>> Nature Journal >> 2024 >> Issue 3 >> 正文
Inversion of cable internal temperature based on microwave radiation measurement and GA-BP neural network
Author: PANG Kai, FENG Li, ZHENG Wenchao Time: 2024-05-15 Counts:

doi:10.16186/j.cnki.1673-9787.2022050029

Received:2022/05/10

Revised:2022/10/05

Published:2024/05/15

Inversion of cable internal temperature based on microwave radiation measurement and GA-BP neural network

PANG Kai, FENG Li, ZHENG Wenchao

Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage SystemHubei University of TechnologyWuhan 430068HubeiChina

Abstract: Objectives The current cable monitoring system could not measure the cable internal temperature non-destructively.  Methods Thereforebased on microwave radiation measurementa cable internal temperature inversion method was proposed.Firstlythe multilayer microwave radiation transmission model was constructed by using the incoherent approachand the exponential function was used for layering.The bright temperature data set measured by microwave radiometer was obtained through finite element simulation.The 10-fold cross-validation was applied to divide the data set.To simulate the effect of the environmental noise on microwave radiometer measured brightness temperature in actual measurementGaussian noise with SNR ranging from 10 ~ 50 dB was added to the calculated value as the measured value for the microwave radiometer.After thatthe GA-BP neural network model was constructedand then the network was trained by using the data set.Finallythe inversion performance of the pre-trained GA-BP neural network model was verified by using the measured values.  Results The specific conclusions were as followsCompared with the one that used the BP neural network onlythe optimized BP one adopting a genetic algorithm was more effective in the cable internal temperature inversion.The inversion effect of the network and the signal-to-noise ratio SNR of added noise were positively correlated.The larger the SNRthe better the inversion effect.When the SNR was greater than 36 dBthe coefficient of determination was greater than 0. 627and the root mean square error was less than 5. 55which indicated that the inversion performed well.The inversion performance probably attained best when the SNR was 50 dB.The coefficient of determination could reach 0. 985.  Conclusions The results proved that GA-BP neural network was effective for cable internal temperature inversionlending a new perspective for cable internal temperature inversion.  

Key words:internal cable temperature;non-uniform stratification;multilayer cable microwave radiation t-ransmission model;BP neural network;genetic algorithm

Lastest