Name
Title | ||
|---|---|---|
Neural Netowrk Based Fault Diagnostics Of Industrial Robots Using Wavelt Multi-Resolution Analysis |
Abstract | ||
|---|---|---|
A multi-resolution wavelet analysis coupled with a neural network based approach is applied in the problem of fault diagnostics of industrial robots. The multi-resolution analysis implements discrete wavelet transforms with filters and decomposes the signal in various levels. The approximate and detailed coefficients of the decomposed signals are then used for training a feedforward neural network whose output determines the state (faulty or normal) of the robot. The neural network classifier was then implemented and monitored in a Matlab-Simulink environment using a state-flow model. Validation of the method was performed offline using experimental data obtained from an industrial robot manipulator used in the semi-conductor industry. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/ACC.2007.4283012 | 2007 AMERICAN CONTROL CONFERENCE, VOLS 1-13 |
Keywords | DocType | ISSN |
neural network,neural networks,signal analysis,computer languages,feedforward neural networks,model validation,wavelet analysis,discrete wavelet transform,feedforward neural network | Conference | 0743-1619 |
Citations | PageRank | References |
2 | 0.65 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| aveek datta | 1 | 2 | 0.65 |
| Constantinos Mavroidis | 2 | 124 | 23.54 |
| jay krishnasamy | 3 | 2 | 0.65 |
| Hosek, M. | 4 | 4 | 1.08 |