Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “computer model calibration”

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 1,045 records · Page 58
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

A predictive discrete-continuum multiscale model of plasticity with quantified uncertainty

Multiscale models of materials, consisting of upscaling discrete simulations to continuum models, are unique in their capability to simulate complex materials behavior. The fundamental limitation in multiscale models is the presence of uncertainty in the computational predictions delivered by them. In this work, a sequential multiscale model has been developed, incorporating discrete dislocation dynamics (DDD) simulations and a strain gradient plasticity (SGP) model to predict the size effect in plastic deformations of metallic micro-pillars. The DDD simulations include uniaxial compression of micro-pillars with different sizes and over a wide range of initial dislocation densities and spatial distributions of dislocations. An SGP model is employed at the continuum level that accounts for the size-dependency of flow stress and hardening rate. Sequences of uncertainty analyses have been performed to assess the predictive capability of the multiscale model. The variance-based global sensitivity analysis determines the effect of parameter uncertainty on the SGP model prediction. The multiscale model is then constructed by calibrating the continuum model using the data furnished by the DDD simulations. A Bayesian calibration method is implemented to quantify the uncertainty due to microstructural randomness in discrete dislocation simulations (density and spatial distribution of dislocations) on the macroscopic continuum model prediction (size effect in plastic deformation). Here, the outcomes of this study indicate that the discrete-continuum multiscale model can accurately simulate the plastic deformation of micro-pillars, despite the significant uncertainty in the DDD results. Additionally, depending on the macroscopic features represented by the DDD simulations, the SGP model can reliably predict the size effect in plasticity responses of the micropillars with below 10% of error.

36 MATERIALS SCIENCE↗
NASA NTRS1984

LANDSAT-4 MSS Geometric Correction: Methods and Results

An automated image registration system such as that developed for LANDSAT-4 can produce all of the information needed to verify and calibrate the software and to evaluate system performance. The on-line MSS archive generation process which upgrades systematic correction data to geodetic correction data is described as well as the control point library build subsystem which generates control point chips and support data for on-line upgrade of correction data. The system performance was evaluated for both temporal and geodetic registration. For temporal registration, 90% errors were computed to be .36 IFOV (instantaneous field of view) = 82.7 meters) cross track, and .29 IFOV along track. Also, for actual production runs monitored, the 90% errors were .29 IFOV cross track and .25 IFOV along track. The system specification is .3 IFOV, 90% of the time, both cross and along track. For geodetic registration performance, the model bias was measured by designating control points in the geodetically corrected imagery.

Brooks, J.↗
NASA NTRS2011

Combustor Operability and Performance Verification for HIFiRE Flight 2

As part of the Hypersonic International Flight Research Experimentation (HIFiRE) Direct-Connect Rig (HDCR) test and analysis activity, three-dimensional computational fluid dynamics (CFD) simulations were performed using two Reynolds-Averaged Navier Stokes solvers. Measurements obtained from ground testing in the NASA Langley Arc-Heated Scramjet Test Facility (AHSTF) were used to specify inflow conditions for the simulations and combustor data from four representative tests were used as benchmarks. Test cases at simulated flight enthalpies of Mach 5.84, 6.5, 7.5, and 8.0 were analyzed. Modeling parameters (e.g., turbulent Schmidt number and compressibility treatment) were tuned such that the CFD results closely matched the experimental results. The tuned modeling parameters were used to establish a standard practice in HIFiRE combustor analysis. Combustor performance and operating mode were examined and were found to meet or exceed the objectives of the HIFiRE Flight 2 experiment. In addition, the calibrated CFD tools were then applied to make predictions of combustor operation and performance for the flight configuration and to aid in understanding the impacts of ground and flight uncertainties on combustor operation.

