SEARCH · Engineering Papers

Results for “Training Time”

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.

SourceResearch connectionFrom yearThrough year

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

At least 1,477 records · Page 82

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Using a Large Language Model as a Building Block to Generate Usable Validation and Verification Suite for OpenMP

In the HPC area, both hardware and software move quickly. Often new hardware is developed and deployed, the corresponding software stack, including compilers and other tools, are under active development while leading edge software developers are working to port and tune their applications, all at the same time. While the software ecosystem is in flux, one of the key challenges for users is obtaining insight into the state of implementation of key features in the programming languages and models their applications are using – whether they have been implemented, and whether the implementation conforms to the specification, especially for newly implemented features (less tested by widespread use). OpenMP is one of the most prominent shared memory programming models used for on-node programming in HPC. With the shift towards accelerators (such as GPUs and FPGAs) and heterogeneous programming OpenMP features are getting more complex. It is natural to ask whether generative AI approaches, and large language models (LLMs) in particular, can help in producing validation and verification test suites to allow users better and faster insights into the availability and correctness of OpenMP features of interest. In this work, we explore the use of ChatGPT-4 to generate a suite of tests for OpenMP features. We have chosen a set of directives and clauses, a total of 78 combinations, which first appeared in OpenMP 3.0 (released in May 2008) but are also relevant for accelerators. We prompted ChatGPT to generate tests in the C and Fortran languages, for both host (CPU) and device (accelerator). On the Summit super-computer using the GNU implementation, we found that, of the 78 generated tests 67 C tests and 43 Fortran tests compiled successfully and fewer than those executed to completion. On further analysis we show that not all generated tests are valid. We document the process, results, and provide detailed analysis regarding the quality of tests generated. With the aim of providing input to a production quality validation and verification suite, we manually implement the corrections required to make the tests valid according to the current OpenMP specification. We quantify this effort as small, medium, or large, and record the lines of code changed to correct the invalid tests. With the corrected tests we validate recent implementations from HPE, AMD, and GNU on the Frontier supercomputer. Our experiment and subsequent analysis show that although LLMs are capable of producing HPC specific codes, they are limited by their understanding of the deeper semantics and restrictions of programming models such as OpenMP. Unsurprisingly more commonly used features have better support, while some OpenMP 3.0 directives such as sections and tasking are not universally supported on accelerators. We demonstrate that successful compilation and execution to completion are inadequate metrics for evaluating generated code and that, at this time, commodity LLMs require expert intervention for code verification. This points to gaps in the training data that is currently available for HPC. We demonstrate that with "small" effort 37% of generated invalid C tests and 63% of generated invalid Fortran tests could be corrected. This improves productivity of test generation as we circumvent writing from scratch and the common programming errors associated with it.

Pophale, Swaroop [ORNL] (ORCID:0000000185446367)↗

DOE OSTI2022

Multirobot Collaborative Pursuit Target Robot by Improved MADDPG

Policy formulation is one of the main problems in multirobot systems, especially in multirobot pursuit-evasion scenarios, where both sparse rewards and random environment changes bring great difficulties to find better strategy. Existing multirobot decision-making methods mostly use environmental rewards to promote robots to complete the target task that cannot achieve good results. This paper proposes a multirobot pursuit method based on improved multiagent deep deterministic policy gradient (MADDPG), which solves the problem of sparse rewards in multirobot pursuit-evasion scenarios by combining the intrinsic reward and the external environment. The state similarity module based on the threshold constraint is as a part of the intrinsic reward signal output by the intrinsic curiosity module, which is used to balance overexploration and insufficient exploration, so that the agent can use the intrinsic reward more effectively to learn better strategies. The simulation experiment results show that the proposed method can improve the reward value of robots and the success rate of the pursuit task significantly. The intuitive change is obviously reflected in the real-time distance between the pursuer and the escapee, the pursuer using the improved algorithm for training can get closer to the escapee more quickly, and the average following distance also decreases.

