Master of Science in Industrial IT and Automation: Nye registreringer
Viser treff 21-40 av 53
-
Comparison between finite impulse response (FIR) and deep neural network (DNN) models for prediction of the CO2 slip in the CO2 removal system of ammonia plant
(Master thesis, 2021)Data-driven modeling of the decarbonization section in an ammonia plant was the main purpose of this project. The available data from plant historians was used for the prediction of CO2 slip from the decarbonization section. ... -
Parallel configuration, control and mirror operation of twin processes using DeltaV
(Master thesis, 2021)The University of South-Eastern Norway has two identical Serial Two Tank systems, a first-order system with time delay. Identical twin processes are systems built with identical physical components. These identical systems ... -
Identification of process models in closed loop
(Master thesis, 2021)In control engineering, there are two types of models known: Open loop and Closed loop. In the open loop model, the input is altered manually by an actuator based on the output desired. But in a closed loop system, the ... -
Optimal Operation of Processes Under Uncertainty Using Robust Model Predictive Control
(Master thesis, 2021)Model Predictive Control (MPC) is a well-established technology for advanced control of many industrial processes. One of its main benefits is the ability to handle process constraints. However, accuracy of the process ... -
Regularization and Machine Learning Features in the System Identification Toolbox and similar MATLAB functions
(Master thesis, 2021)In this thesis we look at the difference of OLS and RLS methods for estimation of system values and coefficient. Estimating system values using different methods such as, ssregest, DSR, DSR-E etc. Lastly looking at what ... -
Application of Reinforcement Learning for Action Evaluation
(Master thesis, 2021)Forsterkende læring er en type maskin læring, hvor læringen er basert på prøving og feiling. Det er vanligvis strukturert som en kobling mellom en agent og et miljø. Agenten velger hvilken handling som skal tas, og får en ... -
Machine learning methods for Industrial processes
(Master thesis, 2021)The general machine learning algorithms are introduced and explained before being implemented in Python. A comparison of various algorithms are made, and their workings are visualized. Time series data is defined and ... -
Development of models for estimating snow depth and snow density using machine learning methods
(Master thesis, 2021)Denne oppgaven tar utgangspunkt i data fra prototyper av et foreslått system for å måle snødybde og snøtetthet med kapasitanssensorer. Den eksterne partneren, Skagerak Energi AS, ønsker et system for å måle dette. Basert ... -
Developing and Testing of an MPC strategy for a four tanks multivariable process using Emerson Delta V system.
(Master thesis, 2020)With the advancement of control system, Model Predictive Control has taken over the mainstream PID controller because of its more efficient and advanced control over the multivariable process. The Quadruple Tank process ... -
State Space Model Based PID Controller Tuning
(Master thesis, 2019)Advances in digital computing over the last years have resulted in new and powerful tools for obtaining process models. An example of such a tool is the dsr toolbox, which gives a state space model based on measured ... -
Modeling of building occupation using motion sensor data
(Master thesis, 2019)As SMART house technology has emerged, the need to estimate position of residents has been important for several cases. In this project, a model of PIR sensor data is presented. The model should be able to predict ... -
Parallel calibration of multiphase flow meters (MPFM) based on measurements of phase streams in separators
(Master thesis, 2019)The Alvheim field suffers from significant production deferrals of oil and gas, during calibration of multiphase flow meters used in ownership allocation. This thesis has developed an algorithm solving a new method, which ... -
Characterization of Rheological Properties of Drilling Fluids Using Ultrasonic Waves
(Master thesis, 2018)Drilling fluid rheology is important for drilling safety and has to be constantly monitored and adjusted during drilling operations. The goal of this thesis is to attempt to create a model with neural networks that can ... -
Object Detection and Tracking on a Raspberry Pi using Background Subtraction and Convolutional Neural Networks
(Master thesis, 2018)Object detection and tracking are key features in many computer vision applications. Most state of the art models for object detection, however, are computationally complex. The goal of this project was to develop a fast ... -
Automatic Tuning of PID Controllers
(Master thesis, 2018)Proportional Integral and Derivative (PID) controllers are the most frequently used controllers in the process industry over the years. The performance is a factor of adequate tuning. The knowledge of the process is ... -
Model based estimation of fluid flow through a venturi channel: Kalman filters and observers
(Master thesis, 2018)In oil drilling operation, the estimation of returning flow is vital for safe operation. The return flow gives an early warning of kick-loss phenomenon. Detecting kick-loss is important to prevent uncontrolled well-blowout. ... -
Experimental Evaluation of MIMO Observers and Model Based Controllers
(Master thesis, 2018)State estimators for MIMO systems and model based controllers are important for multivariable control. Many publications have presented results of multivariable control, however most of the results are obtained from ... -
Developing an activity simulator of a person living in a smart house
(Master thesis, 2018)People tend to follow specific patterns in their daily lives. In a smart house context, this can be useful information to determine normal and abnormal behavior of smart house inhabitants. By using patterns based on the ... -
Improved flow management of Lake Toke
(Master thesis, 2017)The Telemark University College (TUC) Flood server is an advisory system that assist in the regulation of the flood gates at Dalsfos hydroelectric dam. A large flood in September 2015 revealed that the model and data storage ...