Papers by SIMRANJIT SINGH
Neural network prediction of slurry erosion of heavy-duty pump impeller/casing materials 18Cr-8Ni, 16Cr-10Ni-2Mo, super duplex 24Cr-6Ni-3Mo-N, and grey cast iron
Wear, 2021
Abstract The aim of the present study is to develop a neural network model for the prediction of ... more Abstract The aim of the present study is to develop a neural network model for the prediction of slurry erosion (SE) of heavy-duty pump impeller steels and casing material. The heavy-duty pump impeller has a wide range of applications like slurry transportation system and coal conveying system of thermal power stations, and various other industries like mining, chemical and marine industry. In the present study, the slurry erosion performance of three different pump impeller steels namely 18Cr-8Ni, 16Cr-10Ni-2Mo and super duplex 24Cr-6Ni-3Mo-N, and one pump casing material namely Grey cast iron was tested. The SE experiments were carried out on a laboratory scale pot tester using the sand as an erodent. A data set was produced to develop a prediction-based neural network (NN) model and 70% of this data set was used as input to NN model. The learning of NN model was based on an artificial neural network (ANN) and used to build a prediction model that can predict the results while the input data was supplied to it. Firstly, the data were divided into training, validation, and testing. The NN model was trained on 70% of the original dataset and validated by another 15% data. A total of 30 training epochs were performed for training, testing, and validation of the model. The validation of the model indicates that the build NN model was the best fit and comprises no over-fitting and under-fitting issues. In the end, the prepared NN model was given the remaining 15% data for testing. It outputs the corresponding values for each input. These predicted values are then compared with the actual ground truth to check the robustness of the designed model. The various measures used for evaluating the model were R2 (coefficient of determination), Root mean square error, etc. Results show that 18Cr-8Ni steel exhibits the best SE performance followed by 16Cr-10Ni-2Mo, 24Cr-6Ni-3Mo-N, and Grey cast iron.
Neural network supported study on erosive wear performance analysis of Y2O3/WC-10Co4Cr HVOF coating
Journal of King Saud University - Engineering Sciences, 2021
Multimedia Tools and Applications, 2020
Classification of Hyperspectral images is mostly based on the spectral-spatial features in existi... more Classification of Hyperspectral images is mostly based on the spectral-spatial features in existing classification techniques. The captured Hyperspectral images from satellites may contain some noisy bands due to water absorption. The process of radiometric and atmospheric corrections leads to the removal of useful bands present in the acquired HSI. In this paper, a novel framework is proposed in which interpolation is used to accommodate the loss of noisy bands. Further, the extraction of hybrid features is performed using PCA and LPP to preserve spatial information, and these features are passed as input to the machine learning models. The proposed framework is compared with the existing spectralspatial and spectral based frameworks by using the standard datasets-Indian Pines, Salinas, Pavia University, and Kennedy Space Centre. The accuracy of the classification is increased significantly when the proposed framework is blended with state-of-art classifiers.
Ionics, 2018
Gel polymer electrolytes (GPEs) were prepared by dissolving lithium tetrafluoroborate (LiBF 4) sa... more Gel polymer electrolytes (GPEs) were prepared by dissolving lithium tetrafluoroborate (LiBF 4) salt, poly(methylmethacrylate) (PMMA) polymer and distinct non-volatile solvents propylene carbonate (PC), and-N,N-dimethylformamide (DMF) in single as well as binary solvent mixtures. Ionic conductivities of 8.93 mS/cm and 6.68 mS/cm at 25°C have been obtained for gel polymer electrolytes for 10 wt% PMMA in the solution of LiBF 4 in binary solvent mixture of PC:DMF in (1:1) and (2:1) volume ratios respectively. The dispersion of nano-sized silica in gel polymer electrolyte not only exhibits small change in ionic conductivity but also enhances the mechanical strength as well as viscosity of gel polymer electrolytes. At room temperature, the ionic conductivity has been found to be 8.00 mS/cm for 6 wt% nano-sized silica in GPEs. Fourier-transform infrared (FTIR) spectroscopic studies have been used to scrutinize the corroboration of the complexation between PMMA, LiBF 4 , PC, DMF, PC:DMF, and SiO 2. The interactions between salt and solvents in liquid electrolytes have also been analyzed by FTIR spectroscopy illustrating the strong interaction between lithium salt and solvent molecules. The appearance/disappearance and shifting of some peaks confirm the interaction among the constituents of nano-dispersed gel polymer electrolytes. The mechanical strength was confirmed by dynamic mechanical analysis (DMA) and viscosity [η PC:DMF (2:1) > η PC:DMF (1:1) > η PC ] for nano-dispersed silica-based gel polymer electrolytes. The electrical and mechanical stability with high ionic conductivity for such gel polymer electrolytes makes these electrolytes suitable for many device applications like high energy density lithium-ion batteries, supercapacitors, electro-chromic devices etc.
National Academy Science Letters, 2018
In this paper, the performance of return-to-zero/ differential quadrature phase shift keying/pola... more In this paper, the performance of return-to-zero/ differential quadrature phase shift keying/polarization shift keying (RZ/DQPSK/PolSK) orthogonal modulation format is investigated in hybrid optical time division and wavelength division multiplexing (OTDM-WDM) technique to increase the spectral efficiency of the system. The error free performance is achieved over 140 km transmission with the acceptable bit error rate (* 10-12). The original contribution of this paper is to propose a bandwidth efficient OTDM-WDM system that could be projected even in high speed scenario and expected to be more technical viable due to use of optical orthogonal modulation formats.
