Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “language models”

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 1,297 records · Page 72
All sourcesNASA NTRSDOE OSTI
NASA NTRS2007

Object Oriented Modeling and Design

The Object Oriented Modeling and Design seminar is intended for software professionals and students, it covers the concepts and a language-independent graphical notation that can be used to analyze problem requirements, and design a solution to the problem. The seminar discusses the three kinds of object-oriented models class, state, and interaction. The class model represents the static structure of a system, the state model describes the aspects of a system that change over time as well as control behavior and the interaction model describes how objects collaborate to achieve overall results. Existing knowledge of object oriented programming may benefit the learning of modeling and good design. Specific expectations are: Create a class model, Read, recognize, and describe a class model, Describe association and link, Show abstract classes used with multiple inheritance, Explain metadata, reification and constraints, Group classes into a package, Read, recognize, and describe a state model, Explain states and transitions, Read, recognize, and describe interaction model, Explain Use cases and use case relationships, Show concurrency in activity diagram, Object interactions in sequence diagram.

Shaykhian, Gholam Ali↗
DOE OSTI2022

Recent advances and applications of deep learning methods in materials science

Deep learning (DL) is one of the fastest-growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. The recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high-quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science.

36 MATERIALS SCIENCE↗
NASA NTRS1990

Analytical learning and term-rewriting systems

Analytical learning is a set of machine learning techniques for revising the representation of a theory based on a small set of examples of that theory. When the representation of the theory is correct and complete but perhaps inefficient, an important objective of such analysis is to improve the computational efficiency of the representation. Several algorithms with this purpose have been suggested, most of which are closely tied to a first order logical language and are variants of goal regression, such as the familiar explanation based generalization (EBG) procedure. But because predicate calculus is a poor representation for some domains, these learning algorithms are extended to apply to other computational models. It is shown that the goal regression technique applies to a large family of programming languages, all based on a kind of term rewriting system. Included in this family are three language families of importance to artificial intelligence: logic programming, such as Prolog; lambda calculus, such as LISP; and combinatorial based languages, such as FP. A new analytical learning algorithm, AL-2, is exhibited that learns from success but is otherwise quite different from EBG. These results suggest that term rewriting systems are a good framework for analytical learning research in general, and that further research should be directed toward developing new techniques.

Laird, Philip↗
NASA NTRSDate not supplied

What Went Wrong: A Survey of Wildfire UAS Mishaps through Named Entity Recognition

Increasingly, unmanned aircraft systems (UAS) are being applied to wildfire incidents for tasks such as mapping, aerial ignition, and delivery. As a result, aviation incident reporting systems for wildfires are beginning to accumulate data related to UAS mishaps in wildfire response. In this research, we apply state-of-the-art natural language processing (NLP) techniques to develop a custom Named Entity Recognition (NER) model which extracts entities relevant to safety analysts. The custom NER model is built by fine-tuning an existing Bidirectional Encoder Representations from Transformers (BERT) model, resulting in a generalizable NER model that can extract engineering relevant entities including failure modes, causes, effects, control processes, and recommendations from failure-relevant text. This model performs passably, with a weighted average f1 score of 0.33 across entity types, indicating more labeled training data is needed. Extracted entities are used to form a Failure Modes and Effects Analysis (FMEA)-style survey of wildfire UAS mishaps reported using the SAFECOM system. Similar mishaps are manually clustered and reported as single rows within an FMEA. Foreach cluster, we compute frequency, severity, and overall riskin accordance with FAA standards. This methodology can beapplied as part of a broader safety management system totrack trends in mishaps (e.g., likelihood, severity) and discoverknowledge (e.g., causes, effects) that can be utilized to improvesafety outcomes and system performance.

Machine Learning↗
NASA NTRS1999

Modeling the Volcanic Source at Long Valley, CA, Using a Genetic Algorithm Technique

In this project, we attempted to model the deformation pattern due to the magmatic source at Long Valley caldera using a real-value coded genetic algorithm (GA) inversion similar to that found in Michalewicz, 1992. The project has been both successful and rewarding. The genetic algorithm, coded in the C programming language, performs stable inversions over repeated trials, with varying initial and boundary conditions. The original model used a GA in which the geophysical information was coded into the fitness function through the computation of surface displacements for a Mogi point source in an elastic half-space. The program was designed to invert for a spherical magmatic source - its depth, horizontal location and volume - using the known surface deformations. It also included the capability of inverting for multiple sources.

