Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “query generation”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Performance of chatbots in queries concerning fundamental concepts in photochemistry

Abstract The advent of chatbots raises the possibility of a paradigm shift across society including the most technical of fields with regard to access to information, generation of knowledge, and dissemination of education and training. Photochemistry is a scientific endeavor with roots in chemistry and physics and branches that encompass diverse disciplines ranging from astronomy to zoology. Here, five chatbots have each been challenged with 13 photochemically relevant queries. The chatbots included ChatGPT 3.5, ChatGPT 4.0, Copilot, Gemini Advanced, and Meta AI. The queries encompassed fundamental concepts (e.g., “Why is the fluorescence spectrum typically the mirror image of the absorption spectrum?”), practical matters (e.g., “What is the inner filter effect and how to avoid it?”), philosophical matters (“Please create the most important photochemistry questions.”), and specific molecular features (e.g., “Why are azo dyes non‐fluorescent?”). The chatbots were moderately effective in answering queries concerning fundamental concepts in photochemistry but were glaringly deficient in specialized queries for dyes and fluorophores. In some instances, a correct response was embedded in verbose scientific nonsense whereas in others the entire response, while grammatically correct, was utterly meaningless. The unreliable accuracy makes present chatbots poorly suited for unaided educational purposes and highlights the importance of domain experts.

Taniguchi, Masahiko↗
NASA NTRS2020

UAS Pilot Assessments of Display and Alerting for the Next Generation Airborne Avoidance System

Unmanned aircraft systems (UAS) must comply with specific standards to operate in the National Airspace System (NAS). Among the requirements are the detect and avoid (DAA) capabilities, which include display, alerting, and guidance specifications. Previous studies have queried pilots for their subjective feedback on these display elements on earlier systems; the present study sought pilot evaluations with an initial iteration of the unmanned variant of a Next Generation Airborne Collision Avoidance System (ACAS XU). Sixteen participants piloted simulated aircraft with both standalone and integrated DAA displays. Their opinions were gathered using post-block and post-simulation questionnaires as well as guided debriefs. The data showed pilots had better understanding and comfort with the system when using an integrated display. Pilots also rated ACAS Xu alerting and guidance as generally acceptable and effective. Implications for further development of ACAS XU and DAA displays are discussed.

unmanned aircraft systems↗
DOE OSTI2021

Identification of Known and Novel Monomers for Poly(hydroxyurethanes) from Biobased Materials

Sourcing polymers from biobased materials is desirable for a transition to a more sustainable world. However, finding new monomers sourced from biobased molecules requires extensive experimental effort, due to the fact that most biomolecules lack the functional groups or properties needed to serve as a monomer in a particular polymeric system without chemical modification. In this work, we demonstrate a computational screening method to obtain monomers of a non-isocyanate polyurethane (NIPU), polyhydroxyurethane (PHU), from biomolecules. Our method generates candidate monomers from a list of 15 selected biobased starting molecules by performing chemical transformations that are standard to chemical catalysis and organic synthesis on these starting molecules and then screening the results for molecules with moieties that can be used as monomers for a PHU. Product molecules from two generations of reaction, a total number of 20,057, were analyzed automatically to identify molecules that have two or more epoxy or cyclic carbonate functional groups as candidates for further derivatization. These 21 candidate molecules were then subjected to another two generations of reaction, producing a set of 17,913 additional molecules. Further scrutiny of this set for desired functional groups characterizing PHUs and querying against the PubChem database was carried out, and 15 known molecules that are commercially available were identified, with the desirable features that they are predicted to be derived from biobased starting molecules in four or fewer steps. Moreover, molecule space generated from this process was primarily comprised of molecules that were not known to PubChem, indicating the framework also has the ability to generate novel candidate monomers that originate from biobased starting points.