Storch, Andrea M.↗
DOE OSTI2024

Identifying Bayesian optimal experiments for uncertain biochemical pathway models

Abstract Pharmacodynamic (PD) models are mathematical models of cellular reaction networks that include drug mechanisms of action. These models are useful for studying predictive therapeutic outcomes of novel drug therapies in silico. However, PD models are known to possess significant uncertainty with respect to constituent parameter data, leading to uncertainty in the model predictions. Furthermore, experimental data to calibrate these models is often limited or unavailable for novel pathways. In this study, we present a Bayesian optimal experimental design approach for improving PD model prediction accuracy. We then apply our method using simulated experimental data to account for uncertainty in hypothetical laboratory measurements. This leads to a probabilistic prediction of drug performance and a quantitative measure of which prospective laboratory experiment will optimally reduce prediction uncertainty in the PD model. The methods proposed here provide a way forward for uncertainty quantification and guided experimental design for models of novel biological pathways.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Coupled Hydromechanical Modeling and Assessment of Induced Seismicity at FWU: Utilizing Time-Lapse VSP and Microseismic Data

The objective of this work is to utilize integrated geomechanics, field vertical seismic profile (VSP) and microseismic data to characterize the complex subsurface stress conditions at the Farnsworth Unit (FWU). The model is based on a five-spot sector model extracted from a primary geomechanical model. The five-spot well injection pattern is characterized by extensive reservoir characterization data, such well logs, extracted cores and borehole geophone data, to facilitate the detailed examination of stress changes and microseismic event occurrences. The study utilizes field vertical seismic volumes acquired from the injection well 13-10A. The seismic volumes successfully provided snapshots of the behavior of the reservoir at distinct times. The use of VSP and microseismic data provided direct and indirect estimates of the dynamic stress changes occurring in the overburden, reservoir and underburden rock formations. In order to illuminate the stress regions and identify rocks that have undergone inelastic failure, microseismic event occurrences were utilized. Microseismic activity has been detected at the FWU; further study of its locations, timing, and magnitude was needed to deduce the nature of the changing stress state. The results of the study revealed that microseismic events were successfully modeled within the Morrow B formation. Moment magnitudes of seismic events were within the same magnitudes for events in the reservoir, suggesting the suitability of the model. The results of the study showed that the computed moment magnitudes for seismic events were insignificant to warrant safety concerns. The study findings showed the usefulness of coupled hydromechanical models in predicting the subsurface stress changes associated with CO 2 injection. The knowledge gained from this study will serve as a guideline for industries planning to undertake underground CO 2 storage, and characterize the subsurface stress changes.

02 PETROLEUM↗
NASA NTRS1985

Validation of a fault-tolerant multiprocessor: Baseline experiments and workload implementation

In the future, aircraft must employ highly reliable multiprocessors in order to achieve flight safety. Such computers must be experimentally validated before they are deployed. This project outlines a methodology for validating reliable multiprocessors. The methodology begins with baseline experiments, which tests a single phenomenon. As experiments progress, tools for performance testing are developed. The methodology is used, in part, on the Fault Tolerant Multiprocessor (FTMP) at NASA-Langley's AIRLAB facility. Experiments are designed to evaluate the fault-free performance of the system. Presented are the results of interrupt baseline experiments performed on FTMP. Interrupt causing exception conditions were tested, and several were found to have unimplemented interrupt handling software while one had an unimplemented interrupt vector. A synthetic workload model for realtime multiprocessors is then developed as an application level performance analysis tool. Details of the workload implementation and calibration are presented. Both the experimental methodology and the synthetic workload model are general enough to be applicable to reliable multiprocessors beside FTMP.

Feather, Frank↗
DOE OSTI2023

From BEYONDPLANCK to COSMOGLOBE: Preliminary WMAP Q -band analysis

We present the first application of the COSMOGLOBE analysis framework by analyzing nine-year WMAP time-ordered observations that uses similar machinery to that of BEYONDPLANCK for the Planck Low Frequency Instrument (LFI). We analyzed only the Q-band (41 GHz) data and report on the low-level analysis process based on uncalibrated time-ordered data to calibrated maps. Most of the existing BEYONDPLANCK pipeline may be reused for WMAP analysis with minimal changes to the existing codebase. The main modification is the implementation of the same preconditioned biconjugate gradient mapmaker used by the WMAP team. Producing a single WMAP Q1-band sample requires 22 CPU-hrs, which is slightly more than the cost of a Planck 44 GHz sample of 17 CPU-hrs; this demonstrates that a full end-to-end Bayesian processing of the WMAP data is computationally feasible. In general, our recovered maps are very similar to the maps released by the WMAP team, although with two notable differences. In terms of temperature, we find a ~2 μK quadrupole difference that most likely is caused by different gain modeling, while in polarization we find a distinct 2.5 μK signal that has been previously referred to as poorly measured modes by the WMAP team. In the COSMOGLOBE processing, this pattern arises from temperature-to-polarization leakage from the coupling between the CMB Solar dipole, transmission imbalance, and sidelobes. No traces of this pattern are found in either the frequency map or TOD residual map, suggesting that the current processing has succeeded in modeling these poorly measured modes within the assumed parametric model by using Planck information to break the sky-synchronous degeneracies inherent in the WMAP scanning strategy.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1989