Tiampo, Kristy F.↗
DOE OSTI2025

Denoising Autoencoder for Reconstructing Sensor Observation Data and Predicting Evapotranspiration: Noisy and Missing Values Repair and Uncertainty Quantification

Abstract Machine learning (ML) methods applied in scientific research often deal with interrelated features in high‐dimensional data. Reducing data noise and redundancy is needed to increase prediction accuracy and efficiency especially when dealing with data from field sensors. We explored an unsupervised learning method, the denoising autoencoder (DAE), to extract the underlying data structure from noisy raw data in the context of predicting hydrologic quantities from multiple field sensors. These sensors have intrinsic instrumental noise and occasional malfunctions that cause missing values. Our DAE neural network reconstructed meteorological sensor data containing noise and missing values to predict evapotranspiration in a mountainous watershed. The DAE reconstructed the sensor variables with a mean coefficient of determination value of 0.77 across 15 dimensions representing individual sensors. It reduced variance and bias uncertainties compared to a classical autoencoder model. The reconstruction quality varied across dimensions depending on their cross‐correlation and alignment with the underlying data structure. Uncertainties arising from the model structure were overall higher than those resulting from data corruption. We attached the DAE structure to a downstream ET‐prediction neural network in three formats and achieved reasonably accurate ET predictions . The use of the DAE notably reduced variance uncertainty in ET prediction. However, excessive variance reduction may be accompanied by an increase in bias due to the intrinsic bias‐variance tradeoff. Our method of evaluating and reducing uncertainties in aggregated data from different sources can be used to improve predictive models, process understanding, and uncertainty quantification for better water resource management. Plain Language Summary We present a machine learning method, namely the denoising autoencoder, which reduces the effects of data noise and missing values typically present in scientific data sets collected through sensor measurements. This method selects the most relevant information from noisy raw data collected by the instruments and fills in missing values. To demonstrate the effectiveness of our method, we applied it to predict evapotranspiration, a hydrologic variable that represents the water moved from the land surface to the atmosphere through a combination of evaporation and plant water use (transpiration). We also used a random sampling technique (the Monte Carlo method) to compare the uncertainty in the predictions when using the raw and noisy data versus the reconstructed data. The denoising process produced more accurate predictions of evapotranspiration with less uncertainty. Improved predictions of evapotranspiration can lead to a better understanding and accounting of water budgets. This ML approach is broadly suitable for a wide variety of applications that involve noisy sensor data with missing values. Key Points We used a denoising autoencoder (DAE) neural network to reduce noise in meteorological and soil sensor observations by on average We used Monte Carlo sampling to estimate the bias and variance of all model outputs, including uncertainty sources from data and the model We attached the DAE component to a downstream neural network to predict ET with the variance reduced by , compared to that without the DAE

denoising autoencoder↗
NASA NTRS1989

Real-Time MENTAT programming language and architecture

Real-time MENTAT, a programming environment designed to simplify the task of programming real-time applications in distributed and parallel environments, is described. It is based on the same data-driven computation model and object-oriented programming paradigm as MENTAT. It provides an easy-to-use mechanism to exploit parallelism, language constructs for the expression and enforcement of timing constraints, and run-time support for scheduling and exciting real-time programs. The real-time MENTAT programming language is an extended C++. The extensions are added to facilitate automatic detection of data flow and generation of data flow graphs, to express the timing constraints of individual granules of computation, and to provide scheduling directives for the runtime system. A high-level view of the real-time MENTAT system architecture and programming language constructs is provided.

