A Multi-Method Integrated Study on Parameter Constraint Analysis and Optimization for Emergency Maneuver Launch Missions

Zhiyuan Xiao

doi:10.54097/d13tzz23

Authors

Zhiyuan Xiao

DOI:

https://doi.org/10.54097/d13tzz23

Keywords:

Contingency Maneuvering Launch Mission, Coupled Constraints, Dynamic Planning, Spaceflight, Merging.

Abstract

With the intensifying competition in space capabilities, emergency maneuver launches have emerged as a critical research area due to their unique military value and application prospects. Efficient and safe responses to emergency launch requirements are paramount, especially for the co-ordination of multiple tasks within the same launch window. This study integrates various data sources, including rocket depot numbers and satellite depot numbers, to analyze constraints such as launch windows, satellite types, and road traffic. Utilizing unsupervised cluster analysis, the relationships between different constraints and their classification rules are identified. A neural network algorithm establishes connections among various launch mission indicators, and a dynamic comprehensive planning and evaluation model is developed by adjusting S and H parameters in conjunction with a dynamic planning algorithm (DDP). This model optimizes planning schemes across different launch tasks and multiple windows. Additionally, Pearson’s correlation coefficient is used to assess the dynamic impact of constraint changes on mission planning. The proposed optimal planning scheme, based on data analysis and dynamic optimization, offers theoretical support and practical guidance for the efficient execution of space emergency maneuver launches.

Downloads

Download data is not yet available.

References

[1] LI Zhengliang, PENG Sisi, WANG Tao. Sequential sampling method for agent models based on K-fold cross-validation[J].0 Journal of Computational Mechanics, 2022(02): 113-118.

[2] Zaorong Huang, Chunbao Wang, Jianjun Wei, Xueshu Yu, Xiaohai Tan. Abnormal gait detection based on BloazePose and random forest algorithm[J]. Computing Technology and Automation,2024,(02):67-74.

[3] Wang Xiaoqi, Chen Yingcong, Xie Minmin, Zhang Jiahui, Cai Shang. Multi-sensor BPNN and SVM multi-source heterogeneous data fusion algorithm[J]. Computing technology and automation, 2024, (02): 75-81.

[4] HONGXI ZHANG, QI AN, PING LAI, BAOQIAN WANG, XIANG LI. An optimization model of resource emergency allocation based on dynamic planning algorithm[J]. Electronic Design Engineering, 2024, (10): 160-164. DOI: https://doi.org/10.7717/peerj-cs.2294

[5] HE Tianling, ZHANG Wei, CAI Libo, ZHAO Lixin, WANG Yupeng. Realization of automatic multi-routing planning for power communication with coupled network constraints[J]. Fundamentals of Power Information and Communication, 2023, (12): 85-91.

[6] HUANG Manman, WANG Songlin, ZHOU Zhenggui, HOU Xiuli. Research on image recognition method of convolutional neural network based on dual-channel cross-fertilization[J]. Modern Information Technology, 2024, (12): 55-59+63.

[7] WANG Ming, LI Hua, ZHANG Wei. Research on optimization algorithm of space emergency maneuver launch mission[J]. Aerospace control, 2023, 41(5): 56-62.

[8] ZHAO Li, CHEN Chen, LIU Qiang. Deep learning-based space launch window prediction model[J]. Systems engineering and electronics technology, 2022, 44(12): 2345-2352.

[9] YANG Fan, ZHOU Wei, WU Hao. Risk management and decision support in space emergency launch missions[J]. Aerospace Engineering and Management, 2021, 23(4): 78-84.

[10] SUN Yue, GUO Tao, LI Na. Application of reinforcement learning in space emergency launch mission planning[J]. Journal of Aeronautics, 2020, 41(11): 123-130.

[11] CHEN Xiao, ZHENG Yu, WANG Li. Research on rapid deployment and adaptability of mobile space emergency launch platform[J]. Journal of Astronautics, 2019, 40(9): 1025-1032.