36 MATERIALS SCIENCE↗
DOE OSTI2018

FUSRAP Case Study - Benefits and Lessons Learned from Implementation of a Modern Data Solution at Maywood - 18399

This paper focuses on data production and management practices dating back to 1999 that continue to evolve to support the project today. In 2000, the FUSRAP Maywood Project began using a software environmental data management system and laboratory information management system, developed by a single database administrator (DA) and authored in Microsoft Access{sup TM} (MS Access). The original databases included basic functionality including sample number assignment and label generation, tracking of LIMS gamma spec QC and assignment of basic qualifiers and basic database queries. The DA continued over the next fifteen years to refine the EDMS/LIMS by integrating project-specific data evaluation guidance document processes and Quality Assurance/Quality Control (QA/QC) charting and excursion warning tools. With the retirement of the original DA, the U.S. Army Corps of Engineers (USACE)-Cabrera Team procured and implemented a commercial-leaning solution using modern database tools and an established EDMS vendor. For the database transition process, the project team established and configured the new EDMS/LIMS with basic architecture and accessibility; evaluated existing workflows; established/revised LIMS and EDMS-related documentation (manuals and procedures); and conducted dry runs and validation testing. The overall team coordinated closely to facilitate a seamless transition from initial assessment and authoring, to data migration, and finally to resumption of normal ongoing operations. Key features of the new EDMS Subcontractor's software included lookup tables, an import wizard, data checking options and unique indexes. Since the database systems became operational, the technical staff gathered useful feedback from end users (e.g., lab staff, field engineers, task managers, and the third-party data validator) to refine the EDMS/LIMS operation. This feedback triggered improvements in the performance of onsite laboratory qualification forms, promoted consistency in sample ID numbers between the database sample planning screens and field chain-of-custodies, corrected bugs in the LIMS Duplicate Evaluation Report, eliminated data import issues such as blank, inconsistent or missing data from key fields. One of the advantages of the commercial database solution was that it allowed the project to cut cost over time due to the lower cost of database maintenance provided by the commercial database vendor versus the cost of an on-staff DA. Cost savings are estimated at $40,000 per year. There were also indirect cost savings resulting from implementation of the new database since it allowed better integration of the LIMS and EDMS. While there will always be challenges associated with long term records/data management for any old remediation site, the Maywood Team's approach to an upgraded EDMS/LIMS implementation serves as one element of the overall effort to enhance the integrity and reproducibility of critical data that supports the remediation program while at the same time, more effectively using available resources. These lessons-learned will enhance implementation of cost-effective solutions for similar environmental remediation sites. (authors)

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

UAS Pilot Assessments of Display and Alerting for the Next Generation Airborne Collision Avoidance System Xu

Unmanned aircraft systems (UAS) must comply with specific standards to operate in the National Airspace System (NAS). Among the requirements are the detect and avoid (DAA) capabilities, which include display, alerting, and guidance specifications. Previous studies have queried pilots for their subjective feedback on these display elements on earlier systems; the present study sought pilot evaluations with an initial iteration of the unmanned variant of a Next Generation Airborne Collision Avoidance System (ACAS XU). Sixteen participants piloted simulated aircraft with both standalone and integrated DAA displays. Their opinions were gathered using post-block and post-simulation questionnaires as well as guided debriefs. The data showed pilots had better understanding and comfort with the system when using an integrated display. Pilots also rated ACAS Xu alerting and guidance as generally acceptable and effective. Implications for further development of ACAS XU and DAA displays are discussed.

unmanned aircraft systems↗
DOE OSTI2016

Ontobee: A linked ontology data server to support ontology term dereferencing, linkage, query and integration

Linked Data (LD) aims to achieve interconnected data by representing entities using Unified Resource Identifiers (URIs), and sharing information using Resource Description Frameworks (RDFs) and HTTP. Ontologies, which logically represent entities and relations in specific domains, are the basis of LD. Ontobee (http://www.ontobee.org/) is a linked ontology data server that stores ontology information using RDF triple store technology and supports query, visualization and linkage of ontology terms. Ontobee is also the default linked data server for publishing and browsing biomedical ontologies in the Open Biological Ontology (OBO) Foundry (http://obofoundry.org) library. Ontobee currently hosts more than 180 ontologies (including 131 OBO Foundry Library ontologies) with over four million terms. Ontobee provides a user-friendly web interface for querying and visualizing the details and hierarchy of a specific ontology term. Using the eXtensible Stylesheet Language Transformation (XSLT) technology, Ontobee is able to dereference a single ontology term URI, and then output RDF/eXtensible Markup Language (XML) for computer processing or display the HTML information on a web browser for human users. Statistics and detailed information are generated and displayed for each ontology listed in Ontobee. In addition, a SPARQL web interface is provided for custom advanced SPARQL queries of one or multiple ontologies.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2013