Zhou, Xiao↗

DOE OSTI2023

BuildingsBench: A Benchmark for Universal Building Load Forecasting [SWR-23-51]

The residential and commercial building stock in the United States is responsible for a significant percentage of energy consumption and greenhouse gas emissions. Electrification of end-uses, as well as decarbonizing the electrical grid through renewable energy sources such as solar and wind, constitutes the pathway to zero-emission buildings. Forecasting day-ahead building energy consumption is an integral part of this solution. Currently, specialized forecasting models are hand-made for each individual building, which is time-consuming, expensive, and leads to duplicated efforts. BuildingsBench is a Python software framework for training and comparing generalized machine learning models for universal building load forecasting. This challenge tasks a single foundational model to generalize its forecasts for a wide variety of buildings, across geographic regions, building types, weather patterns, and more. This software provide code for pre-training such models and subsequently evaluating their performance on a suite of hundreds of diverse real and synthetic buildings. BuildingsBench is a platform for: - Large-scale pretraining with the synthetic Buildings-900K dataset for short-term load forecasting (STLF). Buildings-900K is statistically representative of the entire U.S. building stock and is extracted from the NREL End-Use Load Profiles database. - Benchmarking on two tasks evaluating generalization: zero-shot STLF and transfer learning for STLF. We provide an index-based PyTorch Dataset for large-scale pretraining, easy data loading for multiple real building energy consumption datasets as PyTorch Tensors or Pandas DataFrames, simple (persistence) to advanced (transformer) baselines, metrics management, and more.

Emami, Patrick↗

DOE OSTI2024

Exploring 2D X-ray diffraction phase fraction analysis with convolutional neural networks: Insights from kinematic-diffraction simulations

Abstract Deep-learning models are effective for analyzing the complex information in 2D X-ray diffraction (XRD) patterns. Accurately collecting parameters of the material sample is crucial during model training, significantly impacting model performance. In this study, we employ a kinematic-diffraction simulator to generate simulated 2D XRD patterns for Ti–6Al–4V alloy, allowing precise control of sample parameters. These simulated patterns are used to train convolutional neural networks, predicting $$\upbeta$$ β -phase volume fractions. The training data set consists exclusively of 2D XRD patterns with pure $$\upalpha$$ α - or pure $$\upbeta$$ β -phase, while the testing set incorporates patterns with intermediate phase volume fraction. In particular, we investigate how the architectures of the model influence prediction reliability and computational performance. Experimental results reveal that, with appropriate training, the convolutional neural network accurately detects intermediate phase volume fractions even trained with only pure-phase patterns, achieving a mean square error accuracy of $$9.4 \times 10^{-4}$$ 9.4 × 10 - 4 . Graphical abstract

Yue, Weiqi↗

NASA NTRS1971

What Made Apollo A Success?

Spacecraft development, mission design planning, flight crew operations, and flight operations are considered. Spacecraft design principles and test activities are described. Determination of the best series of flights leading to a lunar landing at the earliest possible time, flight planning, techniques for establishing flight procedures and carrying out flight operations, and crew training and simulation activities are discussed.

Source record↗

NASA NTRS1973

Automatic photointerpretation for land use management in Minnesota

The author has identified the following significant results. Progress is being made in the areas of sun angle and atmospheric effects on the data and its interpretation. The effort is aimed at correction using only navigation and calendar data needed for satellite operation and derivations from the MSS data. Water estimation of value to land planners and conservationists has been demonstrated with verification of performance by comparison with a concurrent study involving map planimetry, aerial photos, and field-checking. The satellite will provide seasonal and annual coverage with timely information in a way not now feasible by conventional methods. For example, the reference data were obtained using the most recent files, which date back to 1949, and from most recent photography taken in 1968. The calendar time involved was three to four months, which is a reflection on priority pressure on trained manpower available. ERTS-1 data can help relieve this problem by providing the needed information while freeing trained manpower for more appropriate parts of the effort.

