International Telemetering Conference Proceedings, Volume 57 (2022)http://hdl.handle.net/10150/6664992024-03-28T08:43:39Z2024-03-28T08:43:39ZInternational Telemetering Conference Proceedings, Volume 57 (2022)http://hdl.handle.net/10150/6669812023-09-22T01:25:43Z2022-10-01T00:00:00ZInternational Telemetering Conference Proceedings, Volume 57 (2022)
2022-10-01T00:00:00ZSolving Parameter Management with Modern ProcessesFerrill, MicahLowe, DanielFerrill, J. Paulhttp://hdl.handle.net/10150/6669802022-11-25T01:15:30Z2022-10-01T00:00:00ZSolving Parameter Management with Modern Processes
Ferrill, Micah; Lowe, Daniel; Ferrill, J. Paul
The Parameter Management Tool solves the problem of Interface Control Document (ICD) tracking and versioning as well as providing a single source of truth for parameter definitions and automated, modular, and extensible conversion between different ICD formats. Built on open-source technologies like Python, Vue.js, and Docker, the Parameter Management Tool (PMT) can be deployed on bare-metal Linux or Windows as well as running in a cloud-native environment such as Kubernetes. PMT is a component of the Next-Gen Data Center under development by the 412 TW at Edwards AFB.
2022-10-01T00:00:00ZOPAL: Leveraging Open SourceOgden, EddgeCall, KennethMyers, Isaac J.Ma, Zayd L.Lowe, Danielhttp://hdl.handle.net/10150/6669792022-11-25T01:15:23Z2022-10-01T00:00:00ZOPAL: Leveraging Open Source
Ogden, Eddge; Call, Kenneth; Myers, Isaac J.; Ma, Zayd L.; Lowe, Daniel
The current explosion of test and evaluation data being collected from various systems has exposed a strong need for low-cost digital infrastructure to facilitate scalable analytics across all available data. Private industry and academic research have built such systems utilizing Open-Source Software (OSS) with tremendous success. The 309th Software Egineering Group (SWEG) developed OPAL (Open Platform for Advanced Learning) platform is a government owned and developed solution to address this gap and provide data discovery, analytics, and warehousing all license free. OPAL leverages best-in-breed Open-Source Software including JupyterLab (Python analysis environment), MinIO (S3-compliant, redundant and object-versioning data backend), Postgres (Data cataloging), and Dask (scalable compute), among others. In addition to Open-Source tooling, custom integration and software piping are used to further lower the analysts’ barrier to available data: custom Chapter 10 parsing and translating at high speed (10GB/min) into Apache Parquet format, a web-based data catalog for discovery, and lightweight arbitrary object storage organization. This paper will delineate design choices, our DevOps paradigm, benchmarking numbers, and results against a publicly available commercial flight dataset.
2022-10-01T00:00:00ZAdvanced Multi-Variate Time Series Analytic Techniques (Attends)Lau, RichardBagchi, AnindoShen, JohnTriolo, TonySanchez, KennethYao, LihanKovarskiy, JacobCastro, Robertohttp://hdl.handle.net/10150/6669782022-11-25T01:15:18Z2022-10-01T00:00:00ZAdvanced Multi-Variate Time Series Analytic Techniques (Attends)
Lau, Richard; Bagchi, Anindo; Shen, John; Triolo, Tony; Sanchez, Kenneth; Yao, Lihan; Kovarskiy, Jacob; Castro, Roberto
We describe an advanced architecture supporting fast decisions by using multi-variate time series analytic techniques on voluminous datasets that were previously inaccessible. The system, Advanced Multi-Variate Time Series Analytic Techniques (ATTENDS) automates data ingestion, knowledge extraction, and Artificial Intelligence/Machine Learning (AI/ML) algorithm configuration for anomaly detection, failure prediction, causal analysis, and diagnosis. To enable reusability, ATTENDS presents a set of Application Programming Interfaces (API) to support user configurability and remote invocation. The APIs implement state-of-the art AI/ML algorithms for predictive maintenance, sensor component correlation for problem diagnosis, and unsupervised learning of sensor measurement anomaly for support of automated testing and evaluation. We will present two use cases including prediction of Remaining Useful Life (RUL) of Turbofan [1] and sensor diagnosis and recommendation for maintenance actions, as well as detection and quantification of target location error in an airborne platform.
2022-10-01T00:00:00Z