Study on the Fast Search Planning Problem of Lost Targets for Maritime Emergency Response Based on an Improved Adaptive Immunogenetic Algorithm
Abstract
:1. Introduction
- (1)
- The construction of a composite moving target prediction method that fuses distance and heading. This study aims to construct a composite moving target prediction method that can fuse distance and heading information. The method will combine a uniform distribution model and a Gaussian distribution model for predicting the distance and heading of a target, respectively, and calculate the instantaneous distribution probability of the target through Bayes’ theorem. In addition, the study will explore how to effectively incorporate uncertain prior information into motion modeling to exploit the limited prior knowledge to predict the possible distribution probabilities of the target.
- (2)
- The establishment of an area search scheduling model based on the maximum probability of overlap strategy. In this study, a regional search and scheduling model based on the “maximum overlap probability” strategy is developed. The model must consider the limitations of the satellite over the top time window, dynamically adjust the target potential region, and take the overlap probability of the target field of view as the optimization objective function. The core of the research lies in improving the search efficiency and performance of the search task through reasonable model design, to ensure that the optimal search effect is realized under limited resources.
- (3)
- The construction of an improved adaptive immunogenetic optimization model. The model aims to significantly improve the optimization performance of the algorithm by dynamically adjusting the optimization search parameters. The study will introduce the diversity and self-regulation characteristics in the immune mechanism so that the algorithm can automatically adapt to different problem characteristics during the search process, thus improving the success rate of the search. At the same time, the study will also explore how to significantly improve the search efficiency by optimizing the parameter settings of the model to ensure more accurate search results in a limited time.
2. Description of the Problem
3. Moving Target Potential Region Construction and Distribution Probability Modeling
3.1. Construction of Target Potential Areas
3.2. Modeling of the Target Probability Distribution
4. Satellite Search Scheduling Model Based on the IAIGA
4.1. Definition of Model Elements
4.2. Objective Function
4.3. Constraints
- (1)
- , satellites search for observations in a time window that is less than the maximum power-on time of the satellite’s remote sensors.
- (2)
- , indicating that the remote sensing element side-swing angle is less than the maximum side-swing angle when the satellite performs its mission in a time window.
- (3)
- , where performs normalization to indicate the selection of a task for planning when the observation task time windows overlap.
- (4)
- , which indicates the storage capacity limit at any given moment.
- (5)
- , indicating that the satellite storage capacity begins and ends with the maximum storage capacity.
4.4. Improvement of Adaptive Immunogenetic Algorithms
- (1)
- Coding
- (2)
- Adaptation function
- (3)
- Algorithm flow
5. Simulation Experiments and Results
5.1. Scene Parameter Configuration and Visible Window Calculation
5.2. Trajectory Set Observation Test Validation
5.2.1. Feasibility Analysis of the Maximum Probability of Overlap Optimization Metrics
5.2.2. Feasibility Analysis of the “Prediction-Scheduling” Search Strategy
5.3. Scheduling Algorithm Effectiveness Analysis and Comparison
6. Discussion
6.1. Advantages of the IAIGA-Based Predictive-Scheduling Approach
6.2. Limitations and Possible Improvements
7. Conclusions
- (1)
- The composite moving target prediction method, based on distance and heading information, effectively integrates uncertain a priori information, resulting in a more accurate and comprehensive probability distribution of the target under conditions of limited prior information.
- (2)
- The prediction-scheduling search strategy, based on overlap probability maximization, significantly improves search efficiency and performance, providing an effective strategy for satellite search tasks.
