We use state-of-the-art tools like advanced physical models, artificial neural networks, and integrated design, control and optimization algorithms.
PublishedUpdated on
Facts
Staff
2
PhDs / postdocs
6
Projects
3
Deep decarbonization of energy systems is a global challenge we face today, where use of innovative energy conversion technologies will play a central role.
AI enabled Condition Monitoring and Fault Diagnostics for Distributed Energy Systems
This project investigates tools and methods founded on artificial intelligence (AI) for monitoring, analysis and optimum design and operation of energy systems, mainly in buildings, considering both thermal and electrical energy and their coupling. Hence, the main objectives are:
studying advanced tools for real-time monitoring of energy systems;
analyses models development to predict the production, demand, and states of energy systems;
to evaluate how various energy resources, load profiles, and operating strategies affect the performance of multi-vector energy systems;
The work aims to address the following research questions:
In a multi-vector energy system consisting of heating, cooling, and power production technologies, how can the optimal operation of these technologies be determined?
What are the effects of an AI-based energy management system for both demand and supply side control on different indicators such as district energy consumption, costs, and GHG emissions?
How can an AI-based design and operation toolkit be developed to efficiently influence heating and cooling production of a heat pump system?
This Ph.D.-project is funded by the Research Council of Norway and Norconsult AS under the Industrial Ph.D. scheme, which is based on a company collaborating with a university on a doctoral project. The two regional energy projects Triangulum Central Energy Heat Pump Plant and Elnett21 – an emission-free and electric transportation system serve as the main reference cases for the PhD work.
Cutting edge multidisciplinary R&D to make a step change in understanding of Micro Gas Turbines (MGT) systems’ technology and commercialization aspects to enable large increase in their share in the energy market and contribution to the low carbon economy while providing specialized training for 15 researchers to help establish the backbone of an important industry. A training program for highly skilled researchers that can contribute to development of cost effective and environment friendly distributed power generation technologies.
UiS contribution to system analysis and techno-economic evaluation of MGT based systems.
Investigation of real time smart data analytic tools for monitoring and optimum operation of MGT systems and innovative solutions for techno-economic evaluation of MGT based systems are the core activities carried out at UiS.
Data analytic tools for condition monitoring and optimized operation of MGT systems in real-time applications allowed by dynamic modeling, intelligent methods as well as ICT solutions has been carried out. The outcomes of the project are expected to lead to higher reliability and availability, higher operational efficiency, lower operational expenditure, and higher flexibility of the MGT system and those of the integrated energy systems.
Development of innovative tools for techno-economic evaluation of MGT systems, building on existing models and their integration with artificial intelligence for optimization of technical-economic performance is the focus here. This will suggest viable solutions for MGT applications in different scenarios, contributing to increased share of this flexible technology in the growing market of distributed generation and other applications.
There are several researchers in the energy group, lead by Professor Assadi, who are studying the use of data-driven methods, specifically Artificial Intelligence techniques, to improve the predictive capability and condition monitoring of small-scale Distributed Generation (DG) systems. Micro Gas Turbine (MGT) have been specifically targeted, due to their fuel flexibility and low emissions. However, AI-based data driven approaches has been applied to geothermal energy installations, heat pumps, offshore installations and more. Combining multiple methods in a hybrid structure have been investigated at system level, showing great potential to offset the limitations of using a single technique and thus improve accuracy of the prognoses, predictions, and more.
