Title :
A fibre optic sensor for the measurement of surface roughness and displacement using artificial neural networks
Author :
Zhang, K. ; Butler, C. ; Yang, Q. ; Lu, Y.
Author_Institution :
Centre for Manuf. Metrol., Brunel Univ., Uxbridge, UK
Abstract :
This paper presents a fibre optic sensor system. Artificial neural networks using fast backpropagation are employed for the data processing. The use of the neural networks makes it possible for the sensor to be used both for surface roughness and displacement measurement at the same time. The results indicate 100% correct surface classification for ten different surfaces (different materials, different manufacturing methods and different surface roughnesses) and displacement errors less then ±5 μm. The actual accuracy was restricted by the calibration machine. A measuring range of ±0.8 mm for the displacement measurement were achieved
Keywords :
automatic optical inspection; backpropagation; calibration; computerised instrumentation; displacement measurement; fibre optic sensors; neural nets; pattern classification; surface topography measurement; A/D card; Y-coupler; artificial neural networks; automatic inspection; calibration; data processing; displacement errors; displacement measurement; fast backpropagation; fibre optic sensor; manufacturing products; process monitoring; simultaneous sampling and hold circuit; surface classification; surface roughness measurement; Artificial neural networks; Backpropagation; Calibration; Data processing; Displacement measurement; Error correction; Manufacturing; Optical fiber sensors; Rough surfaces; Surface roughness;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 1996. IMTC-96. Conference Proceedings. Quality Measurements: The Indispensable Bridge between Theory and Reality., IEEE
Conference_Location :
Brussels
Print_ISBN :
0-7803-3312-8
DOI :
10.1109/IMTC.1996.507301
