Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “RANDOMNESS”

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 1,333 records · Page 74
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Improved Statistical Analysis for the Neutrinoless Double-Beta Decay Matrix Element of 136Xe

Neutrinoless double beta decay nuclear matrix element (M0ν) for 136Xe was recently analyzed using a statistical approach (Phys. Rev. C 107, 045501 (2023)). In the analysis, three initial shell model effective Hamiltonians were randomly altered, and their results for 23 measured observables were used to infer credibility for the M0ν nuclear matrix element (NME) based on a Bayesian Model Averaging approach. In that analysis, a reasonable Gamow-Teller quenching factor of 0.7 was assumed for each starting effective Hamiltonian. Given that the result of the statistical analysis was sensible to this choice, we are here improving that analysis by assuming that the Gamow-Teller quenching factor is also randomly chosen within reasonabe limits for all three starting Hamiltonians. The outcomes are slightly higher expectation values and uncertainties for the M0ν NME.

Astronomy & Astrophysics↗
DOE OSTI2021

Distant Relatives: The Chemical Homogeneity of Comoving Pairs Identified in Gaia

Comoving pairs, even at the separations of $\mathcal{O}$(10 6 ) are a predicted reservoir of conatal stars. Here we present detailed chemical abundances of 62 stars in 31 comoving pairs with separations of 10 2 –10 7 au and 3D velocity differences <2 km s -1 . This sample includes both bound comoving pairs/wide binaries and unbound comoving pairs. Observations were taken using the Magellan Inamori Kyocera Echelle (MIKE) spectrograph on board the Magellan/Clay Telescope at high resolution (R~ 45,000) with a typical signal-to-noise ratio of 150 pixel -1 . With these spectra, we measure surface abundances for 24 elements, including Li, C, Na, Mg, Al, Si, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Sr, Y, Zr, Ba, La, Nd, and Eu. Taking iron as the representative element, our sample of wide binaries is chemically homogeneous at the level of 0.05 dex, which agrees with prior studies on wide binaries. Importantly, even systems at separations 2 × 10 5 –10 7 au are homogeneous to 0.09 dex, as opposed to the random pairs, which have a dispersion of 0.23 dex. Assuming a mixture model of the wide binaries and random pairs, we find that 73 ± 22% of the comoving pairs at separations 2 × 10 5 –10 7 au are conatal. Our results imply that a much larger parameter space of phase space may be used to find conatal stars, to study M-dwarfs, star cluster evolution, exoplanets, chemical tagging, and beyond.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Using machine learning to derive cloud condensation nuclei number concentrations from commonly available measurements

Cloud condensation nuclei (CCN) number concentrations are an important aspect of aerosol–cloud interactions and the subsequent climate effects; however, their measurements are very limited. We use a machine learning tool, random decision forests, to develop a random forest regression model (RFRM) to derive CCN at 0.4 % supersaturation ([CCN0.4]) from commonly available measurements. The RFRM is trained on the long-term simulations in a global size-resolved particle microphysics model. Using atmospheric state and composition variables as predictors, through associations of their variabilities, the RFRM is able to learn the underlying dependence of [CCN0.4] on these predictors, which are as follows: eight fractions of PM 2.5 (NH 4 , SO 4 , NO 3, secondary organic aerosol (SOA), black carbon (BC), primary organic carbon (POC), dust, and salt), seven gaseous species (NO x , NH 3 , O 3 , SO 2 , OH, isoprene, and monoterpene), and four meteorological variables (temperature (T), relative humidity (RH), precipitation, and solar radiation). The RFRM is highly robust: it has a median mean fractional bias (MFB) of 4.4 % with ≈96.33 % of the derived [CCN0.4] within a good agreement range of -60% 2.5 speciation (NH 4 , SO 4 , NO 3 , and organic carbon (OC)), NO x , O 3 , SO 2 , T, and RH, as well as [CCN0.4] are available. We modify, optimize, and retrain the developed RFRM to make predictions from 19 to 9 of these available predictors. This retrained RFRM (RFRM-ShortVars) shows a reduction in performance due to the unavailability and sparsity of measurements (predictors); it captures the [CCN0.4] variability and magnitude at SGP with ≈67.02 % of the derived values in the good agreement range. This work shows the potential of using the more commonly available measurements of PM 2.5 speciation to alleviate the sparsity of CCN number concentrations' measurements.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Spatial patterns of snow distribution in the sub-Arctic

