The assessment of casualty risks associated with re-entry necessitates a comprehensive analysis of trajectories and the examination of pertinent safety-related quantities such as the ground impact area and ground reaching velocity. In practical scenarios, the presence of uncertainty in input conditions introduces variability in safety-related quantities. Consequently, employing stochastic re-entry trajectory analysis becomes crucial in overcoming the limitations of conventional deterministic analyses. Conducting sensitivity assessments during the break-up phase is imperative to gain more insights into how to manage the variability of safety-related measures. Therefore, this paper conducted a surrogate-based global sensitivity analysis and employed explainability machine learning techniques to unveil the complexities of the relationship between input uncertainty conditions and three key measures: ground-reaching velocity, falling range, and falling time, with the object of interest being the Apollo-type capsule. A three-step polynomial chaos expansion-based strategy was devised to efficiently approximate the discontinuous relationships. The results show that the relationship is characterized by severe discontinuity that separates two modes: low- and high-ground reaching velocity caused by the presence of two distinct trim points, with precautionary measures that should be taken to prevent the occurrence of the latter. From this set of procedures, three key input conditions that significantly affect the safety-related measures were identified, namely, the altitude, pitch rate, and path angle of the capsule during the breakup. Subsequently, explainability techniques were utilized to give suggestions on how to control the input variability and avoid the high ground reaching velocity mode, aiming to achieve more dependable predictions for the three safety parameters mentioned earlier.

中文翻译：

---

使用可解释的替代模型对随机再入轨迹进行全局敏感性分析


评估与再入相关的伤亡风险需要对轨迹进行全面分析，并检查相关的安全相关量，例如地面撞击面积和地面到达速度。在实际场景中，输入条件的不确定性会导致安全相关量的变化。因此，采用随机再入轨迹分析对于克服传统确定性分析的局限性至关重要。在分解阶段进行敏感性评估对于深入了解如何管理安全相关措施的可变性至关重要。因此，本文进行了基于替代的全局敏感性分析，并采用可解释性机器学习技术来揭示输入不确定性条件与到达地面速度、坠落范围和坠落时间这三个关键指标之间关系的复杂性，目的是感兴趣的是阿波罗型太空舱。设计了基于三步多项式混沌展开的策略来有效地近似不连续关系。结果表明，这种关系的特点是严重不连续，将两种模式分开：由于两个不同的纵倾点的存在而引起的低地和高地到达速度，应采取预防措施来防止后者的发生。从这组程序中，确定了显着影响安全相关措施的三个关键输入条件，即解体过程中胶囊的高度、俯仰速率和路径角。 随后，利用可解释性技术就如何控制输入变异性和避免高地到达速度模式提出建议，旨在对前面提到的三个安全参数实现更可靠的预测。