Bat492: Machine Learning for Accelerated Life Prediction and Cell Design 2021
This presentation details work in the early prediction, classification and quantification of battery failure modes and life performance.
25 ENERGY STORAGE↗
SEARCH · Engineering Papers
Results for “life prediction”
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.
A Multiphysics Multiscale Simulation Platform for Damage, Environmental Degradation, and Life Prediction of CMCs in Extreme Environments
This project successfully developed a multiphysics, multiscale computational framework to enhance the design and development of CMCs, with a focus on modeling highly nonlinear, time-dependent damage mechanisms and material degradation under extreme conditions, such as those experienced in turbine service environments. The project made significant advances in improving our understanding of progressive damage, oxidative degradation, and time-dependent inelastic deformation in CMCs, with particular attention to the role of uncertainties in predictions. Key outcomes include the integration of advanced material characterization, uncertainty quantification, and multiphysics constitutive models to predict the behavior of CMCs over their service life. A novel multiscale methodology was employed, which integrated microscale constituent behaviors with structural-scale responses, enabling the manufacturing defects in the microstructure that are prone to damage nucleation. Through the development of DL algorithms, the project advanced the prediction of damage initiation and crack propagation, taking into account the defect morphology and statistical variations across multiple scales. The framework was rigorously validated using thermomechanical experiments, which tested CMCs under various mechanical loadings at elevated temperatures, further enhancing the model's predictive capability. Overall, the research outcomes have provided a more accurate, reliable method for predicting CMC component life, significantly advancing material design, and improving component reliability in extreme environments. This work has strong implications for the optimization of turbine components and other high-performance applications where CMCs are used.
03 NATURAL GAS↗
A comparison of fatigue life prediction methodologies for rotorcraft
Because of the current U.S. Army requirement that all new rotorcraft be designed to a 'six nines' reliability on fatigue life, this study was undertaken to assess the accuracy of the current safe life philosophy using the nominal stress Palmgrem-Miner linear cumulative damage rule to predict the fatigue life of rotorcraft dynamic components. It has been shown that this methodology can predict fatigue lives that differ from test lives by more than two orders of magnitude. A further objective of this work was to compare the accuracy of this methodology to another safe life method called the local strain approach as well as to a method which predicts fatigue life based solely on crack growth data. Spectrum fatigue tests were run on notched (k(sub t) = 3.2) specimens made of 4340 steel using the Felix/28 tests fairly well, being slightly on the unconservative side of the test data. The crack growth method, which is based on 'small crack' crack growth data and a crack-closure model, also predicted the fatigue lives very well with the predicted lives being slightly longer that the mean test lives but within the experimental scatter band. The crack growth model was also able to predict the change in test lives produced by the rainflow reconstructed spectra.
Everett, R. A., Jr.↗
Predicting Life And Reliability Of A Rotating Disk
Report of generalized method for prediction of fatigue life and reliability of rotating disk. Method incorporates computation of life, at given probability of survival, of elemental stressed volumes within body of disk. Effects of design variables, temperature gradients, and speeds examined. Useful in analysis, design, and development of disks for aircraft-engine turbines and compressors and flywheels for industrial and automotive applications.
Zaretsky, Erwin V.↗
Thermal barrier coating life prediction model development
The objective of this program is to establish a methodology to predict Thermal Barrier Coating (TBC) life on gas turbine engine components. The approach involves experimental life measurement coupled with analytical modeling of relevant degradation modes. The coating being studied is a flight qualified two layer system, designated PWA 264, consisting of a nominal ten mil layer of seven percent yttria partially stabilized zirconia plasma deposited over a nominal five mil layer of low pressure plasma deposited NiCoCrAlY. Thermal barrier coating degradation modes being investigated include: thermomechanical fatigue, oxidation, erosion, hot corrosion, and foreign object damage.
Demasi, J. T.↗
End-of-Discharge and End-of-Life Prediction in Lithium-Ion Batteries with Electrochemistry-Based Aging Models
As batteries become increasingly prevalent in complex systems such as aircraft and electric cars, monitoring and predicting battery state of charge and state of health becomes critical. In order to accurately predict the remaining battery power to support system operations for informed operational decision-making, age-dependent changes in dynamics must be accounted for. Using an electrochemistry-based model, we investigate how key parameters of the battery change as aging occurs, and develop models to describe aging through these key parameters. Using these models, we demonstrate how we can (i) accurately predict end-of-discharge for aged batteries, and (ii) predict the end-of-life of a battery as a function of anticipated usage. The approach is validated through an experimental set of randomized discharge profiles.
batteries↗
Advances in fatigue life prediction methodology for metallic materials
The capabilities of a plasticity-induced crack-closure model to predict small- and large-crack growth rates, and in some cases total fatigue life, for four aluminum alloys and three titanium alloys under constant-amplitude, variable-amplitude, and spectrum loading are described. Equations to calculate a cyclic-plastic-zone corrected effective stress-intensity factor range from a cyclic J-integral and crack-closure analysis of large cracks were reviewed. The effective stress-intensity factor range against crack growth rate relations were used in the closure model to predict small- and large-crack growth under variable-amplitude and spectrum loading. Using the closure model and microstructural features, a total fatigue life prediction method is demonstrated for three aluminum alloys under various load histories.
