Home Journals Articles Updates About
CN
image
收藏切换
A Positioning Data Prediction Method for Deep-Sea Mining Vehicles Based on Physics-Informed Neural Networks
收藏切换
Zelong ZHOU1, 2, Yangrui CHENG1, 2, Guiting MAO1, 2, Saifeng PENG1, 2
Mining and Metallurgical Engineering | 2026, 46(3) : 82 - 90
Less
收藏切换
Mining and Metallurgical Engineering | 2026, 46(3): 82-90
• SPECIAL TOPIC ON BREAKTHROUGHS IN KEY TECHNOLOGIES AND COORDINATED DEVELOPMENT OF INDUSTRIAL CHAINS FOR DEEP-SEA MINERAL RESOURCE EXPLOITATION •
A Positioning Data Prediction Method for Deep-Sea Mining Vehicles Based on Physics-Informed Neural Networks
Full
Zelong ZHOU1, 2, Yangrui CHENG1, 2, Guiting MAO1, 2, Saifeng PENG1, 2
Affiliations
  • 1.Changsha Research Institute of Mining and Metallurgy Co. Ltd., Changsha 410012, Hunan, China
  • 2.State Key Laboratory of Exploitation and Utilization of Deep-Sea Mineral Resources, Changsha 410012, Hunan, China
doi: 10.3969/j.issn.0253-6099.2026.03.010
Outline
收藏切换

To improve the positioning accuracy and real-time performance of deep-sea mining equipment in complex nonlinear environments, a positioning data prediction algorithm was proposed based on Physics-Informed Neural Network (PINN). This method introduces the kinematic equations of deep-sea mining vehicle into the neural network structure, and achieves the synergistic fitting of sensor data and physical models by constructing a composite loss function integrating physical constraints. Furthermore, two test scenarios under different working conditions were constructed on the Gazebo simulation platform to systematically compare the prediction performance between the proposed PINN and a traditional Feedforward Neural Network (FNN). The results show that, compared with the FNN model, the PINN model reduces the mean absolute error (MAE) from 0.621 3 m to 0.128 3 m, the root mean square error (RMSE) from 0.674 0 m to 0.137 0 m, and the maximum error from 0.938 6 m to 0.196 2 m in working condition 1; while in working condition 2, the MAE is reduced from 0.823 9 m to 0.335 4 m, the RMSE from 0.935 2 m to 0.379 5 m, and the maximum error from 1.585 8 m to 0.640 2 m. PINN demonstrates significant advantages in extreme error control and robustness, exhibiting lower sensitivity to outliers under complex working conditions in particular.

deep-sea mining  /  mining vehicle positioning  /  positioning algorithm  /  physics-informed neural network  /  kinematic modeling  /  positioning system
周泽龙, 程阳锐, 毛桂庭, 彭赛锋. 基于物理信息神经网络的深海采矿车定位数据预测方法. 矿冶工程杂志, 2026 , 46 (3) : 82 -90 . DOI: 10.3969/j.issn.0253-6099.2026.03.010
Zelong ZHOU, Yangrui CHENG, Guiting MAO, Saifeng PENG. A Positioning Data Prediction Method for Deep-Sea Mining Vehicles Based on Physics-Informed Neural Networks[J]. Mining and Metallurgical Engineering, 2026 , 46 (3) : 82 -90 . DOI: 10.3969/j.issn.0253-6099.2026.03.010
Appendix
Less
Year 2026 volume 46 Issue 3
129
29
Cite this Article
BibTeX
Article Info
doi: 10.3969/j.issn.0253-6099.2026.03.010
  • Receive Date：2026-03-01
  • Online Date：2026-10-08
Article Data
Affiliations
History
  • Received：2026-03-01
Funding
Affiliations
    1.Changsha Research Institute of Mining and Metallurgy Co. Ltd., Changsha 410012, Hunan, China
    2.State Key Laboratory of Exploitation and Utilization of Deep-Sea Mineral Resources, Changsha 410012, Hunan, China
References
Share
https://castjournals.cast.org.cn/joweb/kygczz/EN/10.3969/j.issn.0253-6099.2026.03.010
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House