Neural-network-based method of calibration and measurand reconstruction for a high-pressure measuring system

The problem of applying the neural networks for static calibration of measu ring systems and for measurand reconstruction is addressed. A multilayered neural network based method for the static calibration of this system is pr oposed. The functioning of the calibrated measuring system is based on thre e fiber-optic transducers whose static characteristics are nonmonotonic and significantly influenced by temperature. The applicability of the proposed calibration method is demonstrated in the case under consideration using s ynthetic and real data. The neural network is designed and implemented in a general purpose microcontroller. In comparison with the spline-based metho d of calibration, for the same reference data, the proposed method allows o btention of a better quality of calibration and, most important, when calib rated, the multilayered neural network does not require the measurement of temperature for pressure reconstruction.