Newman, J. C., Jr.↗
Experimental Design for Composite Overwrapped Pressure Vessel Life Prediction
Explore the source record for details and available documents.
COPV↗
NDE: A key to engine rotor life prediction
A key ingredient in the establishment of safe life times for critical components is the means of reliably detecting flaws which may potentially exist. Currently used nondestructive evaluation procedures are successful in detecting life limiting defects; however, the development of automated and computer aided NDE technology permits even greater assurance of flight safety.
Doherty, J. E.↗
Developing Deep Learning Models for System Remaining Useful Life Predictions: Application to Aircraft Engines
Prognostics and health management (PHM) is an important part of ensuring reliable operations of complex safety- critical systems. System-level remaining useful life (RUL) estimation is a much more complex problem than making estimations at the component level, and system-level RUL methodologies remain sparse in the literature. Model-based approaches have traditionally worked in the past for components such as capacitors, MOSFETs, batteries, or hard-drives (to name a few examples), but developing high fidelity dynamics models of cyber physical systems that can be used to study the effects of multiple degrading components in the system remains a challenging task. Some initial work on model-based System RUL predictions was demonstrated in Khorasgani, et al [1], but, to generalize the system-level prognostics problem, we have to resort to pure data driven and hybrid approaches. In this work, we propose an end-to-end data- driven framework for developing deep learning models to predict remaining useful life of cyber physical systems operating under unknown faulty conditions. The raw data is organized with a data schema that improves the model development process and down stream data analysis tasks. Due to the unknown faulty conditions, the raw sensor data is transformed into signals that expose the underlying degradation processes, which are then used for model development. Bayesian Optimization is used to tune the model parameters prior to training and validation. We show that this approach results in accurate predictions within 3 cycles to end of life (EOL). We demonstrate the effectiveness of our approach by applying it to the N-CMAPSS turbofan engine dataset recently released by NASA, which includes high fidelity degradation modeling, real world operating conditions, and a large set of fault operating modes.
Prognostics↗
Uncertainty quantification for Bayesian active learning in rupture life prediction of ferritic steels
Abstract Three probabilistic methodologies are developed for predicting the long-term creep rupture life of 9–12 wt%Cr ferritic-martensitic steels using their chemical and processing parameters. The framework developed in this research strives to simultaneously make efficient inference along with associated risk, i.e., the uncertainty of estimation. The study highlights the limitations of applying probabilistic machine learning to model creep life and provides suggestions as to how this might be alleviated to make an efficient and accurate model with the evaluation of epistemic uncertainty of each prediction. Based on extensive experimentation, Gaussian Process Regression yielded more accurate inference ( $$Pearson\;correlation\;coefficent> 0.95$$ P e a r s o n c o r r e l a t i o n c o e f f i c e n t > 0.95 for the holdout test set) in addition to meaningful uncertainty estimate (i.e., coverage ranges from 94 to 98% for the test set) as compared to quantile regression and natural gradient boosting algorithm. Furthermore, the possibility of an active learning framework to iteratively explore the material space intelligently was demonstrated by simulating the experimental data collection process. This framework can be subsequently deployed to improve model performance or to explore new alloy domains with minimal experimental effort.
20 FOSSIL-FUELED POWER PLANTS↗
Thermal barrier coating life prediction model development
The objectives of this program are to increase understanding of thermal barrier coating (TBC) degradation and failure modes, to generate quantitative ceramic failure life data under cyclic thermal conditions which simulate those encountered in gas turbine engine service, and to develop an analytical methodology for prediction of coating life in the engine. Observations of degradation and failure modes in plasma deposited ceramic indicate that spallation failure results from progressive cracking of the ceramic parallel to and adjacent to, but not coincident with the metal-ceramic interface.