Abstract. The spatial distribution of snow plays a vital role in sub-Arctic and Arctic climate, hydrology, and ecology due to its fundamental influence on the water balance, thermal regimes, vegetation, and carbon flux. However, the spatial distribution of snow is not well understood, and therefore, it is not well modeled, which can lead to substantial uncertainties in snow cover representations. To capture key hydro-ecological controls on snow spatial distribution, we carried out intensive field studies over multiple years for two small (2017–2019; ∼ 2.5 km2) sub-Arctic study sites located on the Seward Peninsula of Alaska. Using an intensive suite of field observations (> 22 000 data points), we developed simple models of the spatial distribution of snow water equivalent (SWE) using factors such as topographic characteristics, vegetation characteristics based on greenness (normalized different vegetation index, NDVI), and a simple metric for approximating winds. The most successful model was random forest, using both study sites and all years, which was able to accurately capture the complexity and variability of snow characteristics across the sites. Approximately 86 % of the SWE distribution could be accounted for, on average, by the random forest model at the study sites. Factors that impacted year-to-year snow distribution included NDVI, elevation, and a metric to represent coarse microtopography (topographic position index, TPI), while slope, wind, and fine microtopography factors were less important. The characterization of the SWE spatial distribution patterns will be used to validate and improve snow distribution modeling in the Department of Energy's Earth system model and for improved understanding of hydrology, topography, and vegetation dynamics in the sub-Arctic and Arctic regions of the globe.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

The importance of round-robin validation when assessing machine-learning-based vertical extrapolation of wind speeds

The extrapolation of wind speeds measured at a meteorological mast to wind turbine rotor heights is a key component in a bankable wind farm energy assessment and a significant source of uncertainty. Industry-standard methods for extrapolation include the power-law and logarithmic profiles. The emergence of machine-learning applications in wind energy has led to several studies demonstrating substantial improvements in vertical extrapolation accuracy in machine-learning methods over these conventional power-law and logarithmic profile methods. In all cases, these studies assess relative model performance at a measurement site where, critically, the machine-learning algorithm requires knowledge of the rotor-height wind speeds in order to train the model. This prior knowledge provides fundamental advantages to the site-specific machine-learning model over the power-law and log profiles, which, by contrast, are not highly tuned to rotor-height measurements but rather can generalize to any site. Furthermore, there is no practical benefit in applying a machine-learning model at a site where winds at the heights relevant for wind energy production are known; rather, its performance at nearby locations (i.e., across a wind farm site) without rotor-height measurements is of most practical interest. To more fairly and practically compare machine-learning-based extrapolation to standard approaches, we implemented a round-robin extrapolation model comparison, in which a random-forest machine-learning model is trained and evaluated at different sites and then compared against the power-law and logarithmic profiles. We consider 20 months of lidar and sonic anemometer data collected at four sites between 50 and 100 km apart in the central United States. We find that the random forest outperforms the standard extrapolation approaches, especially when incorporating surface measurements as inputs to include the influence of atmospheric stability. When compared at a single site (the traditional comparison approach), the machine-learning improvement in mean absolute error was 28 % and 23 % over the power-law and logarithmic profiles, respectively. Using the round-robin approach proposed here, this improvement drops to 20 % and 14 %, respectively. These latter values better represent practical model performance, and we conclude that round-robin validation should be the standard for machine-learning-based wind speed extrapolation methods.