Regression Verification Using Impact Summaries

Regression verification techniques are used to prove equivalence of syntactically similar programs. Checking equivalence of large programs, however, can be computationally expensive. Existing regression verification techniques rely on abstraction and decomposition techniques to reduce the computational effort of checking equivalence of the entire program. These techniques are sound but not complete. In this work, we propose a novel approach to improve scalability of regression verification by classifying the program behaviors generated during symbolic execution as either impacted or unimpacted. Our technique uses a combination of static analysis and symbolic execution to generate summaries of impacted program behaviors. The impact summaries are then checked for equivalence using an o-the-shelf decision procedure. We prove that our approach is both sound and complete for sequential programs, with respect to the depth bound of symbolic execution. Our evaluation on a set of sequential C artifacts shows that reducing the size of the summaries can help reduce the cost of software equivalence checking. Various reduction, abstraction, and compositional techniques have been developed to help scale software verification techniques to industrial-sized systems. Although such techniques have greatly increased the size and complexity of systems that can be checked, analysis of large software systems remains costly. Regression analysis techniques, e.g., regression testing [16], regression model checking [22], and regression verification [19], restrict the scope of the analysis by leveraging the differences between program versions. These techniques are based on the idea that if code is checked early in development, then subsequent versions can be checked against a prior (checked) version, leveraging the results of the previous analysis to reduce analysis cost of the current version. Regression verification addresses the problem of proving equivalence of closely related program versions [19]. These techniques compare two programs with a large degree of syntactic similarity to prove that portions of one program version are equivalent to the other. Regression verification can be used for guaranteeing backward compatibility, and for showing behavioral equivalence in programs with syntactic differences, e.g., when a program is refactored to improve its performance, maintainability, or readability. Existing regression verification techniques leverage similarities between program versions by using abstraction and decomposition techniques to improve scalability of the analysis [10, 12, 19]. The abstractions and decomposition in the these techniques, e.g., summaries of unchanged code [12] or semantically equivalent methods [19], compute an over-approximation of the program behaviors. The equivalence checking results of these techniques are sound but not complete-they may characterize programs as not functionally equivalent when, in fact, they are equivalent. In this work we describe a novel approach that leverages the impact of the differences between two programs for scaling regression verification. We partition program behaviors of each version into (a) behaviors impacted by the changes and (b) behaviors not impacted (unimpacted) by the changes. Only the impacted program behaviors are used during equivalence checking. We then prove that checking equivalence of the impacted program behaviors is equivalent to checking equivalence of all program behaviors for a given depth bound. In this work we use symbolic execution to generate the program behaviors and leverage control- and data-dependence information to facilitate the partitioning of program behaviors. The impacted program behaviors are termed as impact summaries. The dependence analyses that facilitate the generation of the impact summaries, we believe, could be used in conjunction with other abstraction and decomposition based approaches, [10, 12], as a complementary reduction technique. An evaluation of our regression verification technique shows that our approach is capable of leveraging similarities between program versions to reduce the size of the queries and the time required to check for logical equivalence. The main contributions of this work are: - A regression verification technique to generate impact summaries that can be checked for functional equivalence using an off-the-shelf decision procedure. - A proof that our approach is sound and complete with respect to the depth bound of symbolic execution. - An implementation of our technique using the LLVMcompiler infrastructure, the klee Symbolic Virtual Machine [4], and a variety of Satisfiability Modulo Theory (SMT) solvers, e.g., STP [7] and Z3 [6]. - An empirical evaluation on a set of C artifacts which shows that the use of impact summaries can reduce the cost of regression verification.

Backes, John↗
NASA NTRS2004

Standardized Sky Partitioning for the Next Generation Astronomy and Space Science Archives

The Johns Hopkins University and Space Telescope Science Institute are working together on this project to develop a library of standard software for data archives that will benefit the wider astronomical community. The ultimate goal was to develop and distribute a software library aimed at providing a common system for partitioning and indexing the sky in manageable sized regions and provide complex queries on the objects stored in this system. Whilst ongoing maintenance work will continue the primary goal has been completed. Most of the next generation sky surveys in the different wavelengths like 2MASS, GALEX, SDSS, GSC-II, DPOSS and FIRST have agreed on this common set of utilities. In this final report, we summarize work on the work elements assigned to the STScI project team.

Lal, Nand↗
DOE OSTI2019

What Constitutes Optimal Management of T1N0 Esophageal Adenocarcinoma?