NASA Lewis Stirling engine computer code evaluation

In support of the U.S. Department of Energy's Stirling Engine Highway Vehicle Systems program, the NASA Lewis Stirling engine performance code was evaluated by comparing code predictions without engine-specific calibration factors to GPU-3, P-40, and RE-1000 Stirling engine test data. The error in predicting power output was -11 percent for the P-40 and 12 percent for the Re-1000 at design conditions and 16 percent for the GPU-3 at near-design conditions (2000 rpm engine speed versus 3000 rpm at design). The efficiency and heat input predictions showed better agreement with engine test data than did the power predictions. Concerning all data points, the error in predicting the GPU-3 brake power was significantly larger than for the other engines and was mainly a result of inaccuracy in predicting the pressure phase angle. Analysis into this pressure phase angle prediction error suggested that improvements to the cylinder hysteresis loss model could have a significant effect on overall Stirling engine performance predictions.

Sullivan, Timothy J.↗
NASA NTRS2007

NASA Tech Briefs, January 2007

Topics covered include: Flexible Skins Containing Integrated Sensors and Circuitry; Artificial Hair Cells for Sensing Flows; Video Guidance Sensor and Time-of-Flight Rangefinder; Optical Beam-Shear Sensors; Multiple-Agent Air/Ground Autonomous Exploration Systems; A 640 512-Pixel Portable Long-Wavelength Infrared Camera; An Array of Optical Receivers for Deep-Space Communications; Microstrip Antenna Arrays on Multilayer LCP Substrates; Applications for Subvocal Speech; Multiloop Rapid-Rise/Rapid Fall High-Voltage Power Supply; The PICWidget; Fusing Symbolic and Numerical Diagnostic Computations; Probabilistic Reasoning for Robustness in Automated Planning; Short-Term Forecasting of Radiation Belt and Ring Current; JMS Proxy and C/C++ Client SDK; XML Flight/Ground Data Dictionary Management; Cross-Compiler for Modeling Space-Flight Systems; Composite Elastic Skins for Shape-Changing Structures; Glass/Ceramic Composites for Sealing Solid Oxide Fuel Cells; Aligning Optical Fibers by Means of Actuated MEMS Wedges; Manufacturing Large Membrane Mirrors at Low Cost; Double-Vacuum-Bag Process for Making Resin- Matrix Composites; Surface Bacterial-Spore Assay Using Tb3+/DPA Luminescence; Simplified Microarray Technique for Identifying mRNA in Rare Samples; High-Resolution, Wide-Field-of-View Scanning Telescope; Multispectral Imager With Improved Filter Wheel and Optics; Integral Radiator and Storage Tank; Compensation for Phase Anisotropy of a Metal Reflector; Optical Characterization of Molecular Contaminant Films; Integrated Hardware and Software for No-Loss Computing; Decision-Tree Formulation With Order-1 Lateral Execution; GIS Methodology for Planning Planetary-Rover Operations; Optimal Calibration of the Spitzer Space Telescope; Automated Detection of Events of Scientific Interest; Representation-Independent Iteration of Sparse Data Arrays; Mission Operations of the Mars Exploration Rovers; and More About Software for No-Loss Computing.

