FBG temperature measurement error compensation method based on LSTM and attention mechanism

Abstract

Abstract Real-time temperature measurement of power cables is an important part of the power system, and improving the accuracy of temperature measurement is a key factor of the temperature measurement system. The measurement of existing measurement methods is susceptible to interference and has certain errors. In this paper, an error compensation model is established by using a two-layer LSTM network to view the dynamic error in the process of FBG temperature measurement, and the attention mechanism is used to capture the relevant parameters of temperature change, so as to improve the model effect. The experimental results show that the compensation effect of the two-layer LSTM-Focus model is increased by 44.4% compared with the single LSTM model, which can meet the actual measurement requirements.