Purpose and Design: Esophageal adenocarcinoma (EAC) develops as a consequence of gastroesophageal reflux disease and Barrett’s esophagus (BE). While combination therapy with chemotherapy or concurrent chemoradiotherapy followed by esophagectomy improves survival in more advanced tumors, the optimal treatment strategy for early-stage EAC is undefined. Endoscopic eradication therapy, consisting of endoscopic resection and mucosal ablation, has revolutionized therapy for superficial (T1a) EAC in BE and allows for esophageal preservation in appropriate patients at low risk for lymph node metastasis (LNM). This review critically examines the literature regarding evaluation, treatment, and outcomes in patients with T1 EAC. Methods: The literature was queried via the PubMed database to include articles published between 1990 and 2017. Search terms were generated from the key statements “Endoscopic eradication therapy results in equivalent overall survival when compared to esophagectomy for clinical T1aN0 EAC” and “Esophagectomy provides better overall survival than endoscopic eradication therapy for cT1b EAC”. Abstracts were reviewed and included according to predefined selection and exclusion criteria, and were then assessed according to the GRADE system. Results and Conclusions: In patients with T1aN0 EAC, overall survival with endoscopic eradication therapy is equal to esophagectomy. Given the substantial risk of LNM in patients with submucosal (T1b) EAC, esophagectomy remains the standard of care for surgical candidates. In the case of inoperability or low-risk lesions, endoscopic resection may be considered adequate therapy. Chemotherapy and radiation can be offered as primary therapy for non-surgical candidates with lesions not amenable to endoscopic therapy, but does not have a clear role in the adjuvant setting after either endoscopic or surgical resection.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
NASA NTRS2004

Hexagonal Pixels and Indexing Scheme for Binary Images

A scheme for resampling binaryimage data from a rectangular grid to a regular hexagonal grid and an associated tree-structured pixel-indexing scheme keyed to the level of resolution have been devised. This scheme could be utilized in conjunction with appropriate image-data-processing algorithms to enable automated retrieval and/or recognition of images. For some purposes, this scheme is superior to a prior scheme that relies on rectangular pixels: one example of such a purpose is recognition of fingerprints, which can be approximated more closely by use of line segments along hexagonal axes than by line segments along rectangular axes. This scheme could also be combined with algorithms for query-image-based retrieval of images via the Internet. A binary image on a rectangular grid is generated by raster scanning or by sampling on a stationary grid of rectangular pixels. In either case, each pixel (each cell in the rectangular grid) is denoted as either bright or dark, depending on whether the light level in the pixel is above or below a prescribed threshold. The binary data on such an image are stored in a matrix form that lends itself readily to searches of line segments aligned with either or both of the perpendicular coordinate axes. The first step in resampling onto a regular hexagonal grid is to make the resolution of the hexagonal grid fine enough to capture all the binaryimage detail from the rectangular grid. In practice, this amounts to choosing a hexagonal-cell width equal to or less than a third of the rectangular- cell width. Once the data have been resampled onto the hexagonal grid, the image can readily be checked for line segments aligned with the hexagonal coordinate axes, which typically lie at angles of 30deg, 90deg, and 150deg with respect to say, the horizontal rectangular coordinate axis. Optionally, one can then rotate the rectangular image by 90deg, then again sample onto the hexagonal grid and check for line segments at angles of 0deg, 60deg, and 120deg to the original horizontal coordinate axis. The net result is that one has checked for line segments at angular intervals of 30deg. For even finer angular resolution, one could, for example, then rotate the rectangular-grid image +/-45deg before sampling to perform checking for line segments at angular intervals of 15deg.

Johnson, Gordon G.↗
NASA NTRS1987

Understanding natural language for spacecraft sequencing

The paper describes a natural language understanding system, START, that translates English text into a knowledge base. The understanding and the generating modules of START share a Grammar which is built upon reversible transformations. Users can retrieve information by querying the knowledge base in English; the system then produces an English response. START can be easily adapted to many different domains. One such domain is spacecraft sequencing. A high-level overview of sequencing as it is practiced at JPL is presented in the paper, and three areas within this activity are identified for potential application of the START system. Examples are given of an actual dialog with START based on simulated data for the Mars Observer mission.