17 WIND ENERGY↗
DOE OSTI2025

Energy Infrastructure Futures: A Multiscale Evaluation of Projected Power Plant Siting Across the Western Interconnection

Energy Infrastructure Futures: A Multiscale Evaluation of Projected Power Plant Siting Across the Western Interconnection Description This dataset contains input and output data for the manuscript Mongird, K. et al. (under review) titled "Energy Infrastructure Futures: A Multiscale Evaluation of Projected Power Plant Siting Across the Western Interconnection". Input data corresponds to gridded spatial siting attributes that are necessary to conduct a random forest machine learning analysis of siting feature importance. Output data includes SHAP feature analysis outputs, and classification report values. For data on power plant siting results referred to in the manuscript, please refer to the CERF: IM3 Projected Western US Power Plant Locations data download page. The downloadable data includes values for eight different future scenarios for the Western US. The scenarios include combinations of two Shared Socioeconomic Pathways (SSP3 and SSP5) with four high-resolution climate projections specific to the United States (see, https://tgw-data.msdlive.org/). These climate projections include "hotter" and "cooler" variants for two Representative Concentration Pathways (RCP4.5 and RCP8.5). The resulting eight simulations are: rcp45cooler_ssp3 rcp45cooler_ssp5 rcp45hotter_ssp3 rcp45hotter_ssp5 rcp85cooler_ssp3 rcp85cooler_ssp5 rcp85hotter_ssp3 rcp85hotter_ssp5 Technical Information The dataset includes two sets of data files: (1) CERF gridded siting parameters and (2) Feature analysis outputs and classification reports. All downloadable data is in csv file format. Files with x/y coordinate information use the Albers Equal Area Conic projection (ESRI:102003). 1. CERF Gridded Siting Parameters This directory provides a balanced sample of gridded CERF siting parameters data for eight different scenarios for the Western US through 2055, seven different technologies, and eight timesteps. This data serves as input to the feature analysis. It contains the following parameters. region_name - name of region (i.e., state) sited - binary value representing whether the grid cell received a siting of that technology type (1=True) rcp - binary value representing scenario resource concentration pathway (0 = RCP4.5, 1 = RCP8.5) ssp - binary value representing scenario shared socioeconomic pathway (0 = SSP3, 1 = SSP5) climate - binary value representing cooler (0) or hotter (1) GCM forcing tech_name - generation technology name sited_year - year that values correspond to transmission_cost - cost of transmission interconnection pipeline_cost - cost of natural gas pipeline interconnection interconnection_cost - total interconnection cost (sum of transmission cost and gas pipeline cost) lmp - associated locational marginal value ($/MWh) associated with the grid cell, timestep, scenario, and technology xcoord - x-coordinate of location ycoord - y-coordinate of location 2a. Feature Analysis Output The dataset includes the feature analysis shap output for locational marginal price and interconnection cost. It contains the following parameters. technology - generator technology name scenario - name of scenario feature - name of feature, either locational_marginal_price or interconnection_cost value - the mean of absolute value of SHAP values for given feature 2b. Feature Analysis Classification Report This download includes the classification report associated with each random forest model. The dataset contains the following parameters. technology - generation technology name scenario - name of scenario test - one of precision (the proportion of predicted positives that are actually correct), recall (the proportion of actual positives that were correctly identified), f1-score (the harmonic mean of precision and recall) 0.0 - value of test for classification of 0 (grid cell not chosen for siting) 1.0 - value of test for classification of 1 (grid cell chosen for siting) accuracy - accuracy of model (i.e., fraction of all predictions that were right) macro avg - Simple average of test values for all classes weighted avg - Weighted average of test values for all classes, weighted based on Acknowledgment IM3 is a multi-institutional effort led by Pacific Northwest National Laboratory and supported by the U.S. Department of Energy's Office of Science as part of research in MultiSector Dynamics, Earth and Environmental Systems Modeling Program. License This data is made available under a CCBY4 License Disclaimer This material was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor the United States Department of Energy, nor the Contractor, nor any or their employees, nor any jurisdiction or organization that has cooperated in the development of these materials, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness or any information, apparatus, product, software, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof, or Battelle Memorial Institute. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof. PACIFIC NORTHWEST NATIONAL LABORATORYoperated byBATTELLEfor theUNITED STATES DEPARTMENT OF ENERGYunder Contract DE-AC05-76RL01830