- (3)
- Optimizing the moving target fast search planning problem using the IAIGA combines adaptive and immune mechanisms, enabling the algorithm to adapt to different problem characteristics and achieve self-optimization during the search process. This approach demonstrates excellent performance in terms of search success rate and algorithmic solving time, offering strong technical support for practical applications.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
Model Elements | Definition |
Satellite resource set, , is the number of satellites | |
Field of view of the satellite | |
Maximum lateral swing angle of the satellite | |
Side-swing granularity of the satellite | |
Maximum power-on time of the remote sensors of the satellite | |
Observation maneuvers during one transit of satellite | |
Storage capacity of the satellite | |
Storage capacity at start of the satellite | |
Storage capacity at the end of the satellite | |
Search mission start time | |
Search mission end time | |
The set of potential regions, | |
th time window of the satellite | |
Single-satellite transit candidate action strips, |
References
- Ning, Q.; Tao, G.; Chen, B.; Lei, Y.; Yan, H.; Zhao, C. Multi-UAVs Trajectory and Mission Cooperative Planning Based on the Markov Model. Phys. Commun. 2019, 35, 100717. [Google Scholar] [CrossRef]
- Yan, X.; Chen, R.; Jiang, Z. UAV Cluster Mission Planning Strategy for Area Coverage Tasks. Sensors 2023, 23, 9122. [Google Scholar] [CrossRef] [PubMed]
- Thibbotuwawa, A.; Bocewicz, G.; Radzki, G.; Nielsen, P.; Banaszak, Z. UAV Mission Planning Resistant to Weather Uncertainty. Sensors 2020, 20, 515. [Google Scholar] [CrossRef] [PubMed]
- Gao, Q.; Chang, F.; Yang, J.; Tao, Y.; Ma, L.; Su, H. Deep Reinforcement Learning for Autonomous Driving with an Auxiliary Actor Discriminator. Sensors 2024, 24, 700. [Google Scholar] [CrossRef] [PubMed]
- Zhu, B.-J.; Yang, X.-X.; Deng, X.-L.; Ma, Z.-Y.; Hou, Z.-X.; Jia, G.-W. Trajectory Optimization and Control of Stratospheric Airship in Cruising. Proc. Inst. Mech. Eng. Part I J. Syst. Control Eng. 2019, 233, 1329–1339. [Google Scholar] [CrossRef]
- Yang, D.; Li, Z.; Guo, S.; Zhang, J.; Luo, Y. Space-Based LEO-Observation Search Planning for Maritime Moving Targets. Acta Aeronaut. Astronaut. Sin. 2023, 44, 339–358. [Google Scholar] [CrossRef]
- Ueng, S.-K.; Lin, D.; Liu, C.-H. A Ship Motion Simulation System. Virtual Real. 2008, 12, 65–76. [Google Scholar] [CrossRef]
- Rajamanickam, M. Quantized Kalman Filter-Based Pattern Matching for Detection and Tracking of Moving Objects. Int. J. Eng. Adv. Technol. 2021, 9, 3842–3851. [Google Scholar] [CrossRef]
- Qiao, S.; Shen, D.; Wang, X.; Han, N.; Zhu, W. A Self-Adaptive Parameter Selection Trajectory Prediction Approach via Hidden Markov Models. IEEE Trans. Intell. Transport. Syst. 2015, 16, 284–296. [Google Scholar] [CrossRef]
- Dalsnes, B.R.; Hexeberg, S.; Flaten, A.L.; Eriksen, B.-O.H.; Brekke, E.F. The Neighbor Course Distribution Method with Gaussian Mixture Models for AIS-Based Vessel Trajectory Prediction. In Proceedings of the 2018 21st International Conference on Information Fusion (FUSION), Cambridge, UK, 10–13 July 2018. [Google Scholar]
- Rong, H.; Teixeira, A.P.; Guedes Soares, C. Ship Trajectory Uncertainty Prediction Based on a Gaussian Process Model. Ocean Eng. 2019, 182, 499–511. [Google Scholar] [CrossRef]
- Gabrel, V.; Murat, C. Mathematical Programming for Earth Observation Satellite Mission Planning. In Operations Research in Space and Air; Ciriani, T.A., Fasano, G., Gliozzi, S., Tadei, R., Eds.; Applied Optimization; Springer: Boston, MA, USA, 2003; Volume 79, pp. 103–122. ISBN 978-1-4419-5242-4. [Google Scholar]
- Globus, A.; Crawford, J.; Lohn, J.; Morris, R.; Clancy, D. Scheduling Earth Observing Fleets Using Evolutionary Algorithms: Problem Description and Approach. In Proceedings of the 3rd International NASA Workshop on Planning and Scheduling for Space, Houston, TX, USA, 27–29 October 2002. [Google Scholar]
- Li, L.; Chen, H.; Wu, J.; Li, J.; Jing, N.; Emmerich, M. Preference-Based Evolutionary Algorithms for Many-Objective Mission Planning of Agile Earth Observation Satellites. In Proceedings of the Genetic and Evolutionary Computation Conference Companion, Kyoto, Japan, 15–19 July 2018. [Google Scholar]
