About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Advanced Hybrid Information Processing. 5th EAI International Conference, ADHIP 2021, Virtual Event, October 22-24, 2021, Proceedings, Part I

Research Article

Passive Electromagnetic Field Positioning Method Based on BP Neural Network in Underwater 3-D Space

Download(Requires a free EAI acccount)
3 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-030-94551-0_24,
        author={Chaoyi Wang and Yidong Xu and Junwei Qi and Wenjing Shang and Mingxin Liu and Wenjian Chen},
        title={Passive Electromagnetic Field Positioning Method Based on BP Neural Network in Underwater 3-D Space},
        proceedings={Advanced Hybrid Information Processing. 5th EAI International Conference, ADHIP 2021, Virtual Event, October 22-24, 2021, Proceedings, Part I},
        proceedings_a={ADHIP},
        year={2022},
        month={1},
        keywords={BP neural networks Passive positioning Anti-interference},
        doi={10.1007/978-3-030-94551-0_24}
    }
    
  • Chaoyi Wang
    Yidong Xu
    Junwei Qi
    Wenjing Shang
    Mingxin Liu
    Wenjian Chen
    Year: 2022
    Passive Electromagnetic Field Positioning Method Based on BP Neural Network in Underwater 3-D Space
    ADHIP
    Springer
    DOI: 10.1007/978-3-030-94551-0_24
Chaoyi Wang1, Yidong Xu1,*, Junwei Qi1, Wenjing Shang1, Mingxin Liu1, Wenjian Chen2
  • 1: College of Information and Communication Engineering, Harbin Engineering University
  • 2: College of Underwater Acoustic Engineering, Harbin Engineering University
*Contact email: xuyidong@hrbeu.edu.cn

Abstract

This paper studies the positioning method of combining the passive electric field positioning and passive magnetic field positioning under three-dimensional (3-D) water. This technology can be applied to underwater submarine positioning, underwater leakage power supply positioning, underwater rescue and other occasions. We collect the samples data by electromagnetic sensors array, and recover the location of the targets. After the data preprocessing process includes data normalization, de-redundancy process, and generalization process, we use Back Propagation (BP) neural networks to build electric field and magnetic field distribution models of electric dipole source. Finally, we enter the test data to obtain the target position in the well-trained positioning model. We take the Euclidean distance between the ideal position and the model output target position as an absolute error. The results show that this method can effectively improve the accuracy of underwater target positioning and anti-interference ability of the training model, and the nonlinear function model trained by the neural network can be applied to the complex and changeable underwater environment.

Keywords
BP neural networks Passive positioning Anti-interference
Published
2022-01-18
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-030-94551-0_24
Copyright © 2021–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL