Mathematical model of thermocouple characteristic based on neural network
Zheying Song, Chaoying Liu, Xue-Ling Song · 2004
The nonlinear compensation in the intelligent thermometer measurement instrumentation is introduced, and disadvantages of the compensation in hardware or software are discussed. The BP neural network method for the nonlinear compensation and its merits are proposed. The number of the hidden layer nodes and the improved algorithm are analyzed deeply, and the modeling process is presented in this paper. The example demonstrates that a more precise mathematical model of the thermocouple can be obtained based on the improved BP algorithm, which can be implemented by software, is beneficial to improve the instrument accuracy.