Your Destination for Mobility Engineering Resources
Announcements for SAE Mobilus
Browse AllRecent SAE Edge™ Research Reports
Browse All 177Latest Journal Issues
Browse All 16
Recent Books
Browse All 633Recently Published
Browse AllIn this paper, we focus on satellite production lines and design and implement a digital twin simulation and verification system for them. This is to improve manual documentation efficiency and provide sufficient process controllability in the small satellites’ batch production and assembly testing. We built a layered architecture. This allows the system to dynamically interact with AIT data management systems, structured process systems, and equipment data by fusing multi-source data. We also develop functional modules that combine lightweight 3D model visualization, dynamic simulation engines, and hybrid scheduling optimization algorithms. These modules can perform twin simulation, execute processes, intelligently schedule production, manage work reporting, conduct intelligent analysis, trigger anomaly alarms, and perform system management. We also dynamically simulate complex workflows like satellite transfer and automated assembly. These workflows are then verified using 3D virtual scene modeling and physical engines. We use time-series analysis to improve scheduling accuracy and multidimensional dynamic monitoring and hierarchical response to enhance production stability. In practice, the system can provide visualized control over the full process of satellite production. This greatly improves assembly efficiency and process controllability. It can also be an extensible digital way for aerospace manufacturing. The use of hierarchical architecture design and multimodal data fusion can be further applied in the complex equipment intelligent manufacturing.
This paper solves the problem of resource and energy constraints on orbit computing for LEO satellites. By combining MADDPG reinforcement learning and Lyapunov optimization, the paper proposes a computing framework and implements an adaptive task offloading model for space flight using a multi-agent deep actor critic algorithm, MADDPG. The joint optimization mechanism is implemented by multi-agent dynamic task offloading. Through the transformation from the state with long-term constraints into optimization of the status of queue stability, the load scheduling under threshold energy in accordance with the characteristics of energy constraints was realized by introducing Lyapunov virtual queues into the process of policy evaluation of deep reinforcement learning. The experimental results show that the proposed framework enables a lightweight preliminary calculation, balanced energy consumption to reduce resource allocation, and realizes the stable queues through adaptability of tasks under energy balance conditions, which can provide high-efficiency computing assistance and support for space orbit tasks such as monitoring remote sensing of Earth.
Civil aircraft, as typical complex product systems, exhibit characteristics such as a high concentration of high-tech technologies, strong interdisciplinarity, a high level of system integration, long development cycles, substantial project investments, and complex management. During the R&D process of civil aircraft projects, there are often high risks in performance, cost, and schedule. Delays in the schedule can lead to losses in project manpower and material resources, as well as project failure. A mature objective criteria system for maturity assessment provides a reference basis for determining whether the project has reached its optimal state at a specific stage, thereby reducing project management risks and increasing the probability of project success. This research will adopt a research approach combining theoretical studies with practical case analysis. First, it will conduct extensive and in-depth investigations into various maturity models and their applications across the entire product lifecycle within relevant fields. A requirement maturity model and requirement maturity KPI (Key Performance Indicator) indicators will be established to clarify the maturity status of requirements at different development stages, enabling judgment of whether the project is ready to proceed to the next development phase. Concurrently, by developing a KPI statistical system platform integrating application servers and data processing tools, a scientific and quantitative inspection mechanism will be implemented to visualize project development progress, status, and risk data. This will provide actionable insights for project decision-making and achieve effective project management and control.