Grimshaw, Andrew S.↗
NASA NTRSDate not supplied

Design, Formalization, and Verification of Decision Making for Intelligent Systems

The development of autonomous systems requires a rigorous process that can guarantee a system’s reliability in critical applications. At its core, an autonomous system bases its behavior on a well-defined decision making system. In this paper, we present a methodological basis for the design, formalization and formal verification of Decision Making systems for autonomous agents. The approach is generally applicable to operational objectives that can be functionally decomposed and subsequently represented as Hierarchical Finite State Machines. As a case study, we present the application of this method to implement a Decision Making model in Simulink. Furthermore, we present how we use NASA’s FRET tool to write requirements in structured natural language and generate formal specifications that can be automatically digested by NASA’s CoCoSim tool. Finally, we present how, by leveraging CoCoSim, we perform formal verification against the Simulink model and present analysis results.

Model-based development↗
NASA NTRSDate not supplied

Design, Formalization, and Verification of Decision Making for Intelligent Systems

The development of autonomous systems requires a rigorous process that can guarantee a system’s reliability in critical applications. At its core, an autonomous system bases its behavior on a well-defined decision making system. In this paper, we present a methodological basis for the design, formalization and formal verification of Decision Making systems for autonomous agents. The approach is generally applicable to operational objectives that can be functionally decomposed and subsequently represented as Hierarchical Finite State Machines. As a case study, we present the application of this method to implement a Decision Making model in Simulink. Furthermore, we present how we use NASA’s FRET tool to write requirements in structured natural language and generate formal specifications that can be automatically digested by NASA’s CoCoSim tool. Finally, we present how, by leveraging CoCoSim, we perform formal verification against the Simulink model and present analysis results.

Model-based development↗
NASA NTRS1984

Modeling the weather with a data flow supercomputer

A static concept of data flow architecture is considered for a supercomputer for weather modeling. The machine level instructions are loaded into specific memory locations before computation is initiated, with only one instruction active at a time. The machine would have processing element, functional unit, array memory, memory routing and distribution routing network elements all contained on microprocessors. A value-oriented algorithmic language (VAL) would be employed and would have, as basic operations, simple functions deriving results from operand values. Details of the machine language format, computations with an array and file processing procedures are outlined. A global weather model is discussed in terms of a static architecture and the potential computation rate is analyzed. The results indicate that detailed design studies are warranted to quantify costs and parts fabrication requirements.

Dennis, J. B.↗
NASA NTRS1991

Research accomplished at the Knowledge Based Systems Lab: IDEF3, version 1.0

An overview is presented of the foundations and content of the evolving IDEF3 process flow and object state description capture method. This method is currently in beta test. Ongoing efforts in the formulation of formal semantics models for descriptions captured in the outlined form and in the actual application of this method can be expected to cause an evolution in the method language. A language is described for the representation of process and object state centered system description. IDEF3 is a scenario driven process flow modeling methodology created specifically for these types of descriptive activities.

Mayer, Richard J.↗
DOE OSTI2025

Data imbalance in drug response prediction: multi-objective optimization approach in deep learning setting

Abstract Drug response prediction (DRP) methods tackle the complex task of associating the effectiveness of small molecules with the specific genetic makeup of the patient. Anti-cancer DRP is a particularly challenging task requiring costly experiments as underlying pathogenic mechanisms are broad and associated with multiple genomic pathways. The scientific community has exerted significant efforts to generate public drug screening datasets, giving a path to various machine learning models that attempt to reason over complex data space of small compounds and biological characteristics of tumors. However, the data depth is still lacking compared to application domains like computer vision or natural language processing domains, limiting current learning capabilities. To combat this issue and improves the generalizability of the DRP models, we are exploring strategies that explicitly address the imbalance in the DRP datasets. We reframe the problem as a multi-objective optimization across multiple drugs to maximize deep learning model performance. We implement this approach by constructing Multi-Objective Optimization Regularized by Loss Entropy loss function and plugging it into a Deep Learning model. We demonstrate the utility of proposed drug discovery methods and make suggestions for further potential application of the work to achieve desirable outcomes in the healthcare field.