Swanlund, G. D.↗

NASA NTRS1981

As-built design specification for the CLASFYG program

This program produces a file with a Universal-formatted header and data records in a nonstandard format. Trajectory coefficients are calculated from 5 to 8 acquisitions of radiance values in the training field corresponding to an agricultural product. These coefficients are then used to calculate a time of emergence and corresponding trajectory coefficients for each pixel in the test field. The time of emergence, two of the coefficients, and the sigma value for each pixel are written to the file.

Horton, C. L.↗

NASA NTRS1993

Hidden Markov models for fault detection in dynamic systems

The invention is a system failure monitoring method and apparatus which learns the symptom-fault mapping directly from training data. The invention first estimates the state of the system at discrete intervals in time. A feature vector x of dimension k is estimated from sets of successive windows of sensor data. A pattern recognition component then models the instantaneous estimate of the posterior class probability given the features, p(w(sub i) perpendicular to x), 1 less than or equal to i is less than or equal to m. Finally, a hidden Markov model is used to take advantage of temporal context and estimate class probabilities conditioned on recent past history. In this hierarchical pattern of information flow, the time series data is transformed and mapped into a categorical representation (the fault classes) and integrated over time to enable robust decision-making.

Smyth, Padhraic J.↗

NASA NTRS1994

The role of mission operations in spacecraft integration and test

The participation of mission operations personnel in the spacecraft integration and test process offers significant benefits to spacecraft programs in terms of test efficiency, staffing and training efficiency, test completeness, and subsequent cost containment. Operations personnel who have had real-time contact experience and have been responsible for the assessment of on orbit spacecraft operations bring a unique view of spacecraft operations to pre-launch spacecraft test activities. Because of the unique view of the spacecraft/ground interface that experienced operations personnel have, they can propose optimum test approaches and optimum test data analysis techniques. Additionally, the testing that is typically required to validate operations methodologies can be integrated into spacecraft performance testing scenarios.

Harvey, Raymond J.↗

NASA NTRS1995

Hidden Markov models for fault detection in dynamic systems

The invention is a system failure monitoring method and apparatus which learns the symptom-fault mapping directly from training data. The invention first estimates the state of the system at discrete intervals in time. A feature vector x of dimension k is estimated from sets of successive windows of sensor data. A pattern recognition component then models the instantaneous estimate of the posterior class probability given the features, p(w(sub i) (vertical bar)/x), 1 less than or equal to i isless than or equal to m. Finally, a hidden Markov model is used to take advantage of temporal context and estimate class probabilities conditioned on recent past history. In this hierarchical pattern of information flow, the time series data is transformed and mapped into a categorical representation (the fault classes) and integrated over time to enable robust decision-making.

Smyth, Padhraic J.↗

NASA NTRS1999

Modelling the firing pattern of bullfrog vestibular neurons responding to naturalistic stimuli

We have developed a neural system identification method for fitting models to stimulus-response data, where the response is a spike train. The method involves using a general nonlinear optimisation procedure to fit models in the time domain. We have applied the method to model bullfrog semicircular canal afferent neuron responses during naturalistic, broad-band head rotations. These neurons respond in diverse ways, but a simple four parameter class of models elegantly accounts for the various types of responses observed. c1999 Elsevier Science B.V. All rights reserved.

Non-NASA Center↗

NASA NTRSDate not supplied

Data Augmentation for Intelligent Contingency Management Using Generative Adversarial Neural Networks

Artificial intelligence (AI)-based techniques for intelligent contingency management (ICM) require that intelligent agents learn various aspects of system dynamics to create and execute contingencies. For high assurance contingency management, agents achieve the most compelling results through supervised or semi-supervised machine learning, for which agents require large datasets to learn the dynamics of the system. Unfortunately, data collection in aerospace applications can be costly, due to both time and resources. Presented work describes a framework for data augmentation of ICM databases containing training data for machine learning models. This framework populates the database with the outputs of generative adversarial network (GAN) models that were trained on flight data. Methods for evaluating the suitability of these models based on the equations of motion, as well as other physical constraints, are discussed. The paper demonstrates the utility of this database for training intelligent agents on the NASA T2 generic transport aircraft model and experimental vertical takeoff and landing (VTOL) simulation model.

