Blar i NTNU Open på forfatter "Rasheed, Adil"
-
Introducing CoSTA: A Deep Neural Network Enabled Approach to Improving Physics-Based Numerical Simulations
Blakseth, Sindre Stenen (Master thesis, 2021)Hybrid analyse og modellering (HAM) er et fremvoksende modelleringsparadigme hvor fysikkbasert modellering (FBM) og datadreven modellering (DDM) kombineres for å utvikle modeller som er generaliserbare, pålitelige, nøyaktige, ... -
Investigation of the impact of wakes and stratification on the performance of an onshore wind farm
Tabib, Mandar; Rasheed, Adil; Kvamsdal, Trond (Journal article; Peer reviewed, 2015)This work investigates the effects of wakes and stratification on the performance of turbines operating in the Bessaker wind farm. The wind farm is located in a highly complex terrain. Most dominant wind directions recorded ... -
Isogeometric methods for CFD and FSI-simulation of flow around turbine blades
van Opstal, Timo Matteo; Fonn, Eivind; Holdahl, Runar; Kvamsdal, Trond; Kvarving, Arne Morten; Mathisen, Kjell Magne; Nordanger, Knut; Okstad, Knut Morten; Rasheed, Adil; Tabib, Mandar (Journal article; Peer reviewed, 2015)Coupled fluid-structure interaction simulations of wind turbines have traditionally been considered computationally too expensive to carry out. However, more powerful computers and better solution techniques based on ... -
Laying The Foundation For an Intelligence-Powered Extendable Digital Twin Framework For Autonomous Sea Vessels
Sætre, Simon Mork (Master thesis, 2022)Mennesker er hovedårsaken til at det oppstår ulykker til sjøs. Det er derfor ønskelig i noen tilfeller å ta i bruk autonome kjøretøy som er i stand til å fungere uten at mennesker må blande seg inn. Et rammeverk for ... -
LES and RANS simulation of onshore Bessaker wind farm: analyzing terrain and wake effects on wind farm performance
Tabib, Mandar; Rasheed, Adil; Kvamsdal, Trond (Journal article; Peer reviewed, 2015)This work compares the predictive performance of RANS and LES solver in capturing the effect of terrain and wakes on the performance of the Bessaker wind farm. This 25 turbine wind farm is located in a highly complex terrain ... -
A long short term memory for hybrid uplifted reduced order models.
Ahmed, Shady E; San, Omer; Rasheed, Adil; Trian, Iliescu (Peer reviewed; Journal article, 2020)In this paper, we introduce an uplifted reduced order modeling (UROM) approach through the integration of standard projection based methods with long short-term memory (LSTM) embedding. Our approach has three modeling ... -
Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows
Pawar, Suraj; Ahmed, Shady E; San, Omer; Rasheed, Adil; Navon, Ionel M (Peer reviewed; Journal article, 2020)Reduced rank nonlinear filters are increasingly utilized in data assimilation of geophysical flows but often require a set of ensemble forward simulations to estimate forecast covariance. On the other hand, predictor–corrector ... -
Machine Learning for bottom-detection in Doppler Velocity Logs
Skatvedt, Marie (Master thesis, 2021)Den voksende utviklingen og utvidede bruken av autonome undervannsfarkoster (Autonomous Underwater Vehicle, AUV) har bidratt til en økende etterspørsel av nøyaktig, robust og langsiktig undervanns navigasjon. Moderne ... -
Machine Learning-Enabled Predictive Modeling of Building Performance for Electricity Optimization
Hestnes, Henrik Larsson (Master thesis, 2023)Med den raske fremgangen i maskinlæring har prediktiv modellering dukket opp som en attraktiv metode for å optimalisere energibruk, også innen bygningssektoren. Denne avhandlingen utforsker ulike modelleringsparadigmer for ... -
Memory embedded non-intrusive reduced order modeling of non-ergodic flows
Ahmed, Shady E; Rahman, Sk. Mashfiqur; San, Omer; Rasheed, Adil; Navon, Ionel M (Journal article; Peer reviewed, 2019)Generating a digital twin of any complex system requires modeling and computational approaches that are efficient, accurate, and modular. Traditional reduced order modeling techniques are targeted at only the first two, ... -
