saurabh Tewari

Dr. saurabh Tewari

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2021 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
RVRachna Vaish
Rachna Vaish
UDU.D. Dwivedi
U.D. Dwivedi
STsaurabh Tewari
saurabh Tewari
STSaurabh Mani Tripathi
Saurabh Mani Tripathi

1 February 2019 in Computers & Industrial Engineering
Verified
Journal Article
Closed access
STsaurabh Tewari
saurabh Tewari
UDUmakant Dhar Dwivedi
Umakant Dhar Dwivedi

4 February 2020 in Journal of Petroleum Exploration and Production Technology
Verified
Journal Article
Open access
PDF file
STsaurabh Tewari
saurabh Tewari
UDUmakant Dhar Dwivedi
Umakant Dhar Dwivedi
Mudstone reservoirs demand accurate information about subsurface lithofacies for field development and production. Normally, quantitative lithofacies modeling is performed using well logs data to identify subsurface lithofacies. Well logs data, recorded from these unconventional mudstone formations, are complex in nature. Therefore, identification of lithofacies, using conventional interpretation techniques, is a challenging task. Several data-driven machine learning models have been proposed in the literature to recognize mudstone lithofacies. Recently, heterogeneous ensemble methods (HEMs) have emerged as robust, more reliable and accurate intelligent techniques for solving pattern recognition problems. In this paper, two HEMs, namely voting and stacking, ensembles have been applied for the quantitative modeling of mudstone lithofacies using Kansas oil-field data. The prediction performance of HEMs is also compared with four state-of-the-art classifiers, namely support vector machine, multilayer perceptron, gradient boosting, and random forest. Moreover, the contribution of each well logs on the prediction performance of classifiers has been analyzed using the Relief algorithm. Further, validation curve and grid search techniques have also been applied to obtain valid search ranges and optimum values for HEM parameters. The comparison of the test results confirms the superiority of stacking ensemble over all the above-mentioned paradigms applied in the paper for lithofacies modeling. This research work is specially designed to evaluate worst- to best-case scenarios in lithofacies modeling. Prediction accuracy of individual facies has also been determined, and maximum overall prediction accuracy is obtained using stacking ensemble.


21 September 2023 in Structural Health Monitoring
Verified
Journal Article
Closed access
VSVinamra Bhushan Sharma
Vinamra Bhushan Sharma
STsaurabh Tewari
saurabh Tewari
SBSusham Biswas
Susham Biswas
ASASHUTOSH SHARMA
ASHUTOSH SHARMA
An extensive network of pipelines is extensively employed worldwide to carry oil and gas fluids over millions of kilometers. The pipeline channel was constructed to resist environmental dynamic loading conditions to provide safe and reliable oil and gas fluids transportation from the production well sites to depot stations installed at sea coastlines. However, pipeline infrastructure damages such as fractures, cracks, leakages, etc., are significant sources of economic losses in pipeline operations. Moreover, pipeline failures can cause considerable ecological catastrophes, human deaths, and financial loss. Important research initiatives have been committed to establishing pipeline breach detection and localization using various techniques to avoid these threats and maintain a secure and dependable pipeline network. This paper reviews different state-of-the-art damage detection methods and their recent advancement with a case study explaining the application of light detection and ranging for pipeline damage detection. The pros and cons of diverse damage detection methods in pipeline networks are also discussed. Research gaps for pipeline damage detection systems are also provided for better understanding and future research.

27 September 2021 in Metals
Verified
Journal Article
Open access
PDF file
VSVinamra Bhushan Sharma
Vinamra Bhushan Sharma
STsaurabh Tewari
saurabh Tewari
SBSusham Biswas
Susham Biswas
BLBharat Lohani
Bharat Lohani
UDUmakant Dhar Dwivedi
Umakant Dhar Dwivedi
JJJae Pil Jung
Jae Pil Jung
Real-time health monitoring of civil infrastructures is performed to maintain their structural integrity, sustainability, and serviceability for a longer time. With smart electronics and packaging technology, large amounts of complex monitoring data are generated, requiring sophisticated artificial intelligence (AI) techniques for their processing. With the advancement of technology, more complex AI models have been applied, from simple models to sophisticated deep learning (DL) models, for structural health monitoring (SHM). In this article, a comprehensive review is performed, primarily on the applications of AI models for SHM to maintain the sustainability of diverse civil infrastructures. Three smart data capturing methods of SHM, namely, camera-based, smartphone-based, and unmanned aerial vehicle (UAV)-based methods, are also discussed, having made the utilization of intelligent paradigms easier. UAV is found to be the most promising smart data acquisition technology, whereas convolution neural networks are the most impressive DL model reported for SHM. Furthermore, current challenges and future perspectives of AI-based SHM systems are also described separately. Moreover, the Internet of Things (IoT) and smart city concepts are explained to elaborate on the contributions of intelligent SHM systems. The integration of SHM with IoT and cloud-based computing is leading us towards the evolution of future smart cities.