1,544 research outputs found
Forecasting of Time-Dependent Scour Depth based on Bagging and Boosting Machine Learning Approaches
No full textForecasting the time-dependent scour depth (dst) is very important for the protection of bridge structures. Since scour is the result of a complicated interaction between structure, sediment, and flow velocity, empirical equations cannot guarantee an advanced accuracy, although they would preserve the merit of being straightforward and physically inspiring. In this article, we propose three ensemble machine learning methods to forecast the time-dependent scour depth at piers: extreme gradient boosting regressor (XGBR), random forest regressor (RFR), and extra trees regressor (ETR). These models predict the scour depth at a given time, dst, based on the following main variables: the median grain size, d50, the sediment gradation, σg, the approach flow velocity, U, the approach flow depth y, the pier diameter Dp, and the time t. A total of 555 data points from different studies have been taken for this research work. The results indicate that all the proposed models precisely estimate the time-dependent scour depth. However, the XGBR method performs better than the other methods with R = 0.97, NSE = 0.93, AI = 0.98, and CRMSE = 0.09 at the testing stage. Sensitivity analysis exhibits that the time-dependent scour depth is highly influenced by the time scale
Experimental investigation and comparative machine learning prediction of the compressive strength of recycled aggregate concrete incorporated with fly ash, GGBS, and metakaolin
No full textRecycled aggregates (RA) can provide a sustainable solution for replacing natural aggregates (NA) in the concrete mix. However, the stakeholders and inspection professionals lack confidence in predicting their compressive strength (CS) due to limited databases. Most of them solely focus on the concrete mix with natural aggregates only. Even though numerous researchers have proposed alternative mix designs for recycled aggregate concrete (RAC), utilizing RA is still not practicable. One of them is the lack of a simple and effective compressive strength prediction that uses RAC. This study focuses on the application of six different machine learning (ML) techniques: XG Boost, K-nearest neighbors (KNN), artificial neural network (ANN), support vector machine (SVM), linear regression, decision tree (DT), and random forest (RF), for predicting the CS of concrete mixed with RA. The input variables are weights of coarse RA, Portland cement, fly ash, ground granulated blast furnace slag, and metakaolin. The database is prepared by experimental testing of concrete cube specimens for 188 mixes in the concrete technology laboratory of IIT Bhubaneswar. For most of the mixes, coarse RA was the only coarse aggregate to get the compressive strength. It includes variations in water/binder from 0.25 to 0.75. It was observed that the addition of flyash, GGBS, and MK significantly impacted the CS at a later age. The ML model indicates that an accuracy of 0.95 was achieved on the current test database for predicting CS. Among all the machine-learning algorithms, XG Boost can be used for forecasting compressive strength since it provides excellent accuracy with minimal computation. This research can be used as a data-driven novel solution for developing concrete mixes to achieve a specified CS. However, this work employs only experimental data as a machine learning input, which can be improved further by including databases from the literature
Hydrothermal liquefaction of biomass for production of diluents for bitumen transport
Full text linkThis study explores the hydrothermal liquefaction (HTL) of wood chips to bio-crude followed by upgrading to diluents, which are used to transport bitumen through pipelines. In this study, we considered a 2000 dry t day-1 plant capacity with two scenarios. The first scenario uses hydrogen for upgrading from the on-site hydrogen production plant (i.e., the hydrogen production scenario) and the other relies on procuring hydrogen from an external source (i.e., the hydrogen purchase scenario). We developed a data-intensive process model for HTL and used it to estimate plant capital costs. Project investment costs for the hydrogen production and hydrogen purchase scenarios are 559.67 and 429.13 M L-1, respectively, at a 95% confidence interval. The sensitivity analysis shows that diluent yield and internal rate of return (IRR) have the highest impact on the PV of the diluent, followed by capital cost and biomass cost. The optimum plant size at which the cost of production is lowest is 4000 dry t day-1 for PVs of 0.82 L-1 for the hydrogen production and purchase scenarios, respectively. This study offers insights into the techno-economic feasibility of producing diluents from HTL. The results of the study could help in the production of diluents for bitumen transportation for the oil sands industry and help reduce the overall greenhouse gas (GHG) footprint of the oil and gas sector
Torsional springback analysis in thin tubes with non-linear work hardening / Vikas Kumar Choubey, Mayank Gangwar and J. P. Dwivedi
Full text linkA theoretical analysis of the springback of thin tubular sections of non linear work-hardening materials under torsional loading has been carried out. The non-linear behavior of the material is approximated by using Modified Ludwik type stress-strain relation. The theoretical analysis is supported by experimental results for different tubular section viz. square, triangular and rectangular
sections of different thicknesses. Finally analytical generalized expressions relating angle of twist to twisting moment and residual/springback angle of twist per unit length for thin tubular bars under plastic torsion are obtained in non-dimensionalized form. A comparison between the results obtained for thin tubes on non-linear and linear work-hardening material loaded under torsion is also made
Springback analysis of thin tubes under torsional loading / Vikas Kumar Choubey, Mayank Gangwar and J. P. Dwivedi
Full text linkSpringback, the elastic recovery of material on the release of applied load, is the major factor in obtaining the accurate and consistent dimensions of the final parti The mechanics of springback is essential for its effective prediction and compensation. The aim of the paper is to present a theoretical analysis of the torsional springback in thin tubes ofbi-linear work hardening material. The
bi-linear behavior of the material is approximated by using modified Ludwik type stress-strain relation. The theoretical analysis is based on membrane and sand heap analogies. The analytical calculations establishes relationship for angle of twist to twisting moment and residual/springback angle of twist per unit length for thin tubes under plastic torsion in non-dimensionalized form.