Katz, Boris↗
NASA NTRS1997

The Development of a Tool for Semi-Automated Generation of Structured and Unstructured Grids about Isolated Rotorcraft Blades

The grid generation used to model rotorcraft configurations for Computational Fluid Dynamics (CFD) analysis is highly complicated and time consuming. The highly complex geometry and irregular shapes encountered in entire rotorcraft configurations are typically modeled using overset grids. Another promising approach is to utilize unstructured grid methods. With either approach the majority of time is spent manually setting up the topology. For less complicated geometries such as isolated rotor blades, less time is obviously required. This paper discusses the capabilities of a tool called Rotor blade Optimized Topology Organizer and Renderer(ROTOR) being developed to quickly generate block structured grids and unstructured tetrahedral grids about isolated blades. The key algorithm uses individual airfoil sections to construct a Non-Uniform Rational B-Spline(NURBS) surface representation of the rotor blade. This continuous surface definition can be queried to define the block topology used in constructing a structured mesh around the rotor blade. Alternatively, the surface definition can be used to define the surface patches and grid cell spacing requirements for generating unstructured surface and volume grids. Presently, the primary output for ROTOR is block structured grids using 0-H and H-H topologies suitable for full-potential solvers. This paper will discuss the present capabilities of the tool and highlight future work.

Shanmugasundaram, Ramakrishnan↗
DOE OSTI2024

Evaluation of the Self Retrieval Augmented Generation Technique on Common Security Advisory Framework Data

This small experimental report evaluates a variation of Retrieval Augmented Generation (RAG), called Self-RAG. This method uses a generative language model that incorporates retrieved facts into its generation and is explicitly trained to be able to determine whether retrieved information is enough to answer the input query, with a user-defined threshold for confidence. We performed an experiment using data from the publicly available CISA Common Security Advisory Framework (CSAF) repository (https://github.com/cisagov/CSAF) as the database of facts to be used in retrieval. Qualitative results from the experiment demonstrate that the Self-RAG method has some ability to provide reasonable answers to queries that are in the dataset and will often ignore irrelevant information when asked outside of domain questions (e.g., general facts). In settings with deliberately confusing questions (the question is within domain, but asks about a fabricated advisory), it was able to refuse 40% of the time without further adjustments to the original framework. While this performance is not sufficient for current practical use, further improvements to data formatting, disambiguating results, and leveraging threshold values could improve performance significantly. However, evaluating this will require more extensive evaluations on larger datasets and potentially better models.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2022

Air Traffic Management TestBed: Weather Visualization using Map Tiles

Running realistic simulations and developing algorithms for decision support tools usually require weather data access. This document describes the weather data service capability implemented in the Air Traffic Management (ATM) TestBed. The capability provides ways for querying weather data from the weather products provided by the National Aeronautics and Space Administration’s (NASA) Sherlock ATM Data Warehouse. Depending on use cases, weather data can be queried using a Java application programming interface, web data access, and map tile image access. Map tile images are generated using triangular meshes obtained using the Matching Squares contour algorithm. An analysis determines a grid size that will produce both high image quality and fast image rendering. In addition, the visualization of weather data as map tiles on a TestBed visualization tool called Traffic Viewer is presented.