Demasi, J. T.↗
Accelerated battery life predictions through synergistic combination of physics-based models and machine learning
Not Available
25 ENERGY STORAGE↗
A control oriented comprehensive degradation model for battery energy storage system life prediction
In order to ensure that stationary battery energy storage systems (BESSs) provide reliable energy buffering, both for power quality and economic purposes, the degradation must be considered. Cell degradation involves various side reactions and is highly dependent on its operating conditions. To accurately track cell degradation and predict its impact on battery behavior, a comprehensive physics-based degradation model based on an electrolyte phase-enhanced single particle (SP) model is developed. Key degradation physics, namely solid electrolyte interphase (SEI) layer formation and growth, Li plating on the graphite anode, and Mn dissolution on cathode of nickel-cobalt-manganese oxide (NMC622) are considered. The model is validated against experimental capacity data. The results reveal that the deposition rate of both SEI layer and Li metal increase as the charge voltage increases. At the cathode side, the solvent oxidation rate determines the Mn dissolution rate. As a result, the volume fraction of NMC622 in the cathode continually decreases at a gradually increasing rate.
25 ENERGY STORAGE↗
The 3.3K thrust chamber life prediction
The cause of low-cycle fatigue failure of the 3.3K Thrust Chamber was investigated. This thrust chamber typifies the current trend in rocket nozzle design which calls for high performance coupled with weight and volume limitations as well as the requirement of reusability. The analysis was performed with the BOPACE finite-element computer program which provides capability to determine viscoplastic response of a structure subjected to cyclic thermal and mechanical loading. Results are presented which show the critical region for low-cycle fatigue and the history of strain within that region for each thermo-mechanical loading cycle in the 3.3K thrust chamber. The predicted behavior was used to evaluate the low-cycle fatigue life near the throat plane of the chamber. The results show that BOPACE provides an extremely accurate prediction of structural behavior; the critical region was identified and the life determined from computed strains was within 154 cycles of the observed failure at 1013 cycles.
Armstrong, W. H.↗
NASA's Evolutionary Xenon Thruster (NEXT) Project Qualification Propellant Throughput Milestone: Performance, Erosion, and Thruster Service Life Prediction After 450 kg
The NASA s Evolutionary Xenon Thruster (NEXT) program is tasked with significantly improving and extending the capabilities of current state-of-the-art NSTAR thruster. The service life capability of the NEXT ion thruster is being assessed by thruster wear test and life-modeling of critical thruster components, such as the ion optics and cathodes. The NEXT Long-Duration Test (LDT) was initiated to validate and qualify the NEXT thruster propellant throughput capability. The NEXT thruster completed the primary goal of the LDT; namely to demonstrate the project qualification throughput of 450 kg by the end of calendar year 2009. The NEXT LDT has demonstrated 28,500 hr of operation and processed 466 kg of xenon throughput--more than double the throughput demonstrated by the NSTAR flight-spare. Thruster performance changes have been consistent with a priori predictions. Thruster erosion has been minimal and consistent with the thruster service life assessment, which predicts the first failure mode at greater than 750 kg throughput. The life-limiting failure mode for NEXT is predicted to be loss of structural integrity of the accelerator grid due to erosion by charge-exchange ions.
Herman, Daniel A.↗
Life prediction of expulsion bladders through fatigue test and fold strain analysis
Cycle life data are presented in terms of true maximum strain for four metals, two plastics, and two elastomers. The Coffin-Manson fatigue theory was applied for metals and plastics, and cut-growth fatigue theory for elastomers. The data are based on measurements made at room and elevated temperatures. It was found that double folds give rise to far severer folding strains than do simple folds. It was also found that, except for the elastomers, all the bladder materials develop surface cracks due to double folds after only one cycle. The findings indicate that metals, which are bets for premeation resistance, are worst for fatigue resistance, and vice versa for elastomers. The intermediate plastics were found to be unsatisfactory for both permeation and fatigue resistance for missions of extended duration.
Chu, H. N.↗
Decomposition Technique for Remaining Useful Life Prediction
The prognostic tool disclosed here decomposes the problem of estimating the remaining useful life (RUL) of a component or sub-system into two separate regression problems: the feature-to-damage mapping and the operational conditions-to-damage-rate mapping. These maps are initially generated in off-line mode. One or more regression algorithms are used to generate each of these maps from measurements (and features derived from these), operational conditions, and ground truth information. This decomposition technique allows for the explicit quantification and management of different sources of uncertainty present in the process. Next, the maps are used in an on-line mode where run-time data (sensor measurements and operational conditions) are used in conjunction with the maps generated in off-line mode to estimate both current damage state as well as future damage accumulation. Remaining life is computed by subtracting the instance when the extrapolated damage reaches the failure threshold from the instance when the prediction is made.
Saha, Bhaskar↗