Deep-learning-based position prediction model for lost submarines

Jiaming Hu

doi:10.1117/12.3054640

20 January 2025 Deep-learning-based position prediction model for lost submarines

Jiaming Hu

Author Affiliations +

Proceedings Volume 13515, Fourth International Conference on Advanced Manufacturing Technology and Electronic Information (AMTEI 2024); 135151R (2025) https://doi.org/10.1117/12.3054640
Event: 4th International Conference on Advanced Manufacturing Technology and Electronic Information (AMTEI 2024), 2024, Chongqing, China

Abstract

Aiming at the problem of disconnection that may occur during the communication between the submersible and the host ship due to the complex marine environment, this paper investigates the position prediction model of the submersible after disconnection for T time. The triaxial acceleration is obtained by the acceleration sampler on the submersible at the moment of loss of communication, and the model is constructed to predict the pitch angle of the submersible based on the long short-term memory network (LSTM) and the feed-forward neural network. By combining the three-dimensional coordinate method and the projection method, the three-axis acceleration is projected onto the coordinate system, and the position prediction model at the moment of loss is obtained using the heading projection method. This study provides search and rescue personnel with an advanced strategy for predicting the trajectory of the submersible, which significantly improves the accuracy and reliability of the prediction, and is of great significance for improving the safety and success of submersible operations in complex underwater environments.

(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jiaming Hu "Deep-learning-based position prediction model for lost submarines", Proc. SPIE 13515, Fourth International Conference on Advanced Manufacturing Technology and Electronic Information (AMTEI 2024), 135151R (20 January 2025); https://doi.org/10.1117/12.3054640

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE