Physics-informed machine learning with conditional Karhunen-Loève expansions
Not Available
Tartakovsky, A. M. (ORCID:000000032375318X)↗
SEARCH · Engineering Papers
Results for “Physics”
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.
Optimization of an aerostructural machining process using physics-guided Bayesian stability modelling
Existing algorithms for predicting milling chatter have not been widely adopted in industry since they require specialized instruments to measure the stability inputs. This study describes how the machining process for a meter-scale aluminum aerostructure was optimized using a physics-guided Bayesian stability model. The study was performed in collaboration with an industrial partner on production machines to evaluate the practicality of the proposed method under real-world conditions. For each cutting tool, the Bayesian approach automatically selected a small number of cutting tests, which were monitored using a microphone to observe the chatter frequency. The algorithm learned the system dynamics, cutting forces, and stability map from these test results. A novel algorithm for predicting tool bending stress was incorporated into the test selection algorithm to avoid tool breakage. On average, each set of optimized cutting parameters required less than six tests to identify and were 97% more productive than baseline parameters from the cutting tool manufacturer. The machining program was then further optimized using commercial feedrate scheduling software to remove cutting force spikes and reduce air cutting time. Five components were machined using the optimized process. These results demonstrate the potential for physics-guided Bayesian models to improve productivity in industrial settings.
Cornelius, Aaron [UT Knoxville]↗
Hybrid Data-Driven Physics-Based Model Framework Implementation: Towards a Secure Cyber-Physical Operation of the Smart Grid
False data injection cyber-attack detection models on smart grid operation have been much explored recently, considering analytical physics-based and data-driven solutions. Recently, a hybrid data-driven physics-based model framework for monitoring the smart grid is developed. However, the framework has not been implemented in real-time environment yet. In this paper, the framework of the hybrid model is developed within a real-time simulation environment. OPAL-RT real-time simulator is used to enable Hardware-in-the-Loop testing of the framework. IEEE 9-bus system is considered as a testing grid for gaining insight. The process of building the framework and the challenges faced during development are presented. The performance of the framework is investigated under various false data injection attacks.
false data injection attack, machine learning, sta↗
Condition monitoring and anomaly detection in cyber-physical systems
The modern industrial environment is equipping myriads of smart manufacturing machines where the state of each device can be monitored continuously. Such monitoring can help identify possible future failures and develop a cost-effective maintenance plan. However, it is a daunting task to perform early detection with low false positives and negatives from the huge volume of collected data. This requires developing a holistic machine learning framework to address the issues in condition monitoring of high priority components and develop efficient techniques to detect anomalies that can detect and possibly localize the faulty components. This paper presents a comparative analysis of recent machine learning approaches for robust, cost-effective anomaly detection in cyber-physical systems. While detection has been extensively studied, very few researchers have analyzed the localization of the anomalies. We show that supervised learning outperforms unsupervised algorithms. For supervised cases, we achieve near-perfect accuracy of 98% (specifically for tree-based algorithms). In contrast, the best-case accuracy in the unsupervised cases was 63%—the area under the receiver operating characteristic curve (AUC) exhibits similar outcomes as an additional metric.
Marfo, William↗
Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
We developed a new class of physics-informed generative adversarial networks (PI-GANs) to solve forward, inverse, and mixed stochastic problems in a unified manner based on a limited number of scattered measurements. Unlike standard GANs relying solely on data for training, here we encoded into the architecture of GANs the governing physical laws in the form of stochastic differential equations (SDEs) using automatic differentiation. In particular, we applied Wasserstein GANs with gradient penalty (WGAN-GP) for its enhanced stability compared to vanilla GANs. We first tested WGAN-GP in approximating Gaussian processes of different correlation lengths based on data realizations collected from simultaneous reads at sparsely placed sensors. We obtained good approximation of the generated stochastic processes to the target ones even if there is a mismatch between the input noise dimensionality and the effective dimensionality of the target stochastic processes. We also studied the overfitting issue for both the discriminator and the generator, and we found that overfitting occurs also in the generator in addition to the discriminator as previously reported. Subsequently, we considered the solution of elliptic SDEs requiring approximations of three stochastic processes, namely the solution, the forcing, and the diffusion coefficient. Here again, we assumed data collected from simultaneous reads at a limited number of sensors for the multiple stochastic processes. Furthermore, three generators were used for the PI-GANs: two of them were feed forward deep neural networks (DNNs), while the other one was the neural network induced by the SDE. For the case where we have one group of data, we employed one feed forward DNN as the discriminator, while for the case of multiple groups of data we employed multiple discriminators in PI-GANs. We solved forward, inverse, and mixed problems without changing the framework of PI-GANs, obtaining both the means and the standard deviations of the stochastic solution and the diffusion coefficient in good agreement with benchmarks. In this work, we have demonstrated the effectiveness of PI-GANs in solving SDEs for about 120 dimensions. In principle, PI-GANs could tackle very high dimensional problems given more sensor data with low-polynomial growth in computational cost.
97 MATHEMATICS AND COMPUTING↗
On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments
This work describes the investigation of neuromorphic computing-based spiking neural network (SNN) models used to filter data from sensor electronics in high energy physics experiments conducted at the High Luminosity Large Hadron Collider. We present our approach for developing a compact neuromorphic model that filters out the sensor data based on the particle's transverse momentum with the goal of reducing the amount of data being sent to the downstream electronics. The incoming charge waveforms are converted to streams of binary-valued events, which are then processed by the SNN. We present our insights on the various system design choices - from data encoding to optimal hyperparameters of the training algorithm - for an accurate and compact SNN optimized for hardware deployment. Our results show that an SNN trained with an evolutionary algorithm and an optimized set of hyperparameters obtains a signal efficiency of about 91% with nearly half as many parameters as a deep neural network.
R. Kulkarni, Shruti↗
High-power few-cycle Cr:ZnSe mid-infrared source for attosecond soft x-ray physics
The development of mid-infrared, high-energy pulses of extremely short pulse duration is of great importance to the strong-field physics community, as it enables extension of the high-harmonic cutoff towards the keV range of photon energies. Here we demonstrate a C r 2 + : Z n S e laser amplifier delivering 7 mJ, 100 fs pulses at 1 kHz repetition rate and 2.4 µm central wavelength with excellent energy stability and beam quality. These pulses are post-compressed to 39 fs, 6.2 mJ, and 115 GW peak power in a novel nonlinear compression scheme. The laser system was used to generate coherent soft x-ray radiation up to 0.6 keV covering the entire water window, which is of high importance for bio-relevant applications. The obtained results open a wide range of applications in nonlinear optics, attosecond and strong-field physics, and remote sensing.
Leshchenko, Vyacheslav E. (ORCID:0000000199708559)↗
Role of physics in physics-informed machine learning
Physical systems are characterized by inherent symmetries, one of which is encapsulated in the units of their parameters and system states. These symmetries enable a lossless order-reduction, e.g., via dimensional analysis based on the Buckingham theorem. Despite the latter's benefits, machine learning (ML) strategies for the discovery of constitutive laws seldom subject experimental and/or numerical data to dimensional analysis. We demonstrate the potential of dimensional analysis to significantly enhance the interpretability and generalizability of ML-discovered secondary laws. Our numerical experiments with creeping fluid flow past solid ellipsoids show how dimensional analysis enable both deep neural networks and sparse regression reproduce old results, e.g., Stokes law for a sphere, and generate new ones, e.g., an expression for an ellipsoid misaligned with the flow direction. Furthermore, our results suggest the need to incorporate other physics-based symmetries and invariances into ML-based techniques for equation discovery.
