National Repository of Grey Literature 2 records found  Search took 0.01 seconds. 
Architecture optimization of acoustic emission source recognition neural networks
Chlada, Milan ; Blaháček, Michal ; Převorovský, Zdeněk
In the contribution, the acoustic emission model source recognition method is described and discussed. Weighted combinations of tree model pulses were excited in aircraft structure. For the original weight estimation, various artificial neural networks were tested. Within the architecture optimization, the sensitivity analysis of trained networks enabled targeted inputs reduction towards the minimal number of parameters needed for reliable model sources apportionment estimation.
Acoustic emission of cyclical loaded aircraft structures
Blaháček, Michal ; Skála, J.
Aircraft structures fatigue failure is considerable risk of today´s aviation safety. The problem is usually solved by critical parts preventive replacement, regardless of parts real state. It is very expensive and uneconomical solution. NDT method capable to find the changes in the part, that are indication of crack creation and growth, would be very useful and money saving.Acoustic emission (AE) is a NDT procedure that is candidate for the method. In the Aeronautical Research and Test Institute (VZLÚ) set of cyclical fatigue tests was done. During the test, loaded sample AE activity was monitored, during the loading sequence pauses, the sample state was checked using NDT methods such us ultrasound, eddy current, optical methods, non-linear ultrasound, etc. Presented paper attends to desription and analysis of AE measurement on cyclical loaded aircraft structure.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.