The theoretical analysis is supported by experiments performed on thin tubes of mild steel and aluminium with different geometry and mechanical properties. A comparison between the results obtained for thin tubes on bi-linear and nonlinear work-hardening material loaded under torsion is also made
Monitoring sugar release during pipeline hydro-transport of wheat straw
Full text linkPipeline transport of biomass is an economically viable and technically feasible approach to replace conventional truck delivery approach and make the biomass-based energy industry more competitive with fossil fuel-based plants. A 25 m long and 50 mm diameter closed-circuit pipeline facility was fabricated to experimentally investigate the mechanical and chemical feasibility of transporting agricultural residue biomass-water mixtures (slurries) through pipelines. This research used the pipeline facility to study the loss of sugars (glucose and xylose) while pipelining wheat straw-water mixtures. The release of similar sugars was also measured in shake-flask cultures under controlled conditions. The output of this research is important for bio-processing facilities as a high sugar content slurry would improve the yield of biofuels produced from pipelined lignocellulosic materials. After several hours of recirculating throughout the pipeline, as well as shaking in the flask, a drop in sugar concentration was detected. A microbiological analysis performed on both slurries proved the decline to be due to microbial proliferation. Accordingly, diethyl pyrocarbonate oxidizing antimicrobial agent and glutaraldehyde and bronopol non-oxidizing agents were alternatively tested to restrict microbial proliferation. These agents demonstrated reduced sugar loss and, in turn, showed an enhancement in the yield of glucose and xylose. This research aims at maximizing possible sugar release through mechanical action throughout the pipeline in the presence of antimicrobial compounds, which would increase the yield of biofuel produced from pipelined agricultural residue biomass
Assessment of renewable energy technologies for charging electric vehicles in Canada
Full text linkElectric vehicle charging by renewable energy can help reduce greenhouse gas emissions. This paper presents a data-intensive techno-economic model to estimate the cost of charging an electric vehicle with a battery capacity of 16 kWh for an average travel distance of 65 km from small-scale renewable electricity in various jurisdictions in Canada. Six scenarios were developed that encompass scale of operation, charging time, and type of renewable energy system. The costs of charging an electric vehicle from an off-grid wind energy system at a charging time of 8 hours is 56.8-58.5 cents/km in Montreal, Quebec, and 58.5-60.0 cents/km in Ottawa, Ontario. However, on integration with a small-scale hydro, the charging costs are 9.4-11.2 cents/km in Montreal, 9.5-11.1 cents/km in Ottawa and 10.2-12.2 cents/km in Vancouver, British Columbia. The results show that electric vehicle charging from small-scale hydro energy integration is cost competitive compared charging from conventional grid electricity in all the chosen jurisdictions. Furthermore, when the electric vehicle charging time decreases from 8 to 4 hours, the cost of charging increases by 83% and 11% from wind and hydro energy systems, respectively
An Adaptive Zooming Algorithm for Images
No full textImage zooming is the process of enlarging the image to as desired magnification
factor. But while enlarging an image there are few parameters that we have to keep in
mind. When the image is zoomed, artifacts like blurring, jagging and ghosting may
arise. So the main focus is on the reduction of these artifacts.
Our algorithm deals with the edges. It is basically designed to preserve the edges.
It’s as adaptive zooming algorithm which focuses on preserving edges. Our algorithm
reduces the jagging. Blurring is reduced a lot in our algorithm.
To compare our algorithm with existing algorithms, we have taken few real world
images and results are visually compared. And we have come to the decision that our
algorithm is better than the traditional methods. We have compared the images by
four ways – MAE, MSE, CCC, and PSNR
Video Documentation of Maemo Final Presentation
No full textThis video documents the final presentation of Maemo (group members Kumar Mayank, Sui Yan, Zhenan Hong, Manaswi Shukla, and Janani B.S) in SI 682, Interface and Interaction Design.http://deepblue.lib.umich.edu/bitstream/2027.42/61389/3/si682maemo.av
A review on the current status of various hydrothermal technologies on biomass feedstock
No full textHydrothermal processing, a thermochemical approach, is an excellent method of converting energy-rich biomass into useful products. This approach offers the advantage of handling biomass with relatively high moisture content by precluding an energy-intensive pretreatment step. Hydrothermal processing is of world-wide interest in view of depleting fossil-fuel reserves and increased environmental greenhouse gas emissions. There is potential to develop this novel technology at demonstration scale. This paper reviews the three hydrothermal technologies, namely hydrothermal liquefaction, gasification and carbonization, to provide insight into the likelihood of commercialization. The study discusses the role of different process parameters that have key impacts on the quality and yield of the desired products. This study also identifies the gaps in the literature including the need to establish a baseline to develop key process models and to perform a techno-economic assessment to get a better sense of the viability of the technology in future
- …
