographs have shown a feed rate of 5 µm/s produced smooth surfaces at voltages and concentrations less than 55 V and 17.5 wt%, respectively. © 2022 Elsevier LtdItem Optimal design of ow mode semi-active prosthetic knee dampers(Sharif University of Technology, 2022) Saini, R.S.T.; Kumar, H.; Chandramohan, S.Magnetorheological (MR) fluid devices operate in four modes: ow, shear, squeeze, and pinch. Among these, the flow mode is the most efficient one and results in large field-induced pressure differences. Despite being the least efficient, shear mode is the most commonly used in numerous applications, including prosthetic knees, due to its ease of construction. Additionally, shear mode designs require larger shear areas and reduced fluid gap tolerance compared to their ow mode counterparts, resulting in a complex design such as the commercially available multi-plate MR brake. Therefore, in this study, two ow mode designs, twin-rod and rotary vane MR dampers, are optimally designed for prosthetic knee application. The optimal designs obtained from solving a multi-objective particle swarm optimization problem are fabricated and experimentally characterized for various harmonic excitations of varying amplitudes, frequencies, and currents. The optimal designs are compared with many MR fluid-based prosthetic knee design configurations. Based on the results, a twin-rod MR damper with a mass of 0.71 kg and a damping force of 1020 N at 1 A is identified as the optimal design configuration for prosthetic knee application. © 2022 Sharif University of Technology. All rights reserved.Item A machine learning algorithm for scheduling a burn-in oven problem(Inderscience Publishers, 2023) Mathirajan, M.; Reddy, S.; Vimala Rani, M.V.; Dhaval, P.This study applies artificial neural network (ANN) to achieve more accurate parameter estimations in calculating job-priority-data of jobs and the same is applied in a proposed dispatching rule-based greedy heuristic algorithm (DR-GHA) for efficiently scheduling a burn-in oven (BO) problem. The integration of ANN and DR-GHA is called as a hybrid neural network (HNN) algorithm. Accordingly, this study proposed eight variants of HNN algorithms by proposing eight variants of DR-GHA for scheduling a BO. The series of computational analyses (empirical and statistical) indicated that each of the variants of proposed HNN is significantly enhancing the performance of the respective proposed variants of DR-GHA for scheduling a BO. That is, more accurate parameter estimations in calculating job-priority-data for DR-GHA via back-propagation ANN leads to high-quality schedules w.r.t. total weighted tardiness. Further, proposed HNN variant: HNN-ODD is outperforming relatively with other HNN variants and provides very near optimal/estimated solution. © © 2023 Inderscience Enterprises Ltd.Item An adaptive modeling for bifacial solar module levelized cost and performance analysis for mining application(John Wiley and Sons Ltd, 2024) Shiva Kumar, B.S.; Kunar, B.M.; Murthy, C.S.N.Power density and efficiency typically dominate design approaches for power electronics. However, cost optimality is in no way guaranteed by these strategies. A design framework that minimizes the (i) levelized cost of electricity (LCOE), (ii) collection of light, and (iii) irradiance of the generation system is proposed as a solution to this flaw. From an improvement of the swarm behavior optimization model to get a minimum LCOE of solar panel, we design to optimize height, tilt angle, azimuth angle, and some parameters to solve the objective function and LCOE improvement problem to obtain the optimal design problem. In adaptive salp swarm optimization (ASSO), this change's proposed model producer swarm behavior is regarded as an adaptive process that keeps the algorithm from prematurely converging during exploration. The proposed algorithm's performance was confirmed using benchmark test functions, and the results were compared with those of the salp swarm optimization (SSO) and other efficient optimization algorithms. LCOE condition as far as “land-related cost” and “module-related cost” demonstrates that the optimal design of bifacial farms is determined by the interaction of these parameters. This proposed model can be used to evaluate visibility on building surfaces that are suitable for mining applications like crushing. Experimentation results show Minimum LCOE AS 0.05 (€/Kw)minimum irradiance and collection light as 336.23(w/m2) and 83.02%n proposed framework model. The swarm optimization method is contrasted with the optimal parameters derived from a conventional solver. © 2023 John Wiley & Sons Ltd.