Indian Institute of Technology Kharagpur

About: Indian Institute of Technology Kharagpur is a education organization based out in Kharagpur, India. It is known for research contribution in the topics: Computer science & Dielectric. The organization has 16887 authors who have published 38658 publications receiving 714526 citations.

A genetic algorithms based multi-objective neural net applied to noisy blast furnace data

Abstract: A genetic algorithms based multi-objective optimization technique was utilized in the training process of a feed forward neural network, using noisy data from an industrial iron blast furnace. The number of nodes in the hidden layer, the architecture of the lower part of the network, as well as the weights used in them were kept as variables, and a Pareto front was effectively constructed by minimizing the training error along with the network size. A predator-prey algorithm efficiently performed the optimization task and several important trends were observed.

Influence of bainite/martensite-content on the tensile properties of low carbon dual-phase steels

Abstract: This investigation aims to examine structure–property relations of ferrite–bainite dual-phase (FBDP) steels and to compare these against that of ferrite–martensite dual-phase (FMDP) steels. For this purpose, a series of FBDP and FMDP steels containing wide variation (20–90%) of the harder constituents have been prepared from a low carbon Nb-micro-alloyed base material by suitable heat treatments. Hardness and tensile properties of the developed steels have been examined against the volume fraction of bainite or martensite. The nature of variation of the estimated mechanical properties such as hardness, yield and tensile strength, percentage elongation and strain-hardening exponent with the amount of the harder constituents of the FBDP and FMDP steels exhibits subtle to significant differences. These differences have been explained using the influence of the nature of the microstructural constituents and their mutual interactions. Low carbon FBDP steel with 60–70% bainite appears to possess excellent potential for structural applications.

Hydrothermal carbonization of renewable waste biomass for solid biofuel production: A discussion on process mechanism, the influence of process parameters, environmental performance and fuel properties of hydrochar

Abstract: The energy demand of the world is expected to reach 739 quadrillions BTU in 2040, which therefore demand for exploring more alternative source of renewable energy. Waste biomass though vast in reserve for generating renewable energy has its own downside. High moisture, fibrous nature, high bulk volume, hydrophilic nature and low calorific value are some of the inferior quality of waste biomass which creates bottleneck for easy renewable energy generation. Pre-treatment of biomass to overcome these challenges has created a new research interest. Among the treatment options available, the hydrothermal carbonization (HTC) method, which can process wet waste has become the most preferred choice among researchers recently. The HTC eliminates energy-intensive pre-drying process needed for other treatment methods such as pyrolysis, dry torrefaction and incineration. Through this article, we attempt to provide a detailed review of how renewable biomass can be effectively used to produce renewable energy by improving their inherent inferior characteristics. The review also highlights bottlenecks that constrain the deployment of renewable energy using HTC methods. The scope of further research direction is well identified in this review. The paper also present recent advancements which are filling the knowledge gap of HTC technology that were there earlier. Critical analysis of microwave assisted HTC and conventional heated HTC is also presented in this review. The analysis in this paper reveals that biomass is a valuable resource, and should be explored to take advantage of its renewable energy generation potential. The HTC method of biomass upgradation improves transport, storage and fuel characteristics by improving grindability, pellets durability, hydrophobicity, energy density, combustion behaviour and calorific value, and also helps in improving the environmental performance of solid fuel produced. Despite the fact that the technology is in the early stage of development and there still exist knowledge gap and shortcomings, the vast literature reviewed suggests that it has a potential of being future technology. Therefore, it needs further investigation which should fill existing shortcoming of the technology.

Drought Forecasting Using a Hybrid Stochastic and Neural Network Model

Abstract: Treating the occurrence and severity of droughts as random, a hybrid model, combining a linear stochastic model and a nonlinear artificial neural network (ANN) model, is developed for drought forecasting. The hybrid model combines the advantages of both stochastic and ANN models. Using the Standardized Precipitation Index series, the hybrid model as well as the individual stochastic and ANN models were applied to forecast droughts in the Kansabati River basin in India, and their performances were compared. The hybrid model was found to forecast droughts with greater accuracy.

EEG signal analysis for the assessment and quantification of driver’s fatigue

Abstract: Fatigue in human drivers is a serious cause of road accidents. Hence, it is important to devise methods to detect and quantify the fatigue. This paper presents a method based on a class of entropy measures on the recorded Electroencephalogram (EEG) signals of human subjects for relative quantification of fatigue during driving. These entropy values have been evaluated in the wavelet domain and have been validated using standard subjective measures. Five types of entropies i.e. Shannon’s entropy, Renyi entropy of order 2 and 3, Tsallis wavelet entropy and Generalized Escort-Tsallis entropy, have been considered as possible indicators of fatigue. These entropies along with alpha band relative energy and ( α + β )/ δ 1 relative energy ratio have been used to develop a method for estimation of unknown fatigue level. Experiments have been designed to test the subjects under simulated driving and actual driving. The EEG signals have been recorded along with subjective assessment of their fatigue levels through standard questionnaire during these experiments. The signal analysis steps involve preprocessing, artifact removal, entropy calculation and validation against the subjective assessment. The results show definite patterns of these entropies during different stages of fatigue.