97 MATHEMATICS AND COMPUTING↗
Big data health physics: a case study in operational health physics
This paper, written as a two part project as required by Illinois Institute of Technology’s Phys597 Reading & Special Problems class and health physics professional master’s program, focuses on the results of a prototype data collection process implemented at a Los Alamos National Laboratory facility. In particular, this paper examines the data in a statistical context in an effort to optimize operational health physics processes at the Los Alamos National Laboratory.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
Report of the Topical Group on Higgs Physics for Snowmass 2021: The Case for Precision Higgs Physics
A future Higgs Factory will provide improved precision on measurements of Higgs couplings beyond those obtained by the LHC, and will enable a broad range of investigations across the fields of fundamental physics, including the mechanism of electroweak symmetry breaking, the origin of the masses and mixing of fundamental particles, the predominance of matter over antimatter, and the nature of dark matter. Future colliders will measure Higgs couplings to a few per cent, giving a window to beyond the Standard Model (BSM) physics in the 1-10 TeV range. In addition, they will make precise measurements of the Higgs width, and characterize the Higgs self-coupling. Here, this report details the work of the EF01 and EF02 working groups for the Snowmass 2021 study.
Dawson, Sally↗
Kaon physics without new physics in $$ \varepsilon _K$$
Abstract Despite the observation of significant suppressions of $$b\rightarrow s\mu ^+\mu ^-$$ b → s μ + μ - branching ratios no clear sign of New Physics (NP) has been identified in $$\Delta F=2$$ Δ F = 2 observables $$\Delta M_{d,s}$$ Δ M d , s , $$\varepsilon _K$$ ε K and the mixing induced CP asymmetries $$S_{\psi K_S}$$ S ψ K S and $$S_{\psi \phi }$$ S ψ ϕ . Assuming negligible NP contributions to these observables allows to determine CKM parameters without being involved in the tensions between inclusive and exclusive determinations of $$|V_{cb}|$$ | V cb | and $$|V_{ub}|$$ | V ub | . Furthermore this method avoids the impact of NP on the determination of these parameters present likely in global fits. Simultaneously it provides SM predictions for numerous rare K and B branching ratios that are most accurate to date. Analyzing this scenario within $$Z^\prime $$ Z ′ models we point out, following the 2009 observations of Monika Blanke and ours of 2020, that despite the absence of NP contributions to $$\varepsilon _K$$ ε K , significant NP contributions to $$K^+\rightarrow \pi ^+\nu {\bar{\nu }}$$ K + → π + ν ν ¯ , $$K_{L}\rightarrow \pi ^0\nu {\bar{\nu }}$$ K L → π 0 ν ν ¯ , $$K_S\rightarrow \mu ^+\mu ^-$$ K S → μ + μ - , $$K_L\rightarrow \pi ^0\ell ^+\ell ^-$$ K L → π 0 ℓ + ℓ - , $$\varepsilon '/\varepsilon $$ ε ′ / ε and $$\Delta M_K$$ Δ M K can be present. In the simplest scenario, this is guaranteed, as far as flavour changes are concerned, by a single non-vanishing imaginary left-handed $$Z^\prime $$ Z ′ coupling $$g^L_{sd}$$ g sd L . This scenario implies very stringent correlations between the Kaon observables considered by us. In particular, the identification of NP in any of these observables implies automatically NP contributions to the remaining ones under the assumption of non-vanishing flavour conserving $$Z^\prime $$ Z ′ couplings to $$q{\bar{q}}$$ q q ¯ , $$\nu {\bar{\nu }}$$ ν ν ¯ , and $$\mu ^+\mu ^-$$ μ + μ - . A characteristic feature of this scenario is a strict correlation between $$K^+\rightarrow \pi ^+\nu {\bar{\nu }}$$ K + → π + ν ν ¯ and $$K_{L}\rightarrow \pi ^0\nu {\bar{\nu }}$$ K L → π 0 ν ν ¯ branching ratios on a branch parallel to the Grossman-Nir bound. Moreover, $$\Delta M_K$$ Δ M K is automatically suppressed as seems to be required by the results of the RBC-UKQCD lattice QCD collaboration. Furthermore, there is no NP contribution to $$K_L\rightarrow \mu ^+\mu ^-$$ K L → μ + μ - which otherwise would bound NP effects in $$K^+\rightarrow \pi ^+\nu {\bar{\nu }}$$ K + → π + ν ν ¯ . Of particular interest are the correlations of $$K^+\rightarrow \pi ^+\nu {\bar{\nu }}$$ K + → π + ν ν ¯ and $$K_{L}\rightarrow \pi ^0\nu {\bar{\nu }}$$ K L → π 0 ν ν ¯ branching ratios and of $$\Delta M_K$$ Δ M K with the ratio $$\varepsilon '/\varepsilon $$ ε ′ / ε . We investigate the impact of renormalization group effects in the context of the SMEFT on this simple scenario.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Kilonovae Across the Nuclear Physics Landscape: The Impact of Nuclear Physics Uncertainties on r-process-powered Emission
