Autocalibration of fiber-optic strain sensor using a self-learning system

The authors describe a fiber-optic strain sensor and a procedure for autocalibration as applied to the measurement of longitudinal strain. The sensor exploits variation in the intermodal interference pattern in a few-mode birefringent fiber under the influence of strain. The sensor produces a far field light distribution varying with the interference pattern. An array of light-to-voltage converters carries out sampling of the sensor output. A small-size connectionist network integrated within the sensor computes strain values from samples dealing with the implicit, nonlinear dependencies between the parameter and the sampling data. The autocalibration method is based on the principle of self-learning. It involves supervised sampling, optimal selection of training inputs, and automated modulation of connection weights in the neural processor