Mongird, Kendall [Pacific Northwest National Labor↗
DOE OSTI2025

Testing convolutional neural network based deep learning systems: a statistical metamorphic approach

Machine learning technology spans many areas and today plays a significant role in addressing a wide range of problems in critical domains,i.e., healthcare, autonomous driving, finance, manufacturing, cybersecurity,etc. Metamorphic testing (MT) is considered a simple but very powerful approach in testing such computationally complex systems for which either an oracle is not available or is available but difficult to apply. Conventional metamorphic testing techniques have certain limitations in verifying deep learning-based models (i.e., convolutional neural networks (CNNs)) that have a stochastic nature (because of randomly initializing the network weights) in their training. In this article, we attempt to address this problem by using a statistical metamorphic testing (SMT) technique that does not require software testers to worry about fixing the random seeds (to get deterministic results) to verify the metamorphic relations (MRs). We propose seven MRs combined with different statistical methods to statistically verify whether the program under test adheres to the relation(s) specified in the MR(s). We further use mutation testing techniques to show the usefulness of the proposed approach in the healthcare space and test two CNN-based deep learning models (used for pneumonia detection among patients). The empirical results show that our proposed approach uncovers 85.71% of the implementation faults in the classifiers under test (CUT). Furthermore, we also propose an MRs minimization algorithm for the CUT, thus saving computational costs and organizational testing resources.

Computer Science↗
DOE OSTI2024

Experimental trials of species-specific bat flight responses to an ultrasonic deterrent

Unintended consequences of increasing wind energy production include bat mortalities from wind turbine blade strikes. Ultrasonic deterrents (UDs) have been developed to reduce bat mortalities at wind turbines. Our goal was to experimentally assess the species-specific effectiveness of three emission treatments from the UD developed by NRG Systems. We conducted trials in a flight cage measuring approximately 60 m × 10 m × 4.4 m (length × width × height) from July 2020 to May 2021 in San Marcos, Texas, USA. A single UD was placed at either end of the flight cage, and we randomly selected one for each night of field trials. Trials focused on a red bat species group (Lasiurus borealis and Lasiurus blossevillii; n = 46) and four species: cave myotis (Myotis velifer; n = 57), Brazilian free-tailed bats (Tadarida brasiliensis; n = 73), evening bats (Nycteceius humeralis; n = 53), and tricolored bats (Perimyotis subflavus; n = 17). The trials occurred during three treatment emissions: low (emissions from subarrays at 20, 26, and 32 kHz), high (emissions from subarrays at 38, 44, and 50 kHz), and combined (all six emission frequencies). We placed one wild-captured bat into the flight cage for each trial, which consisted of an acclimation period, a control period with the UD powered off, and the three emission treatments (order randomly selected), each interspersed with a control period. We tracked bat flight using four thermal cameras placed outside the flight cage. We quantified the effectiveness of each treatment by comparing the distances each bat flew from the UD during each treatment vs. the control period using quantile regression. Additionally, we conducted an exploratory analysis of differences between sex and season and sex within season using analysis of variance. Broadly, UDs were effective at altering the bats’ flight paths as they flew farther from the UD during treatments than during controls; however, results varied by species, sex, season, and sex within season. For the red bat group, bats flew farther from the UD during all treatments than during the control period at all percentiles (p < 0.001), and treatments were comparable in effectiveness. For cave myotis, all percentile distances were farther from the UD during each of the treatments than during the control, except the 90th percentile distance during high, and low was most effective. For evening bats and Brazilian free-tailed bats, results were inconsistent, but high and low were most effective, respectively. For tricolored bats, combined and low were significant at the 10th–75th percentiles, high was significant at all percentiles, and combined was most effective. Results suggest UDs may be an effective means of reducing bat mortalities due to wind turbine blade strikes. We recommend that continued research on UDs focus on low emission treatments, which have decreased sound attenuation and demonstrated effectiveness across the bat species evaluated in this study.

