摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-研究人员详细介绍了机器学习的新数据。根据NewsRx Jo Urnalists在加州埃尔塞贡多的新闻报道，研究表明，“发射异常经常发生在项目的早期阶段，其中许多异常归因于推进系统。识别和减轻潜在推进故障的方法可以帮助开发项目，并加快解决根本原因调查。”这项研究的财政支持来自内部研究和开发。新闻记者从航空航天公司的研究中获得了一句话：“在可重用的系统中，异常检测方法可以用来检测潜在的系统健康问题，这些问题可能随着系统老化而变得有问题。现代发射支持依赖于人类判断来生成红线限制，并在许多操作方面进行可视化家族数据比较。”这使得识别故障模式和诊断异常非常困难。新飞行器的前几次发射无法进行家庭数据比较。快速识别新系统和可重复使用系统故障的自动工具可以弥补这些差距。基于物理的建模和机器学习(PBMML)提供了一些方法，可以通过在推进异常或问题危及未来空间飞行之前识别它们来提高新的或可重复使用的运载火箭的可靠性。然后，PBML可以被用于通知纠正措施。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Machine Learning. According to news reporting from El Segundo, California, by NewsRx jo urnalists, research stated, "Launch anomalies occur frequently during the early phase of a program, with many of the anomalies attributed to propulsion systems. Approaches for identifying and mitigating potential propulsion failures can aid development programs and accelerate the resolution of root cause investigations ." Financial support for this research came from Internal Research and Development. The news correspondents obtained a quote from the research from Aerospace Corpor ation, "In reusable systems, anomaly detection methods can be employed to detect latent system health issues that could become problematic as the system ages. M odern launch support relies on human judgement for redline limit generation and visual family data comparison for many operational aspects, which makes it chall enging to identify failure modes and to diagnose an anomaly. Additionally, famil y data comparison is unavailable for the first few launches of a new vehicle. Au tomated tools to quickly identify system failures of new and reusable systems ca n bridge these gaps. Physics-based modeling and machine learning (PBMML) offers methods that can improve the reliability of new or reusable launch vehicles by i dentifying propulsion anomalies or issues before they jeopardize future space mi ssions. PBMML can then be used to inform corrective actions."
NETL
NSTL