Search NASA⌕ Search

SEARCH · Search NASA

Results for “PINNs”

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.

16 records
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Flow Reconstruction in A Transonic Turbine Cascade Using Physics-Informed Neural Networks (PINNS)

This paper investigates the application of Physics-Informed Neural Networks (PINNs) for the analysis of turbine blades in a transonic cascade. The 2-D flow field in a transonic turbine cascade is reconstructed in three ways: the traditional forward approach (PINN not trained on experimental data), by training the PINN using discrete sets of experimentally measured pressure at midspan, and in the inverse sense where no inlet or outlet pressure boundary conditions are applied. Comparisons between the PINN solutions to measured data are made. This is repeated for three different turbine blades with distinct loading characteristics. Good agreement is shown between a CFD calculation of the CMC7 blade, and the PINN model trained with all data. The PINN is trained utilizing all available data, half the available data, data from only the leading edge region, and data from only the trailing edge region. The forward problem results deviate the most from experimental data but show promise. Solutions from the assisted training cases show that the PINN can reconstruct the flow field with acceptable accuracy when trained on measurements along the entire blade. In the inverse case, it is shown that to simultaneously achieve acceptable errors for inlet Mach number and outlet isentropic Mach number, the PINN must be trained on the static pressure data along the entire blade.

Machine Learning↗
NASA NTRSDate not supplied

GT2024-128885: Flow Reconstruction in a Transonic Turbine Cascade using Physics-Informed Neural Networks (PINNs)

This presentation investigates the application of Physics-Informed Neural Networks (PINNs) for the analysis of turbine blades in a transonic cascade. PINNs are a machine learning method trained on losses calculated from reconstructed governing equations, assigned boundary/initial conditions, and measured data. We reconstruct the 2-D flow field in a transonic turbine cascade in two ways: the traditional forward approach (without training/experimental data) and by training the PINN using experimental data. We then compare the PINN solutions to measured data. This is repeated for three different turbine blades with distinct loading characteristics. The experimental data used for training is the static pressure measurements along the suction and pressure sides of each blade. The PINN is trained utilizing all available data, half the available data, data from only the leading edge region, and data from only the trailing edge region. It's shown that the PINN can reconstruct the flow field in all cases with acceptable errors. Cases where the PINN is trained on all the data, and even half the data, resulted in the lowest errors. The exit Mach number is inferred for each case and compared to the experimentally calculated value.

Machine Learning↗
NASA NTRS2019

Physically-Informed Artificial Neural Networks for Atomistic Modeling of Materials

A new approach is presented for the development of classical interatomic potentials using physically-informed neural networks (PINN) combined with an analytical bond-order atomic interaction model. Due to the strong physical underpinnings, the PINN potentials demonstrate much better transferability than the existing machine-learning potentials while drastically improving the accuracy in comparison with traditional potentials. PINN potentials can be constructed for both metallic and covalent materials in a unified manner. A number of applications of PINN potentials to large-scale molecular dynamics and Monte Carlo simulations and calculation of thermal and mechanical properties of diverse materials are demonstrated. Some of the specific materials systems include silicon and aluminum, as well as alloys and compounds. Computational aspects of PINN potentials are discussed and future developments in this field are outlined.

J Hickman↗
NASA NTRSDate not supplied

Predicting Melt Properties Using Atomistic Simulations With A Highly Accurate Physically Informed Neural Network Interatomic Potential

The use of a recently developed machine learning (ML) interatomic potential for molecular dynamics simulations of aluminum melt properties will be presented. Such properties are critical for process modeling in additive manufacturing, including the melt pool size, solidification, and formation of solidification microstructures. Direct first-principles modeling of these processes is computationally prohibitive whereas simulations employing ML potentials combine the high accuracy of quantum-mechanical methods with high computational speeds. The physically-informed neural network (PINN) method used herein, integrates a high-dimensional regression implemented by an artificial neural network with a physics-based bond-order interatomic potential. PINN potentials can accurately reproduce many properties of aluminum in both crystalline-solid and liquid phases. We examine the accuracy of a PINN Al potential in predicting the density, self-diffusivity, viscosity, and the tension of the liquid surface and liquid-solid interfaces. Comparison with experimental data and ab initio molecular dynamics calculations shows very good agreement for all properties tested.