Merging neutron stars produce “kilonovae”—electromagnetic transients powered by the decay of unstable nuclei synthesized via rapid neutron capture (the r-process) in material that is gravitationally unbound during inspiral and coalescence. Kilonova emission, if accurately interpreted, can be used to characterize the masses and compositions of merger-driven outflows, helping to resolve a long-standing debate about the origins of r-process material in the Universe. We explore how the uncertain properties of nuclei involved in the r-process complicate the inference of outflow properties from kilonova observations. Using r-process simulations, we show how nuclear physics uncertainties impact predictions of radioactive heating and element synthesis. For a set of models that span a large range in both predicted heating and final abundances, we carry out detailed numerical calculations of decay product thermalization and radiation transport in a kilonova ejecta with a fixed mass and density profile. The light curves associated with our models exhibit great diversity in their luminosities, with peak brightness varying by more than an order of magnitude. We also find variability in the shape of the kilonova light curves and their color, which in some cases runs counter to the expectation that increasing levels of lanthanide and/or actinide enrichment will be correlated with longer, dimmer, redder emission.
73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
Automated extraction of physical parameters from experimentally obtained thermal profiles using a machine learning approach
Explore the source record for details and available documents.
99 GENERAL AND MISCELLANEOUS↗
Physical vapor deposition process for engineering Pt based oxygen reduction reaction catalysts on NbOx templated carbon support
Explore the source record for details and available documents.
99 GENERAL AND MISCELLANEOUS↗
Mass spectrometric analyses of high performance polymers to assess their radiopurity as ultra low background materials for rare event physics detectors
Not Available
Grate, Jay W. (ORCID:0000000221638383)↗
LHC physics dataset for unsupervised New Physics detection at 40 MHz
In the particle detectors at the Large Hadron Collider, hundreds of millions of proton-proton collisions are produced every second. If one could store the whole data stream produced in these collisions, tens of terabytes of data would be written to disk every second. The general-purpose experiments ATLAS and CMS reduce this overwhelming data volume to a sustainable level, by deciding in real-time whether each collision event should be kept for further analysis or be discarded. We introduce a dataset of proton collision events that emulates a typical data stream collected by such a real-time processing system, pre-filtered by requiring the presence of at least one electron or muon. This dataset could be used to develop novel event selection strategies and assess their sensitivity to new phenomena. In particular, we intend to stimulate a community-based effort towards the design of novel algorithms for performing unsupervised new physics detection, customized to fit the bandwidth, latency and computational resource constraints of the real-time event selection system of a typical particle detector.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Quantum information meets high-energy physics: input to the update of the European strategy for particle physics
Some of the most astonishing and prominent properties of Quantum Mechanics, such as entanglement and Bell nonlocality, have only been studied extensively in dedicated low-energy laboratory setups. The feasibility of these studies in the high-energy regime explored by particle colliders was only recently shown and has gathered the attention of the scientific community. For the range of particles and fundamental interactions involved, particle colliders provide a novel environment where quantum information theory can be probed, with energies exceeding by about 12 orders of magnitude those employed in dedicated laboratory setups. Furthermore, collider detectors have inherent advantages in performing certain quantum information measurements and allow for the reconstruction of the state of the system under consideration via quantum state tomography. Here, we elaborate on the potential, challenges, and goals of this innovative and rapidly evolving line of research and discuss its expected impact on both quantum information theory and high-energy physics.
Physics↗