17 WIND ENERGY↗
DOE OSTI2019

Method and apparatus for reducing memory access latency

Logic such as a memory controller writes primary data from an incoming write request as well as corresponding replicated primary data (which is a copy of the primary data) to one or more different memory banks of random access memory in response to determining a memory access contention condition for the address (including a range of addresses) corresponding to the incoming write request. When the memory bank containing the primary data is busy servicing a write request, such as to another row of memory in the bank, a read request for the primary data is serviced by reading the replicated primary data from the different memory bank of the random access memory to service the incoming read request.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Nonlinear power flow control for networked AC/DC microgrids

A method for designing feedforward and feedback controllers for integration of stochastic sources and loads into a nonlinear networked AC/DC microgrid system is provided. A reduced order model for general networked AC/DC microgrid systems is suitable for HSSPFC control design. A simple feedforward steady state solution is utilized for the feedforward controls block. Feedback control laws are provided for the energy storage systems. A HSSPFC controller design is implemented that incorporates energy storage systems that provides static and dynamic stability conditions for both the DC random stochastic input side and the AC random stochastic load side. Transient performance was investigated for the feedforward/feedback control case. Numerical simulations were performed and provided power and energy storage profile requirements for the networked AC/DC microgrid system overall performance. The HSSPFC design can be implemented in the Matlab/Simulink environment that is compatible with real time simulation/controllers.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Using the Monte Carlo Method to Evaluate the Reliability of Screening Multifamily Housing for Radon

When screening for radon in a multifamily housing complex using a fixed sample density (e.g., testing 1 in 10 (10%) or 1 in 4 units (25%)), the statistical confidence is dependent upon the assumed elevated radon frequency. For example, testing 25% of units in a complex estimated to have eight units with elevated radon levels will provide 90% confidence. However, if it is assumed that, in the same complex, there are only three units with elevated radon levels, the confidence drops to around 58% for the same sample density. Furthermore, in the previous example, if elevated radon levels are not found during the screening, all that can be stated is that the screening provides 90% confidence that there are no more than seven units in the complex with elevated radon levels. To more fully illustrate this uncertainty, ten separate multifamily housing radon data sets with 1 to 10 units with radon levels ≥4 pCi/L (Table 1) were selected for analysis using the Monte Carlo statistical method. Unlike other mathematically based statistical approaches, the Monte Carlo statistical method relies on repeated analysis of randomly selected data. from a 100% sampled complex at various sample densities. Success for each simulation is defined as finding at least one unit with elevated radon levels. In this statistical method, confidence in the overarching conclusion can be greatly enhanced by repeating the simulated screening hundreds or even thousands of times. For this study, each of the ten data sets was simulated 1,000 times. For each simulation, the data set was randomized three times before the fixed percentage of data was selected.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2021

System and method for obfuscation of electronic circuits

A computer-implemented method of generating randomized electrical interconnects for an electronic circuit comprises steps of receiving a netlist of nodes of electronic components to be connected, each connection between the nodes forming an electrical interconnect; determining a list of one or more path directions for each electrical interconnect; determining a plurality of path direction distances for each electrical interconnect; generating a plurality of segments for each electrical interconnect, each segment having one path direction and a length which are selected at random; calculating a sum of the lengths of all of the segments in each path direction each time a segment is generated for each electrical interconnect; removing one path direction from the list of path directions when a first condition is met; and stopping the generating a plurality of segments for each electrical interconnect when a second condition is met.