- Wen, X.; Liu, M.; Hu, Q. Satellite Mission Planning for Moving Targets Observation via Data Driven Approach. In Proceedings of the 2019 Chinese Control Conference (CCC), Guangzhou, China, 27–30 July 2019. [Google Scholar]
- Chen, Y.; Yang, S.; Suo, Y.; Zheng, M. Ship Track Prediction Based on DLGWO-SVR. Sci. Program. 2021, 2021, 9085617. [Google Scholar] [CrossRef]
- Zhang, H.; Xia, W.; Hu, X.; Yang, B.; Tang, H. Method for Moving Targets Search by Satellites on Multi-Obstacle Sea. Syst. Eng. Electron. 2018, 40, 2256–2262. [Google Scholar] [CrossRef]
- Ran, C.; Wang, H.; Xiong, G.; Qiu, D. Research on Mission-Planning of Ocean Moving Targets Imaging Reconnaissance Based on Improved Genetic Algorithm. J. Astronaut. 2010, 31, 457–465. [Google Scholar] [CrossRef]
- Mei, G. Research on Satellite Scheduling Technology for Moving Target Surveillance. Master’s Thesis, PLA Information Engineering University, Zhengzhou, China, 2016. [Google Scholar]
- Lou, Y.; Zou, J.; Zhou, X. Prediction of Motion Trend of Dynamic Target Based on Hidden Markov Model. Ship Electron. Eng. 2021, 41, 30–33. [Google Scholar] [CrossRef]
- Zhou, M.; Yin, X.; Liu, C.; Zhang, Z.; Xing, Q.; Yin, L. Multi-Satellite Task Scheduling Model and Algorithm. Command Inf. Syst. Technol. 2023, 14, 57–64. [Google Scholar] [CrossRef]
- Qi, J.; Guo, J.; Wang, M.; Wu, C. A Cooperative Autonomous Scheduling Approach for Multiple Earth Observation Satellites with Intensive Missions. IEEE Access 2021, 9, 61646–61661. [Google Scholar] [CrossRef]
Satellite Name | a/km | i/(°) | Ω/(°) | ω/(°) | M/(°) | |
---|---|---|---|---|---|---|
Sat1 | 6775 | 97.5820 | 319.4822 | 0.009 | 81.1158 | 311.88 |
Sat2 | 7062 | 98.2298 | 194.5448 | 0.002 | 92.1078 | 268.03 |
Sat3 | 6972 | 97.8413 | 204.6933 | 0.001 | 111.172 | 248.95 |
Sat4 | 7347 | 97.9118 | 201.5720 | 0.001 | 25.4327 | 334.69 |
Sat5 | 7229 | 97.9135 | 187.3469 | 0.001 | 297.53 | 189.14 |
Sat6 | 6814 | 98.251 | 147.204 | 0.002 | 46.485 | 172.394 |
Satellite Name | Remote Sensor Field of View/° | Maximum Power-on Time/s | Maximum Side-Swing Angle/° | Side Pendulum Rate/(°/s) | Side-Swing Stabilization Time/s |
---|---|---|---|---|---|
Sat1 | 5 | 400 | 30 | 0.2 | 200 |
Sat2 | 6 | 450 | 30 | 0.2 | 200 |
Sat3 | 7 | 500 | 35 | 0.3 | 200 |
Sat4 | 7 | 500 | 40 | 0.3 | 150 |
Sat5 | 7 | 550 | 40 | 0.4 | 150 |
Sat6 | 7 | 550 | 40 | 0.4 | 150 |
Satellite Name | Start Time | Stop Time | Duration |
---|---|---|---|
Sat1 | 7 March 2024 12:09:55.469 | 7 March 2024 12:20:29.826 | 634.357 |
7 March 2024 13:42:58.892 | 7 March 2024 13:53:24.988 | 626.095 | |
Sat2 | 7 March 2024 12:09:06.152 | 7 March 2024 12:24:08.762 | 902.611 |
7 March 2024 13:47:48.302 | 7 March 2024 14:03:09.674 | 921.372 | |
Sat3 | 7 March 2024 12:00:41.158 | 7 March 2024 12:13:24.359 | 763.201 |
7 March 2024 13:36:46.173 | 7 March 2024 13:51:00.418 | 854.246 | |
Sat4 | 7 March 2024 12:37:44.446 | 7 March 2024 12:56:18.582 | 1114.136 |
Sat5 | 7 March 2024 13:02:10.258 | 7 March 2024 13:19:49.275 | 1059.018 |
Sat6 | 7 March 2024 12:22:27.887 | 7 March 2024 12:33:26.289 | 658.402 |
7 March 2024 13:55:28.136 | 7 March 2024 14:05:57.235 | 629.100 |
Algorithm | Search Success Rate | Time |
---|---|---|
Greedy algorithm | 0.75 | 36.96 |
ACO | 0.945 | 48.56 |
GA | 0.855 | 56.93 |
IGA | 0.935 | 56.04 |
IAIGA | 0.955 | 14.91 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yu, T.; Zhang, Y.; Yang, J. Study on the Fast Search Planning Problem of Lost Targets for Maritime Emergency Response Based on an Improved Adaptive Immunogenetic Algorithm. Sensors 2024, 24, 3904. https://doi.org/10.3390/s24123904
Yu T, Zhang Y, Yang J. Study on the Fast Search Planning Problem of Lost Targets for Maritime Emergency Response Based on an Improved Adaptive Immunogenetic Algorithm. Sensors. 2024; 24(12):3904. https://doi.org/10.3390/s24123904
Chicago/Turabian StyleYu, Tianyue, Yasheng Zhang, and Jie Yang. 2024. "Study on the Fast Search Planning Problem of Lost Targets for Maritime Emergency Response Based on an Improved Adaptive Immunogenetic Algorithm" Sensors 24, no. 12: 3904. https://doi.org/10.3390/s24123904