CORDIS provides links to public deliverables and publications of HORIZON projects.
Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .
Exploitable results
TIGER employs knowledge-based system techniques for the continuous, in-service monitoring of gas turbines.
Gas turbines provide the principal source of power throughout many industrial sectors, and it is crucial that they operate to maximum efficiency with no unexpected failures. An automatic, continuous monitoring system is needed to assess the condition of a running gas turbine and give early warning or potential failure or loss of efficiency so that preventative action can be taken. TIGER achieves this through state-of-the-art knowledge-based system techniques.
The software system and toolkit, developed under the TIGER project, provides continuous on-line monitoring and diagnosis for gas turbines. High speed monitoring and fault detection is achieved through a real-time, rule-based, knowledge-based system which captures explicit knowledge. The system features a real-time data link to the gas turbine system and a real-time expert system capable of rapid fault identification. Using artificial intelligence and qualitative simulation techniques, the TIGER system is able to model the behaviour of the turbine, compare actual behaviour with predicted behaviour and identify possible faults. A state-of-the-art user interface, signal processing and data acquisition integration system support the operator in investigating their own theories of possible problems.
The TIGER system is being piloted at the Exxon chemical plant in Scotland where it monitors the gas turbine condition every second. While the system was specifically designed for monitoring gas turbines, it may also be applied in other situations such as building energy control systems.
Searching for OpenAIRE data...
There was an error trying to search data from OpenAIRE
No results available