The current article describes the results of the study of the neural networks temperature prediction error dependence on measurement errors, which are random, nonlinear and multiplicative errors. It is noted applicability of the architecture of neural network for temperature prediction. The formula of temperature step response for ideal sensor is given.
At the very beginning an algorithm for calculating and creating test sequences for neural network training is developed. The studies described in this article are implemented in the computing environment. There are given formulas and figures of measurement errors models. After considering the measurement error, which neural networks were trained and verified with the training set.
The results of the study of the temperature prediction error dependence on the multiplicative measurement error and nonlinear measurement error are presented. They allow conclude that raising the measurement errors with the prediction errors increase. As the result, for the maximal measurement error (2.5 %) an absolute temperature prediction error is achieved at the level lower than 5∙10-5 °C. The results of the similar studies of dependence on the random measurement error are presented. They underline the mentioned errors increasing with the prediction error. For random measurement error (0.5 %) absolute temperature prediction error is of 0.5 °C and for 2.5 % random measurement error absolute temperature prediction error is of 1.5 °C.
It is described also the study of the temperature prediction error dependence on the aforesaid three types of measurement errors.
The major conclusion of the received results (the dependences of the temperature prediction error on the measurement errors) consists in the next. The prediction temperature value slightly depends on multiplicative and nonlinear errors. In addition, the main impact on neural network temperature prediction error is caused by the random error.
 F. Bernhard, Handbuch der technischen temperaturmessung, Springer Vieweg, 2014.
 N. Yaryshev, Theoretical basis for measuring non-stationary temperature, Leningrad, USSR: Energoatomizdat, 1990.
 D. Kriesel. A Brief, Introduction to Neural Networks, 2007. [On-line], Available: http://www.dkriesel.com/ en/science/neural_networks.
 R. Bordawekar, B. Blainey, R. Puri, Analyzing Analytics. Morgan & Claypool Publishers, 2015.
 O. Lopatko, I. Mykytyn, “Temperature value prediction errors using neural networks and ideal transition process”, Measuring equipment and metrology, vol. 78, p. 20–24. 2017.
 M. Dorozhovets, V. Motalo, B. Stadnyk, Fundamentals of metrology and measuring technique, vol. 1. Lviv, Ukraine: Publ. House Lviv Pol. Nat. Univ., 2005.