Source record↗
DOE OSTI2021

Terry Turbopump Expanded Operating Band Modeling and Simulation Efforts in Fiscal Year 2021 Extended Period of Performance (Final Report)

This report documents the progress made under the Terry Turbine Expanded Operating Band (TTEXOB) program's modeling and simulation (MODSIM) initiative at Sandia National Laboratories (SNL ). It describes the US Federal Fiscal Year 2021 (FY21) extended period-of-performance MODSIM work completed since the closure of FY20 with due reference to the Texas A&M University (TAMU) hybrid milestone 5/6 experimental program. This work, which falls under Milestone 7 of the program, provides a counterpart to the various experiments. The overall TTEXOB program and its milestone-based approach are described in the program's Summary Plan. Details of the individual milestone test plans can be found in the corresponding detailed test plan, e.g. the Milestone 3 and 4 Detailed Test Plan. SNL MODISM is conducted alongside experiments performed at TAMU, and SNL technical staff regularly consults with TAMU on the experimental program. In FY21, MELCOR code models and capabilities were exercised in two different contexts: experimental comparisons to the TAMU ZS-1 and GS-2, and stand-alone analyses of a station black-out (SBO) scenario in a generic boiling water reactor (BWR). Code to experiment comparisons met with fair success when turbine losses were well characterized as for the ZS-1 turbine. Both deterministic and Bayesian calibration processes were used to find a recommended turbine torque multiplier for ZS-1 type turbines. This process could be repeated for GS-2 type turbines if GS-2 losses were better understood. Stand-alone generic BWR SBO calculations revealed that three different modes of self-regulating turbopump behavior may be observed depending on certain modeling parameters and choices having to do with turbine nozzles. Aspects of this predicted behavior may have been observed in TAMU GS-2 experiments.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
NASA NTRSDate not supplied

Scalar Atomic Defect-Based Solid-State Self-calibrating Magnetometer (3SM) for Space Plasma Analysis

The Earth’s magnetosphere is a system of multiple, co-located particle populations interacting via plasma waves. Things to understand are driving processes, radiation belt and ring current issues, auroral physics, internal plasma processes, and magnetosphere-ionosphere mapping issues. These plasma-physics processes enable the Earth’s magnetosphere to evolve in response to temporal changes in the solar wind and they underlie the phenomena of space weather, which impacts spacecraft systems, astronauts, radio communications, and ground based electric-power grids. The objective of 3SM is to measure magnetic field strength and to calibrate the Vector Magnetometer (VM) device to maintain absolute accuracy during a mission. The 3SM features make the instrument preferably suited not only for the traditional role of scalar magnetometers as absolute references for the calibration of the on-board vector instruments, but also for extended operational capacities, such as higher frequency scalar measurements (of potential interest for magnetosphere studies for the low frequency part of the spectrum) or autonomous scalar / vector operations. Diamond has been the solid-state platform of choice for quantum device technologies for some time, however, it suffers from difficulties such as scalability, integration, and cost. While the diamond platform is very useful for quantum technologies, further development is needed to make it viable. The material platform of choice for NASA Glenn’s Quantum Sensing And Spin Physics (Q-SASP) is silicon carbide (SiC). This is due to the much higher industry development of the SiC material platform for high-power and high-temperature electronics. It leverages both the decades-long SiC development expertise and infrastructure at NASA Glenn and its growing capabilities in quantum metrology. To make SiC devices usable for quantum technologies such as quantum sources, a much deeper understanding of defects is needed. Q-SASP is developing quantum metrology capabilities to evaluate the energy structure, defect formation energy, band structure augmentation, generation/recombination rates, and limits of dipole-dipole coupling in non-metal implanted SiC devices. This can be achieved by analysis of zero-field splitting, low-field resonance, and singlet-triplet mixing through various forms of Electrically Detectable Magnetic Resonance (EDMR) and Near-Zero Field Magnetic Resonance (NZFMR) spectroscopy. This work will discuss recent system developments, device developments, computational modeling, and spectroscopy results and analysis of defects created by non-metal implantations in SiC devices. The defect formation energies of V Si ,V C , V C V Si , N C V Si , N Si , N C in 4H-SiC are previously reported values in other research [2]-[3]. The defect formation energies of PSi and PC were calculated in GPAW [fig 1A]. The basic underlying mechanism of the zero-field phenomenon is the mixing of singlet and triplet states [4]-[5]. In most spin-dependent transport, two electron spins are involved, and thus one must consider each of their interactions with the field. We investigated the electronic and magnetic properties of 4H-SiC and 6H-SiC. The defect formation energy helps us determine what types of defects we are observing in the SiC EDMR experiment. They have very low formation energy (it is negative). The phosphorus substitution in 4H-SiC is a very stable defect. The band diagrams provide us with vital information about how the electronic properties of SiC (such as band gap) change as we add non-metal defects. The zero-field splitting parameters allow us to study the inflection point in the NZFMR [fig 1B]. We clearly observed zero-field splitting. We also noted that the zero-field splitting remained constant with changing bias. We aspect it zero-field splitting to remain constant while the hyperfine and exchange interaction perturbations shift under the influence of an external magnetic field. This is the essence of quantum magnetometry and self-calibration.