Biochemistry & Molecular Biology↗
DOE OSTI2022

WORM (Write One, Read Many)

WORM (Write One, Run Many) is an easy to use, cross platform, embedded and extensible, functional programming language designed to facilitate the creation of input-decks for computer codes that use standard ASCII text files for input. WORM makes it easy to create generic (yet, complex and powerful) reusable models. Additionally its nature allows for complex calculations and routines to be coded once and easily reused, further simplifying the creation of input decks. WORM (Write One, Run Many) is a powerful and versatile tool designed to improve the efficiency of today’s criticality safety analyst by allowing: + input decks for parametric studies to be created quickly and easily, + calculations and variables to be imbedded into any input deck, thus allowing for meaningful parameter specifications, + problems to be specified using any combination of units, and + complex mathematically defined models to be created. A very simple syntax is employed, and therefore the WORM is easy to learn. A WORM model is essentially a standard input deck with some of its numerical values replaced by WORM code. WORM code may include and evaluate the following mathematical operators and functions: addition, subtraction, multiplication, division, exponentiation, modulus, sine, cosine, tangent, arcsine, arccosine, arctangent, the natural logarithm, logarithm base 10, integer truncation, absolute value, and random number. Several common constants, e.g., pi, e, and Avogadros’s Number (both as 6.022e23 and 0.6022), are predefined in WORM. Additionally, many unit conversion factors are also predefined: millimeters, meters, inches, feet, yards, and mils to centimeters; kilograms, pounds, and ounces to grams; liters, milliliters, gallons, and fluid ounces to cubic centimeters; and angular degrees to radians. For parametric studies, WORM supports various shorthand list specifications: the explicit step size, linear interpolation, and logarithmic interpolation. The list notation sequentially assigns multiple values to a name. WORM creates an input deck for each value of the name. If multiple lists are used, WORM steps through each list individually, i.e., WORM creates input decks corresponding to each and every permutation of the list values. Additionally, a library of standard material definitions and Perl subroutines are included. Any one of these files can be incorporated into the subject model with a simple WORM read command. WORM is completely written in Perl, the Practical Extraction and Reporting Language. Perl is one of the most portable programming languages available today. As such, the WORM works on practically any computer platform.

Sartor, Raymond↗
NASA NTRSDate not supplied

In-Situ Resource Utilization Modeling of a Lunar Water Processing System

A key element of achieving a sustained surface presence, such as defined in NASA’s Artemis plan, is In-Situ Resource Utilization (ISRU). ISRU is the practice of using local resources to provide mission consumables that reduce system launch mass requirements, and regenerate resources (chiefly, water and oxygen) for propulsion and life support supporting both Lunar and Martian missions. ISRU systems require multiple complex processes, such as excavation, chemical reactors, and electrolysis subsystems that must operate in harmony to optimize the overall system process from beginning to end. The Mission Analysis and Integration Tool (MAIT) was previously developed with MATLAB in FY22 to connect individual subsystem models into a customized, flexible framework for the purpose of technology downselect, optimization, and end-to-end process planning. Beginning in FY24, MAIT was leveraged and evolved using MATLAB/Simulink due to its ability to communicate with a vast number of other programming languages and makes up the backbone of data flow between inputs and outputs to the subsystem models. MAIT initially evaluated a suite of ISRU-related technologies, including the water processing Lunar Auger Dryer for ISRU (LADI) system with integrated upstream excavation and downstream electrolysis subsystems. With individual models consolidated, the MAIT tool generated over 60,000 cases during its parametric sweeps; these system iterations produced valuable insight into the optimal LADI geometry for minimizing energy demands, estimating carbothermal reactor and radiator mass relationships, and calculated the power dynamics of the electrolysis unit. Advanced efforts with advanced models will include examining multiple production targets to demonstrate the ability to scale ISRU technologies supporting the Space Technology Mission Directorate’s (STMD) commercialization strategy, and increase the MAIT software capability to handle a wide array of ISRU system models beyond the Lunar environment, e.g. production of propellant for a Martian lander.