Generative Machine Learning↗

NASA NTRSDate not supplied

Data Augmentation for Intelligent Contingency Management Using Generative Adversarial Neural Networks

Generative Machine Learning↗

NASA NTRS2021

Automated Data Accountability for Missions in Mars Rover Data

As the Mars Curiosity Rover transmits data to the JPL Ground Data System (GDS), it frequently observes data loss and corruption, requiring re-transmits from the rover and Ground Data System Analysts (GDSA) to monitor the downlink process. As new missions are launched, the GDSA team redistributes analysts to these new missions, causing shortages in previous missions. The GDSA team can significantly benefit from the automation and optimization of the downlink process of telemetry data. In fact, there is a need for a better understanding of why the data is corrupted, so that the GDSA team can best determine the root cause of the issues in the GDS. This paper presents machine learning and deep learning based approaches to automate and optimize the detection of data loss. We first created a pipeline to automatically accumulate data from the telemetry databases (MAROS, Telemetry Data Storage, and GDS Elastic Search Database) in the downlink process. With our newly created datasets, we perform feature selection to supplement the GDSA understanding of the downlink process and provide supplemental analysis on the importance of different features. We implement various machine learning and deep learning based models, including support vector machines, ensemble methods, and deep neural networks and evaluate their accuracies in identifying whether a downlink process is complete or incomplete. We utilize fast hyperparameter optimization methods that allow our models to quickly be re-trained, allowing them to quickly be tuned and optimized on daily incoming data in real time. This hyperparameter optimization also allows our methods to be quickly integrated into other JPL missions. Our results show that our best-performing machine learning and deep learning based models outperform the existing GDSA detection software by 6 accuracy points and can aid analysts by providing insights into the data accountability problem. Since these various machine learning and deep learning approaches vary significantly in interpretability, we provide a discussion on the tradeoffs between their performance and trustworthiness in helping detect issues in data transmission.

Divsalar, Dariush↗

DOE OSTI2026

Fermilab VALOR Program

The Veteran Applied Laboratory Occupational Retraining (VALOR) Program is an expansion of Fermilab’s established VetTech internship program originally initiated in 2016. The enhanced program seeks to recruit, hire, train, and retain veterans and transitioning service members by providing multiple entry points for full time STEM-based careers at Fermilab. VALOR is comprised of four paid internships/apprenticeships supplemented by professional development opportunities.

Fermilab, Fermilab↗

NASA NTRS2001

Techniques for Improving Pilot Recovery from System Failures

This project examined the application of intelligent cockpit systems to aid air transport pilots at the tasks of reacting to in-flight system failures and of planning and then following a safe four dimensional trajectory to the runway threshold during emergencies. Two studies were conducted. The first examined pilot performance with a prototype awareness/alerting system in reacting to on-board system failures. In a full-motion, high-fidelity simulator, Army helicopter pilots were asked to fly a mission during which, without warning or briefing, 14 different failures were triggered at random times. Results suggest that the amount of information pilots require from such diagnostic systems is strongly dependent on their training; for failures they are commonly trained to react to with a procedural response, they needed only an indication of which failure to follow, while for 'un-trained' failures, they benefited from more intelligent and informative systems. Pilots were also found to over-rely on the system in conditions were it provided false or mis-leading information. In the second study, a proof-of-concept system was designed suitable for helping pilots replan their flights in emergency situations for quick, safe trajectory generation. This system is described in this report, including: the use of embedded fast-time simulation to predict the trajectory defined by a series of discrete actions; the models of aircraft and pilot dynamics required by the system; and the pilot interface. Then, results of a flight simulator evaluation with airline pilots are detailed. In 6 of 72 simulator runs, pilots were not able to establish a stable flight path on localizer and glideslope, suggesting a need for cockpit aids. However, results also suggest that, to be operationally feasible, such an aid must be capable of suggesting safe trajectories to the pilot; an aid that only verified plans entered by the pilot was found to have significantly detrimental effects on performance and pilot workload. Results also highlight that the trajectories suggested by the aid must capture the context of the emergency; for example, in some emergencies pilots were willing to violate flight envelope limits to reduce time in flight - in other emergencies the opposite was found.

