AUTHOR=Tian Wu , Hesheng Zhu , Qinghua Zhan , Nanji Wang TITLE=A precise inversion method of cable joint core temperature with non-embedded detection based on UMAP and ISSA-BPNN JOURNAL=Frontiers in Energy Research VOLUME=Volume 10 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.1028423 DOI=10.3389/fenrg.2022.1028423 ISSN=2296-598X ABSTRACT=Obtaining the core temperature of cable joint is vital to ensure the safe operation of modern power system with integration. To improve the speed and accuracy of core temperature inversion, this paper proposed a non-embedded cable joint temperature inversion method named Uniform Manifold Approximation and Projection (UMAP) and improved sparrow search algorithm (ISSA) optimized back propaganda neural network (BPNN). Firstly, UMAP is used to reduce the feature dimension of sample data input, enhance the data visualization effect, and improve the calculation speed and accuracy of the model. In order to improve the optimization ability of SSA, the Tent chaotic operator is introduced, and then the ISSA is used to optimize BPNN to address the issue of unstable output and easy to fall into local minimum. At last, the optimization ability and temperature inversion effect of the improved model were compared with other competing algorithms based on 10kV cable joint temperature rise test and CEC2017 benchmark function. The experimental results show that the proposed method shortens the calculation time of the model, and the mean absolute error of temperature inversion is about 0.1 °C. The overall performance is the most outstanding, which can provide a reference for line operation and maintenance personnel.