Avery Carlson↗
DOE OSTI2026

Digitizing Today’s Buildings in the Real World: Lessons from Field Demonstrations

Digital twins, created by generating a virtual replica of a building, enable safe evaluation of operational scenarios and applications like fault detection and diagnosis and advanced controls. However, a prerequisite is the creation of a machine-readable digital representation of a building, currently hindered by fragmented information scattered across mechanical drawings, point lists, and natural language sequences. As a result, digital twin development remains labor-intensive, error-prone, and difficult to validate. To address these challenges, two efforts from ASHRAE aim to support the digitalization of buildings. ASHRAE s223 establishes a semantic model of buildings, representing system components, configuration, and data sources. ASHRAE s231 defines a vendor-neutral programming language for expressing their control logic. As the industry evaluates implementing them in their products, understanding the challenges that vendors and implementers may face is crucial. In this paper, we present findings and lessons learned from field demonstrations in five buildings that implemented control applications using ASHRAE s223 and s231. The demonstrations highlight how semantic modeling and formalized control descriptions can significantly reduce software development time, manual point mapping, and hard-coding. Beyond time efficiency, they enable reliable automation by minimizing human interpretation and providing a means for consistency across projects. We describe the processes and best practices for model creation and model usage, from translating heterogeneous building documentation into semantic representations to implementing control logic in real-world systems. Finally, we discuss the challenges that persist, including integration with legacy software environments, gaps in interoperability, and the level of expertise still required to effectively leverage semantic models.

Prakash, Anand Krishnan↗
NASA NTRS1990

Simulated dynamic response of a servovalve controlled hydraulic actuator

A general purpose math model of a servovalve controlled hydraulic actuator system is derived. The system consists of a linear actuator with unequal piston areas, a single stage servovalve, a gas charged hydraulic accumulator, and the interconnecting piping. The state equations are integrated using the Advanced Continuous Simulation Language (ACSL) for determining the system's dynamic response characteristics. Using this generalized hydraulic actuator system model, response characteristics were determined for various servovalve commands.

Babcock, Dale A.↗
NASA NTRSDate not supplied

Integrated In-Situ Resource Utilization Modeling of a Lunar Water Processing System

A key element of achieving a sustained surface presence, such as defined in NASA’s Artemis plan, is In-Situ Resource Utilization (ISRU). ISRU is the practice of using local resources to provide mission consumables that reduce system launch mass requirements, and regenerate resources (chiefly, water and oxygen) for propulsion and life support supporting both Lunar and Martian missions. ISRU systems require multiple complex processes, such as excavation, chemical reactors, and electrolysis subsystems that must operate in harmony to optimize the overall system process from beginning to end. The Mission Analysis and Integration Tool (MAIT) connects individual subsystem models into a customized, flexible framework for the purpose of technology downselect, optimization, and end-to-end process planning. MATLAB was favorable to use as the main software integration tool due to its ability to communicate with a vast number of other programming languages and makes up the backbone of data flow between inputs and outputs to the subsystem models. MAIT initially evaluated a suite of technologies, including but not limited to, the water processing Lunar Auger Dryer for ISRU (LADI) system and an oxygen extraction carbothermal reduction process. With individual models consolidated, the MAIT tool generated over 60,000 cases during its parametric sweeps; these system iterations produced valuable insight into the optimal LADI geometry for minimizing heater energy demands, estimating carbothermal reactor and radiator mass relationships, and calculated the power dynamics of the electrolysis unit. Efforts to update the MAIT tool are ongoing to accommodate and scale ISRU technologies supporting the Space Technology Mission Directorate’s (STMD) commercialization strategy, and increase the MAIT software capability to handle a wide array of ISRU system models beyond the Lunar environment, e.g. production of propellant for a Martian lander.

Avery Carlson↗
NASA NTRS2015

The SeaHorn Verification Framework

In this paper, we present SeaHorn, a software verification framework. The key distinguishing feature of SeaHorn is its modular design that separates the concerns of the syntax of the programming language, its operational semantics, and the verification semantics. SeaHorn encompasses several novelties: it (a) encodes verification conditions using an efficient yet precise inter-procedural technique, (b) provides flexibility in the verification semantics to allow different levels of precision, (c) leverages the state-of-the-art in software model checking and abstract interpretation for verification, and (d) uses Horn-clauses as an intermediate language to represent verification conditions which simplifies interfacing with multiple verification tools based on Horn-clauses. SeaHorn provides users with a powerful verification tool and researchers with an extensible and customizable framework for experimenting with new software verification techniques. The effectiveness and scalability of SeaHorn are demonstrated by an extensive experimental evaluation using benchmarks from SV-COMP 2015 and real avionics code.

Model Checking↗