We consider the procedure for constructing of the calibration curves of measuring tools using artificial neural networks in the presence of significant uncertainties in the measurement results of reference values and the readings of measuring devices. Application of artificial neural networks can also take into account the form of the distribution with the transition from the estimates and the standard uncertainty values to their expanded uncertainty. The algorithm of Levenberg-Markvadrta is applied to artificial neural networks that operate on the basis of the theory of interval arithmetic.
measurement uncertainty, calibration of measuring tools, neural network
"Yspolzovanye yskusstvennыkh neironnыkh setei s yntervalnoi aryfmetykoi pry postroenyy kalybrovochnoi zavysymosty sredstva yzmerenyia" ,
Scientific Works of Kharkiv National Air Force University,