Title :
Diagnosis of helicopter gearboxes using structure-based network
Author :
Jammu, Vinay B. ; Danai, Kourosh ; Lewicki, David G.
Author_Institution :
Dept. of Mech. Eng., Massachusetts Univ., Amherst, MA, USA
Abstract :
A connectionist network is introduced for fault diagnosis of helicopter gearboxes that incorporates knowledge of the gearbox structure and characteristics of the vibration features as its fuzzy weights. Diagnosis is performed by propagating the abnormal features of vibration measurements through this structure-based connectionist network (SBCN), the outputs of which represent the fault possibility values for individual components of the gearbox. The performance of this network is evaluated by applying it to experimental vibration data from an OH-58A helicopter gearbox. The diagnostic results indicate that the network performance is comparable to those obtained from supervised pattern classification
Keywords :
fault diagnosis; fuzzy neural nets; helicopters; OH-58A helicopter gearbox; SBCN; fault diagnosis; fuzzy weights; gearbox structure; helicopter gearbox diagnosis; neural network; structure-based connectionist network; supervised pattern classification; vibration features; vibration measurement normal features propagation; Aircraft; Costs; Fault detection; Fault diagnosis; Helicopters; Pattern classification; Pollution measurement; Power system reliability; Sensor phenomena and characterization; Vibrations;
Conference_Titel :
American Control Conference, Proceedings of the 1995
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-2445-5
DOI :
10.1109/ACC.1995.529782