Chok Fung Lai↗
NASA NTRS1998

A Geometry Based Infra-Structure for Computational Analysis and Design

The computational steps traditionally taken for most engineering analysis suites (computational fluid dynamics (CFD), structural analysis, heat transfer and etc.) are: (1) Surface Generation -- usually by employing a Computer Assisted Design (CAD) system; (2) Grid Generation -- preparing the volume for the simulation; (3) Flow Solver -- producing the results at the specified operational point; (4) Post-processing Visualization -- interactively attempting to understand the results. For structural analysis, integrated systems can be obtained from a number of commercial vendors. These vendors couple directly to a number of CAD systems and are executed from within the CAD Graphical User Interface (GUI). It should be noted that the structural analysis problem is more tractable than CFD; there are fewer mesh topologies used and the grids are not as fine (this problem space does not have the length scaling issues of fluids). For CFD, these steps have worked well in the past for simple steady-state simulations at the expense of much user interaction. The data was transmitted between phases via files. In most cases, the output from a CAD system could go to Initial Graphics Exchange Specification (IGES) or Standard Exchange Program (STEP) files. The output from Grid Generators and Solvers do not really have standards though there are a couple of file formats that can be used for a subset of the gridding (i.e. PLOT3D data formats). The user would have to patch up the data or translate from one format to another to move to the next step. Sometimes this could take days. Specifically the problems with this procedure are:(1) File based -- Information flows from one step to the next via data files with formats specified for that procedure. File standards, when they exist, are wholly inadequate. For example, geometry from CAD systems (transmitted via IGES files) is defined as disjoint surfaces and curves (as well as masses of other information of no interest for the Grid Generator). This is particularly onerous for modern CAD systems based on solid modeling. The part was a proper solid and in the translation to IGES has lost this important characteristic. STEP is another standard for CAD data that exists and supports the concept of a solid. The problem with STEP is that a solid modeling geometry kernel is required to query and manipulate the data within this type of file. (2) 'Good' Geometry. A bottleneck in getting results from a solver is the construction of proper geometry to be fed to the grid generator. With 'good' geometry a grid can be constructed in tens of minutes (even with a complex configuration) using unstructured techniques. Adroit multi-block methods are not far behind. This means that a million node steady-state solution can be computed on the order of hours (using current high performance computers) starting from this 'good' geometry. Unfortunately, the geometry usually transmitted from the CAD system is not 'good' in the grid generator sense. The grid generator needs smooth closed solid geometry. It can take a week (or more) of interaction with the CAD output (sometimes by hand) before the process can begin. One way Communication. (3) One-way Communication -- All information travels on from one phase to the next. This makes procedures like node adaptation difficult when attempting to add or move nodes that sit on bounding surfaces (when the actual surface data has been lost after the grid generation phase). Until this process can be automated, more complex problems such as multi-disciplinary analysis or using the above procedure for design becomes prohibitive. There is also no way to easily deal with this system in a modular manner. One can only replace the grid generator, for example, if the software reads and writes the same files. Instead of the serial approach to analysis as described above, CAPRI takes a geometry centric approach. This makes the actual geometry (not a discretized version) accessible to all phases of the analysis. The connection to the geometry is made through an Application Programming Interface (API) and NOT a file system. This API isolates the top-level applications (grid generators, solvers and visualization components) from the geometry engine. Also this allows the replacement of one geometry kernel with another, without effecting these top-level applications. For example, if UniGraphics is used as the CAD package then Parasolid (UG's own geometry engine) can be used for all geometric queries so that no solid geometry information is lost in a translation. This is much better than STEP because when the data is queried, the same software is executed as used in the CAD system. Therefore, one analyzes the exact part that is in the CAD system. CAPRI uses the same idea as the commercial structural analysis codes but does not specify control. Software components of the CAD system are used, but the analysis suite, not the CAD operator, specifies the control of the software session. This also means that the license issues (may be) minimized and individuals need not have to know how to operate a CAD system in order to run the suite.

Haimes, Robert↗
NASA NTRSDate not supplied

Developing Concepts of Operations Using Multi-Step Tool Techniques With Large Language Models