Trujillo, Joshua↗
DOE OSTI2022

GANISP: A GAN-Assisted Importance Splitting Probability Estimator

Designing manufacturing processes with high yield and strong reliability relies on effective methods for rare event estimation. Genealogical importance splitting reduces the variance of rare event probability estimators by iteratively selecting and replicating realizations that are headed towards a rare event. The replication step is difficult when applied to deterministic systems where the initial conditions of the offspring realizations need to be modified. Typically, a random perturbation is applied to the offspring to differentiate their trajectory from the parent realization. However, this random perturbation strategy may be effective for some systems while failing for others, preventing variance reduction in the probability estimate. This work seeks to address this limitation using a generative model such as a Generative Adversarial Network (GAN) to generate perturbations that are consistent with the attractor of the dynamical system. The proposed GAN-assisted Importance SPlitting method (GANISP) improves the variance reduction for the system targeted. An implementation of the method is available in a companion repository (https://github.com/NREL/GANISP).

generative adversarial network↗
DOE OSTI2022

GANISP: A GAN-Assisted Importance Splitting Probability Estimator: Preprint

To reduce the variance of rare event probability estimator, genealogical importance splitting marches towards a rare event by iteratively selecting and replicating realizations that are headed towards a rare event. The replication step is made difficult when applied to deterministic systems as the initial conditions of the offspring realizations need to be modified. Typically, a random perturbation is applied to the offspring to differentiate their trajectory from the parent realization. It is shown that a random perturbation strategy may be effective for some systems but may also fail for others, thereby preventing variance reduction in the probability estimate. To address this limitation, it is proposed to use a generative model such as a Generative Adversarial Network (GAN) to generate perturbations that are consistent with the attractor of the dynamical system. The GAN-assisted Importance SPlitting method (GANISP) improves the variance reduction for the system targeted. An implementation of the method is available in a companion repository (https://github.com/NREL/GANISP).

generative adversarial network↗
DOE OSTI2022

System and method for x-ray compatible 2D streak camera for a snapshot multiframe imager

The present disclosure is directed to a snapshot multiframe imager having an aperture element having at least one aperture, an adjacently positioned random mask, an imaging element and a computer. The random mask has a plurality of micron scale apertures and receives light passing through the aperture element, which represents the spatial information from the scene being imaged, and generates a plurality of image frames encoded in a spatial domain. The imaging element may operate in a drift-scan mode receives the encoded image frames and generates a streaked pattern of electrons representing a plurality of images of the scene at a plurality of different times. The computer analyzes the streaked pattern of electrons and mathematically reconstructs the plurality of images.

Dayton, Matthew S.↗
DOE OSTI2022

System and method for obfuscation of electronic circuits

A computer-implemented method of generating randomized electrical interconnects for an electronic circuit comprises steps of receiving a netlist of nodes of electronic components to be connected, each connection between the nodes forming an electrical interconnect; determining a list of one or more path directions for each electrical interconnect; determining a plurality of path direction distances for each electrical interconnect; generating a plurality of segments for each electrical interconnect, each segment having one path direction and a length which are selected at random; calculating a sum of the lengths of all segments of the plurality of segments in each path direction each time a segment is generated for each electrical interconnect; removing one path direction from the list of path directions when a first condition is met; and stopping the generating a plurality of segments for each electrical interconnect when a second condition is met.

