9 September 2002 Intelligent signal processing of fiber optic sensor for simultaneous measurement of displacement and surface roughness
Author Affiliations +
Abstract
This paper discusses the working principle of reflective fiber optic sensor with intensity compensation for simultaneous measurement of displacement and surface roughness. The sensor with a single sensing head is a combination of an illuminating fiber bundle transmitting incoming light beam and two receiving fiber bundles employed to collect the reflected beam from the workpiece surface. Three fiber bundles with same type are put together and arranged side by side, but the two receiving fiber bundles endface have different distances from the workpiece surface. The output characteristics of the sensor are analyzed. Although the sensor can simultaneously output two different readings containing displacement and surface roughness information using such a sensing head, it suffers from the influence of the cross-sensitivity and non-linearity. An intelligent signal processing method based on artificial neural network for the sensor output is proposed. The artificial neural network is trained to properly represent the complex nonlinear mapping between the sensor outputs information and the actual sensed measuring values. The example shows that the method can be used for both separation and linearization of the sensor output signals. Wide measuring range and high measuring precision of the two parameters are also obtained by means of the artificial neural network.
© (2002) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiaodong Wang, "Intelligent signal processing of fiber optic sensor for simultaneous measurement of displacement and surface roughness", Proc. SPIE 4920, Advanced Sensor Systems and Applications, (9 September 2002); doi: 10.1117/12.482008; https://doi.org/10.1117/12.482008
PROCEEDINGS
6 PAGES


SHARE
Back to Top