molecular dynamics↗
NASA NTRSDate not supplied

Physics-Guided Deep Learning for Complex System Health Management and Decision Making

The landscape of complex engineered systems is rapidly evolving, from smart manufacturing facilities to next-generation transportation vehicles. As these systems become increasingly sophisticated and interconnected, the need for advanced health management systems grows ever more critical. These systems must go beyond simple monitoring, actively predicting potential failures before they occur. This paradigm shift from fixed maintenance schedules to condition-based predictions is key to optimizing system performance, enhancing safety, and paving the way for autonomous decision-making across various industries. Whether in industrial processes, energy systems, or advanced transportation, the ability to anticipate and prevent failures is becoming a cornerstone of operational excellence. To accurately predict the future health of any complex system, knowledge of its current health state and future operational conditions is essential. Recent advancements in data-driven algorithms have generated growing interest in artificial intelligence for industrial applications. However, the limitations of pure data-driven methods, particularly in industries where data acquisition is costly and limited, have become apparent. This has led to a focus on blending physics with data-driven algorithms, mitigating the drawbacks of both approaches while emphasizing their respective advantages. This research proposes a novel framework for integrating physics-based performance models with deep learning algorithms for the prognostics of complex safety-critical systems. In this approach, physics-based models serve as a blueprint, capturing fundamental system behaviors, while deep learning algorithms, leveraging real-world sensor data, fill in gaps and identify subtle patterns indicative of potential problems. This hybrid methodology, utilizing techniques such as Physics-Informed Neural Networks (PINNs), offers a powerful solution for predicting system health. By fusing domain knowledge with data-driven insights, this approach promises more accurate, adaptable, and reliable models for health prediction. The resulting framework is versatile, applicable across various sectors including aerospace, manufacturing, and energy systems, ultimately contributing to safer, more efficient operations in our increasingly complex technological landscape.

Diagnostics↗
NASA NTRS1964

The X-Irradiation of Hydrazine and 1,1- Dimethylhydrazine

Hydrazine and 1,1-dimethylhydrazine were radiolyzed at room temperature by using about 1 gram of liquid or 1/2 to 2 liters of vapor at room-temperature vapor pressure. A tungsten-target X-ray source operating at 300 kilovolts and 6 to 8 milliamperes (0.1 to 1.0 A) was used at intensities of 1 times 10 (sup 2) to 1 times 10 (sup 3) roentgens per minute to give total doses of 4.1 rads to 2.3 times 10 (sup 6) rads. The amounts of decomposition were dependent on total dose and independent of dose rate. In the case of hydrazine vapor, the decomposition was also directly related to surface area. There was a lesser surface effect with liquid hydrazine, but this variable was not studied for 1,1-dimethylhydrazine. The order of decreasing sensitivity to X-radiation is as follows: hydrazine vapor, 1,1-dimethylhydrazine vapor, 1,1-dimethylhydrazine liquid, and hydrazine liquid. The decomposition products of hydrazine were nitrogen, hydrogen, ammonia, and unidentified products. The same products plus methylamine, dimethylamine, and hydrazine were found from the decomposition of 1,1-dimethylhydrazine. In addition, the 1,1-dimethylhydrazine underwent post-irradiation changes. Values for G (number of molecules of sample decomposed per 100 electronvolts of absorbed energy) of the order of 10 (sup 6) suggest that the vapor-phase decompositions are chain reactions.