Merging Classical Control and Deep Reinforcement Learning for Dynamic Collision Avoidance for a Quadcopter
Carlsen, Ørjan (Master thesis, 2023)Selvstyrte ubemannede luftfartøy (UAVs, engelsk: Unmanned Aerial Vehicles), som eksempelvis kvadrokoptere, kan forbedre effektiviteten ved leveranser, utføre risikofylte inspeksjoner av strukturelle eiendeler, eller til ... -
Model fusion with physics-guided machine learning: Projection-based reduced-order modeling
Pawar, Suraj; San, Omer; Nair, Aditya; Rasheed, Adil; Kvamsdal, Trond (Journal article; Peer reviewed, 2021)The unprecedented amount of data generated from experiments, field observations, and large-scale numerical simulations at a wide range of spatiotemporal scales has enabled the rapid advancement of data-driven and especially ... -
Modeling Dynamical Systems with Physics Informed Neural Networks with Applications to PDE-Constrained Optimal Control Problems
Johannessen, Albert (Master thesis, 2024)Å modellere dynamiske systemer eksplisitt vil føre til modeller som er like nøykatige som antagelsene som gikk inn i modelleringen. Mange fysiske lover er nyttige modelleringsverktøy for mange bruksområder, men er ikke ... -
Modular Collision Avoidance Using Predictive Safety Filters
Vaaler, Aksel; Robinson, Haakon Rennesvik; Tengesdal, Trym; Rasheed, Adil (Chapter, 2023)The number of maritime projects is increasing yearly, including offshore applications, underwater robotics for ocean condition monitoring, and autonomous ship transport. Many of these activities are safety-critical, making ... -
Multi-fidelity information fusion with concatenated neural networks
Pawar, Suraj; San, Omer; Vedula, Prakash; Rasheed, Adil; Kvamsdal, Trond (Journal article; Peer reviewed, 2022)Recently, computational modeling has shifted towards the use of statistical inference, deep learning, and other data-driven modeling frameworks. Although this shift in modeling holds promise in many applications like design ... -
Multifidelity computing for coupling full and reduced order models
Ahmed, Shady E; San, Omer; Kara, Kursat; Younis, Rami; Rasheed, Adil (Peer reviewed; Journal article, 2021)Hybrid physics-machine learning models are increasingly being used in simulations of transport processes. Many complex multiphysics systems relevant to scientific and engineering applications include multiple spatiotemporal ... -
Near wake region of an industrial scale wind turbine: comparing LES-ALM with LES-SMI simulations using data mining (POD)
Tabib, Mandar; Rasheed, Adil; Fonn, Eivind; Siddiqui, Muhammad Salman; Kvamsdal, Trond (Journal article, 2017)Accurate prediction of power generation capability needs proper assessment of blade loading and wake behavior. In this regard, the Sliding Mesh Interface (SMI) approach and the Actuator Line Model (ALM) are two diverse ... -
A nested multi-scale model for assessing urban wind conditions : Comparison of Large Eddy Simulation versus RANS turbulence models when operating at the finest scale of the nesting
Tabib, Mandar; Midtbø, Knut Helge; Rasheed, Adil; Kvamsdal, Trond; Skaslien, Tor (Journal article; Peer reviewed, 2021)Good understanding of micro-scale urban-wind phenomena is needed for optimizing power generation capabilities of building-integrated wind turbines and for safety of futuristic urban transport involving drones. The current ... -
A nonintrusive hybrid neural-physics modeling of incomplete dynamical systems: Lorenz equations
Pawar, Suraj; San, Omer; Rasheed, Adil; Navon, Ionel M. (Peer reviewed; Journal article, 2021)This work presents a hybrid modeling approach to data-driven learning and representation of unknown physical processes and closure parameterizations. These hybrid models are suitable for situations where the mechanistic ... -
Nonlinear proper orthogonal decomposition for convection-dominated flows
Ahmed, Shady E; San, Omer; Rasheed, Adil; Trian, Iliescu (Peer reviewed; Journal article, 2021)Autoencoder techniques find increasingly common use in reduced order modeling as a means to create a latent space. This reduced order representation offers a modular data-driven modeling approach for nonlinear dynamical ...