ISSN:
1013-9826
Quelle:
Scientific.Net: Materials Science & Technology / Trans Tech Publications Archiv 1984-2008
Thema:
Maschinenbau
Notizen:
Rotating machinery, such as steam turbo, compressor, and aeroengine etc., are widely usedin many industrial fields. Among the important rotor faults, the fatigue crack fault, which can lead tocatastrophic failure and cause injuries and severe damage to machinery if undetected in its earlystages, is most difficult to detect efficiently with traditional methods. In the paper, based on the truthof the change of the mode shapes of the cracked structure, a new method by combining accurate finiteelement model of rotor with multi-crack in shaft and artificial neural network (ANN) is proposed toidentify the location and depth of cracks in rotating machinery. First, based on fracture mechanics andthe energy principle of Paris, the accurate FE model of the rotor system considering several localizedon-edge non-propagating open cracks with different depth, is built to produce the specific modeshapes. Then a set of different mode shapes of a rotor system with localized cracks in several differentpositions and depths, which will be treated as the input of the designed ANN model, can be obtainedby repeating the above step. At last, with several selected crack cases, the errors between the resultsobtained by using the trained ANN model and FEM ones are compared and illustrated. Meanwhile,the influences of crack in the different position on the identification success are analyzed. The methodis validated on the test-rig and proved to have good effectiveness in identification process
Materialart:
Digitale Medien
URL:
http://www.tib-hannover.de/fulltexts/2011/0528/01/55/transtech_doi~10.4028%252Fwww.scientific.net%252FKEM.353-358.2463.pdf