space plasma↗
NASA NTRS1989

The use of a Navier-Stokes code in the wing design process

The feasibility was determined of incorporating the Navier-Stokes computational code, CFL3D, into the supersonic wing design process. The approach taken is of two steps. The first step was to calibrate CFL3D against existing experimental data sets obtained on thin sharp edged delta wings. The experimental data identified six flow types which are dependent on the similarity parameters of Mach number and angle of attack normal to the leading edge. The calibration showed CFL3D capable of simulating these various separated and attached flow conditions. The second step was to use CFL3D to study the initial formation of leading edge separation over delta wings at supersonic speeds. This consisted of examining solutions obtained on a 65 deg delta wing at Mach number of 1.6 with varying cross sectional shapes. Reynolds number was held constant at 1000000 and the Baldwin-Lomax turbulence model was used. The study showed that through the use of leading edge radius and/or camber, the onset of leading edge separation can be delayed to a higher angle of attack than observed on a flat sharp edged wing. Based on the geometries studied, three wind tunnel models are being designed to verify these results.

Mcmillin, S. Naomi↗
NASA NTRS2005

Transferable Calibration Standard Developed for Quantitative Raman Scattering Diagnostics in High-Pressure Flames

Researchers from NASA Glenn Research Center s Combustion Branch and the Ohio Aerospace Institute (OAI) have developed a transferable calibration standard for an optical technique called spontaneous Raman scattering (SRS) in high-pressure flames. SRS is perhaps the only technique that provides spatially and temporally resolved, simultaneous multiscalar measurements in turbulent flames. Such measurements are critical for the validation of numerical models of combustion. This study has been a combined experimental and theoretical effort to develop a spectral calibration database for multiscalar diagnostics using SRS in high-pressure flames. However, in the past such measurements have used a one-of-a-kind experimental setup and a setup-dependent calibration procedure to empirically account for spectral interferences, or crosstalk, among the major species of interest. Such calibration procedures, being non-transferable, are prohibitively expensive to duplicate. A goal of this effort is to provide an SRS calibration database using transferable standards that can be implemented widely by other researchers for both atmospheric-pressure and high-pressure (less than 30 atm) SRS studies. A secondary goal of this effort is to provide quantitative multiscalar diagnostics in high pressure environments to validate computational combustion codes.

Nguyen, Quang-Viet↗
DOE OSTI2021

TQEA: Temporal Quantum Error Analysis

For the last few years quantum computers have captured researchers’ interest in solving complicated problems in finance, chemistry, machine learning, and many other NP problems. Quantum computing benefits from parallel computation, entanglement, and calculation speedup compared to classical computing. Even though the operations and number of qubits in quantum computers are limited, previous research showed that using quantum computers can be beneficial. These benefits gained researchers’ interest to work on the improvement of quantum computers and overcome the limitations by building more advanced quantum computers with fault tolerance capability, more physical qubits, and better operational gates. In practice, Quantum applications would be translated into Quantum Circuits and each circuit can contain one or many entanglements (s), single qubits operations, and readouts. The importance of running Quantum applications with controlled errors or without errors is critical to the desired result from Quantum readout. In this paper, we study the characteristics of superconducting quantum machines along with the previously proposed methods of Quantum error detection/correction and in order to build a better error model we propose a temporal method for analyzing the the behavior of qubits errors (T1 and T2), frequency of operation, entanglement errors, and readout errors. In order to detect and predict the behavior of each machine, we use simple exponential smoothing analysis on heuristic calibration data. Finally, based on observation, we show that based on frequency, qubits, readout and single operation errors we can build a temporal based model to study and predict the outcome of runs on each Quantum machine.