Pritchett, Amy R.↗

NASA NTRS2018

Addressing Human Error in International Space Station Flight Control Teams: Advances in Ground Training for Science Operators

In flight control, as with any human in the loop system, operator error is an inevitable reality. On the International Space Station (ISS) where crew time and physical resources are precious and often irreplaceable, operator errors can result in significant, irreversible consequences. Flight controllers at the Payload Operations Integration Center (POIC) located at NASA's Marshall Space Flight Center (MSFC) in Huntsville, Alabama know this reality well. At the POIC, operator errors can be caused by a variety of factors, from poor hardware or software design to environmental factors such as time pressure or fatigue. The most difficult errors to address, however, are those which result from ineffective teamwork. To address these teamwork errors, trainers at the POIC have drawn best practices from high reliability industries as well as from our sister ISS control center at the Johnson Space Center (JSC) in Houston, Texas, to develop and implement a new training program focused specifically on teamwork skills. This training program, called Team Skills Training, is inspired by modern and historical training programs developed by NASA and is specifically tailored to the needs of the payload operations flight control team at the POIC. The program consists of training for both certified and trainee flight controllers, and covers team skills topics such as situational awareness, leadership, and communication skills. To maximize effectiveness, the program uses novel instructional techniques which extend beyond the classroom to encourage students to apply what they have learned to their day to day work. Minimizing operator errors in flight control is an endeavor which requires constant vigilance and continuous improvement. At the POIC, Team Skills Training is an important step in this journey.

Harris, Samantha S.↗

NASA NTRS2022

Multi-Mission Terrain Classifier for Safe Rover Navigation and Automated Science

We previously presented Soil Property and Object Classification (SPOC), a machine learning-based terrain classifier for Mars rovers, for automatically segmenting rover images by its surface type such as sand and bedrock. This paper presents a number of practical improvements to pave the way for potential future onboard deployment. First, we achieved 97.0% overall pixel accuracy, evaluated against the classification generated by human experts on images from Mars Science Laboratory (MSL) missions. The substantial increase in accuracy was primarily enabled by the sheer volume of data used for training; we created a new large-scale dataset of Martian terrain labels, namely AI4Mars, which contains more than 400k labels contributed by citizen scientists for 50k images taken by the Mars Exploration Rovers (MER) and Mars Science Laboratory (MSL) rover. Second, we demonstrated that SPOC can quickly adapt to a new mission landed on a previously unseen site. Specifically, we pretrained a model with MER and MSL data from the AI4Mars dataset and then adapted to the Mars 2020 Rover (M2020) by feeding a small volume of data between Sol 0 and 157; the adapted model was tested on Sol 200-203 and resulted in 84.2% overall pixel accuracy and 93.4% reliability (recall) for detecting sand, the most concerning class for rover’s traversability. Third, we found that pretraining can substantially mitigate the decline of accuracy over time. We showed that the performance of a SPOC model pretrained with the ImageNet dataset and then trained by MSL images only up to Sol 390 remains comparable to a model trained by images up to Sol 1689 on the test data after Sol 1689. Fourth, we reimplemented SPOC with a light-weight convolutional neural network (CNN), MobileNetV2, which typically runs within tens of milliseconds (ms) on mobile processors such as Qualcomm’s Snapdragon. Finally, we released the AI4Mars dataset to the public to encourage open innovation.

Ono, Masahiro↗