X-RAY IRRADIATION↗
NASA NTRS1954

Study of the physical properties of petrolatum-stabilized magnesium-hydrocarbon slurry fuels

Magnesium-hydrocarbon slurries containing a moderate proportion of petrolatum have physical properties such that they offer promise as experimental aircraft fuels. The settling of the magnesium is greatly retarded by the petrolatum, and the slurries can easily be remixed to their original condition after storage. Successive batches which have closely similar properties can be prepared readily. The apparent viscosity of these slurries increased rapidly with increasing magnesium concentration, with increasing petrolatum concentration, and with decreasing temperature. As the apparent viscosity increased, the extent of settling and the ease of remixing both decreased. Although no quantitative correlation was found between the properties of the slurry and those of the petrolatum, and no one petrolatum gave slurries which were best in all respects, one of the five petrolatum used was judged to be superior to the others.

FUELS - PROPERTIES, PHYSICAL AND CHEMICAL↗
NASA NTRS1955

Effect of Surface-active Additives on Physical Properties of Slurries of Vapor-process Magnesium

The presence of 3 to 5 percent surface-active additive gave the lowest Brookfield apparent viscosity, plastic viscosity, and yield value that were obtained for slurry fuels containing approximately 50 percent vapor-process magnesium in JP-1 fuel. The slurries settled little and were easily remixed. A polyoxyethylene dodecyl alcohol was the most effective of 13 additives tested in reducing the Brookfield apparent viscosity and the yield value of the slurry. The seven most effective additives all had a hydroxyl group plus an ester or polyoxethylene group in the molecule. The densities of some of the slurries were measured.

Pinns, Murray L↗
NASA NTRS1958

NACA Research on Slurry Fuels

An extensive program was conducted to investigate the use of concentrated slurries of boron and magnesium in liquid hydrocarbon as fuels for afterburners and ramjet engines. Analytical calculations indicated that magnesium fuel would give greater thrust and that boron fuel would give greater range than are obtainable from jet hydrocarbon fuel alone. It was hoped that the use of these solid elements in slurry form would permit the improvement to be obtained without requiring unconventional fuel systems or combustors. Small ramjet vehicles fueled with magnesium slurry were flown successfully, but the test flights indicated that further improvement of combustors and fuel systems was needed.

Pinns, M L↗
NASA NTRSDate not supplied

Li-ion Battery Aging with Hybrid Physics-Informed Neural Networks and Fleet-wide Data

In this work, we propose a hybrid model for Li-ion battery discharge and aging prediction that leverages fleet-wide data to predict future capacity drops.The model is built upon an hybrid approach merging physics-based and empirical equations, as well as neural network models in a recurrent neural network cell. The hybrid physics-informed neural network can predict voltage discharge cycles given the loading profile, and estimate the used capacity of the battery under random-loading conditions by tracking aging parameters connected to the residual capacity of the battery. By merging information on the battery aging parameters with existing fleet-wide aging data, the model can predict the future residual capacity of the battery that is being monitored, and therefore enable predictions of voltage discharge curves far ahead in the battery life cycle. We validated the approach using the NASA Prognostics Data Repository Battery data-set, which contains experimental data on Li-ion batteries discharged at random loading conditions in a controlled environment. The approach also allows the identification of discrepancies between the battery aging trend and the trend observed at the fleet level, so that batteries behaving differently from the rest of the fleet can be subject to closer monitoring and further testing to refine predictions.

PINN↗
NASA NTRSDate not supplied

Hybrid Modeling for Complex Systems Health Management

The research work presents application of hybrid physics-informed machine learning to a representative electric powertrain for unmanned aerial vehicles. The model is composed of physics-derived and empirical equations, integrated with connected networks that are strategically placed within the model to substitute equations that are subject to large uncertainty. Polynomial fit driven by heuristics or empirical observations can be substituted by more flexible networks that can minimize the error between model predictions and observations without being restricted to a predefined functional form. This modeling strategy allows training of networks deep inside the model and unknown parameters in a single learning stage. The powertrain model consists of Li-ion batteries, electronic speed controller with pulse-width modulation, and brush-less DC motor with connected propeller. Results obtained from combination of laboratory and simulation tests are discussed in this work.

PINNS↗