Multimedia Tools and Applications, 2018
Background Hyperspectral imaging is emerging as a promising approach for plant disease identifica... more Background Hyperspectral imaging is emerging as a promising approach for plant disease identification. The large and possibly redundant information contained in hyperspectral data cubes makes deep learning based identification of plant diseases a natural fit. Here, we deploy a novel 3D deep convolutional neural network (DCNN) that directly assimilates the hyperspectral data. Furthermore, we interrogate the learnt model to produce physiologically meaningful explanations. We focus on an economically important disease, charcoal rot, which is a soil borne fungal disease that affects the yield of soybean crops worldwide. Results Based on hyperspectral imaging of inoculated and mock-inoculated stem images, our 3D DCNN has a classification accuracy of 95.73% and an infected class F1 score of 0.87. Using the concept of a saliency map, we visualize the most sensitive pixel locations, and show that the spatial regions with visible disease symptoms are overwhelmingly chosen by the model for classification. We also find that the most sensitive wavelengths used by the model for classification are in the near infrared region (NIR), which is also the commonly used spectral range for determining the vegetative health of a plant. Conclusion The use of an explainable deep learning model not only provides high accuracy, but also provides physiological insight into model predictions, thus generating confidence in model predictions. These explained predictions lend themselves for eventual use in precision agriculture and research application using automated phenotyping platforms.
Ionics, 2017
Nano-sized silica poly(methylmethacrylate)-based gel electrolyte containing lithium hexafluoropho... more Nano-sized silica poly(methylmethacrylate)-based gel electrolyte containing lithium hexafluorophosphate (LiPF 6) was synthesized by using different binary solvent mixture (propylene carbonate(PC) and dimethylformamide (DMF) in different volume ratio). Role of DMF in PC: Higher DMF content in PC-based electrolyte shows higher ionic conductivity at all polymer content and at wide temperature regions (10-70°C). A small increment in ionic conductivity at lower content of polymer in liquid/gel electrolyte was observed and having maximum conductivity of 13.12 mS/cm at 25°C. Stability (mechanically and electrically), viscosity and ionic conductivity of gel electrolytes were improved with the addition of nano-sized silica at ambient temperature. Ionic conductivity of nano-sized silica-based gel electrolyte does not change much over 5 o-70°C temperature range and is factor-wise only which make indispensable in different electrochemical devices. Also polymer gel electrolyte membranes as such and with dispersed silica nano-particles were characterized through scanning electron microscope to study the morphology of gel matrix.
IEEE Transactions on Vehicular Technology, 2012
This paper analyzes and evaluates the performance of digital communication systems that operate o... more This paper analyzes and evaluates the performance of digital communication systems that operate over the α−η−μ fading channels. More specifically, we derived novel, unified, and exact closed-form analytical expressions for the cumulative density function (CDF), the moment generating function (MGF), the average channel capacity, and the average symbol error probability (SEP) for several coherent and non-coherent modulation schemes. Note that, the derived expressions are valid for arbitrary values of the fading parameters. The derived expressions are then used to study the implication of the fading parameters on the system performance. In addition, the performance over other well-known fading channels such η−μ and α−μ, and their inclusive special cases can be analyzed using our results. To validate the correctness of our derivations, the numerical results are compared with Monte-Carlo simulation results. Both results are in perfect agreement over a wide range of average signal-to-noise ratio (SNR) and different values of the fading parameters. Index Terms-Average channel capacity, symbol error probability, moment generating function, outage probability. I. INTRODUCTION I N WIRELESS communication systems, the overall system performance is highly affected by the statistical modeling and characterization of the wireless channel between the transmitterand the receiver-side. Therefore, modeling of such a wireless channel plays an important role in the design and in the performance evaluation of communication systems. In the literature, there are different channel models that accurately describe different types of phenomena such as multi-path, shadowing, large-and small-scale fading [1]. In the literature, there are many different performance metrics that can be used to analyze communication systems, for example, outage probability, average symbol error probability (SEP), average bit error probability (BEP), amount of fading, and average channel capacity. Generally, obtaining closed-form expressions for the previously mentioned metrics is a challenging problem. However, this challenge becomes very difficult when dealing with complicated generalized fading channel models such as the α−λ−μ 1 , the α−η−μ, the α−κ−μ, the α−λ−μ−η 1 , the η−λ−μ 1 , the λ−μ 1 , the κ−μ and the η−μ fading channels [2-7].
Alterations in Serum Lipid Profile Patterns in Oral Lichen Planus
American Journal of Clinical Dermatology, 2012
Oral lichen planus (OLP) is a chronic inflammatory disorder. Recently, a case-control study found... more Oral lichen planus (OLP) is a chronic inflammatory disorder. Recently, a case-control study found that lichen planus was associated with dyslipidemia in a large series of patients. However, no data were presented about lipid values in patients and controls. The aim of this study was to investigate the hypothetical association between OLP and dyslipidemia. The study included a total of 400 patients (200 with OLP and 200 controls with other oral diseases) and investigated the prevalence of dyslipidemia. The variables analyzed were age, sex, tobacco and alcohol consumption, clinical form of OLP and lipid profiles. A 54% prevalence of dyslipidemia was found (58% among the OLP group and 50% in the control group). Statistically significant differences in high-density lipoprotein were found between OLP patients and the control group (p = 0.003). A logistic regression model for presence/absence of cardiovascular risk (Castelli's atherogenic index of ≥ 5.1 for men and ≥ 4.5 for women) found statistically significant differences for sex and tobacco consumption. The study found a higher atherogenic index amongst OLP patients.
Uploads
Papers by SIMRANJIT SINGH