Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item Parallel method for discovering frequent itemsets using weighted tree approach(2009) Kumar, P.; Ananthanarayana, V.S.Every element of the transaction in a transaction database may contain the components such as item number, quantity, cost of the item bought and some other relevant information of the customer. Most of the association rules mining algorithms to discover frequent itemsets do not consider the components such as quantity, cost etc. In a large database it is possible that even if the itemset appears in a very few transactions, it may be purchased in a large quantity. Further, this may lead to very high profit. Therefore these components are the most important information and without which it may cause the lose of information. This motivated us to propose a parallel algorithm to discover all frequent itemsets based on the quantity of the item bought in a single scan of the database. This method achieves its efficiency by applying two new ideas. Firstly, transaction database is converted into an abstraction called Weighted Tree that prevents multiple scanning of the database during the mining phase. This data structure is replicated among the parallel nodes. Secondly, for each frequent item assigned to a parallel node, an item tree is constructed and frequent itemsets are mined from this tree based on weighted minimum support. © 2009 IEEE.Item DQ modeling of induction motor for virtual flux measurement(2010) Sushma, P.; Rajalakshmi Samaga, R.; Vittal, K.P.Three phase induction motors are continuing to remain as work horses in industrial applications. The accurate behavioral modeling of induction motor helps in designing controller for the machine and also useful in detection of faults in machines. Almost all faults in the induction motor affect the flux in the air gap. These fluxes can be measured virtually using dq model of induction motor by feeding voltage and current values extracted in real time and stored. In this paper, DQ model is developed in stator reference frame using MATLAB-SIMULINK platform and a data acquisition system supported with LabVIEW is used to obtain motor terminal voltage and current signals which are useful in estimation of flux in an actual machine. ©2010 IEEE.Item Reliability Analysis of LHD Machine - A Case Study(Springer Nature, 2020) BalaRaju, J.; Govinda Raj, M.; Murthy, C.S.N.In the present global scenario, survival of the industry is more critical unless it produces their intended targets. Accomplishment of expected rate of production levels are depends on the performance of equipment. Hence, it is very important to predict the maintenance schedules for replacement or repair actions of the defective parts. Keeping in view, every industry is constantly looking for enhancement equipment life. Reliability analysis is one of the well appropriated techniques used to estimate the life of the equipment. In this paper, performance of Load-Haul-Dumper (LHD) has been analyzed. Renewal process approach has been utilized for reliability investigation. Best fit distribution of data sets were made by the utilization of Kolmogorov-Smirnov (K-S) test. Parametric estimation of theoretical probability distributions was done by utilizing Maximum Likelihood Estimate (MLE) method. Reliability of each individual sub-system has been computed according to the best fit distribution. In addition to that, reliability based preventive maintenance (PM) time schedules were calculated for the expected 90% reliability level. The possible recommendations were suggested for improvement of reliability level. © 2020, Springer Nature Switzerland AG.Item Image Captioning with Attention Based Model(Institute of Electrical and Electronics Engineers Inc., 2021) Yv, S.S.; Choubey, Y.; Naik, D.Defining the content of an image automatically in Artificial Intelligence is basically a rudimentary problem that connects computer vision and NLP (Natural Language Processing). In the proposed work, a generative model is presented by combining the recent developments in machine learning and computer vision based on a deep recurrent architecture that describes the image using natural language phrases. By integrating the training picture, the trained model maximizes the likelihood of the target description sentence. The efficiency of the model, its accuracy and the language it learns is only dependent on the image descriptions, which was demonstrated by experiments performed on several datasets. © 2021 IEEE.Item Reliability block diagram (RBD) and fault tree analysis (FTA) approaches for estimation of system reliability and availability – a case study(Emerald Group Holdings Ltd., 2021) Balaraju, B.; Raj, G.R.; Ch.S.N, M.Purpose: In the present worldwide situation, the survival of a business is a major crucial aspect. The business cannot be succeeded unless it produces the anticipated production levels. Achievement of this can be possible only by maintaining the equipment into an adequate level. Load-Haul-Dumpers (LHDs), as the main workhorse and massive transporting machines, are highly utilized in underground mining operations. Despite the usage of LHDs, these are prone to the uneven and unexpected occurrence of potential failures. These are causes to minimize the production and productivity of capital intensive equipment. To get a good profitability index, it is very necessary to have the required levels of equipment reliability and availability. Estimation of reliabilities and availabilities play a critical role in the performance evaluation of equipment. Design/methodology/approach: By keeping the significance of the present research work in view in this research paper one of the well appropriate techniques such as fault tree analysis (FTA) was utilized to assess the reliability of the LHD system based on the function flow diagram. Best fit distribution of data sets were made by the utilization of Kolmogorov–Smirnov (K-S) test. Parametric estimation of theoretical probability distributions was done by utilizing the maximum likelihood estimation (MLE). Failure rate of each LHD system has computed based on the best fit results from “Isograph Reliability Workbench 13.0”. Reliability configuration of each LHD system has modeled using reliability block diagram (RBD), as well as the FTA. Findings: Independent and identical distribution (IID) assumption of data sets was validated through statistic U-test (Chi Squared test). On the basis of test results, the data sets are in accordance with IID assumption. Therefore renewal process approach has been utilized for further investigation. Allocations of best fit distribution of data sets were made by the utilization ofK-S test. Parametric estimation of theoretical probability distributions was made by utilizing maximum likelihood estimation (MLE) method. Reliability of each individual subsystem has been computed according to the best fit distribution. The deductive method called RBD was utilized to investigate the given system reliability by analyzing with graphical representations of logic system and observed highest percentage of reliability as 69.44% (LH29). FTA has been utilized to investigate the availability percentage of a system and observed highest percentage value as 79.51% (LH29). This technique also helps to identify the most critical parts/cut sets by using Fussell-Vesely (F-V) importance measure. Research limitations/implications: As the reliability analysis is one of the complex techniques, it requires strategic decision-making knowledge for the selection of methodology to be used. As the present case study was from a public sector company, operating under financial constraints the conclusions/findings may not be universally applicable. Originality/value: The present study throws light on this equipment that need a tailored maintenance schedules, partly due to the peculiar mining conditions, under which they operate. This analysis provides the information on several aspects such as present working condition of the machines, occurrence of various potential failure modes, influence of failure modes on its performance and reliable life aspects etc. Also, these investigations asses the forecasting of necessary managerial practices or control measures like possible design modifications and replacement actions of components to ensure the required levels of availability and utilization of the equipment. Both qualitative and quantitative analysis of FTA has been performed to determine the minimal/most influencing cut sets of the system and to estimate overall system availability within the work environment. Based on the computed results reasons for performance drop of each machine was identified and suitable recommendations were suggested to improve the performance of capital intensive systems. © 2020, Emerald Publishing Limited.