The National Aeronautics and Space Administration (NASA) Air Mobility Pathfinders (AMP) project is developing and evaluating concepts of operations (ConOps) for safe, secure, and scalable Urban Air Mobility (UAM) operations. The AMP project’s Operational Concepts, Architecture, and Requirements Integration (OCARI) Team is using a Model Based System Engineering (MBSE) approach for integration, interoperability, and traceability of Advanced Air Mobility (AAM) ecosystems centered around urban air taxi services. The team’s goal is to define structures and behaviors needed for system feasibility, readiness, and interoperability, establish a UAM knowledge base, and trace and validate assumptions and requirements relevant to AAM. NASA Langley Research Center (LaRC) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of multi-modal transportation systems. The Knowledge-based Digital Platform (KbDP) is a concept being developed that ties the workflows of Project Managers (PM), Principal Investigators (PI), and System Engineers together across organizational boundaries. It does so through the management of an information database defined by mathematical, data science, and system engineering principles. Machine Learning (ML) algorithms play a key role in this concept by extracting meaningful knowledge from relational and graph databases, document repositories, and system artifacts, which the human user leverages to greatly improve the efficiency and effectiveness of their research. Recent advancements in the field of Large Language Models (LLMs), specifically models trained for tool use, such as Command-R , now allow for the reliable implementation of single-step and multi-step tool-centric systems. These techniques provide the LLM with a set of tools, in our case Python functions, that can be called on to answer a much wider range of questions compared to LLMs implemented using a traditional single-source or Retrieval Augmented Generation (RAG) approach. Through this method, the LLM can pull information from multiple data sources, such as relational or graph databases, document repositories, application programming interfaces (APIs), and SysML artifacts depending on the user’s question. The LLM can also output the information in a variety of different formats, using output generation tools, such as CSV, UML, or SysML artifacts. Additionally, tools can be assigned roles and can work together to provide answers to queries in an “agent” like approach, similar to that implemented by Microsoft’s AutoGen framework where different agents can converse with each other to accomplish tasks. Previously, our team developed a chatbot system with “agent like” functionality in the form of different “modes” the user could select from a user interface (UI), this architecture can be seen on the left in figure 1. Three different modes were implemented, the first mode allowed the LLM to utilize the structures and algorithms within a graph database to trace UAM requirements. The second mode gave the LLM access to a vector search capable of providing relevant information from thousands of document pages related to UAM ConOps and requirements. The third mode served as a general assistant where users could enter open-ended questions and custom prompts to utilize the LLM for different use-cases. This system improved the process surrounding generating and analyzing information related to UAM requirements, however, the implementation provided a clunky user experience. Users were required to know what mode to select within the UI in advance before entering their question to the selected tool. Moreover, the different tools were isolated from each other, they lacked bidirectional links that would allow for tools to collaborate to generate better responses. Our team is working on a new architecture, seen on the right in the below figure, with the goal to address many of the UX shortcomings of our original system while improving the accuracy and depth of responses from the LLM. This new system will automatically select the appropriate tool to use based off the user’s question. Each tool will be capable of calling on any of the other tools available to the LLM, resulting in a collaborative pipeline where tools can pass data between other tools until enough data is received to generate an answer to the user’s question. Using a locally deployed, open-source, LLM, the NASA OCARI team, in collaboration with Collins Aerospace, will implement a prototype application that will bridge knowledge across multiple sources to assist System Engineers (SEs) with requirements discovery and tracing, research question and use case identification, and assumption validation. Such a system will also allow SEs to more easily, and intuitively, explore the AAM ecosystem, ultimately improving the efficiency and effectiveness of the SE's research and decision-making processes surrounding ConOps development and validation. In this session, our team will provide a video demonstration of our new prototype architecture in action. We will also present an overview of our prototype system architecture and talk about its advantages over traditional LLM deployments along with how those advantages can provide additional value to the field of System Engineering.

systems engineering↗
DOE OSTI2016

SU-G-TeP4-09: Development of a Plan Data Aggregator for Time Efficient Physics Second-Checks of Machine Parameters for External Beam Treatment Plans

Purpose: Physics second-checks for external beam radiation therapy are performed, in-part, to verify that the machine parameters in the Record-and-Verify (R&V) system that will ultimately be sent to the LINAC exactly match the values initially calculated by the Treatment Planning System (TPS). While performing the second-check, a large portion of the physicists’ time is spent navigating and arranging display windows to locate and compare the relevant numerical values (MLC position, collimator rotation, field size, MU, etc.). Here, we describe the development of a software tool that guides the physicist by aggregating and succinctly displaying machine parameter data relevant to the physics second-check process. Methods: A data retrieval software tool was developed using Python to aggregate data and generate a list of machine parameters that are commonly verified during the physics second-check process. This software tool imported values from (i) the TPS RT Plan DICOM file and (ii) the MOSAIQ (R&V) Structured Query Language (SQL) database. The machine parameters aggregated for this study included: MLC positions, X&Y jaw positions, collimator rotation, gantry rotation, MU, dose rate, wedges and accessories, cumulative dose, energy, machine name, couch angle, and more. Results: A GUI interface was developed to generate a side-by-side display of the aggregated machine parameter values for each field, and presented to the physicist for direct visual comparison. This software tool was tested for 3D conformal, static IMRT, sliding window IMRT, and VMAT treatment plans. Conclusion: This software tool facilitated the data collection process needed in order for the physicist to conduct a second-check, thus yielding an optimized second-check workflow that was both more user friendly and time-efficient. Utilizing this software tool, the physicist was able to spend less time searching through the TPS PDF plan document and the R&V system and focus the second-check efforts on assessing the patient-specific plan-quality.

60 APPLIED LIFE SCIENCES↗