Search results for "Prediction."
showing 10 items of 490 documents
Micromechanisms of load transfer in a unidirectional carbon fibre-reinforced epoxy composite due to fibre failures: Part 3. Multiscale reconstruction…
2008
International audience; This third article describes a multiscale process which takes into account the most important microscopic phenomena associated with composite degradation, including fibre fractures and interfacial debonding, overloading of fibres neighbouring a fibre break as well as viscoelastic behaviour of the matrix. The results have been used to accurately predict the macroscopic failure of unidirectional carbon fibre-reinforced epoxy and quantify damage accumulation in pressure vessels made of the same material. The approach described has allowed the acoustic emission activity resulting from fibres breaks to be evaluated and shown how the residual lifetimes of such vessels, whe…
Continuous Discharge Monitoring Using Non-contact Methods for Velocity Measurements: Uncertainty Analysis
2014
At gauged site, water stage and discharge hydrographs can be related also during unsteady flow conditions, using the one-dimensional diffusive hydraulic model, DORA, and exploiting sporadic surface velocity measurements carried out with a radar sensor, during the rising limb of the flood. Indeed, starting from the measured surface velocity, the application of a simplified entropic velocity distribution model allows obtaining the benchmark discharge for the Manning’s roughness calibration. The aim of this work is twofold. First, to address the uncertainty of the approach. Second, to detect the minimum water level along the rising limb in which the occasional surface velocity measurement shou…
Signal Spectrum-Based Machine Learning Approach for Fault Prediction and Maintenance of Electrical Machines
2022
Industrial revolution 4.0 has enabled the advent of new technological advancements, including the introduction of information technology with physical devices. The implementation of information technology in industrial applications has helped streamline industrial processes and make them more cost-efficient. This combination of information technology and physical devices gave birth to smart devices, which opened up a new research area known as the Internet of Things (IoT). This has enabled researchers to help reduce downtime and maintenance costs by applying condition monitoring on electrical machines utilizing machine learning algorithms. Although the industry is trying to move from schedu…
Training Deep Neural Networks with Novel Metaheuristic Algorithms for Fatigue Crack Growth Prediction in Aluminum Aircraft Alloys
2022
Fatigue cracks are a major defect in metal alloys, and specifically, their study poses defect evaluation challenges in aluminum aircraft alloys. Existing inline inspection tools exhibit measurement uncertainties. The physical-based methods for crack growth prediction utilize stress analysis models and the crack growth model governed by Paris’ law. These models, when utilized for long-term crack growth prediction, yield sub-optimum solutions and pose several technical limitations to the prediction problems. The metaheuristic optimization algorithms in this study have been conducted in accordance with neural networks to accurately forecast the crack growth rates in aluminum alloys. Through ex…
Prediction of Peak Shape and Characterization of Column Performance in Liquid Chromatography as a Function of Flow Rate
2015
Traditionally, column performance in liquid chromatography has been studied using information from the elution of probe compounds at different flow rates through van Deemter plots, which relate the column plate height to the linear mobile phase velocity. A more recent approach to characterize columns is the representation of the peak widths (or the right and left peak half-widths) for a set of compounds versus their retention times, which, for isocratic elution, give rise to almost linear plots. In previous work, these plots have been shown to facilitate the prediction of peak profiles (width and asymmetry) with optimization purposes. In this work, a detailed study on the dependence of the …
First Retrievals of ASCAT-IB VOD (Vegetation Optical Depth) at Global Scale
2021
Global and long-term vegetation optical depth (VOD) dataset are very useful to monitor the dynamics of the vegetation features, climate and environmental changes. In this study, the radar-based global ASCAT (Advanced SCATterometer) IB (INRAE-BORDEAUX) VOD was retrieved using a model which was recently calibrated over Africa. In order to assess the performance of IB VOD, the Saatchi biomass and three other VOD datasets (ASCAT V16, AMSR2 LPRM V5 and VODCA LPRM V6) derived from C-band observations were used in the comparison. The preliminary results show that IB VOD has a promising ability to predict biomass $(\mathrm{R}=0.74,\ \text{RMSE} =44.82\ \text{Mg}\ \text{ha}^{-1})$ , which is better …
Modern small wind turbine design solutions comparison in terms of estimated cost to energy output ratio
2015
This paper presents a series of estimations performed in order to establish the actual cost-effectiveness of three different small wind turbines (SWTs) design solutions. Each of them was evaluated and based on their power curves and installation costs, using wind data from a numerical weather prediction (WNP) model, a return on investment (ROI) period was calculated. The chosen turbines are: a standard three bladed horizontal axis wind turbine (HAWT), an advanced diffuser augmented HAWT and a Darrieus type vertical axis wind turbine (VAWT). The conclusions drawn from this study entertain the idea that from the economical point of view, a price reduction of SWT systems is more important than…
Convolutional architectures for virtual screening
2020
Abstract Background A Virtual Screening algorithm has to adapt to the different stages of this process. Early screening needs to ensure that all bioactive compounds are ranked in the first positions despite of the number of false positives, while a second screening round is aimed at increasing the prediction accuracy. Results A novel CNN architecture is presented to this aim, which predicts bioactivity of candidate compounds on CDK1 using a combination of molecular fingerprints as their vector representation, and has been trained suitably to achieve good results as regards both enrichment factor and accuracy in different screening modes (98.55% accuracy in active-only selection, and 98.88% …
Visual mismatch negativity (vMMN): a prediction error signal in the visual modality
2015
Frontiers in Human Neuroscience, 8
Calibration of a knock prediction model for the combustion of a gasoline-natural gas mixture
2009
Gaseous fuels, such as Liquefied Petroleum Gas (LPG) and Natural Gas (NG), thank to their good mixing capabilities, allow complete and cleaner combustion than normal gasoline, resulting in lower pollutant emissions and particulate matter. Moreover natural gas, which is mainly constituted by methane, whose molecule has the highest hydrogen/carbon ratio, leads also to lower ozone depleting emissions. The authors in a previous work (1) experienced the simultaneous combustion of gasoline and natural gas in a bi-fuel S.I. engine, exploiting so the high knock resistance of methane to run the engine with an ‘overall stoichiometric’ mixture (thus lowering fuel consumption and emissions) and better …