Baheri, Betis↗
NASA NTRS1978

Variation of solar cell sensitivity and solar radiation on tilted surfaces

An empirical study was performed (1) to evaluate the validity of various insolation models used to compute solar radiation incident on tilted surfaces from global data measured on horizontal surfaces and (2) to determine the variation of solar cell sensitivity to solar radiation over a wide range of atmospheric condition. Evaluation of the insolation data indicates that the isotropic sky model of Liu and Jordan underestimates the amount of solar radiation falling on tilted surfaces by as much as 10%. An anisotropic-clear-sky model proposed by Temps and Coulson was also evaluated and found to be deficient under cloudy conditions. A new model, formulated herein, reduced the deviations between measured and predicted insolation to less than 3%. Evaluation of solar cell sensitivity data indicates small change (2-3%) in sensitivity from winter to summer for tilted cells. The feasibility of using such global data as a means for calibrating terrestrial solar cells as done by Treble is discussed.

Klucher, T. M.↗
DOE OSTI2023

Deep material network via a quilting strategy: visualization for explainability and recursive training for improved accuracy

Recent developments integrating micromechanics and neural networks offer promising paths for rapid predictions of the response of heterogeneous materials with similar accuracy as direct numerical simulations. The deep material network is one such approaches, featuring a multi-layer network and micromechanics building blocks trained on anisotropic linear elastic properties. Once trained, the network acts as a reduced-order model, which can extrapolate the material’s behavior to more general constitutive laws, including nonlinear behaviors, without the need to be retrained. However, current training methods initialize network parameters randomly, incurring inevitable training and calibration errors. Here, we introduce a way to visualize the network parameters as an analogous unit cell and use this visualization to “quilt” patches of shallower networks to initialize deeper networks for a recursive training strategy. The result is an improvement in the accuracy and calibration performance of the network and an intuitive visual representation of the network for better explainability.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Improving High-Energy Particle Detectors with Machine Learning

Microseconds after the Big Bang, the universe existed in a state called the quark-gluon plasma (QGP). To experimentally study its properties, the QGP is recreated in high-energy nuclear collisions at the LHC, and the particles produced from the QGP are reconstructed from their energy deposition in the ATLAS calorimeter. This requires both classifying the particles and calibrating their deposited energy. The objective of this project is to improve the reconstruction by using machine learning techniques, where the energy depositions of clusters of cells, formed by ATLAS topo-clustering methods, are treated as three-dimensional images when inputted to neural networks. This approach significantly improves the calibration of deposited energies when cross-validating while training, and models trained on idealized data predict the calibrated energies of particles in more complex data sets well. Additionally, implementation of a data generator using uproot allows the program to load input data into memory as needed while training or predicting, significantly reducing the amount of memory used. The data generator also allows for use of multiprocessing to speed up training and evaluating. This work illustrates that using machine learning methods for both classification and calibration has the potential to significantly improve particle reconstruction.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Physics-informed machine learning for building performance simulation-A review of a nascent field

Building performance simulation (BPS) is critical for understanding building dynamics and behavior, analyzing the performance of the built environment, optimizing energy efficiency, improving demand flexibility, and enhancing building resilience. However, conducting BPS is not trivial. Traditional BPS relies on accurate building energy models, which are primarily physics-based and heavily dependent on detailed building information, expert knowledge, and case-by-case model calibrations, significantly limiting their scalability. With the development of sensing technology and the increased availability of data, there is growing attention and interest in data-driven BPS. However, purely data-driven models often suffer from limited generalization ability and a lack of physical consistency, resulting in poor performance in real-world applications. To address these limitations, recent studies have begun integrating physics priors into data-driven models, a methodology known as physics-informed machine learning (PIML). PIML is an emerging field where its definitions, methodologies, evaluation criteria, application scenarios, and future directions remain open. To bridge those gaps, this study systematically reviews the state-of-the-art PIML for BPS, offering a comprehensive definition of PIML and comparing it to traditional BPS approaches regarding data requirements, modeling effort, performance, and computational cost. We also summarize the commonly used methodologies, validation approaches, application domains, available data sources, open-source packages, and testbeds. In addition, this study provides a general guideline for selecting appropriate PIML models based on BPS applications. Finally, this study identifies key challenges and outlines future research directions, providing a solid foundation and valuable insights to advance R&D of PIML in BPS.

Jiang, Zixin↗