Trujillo, Joshua↗
DOE OSTI2023

Label Assist: Personalized Travel Models for Longitudinal Data Collection

Understanding travel behavior is crucial to transportation decarbonization. OpenPATH is an open-source mobility platform which collects and analyzes human travel behavior at the individual level. The mobile application passively senses trips and prompts users to label them. However, users find the labeling process burdensome; less than half the trips are typically labeled, making much of the data unusable in aggregate analyses of mobility patterns. Prior work has addressed the response fatigue challenge through automated mode inference using sensor data, but sensors cannot capture all aspects of travel behavior. We explore an alternative approach in which we leverage prior user input to predict travel choices in novel trips. We first explore trip clustering methods and develop a novel two-step pipeline using DBSCAN and SVMs to extract realistic geospatial clusters. We then propose two strategies to predict trip labels: (i) clustering trips and extrapolating labels for similar trips, and (ii) random forest classification. The random forest approach is able to achieve - $70-80% accuracy (purpose: 72%, mode: 79%, replaced mode: 81%). These novel approaches to trip classification allow us to increase the rate of user labeling by suggesting predicted labels to be verified by the user. Unlabeled trips can also contribute to aggregate analyses, using label predictions and their associated confidences as a substitute. While there exist other travel survey apps with the ability to infer travel choices, to our knowledge, this is the first paper to describe such a supervised system and rigorously evaluate it.

ADVANCED PROPULSION SYSTEMS,ENERGY PLANNING, POLIC↗
DOE OSTI2023

Lithium-Ion Battery Diagnostics Using Electrochemical Impedance via Machine-Learning

Diagnosing battery states such as health, state-of-charge, or temperature is crucial for ensuring the safety and reliability of electrochemical energy storage systems. While some states, such as temperature, may be measured using cheap sensors, accurate diagnosis of battery health metrics usually requires time-consuming performance measurements, making them infeasible for use in real-world operation. These health metrics can be measured during lab-testing and then estimated on-line using predictive life models or via state observer algorithms such as Kalman filters, but these predictive methods should be supplemented by actual measurement of battery health whenever possible to ensure reliability. Rapid measurement of battery health may be done by various types of fast diagnostic techniques such as electrochemical impedance spectroscopy (EIS), which can be performed in only a few minutes and require only a fraction of the energy and power needed for a full charge and discharge measurement. But there is a substantial challenge for estimating battery health using EIS data, as EIS is sensitive to cell temperature, state-of-charge, current, and resting time in addition to health. Thus, utilizing EIS data to predict battery capacity requires correcting for all these additional variables, a task that is extremely difficult to handle analytically. This talk utilizes machine-learning methods to estimate the effectiveness of battery capacity prediction from EIS data, leveraging a data set of hundreds of EIS measurements recorded at varying temperature and state-of-charge throughout a 500-day aging study of 32 commercial, large-format NMC-Graphite lithium-ion batteries. Using EIS as input to machine-learning models is complicated by the nonlinear response of impedance to battery health, temperature, and state-of-charge, as well as the collinearity between the impedance response at neighboring frequencies, which can easily lead to overfit models. To train robust models, features from EIS data need to be extracted from the data or some subset of critical frequencies selected. Many approaches for extracting and selecting features from EIS data from electrochemical analysis and machine-learning fields were identified for analysis: using the entire raw spectra; selection of one, two, or many frequencies from the entire spectra; selecting interesting points from the EIS measurement using domain knowledge; fitting EIS with an equivalent-circuit model; calculating statistics on the raw impedance values; and reducing the dimensionality of the data using unsupervised linear (principal component analysis) and non-linear (uniform manifold approximation and projection) methods. These approaches were rigorously compared using a machine-learning pipeline approach, training linear, Gaussian process, and random forest regression models and quantifying performance using cross-validation as well as a held-out test set. An artificial neural network model trained on the raw spectra was also tested. Promising pipelines were fine-tuned via Bayesian hyperparameter optimization using cross-validation loss and training with class-specific weights to counter data set imbalance. The most reliable method for utilizing impedance in this work was the selection of two optimal frequencies through an exhaustive search, resulting in about 2% mean absolute error on test data for both Gaussian process and random forest model architectures. Interrogation of a variety of models reveals critical frequencies of 100 Hz and 103 Hz for this data set, though the optimal set of frequencies is not necessarily intuitive, i.e., the best performing models are not simply those that use impedance at frequencies that have the highest correlation to the relative discharge capacity. The best performing model is an ensemble model, which is able to predict battery capacity with 1.9% mean absolute error for unseen cells using impedance recorded at a variety of temperatures and states-of-charge.

battery↗