Artificial intelligence methods application in motor fault detection and power consumption prediction
Decanato - Facoltà di scienze informatiche
Data d'inizio: 17 Luglio 2013
Data di fine: 18 Luglio 2013
The Faculty of Informatics is pleased to announce a seminar given by Filip Kulic
DATE: Wednesday, July 17th 2013
PLACE: USI Lugano Campus, room SI 003, Informatics building (Via G. Buffi 13)
TIME: 11.00
ABSTRACT:
Artificial intelligence (AI) methods such as artificial neural networks, fuzzy logic, support vector machines or evolutionary computation are widely used for solving a number of problems that occur in industry. This talk will be focused on the two possible use cases of application of AI in solving specific problems related to industrial processes.
The first application use case represents a method for short-term load forecasting based on artificial neural network, targeted for use in large-scale electric power distribution systems. Predicting the electricity load from one to several days ahead is referred to as Short-Term Load Forecasting (STLF). Precise STLF is a key requirement for power system managing and operation. Described method for STLF is based on an Artificial Neural Network (ANN), which has a reduced input space, and is thus eligible for online training and adaptation in systems where a large number of forecasts must run in parallel.
The second application represents support vector machine classifier for broken bar detection in electrical induction machine. It is a reliable online method, which has high robustness to load variations and changing operating conditions. The phase current is only physical value to be measured. The steady state current is analyzed for broken bar fault via motor current signature analysis technique.
BIO:
Filip Kulic received his PhD in 2003 from Faculty of Technical Sciences at University of Novi Sad in area of artificial intelligence application in electrical power engineering. His research work is now focused to control systems in process industry and power engineering, especially to artificial intelligence methods as a tool for control problem solving. Currently, he is associate professor and vice dean for research and international cooperation at Faculty of Technical Science Novi Sad.
HOST: Prof. Miroslaw Malek, ALaRI