Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “machine”

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 559 records · Page 31

Transient Optimization of an Electrified Gas Turbine Engine Using Machine Learning

Gas turbine engines are designed with sufficient margin to prevent stall under normal operating conditions throughout their life. This compromise ensures that during rapid accelerations, compressor operation remains stable, but at the cost of efficiency and thrust responsiveness. The design margin encompasses multiple sources of uncertainty and systematic deviances from the operating line, the largest of which is the transient allowance. This set-aside accounts for the temporary incoordination of the engine spools during an acceleration while still enabling it to meet the certification requirement to accelerate from low to high power within a specified time, and without experiencing overtemperature, surge, stall, or other detrimental factors. Electrification of the powertrain provides the opportunity to address this reserve and truly optimize the design. The addition of electric machines inherent in hybrid propulsion concepts offers a means to interact with the engine shafts such that the necessary margin can be reduced, which can positively impact the engine design. By adjusting the amount of power extracted from or injected to the engine spools by the electric machines during transient operation, excursions from the operating line can be minimized. Past work using a dynamic engine model has shown that optimization of the fuel flow schedule during acceleration can reduce the required margin while still meeting the time requirement, and results are further improved when combined with power injection and extraction. The current work uses machine learning through a genetic algorithm to address the problem holistically by concurrently optimizing the electric machine power command and fuel flow acceleration schedule using an updated, higher fidelity version of the original engine model.

Stall Margin↗

Transient Optimization of an Electrified Gas Turbine Engine Using Machine Learning

Gas turbine engines are designed with sufficient margin to prevent stall under normal operating conditions throughout their life. This compromise ensures that during rapid accelerations, compressor operation remains stable, but at the cost of efficiency and thrust responsiveness. The design margin encompasses multiple sources of uncertainty and systematic deviances from the operating line, the largest of which is the transient allowance. This set-aside accounts for the temporary incoordination of the engine spools during an acceleration while still enabling it to meet the certification requirement to accelerate from low to high power within a specified time, and without experiencing overtemperature, surge, stall, or other detrimental factors. Electrification of the powertrain provides the opportunity to address this reserve and truly optimize the design. The addition of electric machines inherent in hybrid propulsion concepts offers a means to interact with the engine shafts such that the necessary margin can be reduced, which can positively impact the engine design. By adjusting the amount of power extracted from or injected to the engine spools by the electric machines during transient operation, excursions from the operating line can be minimized. Past work using a dynamic engine model has shown that optimization of the fuel flow schedule during acceleration can reduce the required margin while still meeting the time requirement, and results are further improved when combined with power injection and extraction. The current work uses machine learning through a genetic algorithm to address the problem holistically by concurrently optimizing the electric machine power command and fuel flow acceleration schedule using an updated, higher fidelity version of the original engine model.

Stall Margin↗

Transient Optimization of an Electrified Gas Turbine Engine Using Machine Learning

Gas turbine engines are designed with sufficient margin to prevent stall under normal operating conditions throughout their life. This compromise ensures that during rapid accelerations, compressor operation remains stable, but at the cost of efficiency and thrust responsiveness. The design margin encompasses multiple sources of uncertainty and systematic deviances from the operating line, the largest of which is the transient allowance. This set-aside accounts for the temporary incoordination of the engine spools during an acceleration while still enabling it to meet the certification requirement to accelerate from low to high power within a specified time, and without experiencing overtemperature, surge, stall, or other detrimental factors. Electrification of the powertrain provides the opportunity to address this reserve and truly optimize the design. The addition of electric machines inherent in hybrid propulsion concepts offers a means to interact with the engine shafts such that the necessary margin can be reduced, which can positively impact the engine design. By adjusting the amount of power extracted from or injected to the engine spools by the electric machines during transient operation, excursions from the operating line can be minimized. Past work using a dynamic engine model has shown that optimization of the fuel flow schedule during acceleration can reduce the required margin while still meeting the time requirement, and results are further improved when combined with power injection and extraction. The current work uses machine learning through a genetic algorithm to address the problem holistically by concurrently optimizing the electric machine power command and fuel flow acceleration schedule using an updated, higher fidelity version of the original engine model.

Stall Margin↗

U.S. Department Of Energy Advanced Small Modular Reactor R&D Program: Instrumentation, Controls, and Human-Machine Interface (ICHMI) Pathway

Instrumentation, controls, and human-machine interfaces (ICHMI) are essential enabling technologies that strongly influence nuclear power plant performance and operational costs. The nuclear power industry is currently engaged in a transition from traditional analog-based instrumentation, controls, and human-machine interface systems to implementations employing digital technologies. This transition has primarily occurred in an ad hoc fashion through individual system upgrades at existing plants and has been constrained by licenseability concerns. Although the recent progress in constructing new plants has spurred design of more fully digital plant-wide ICHMI systems, the experience base in the nuclear power application domain is limited. Additionally, development of advanced reactor concepts, such as Generation IV designs and small modular reactors, introduces different plant conditions (e.g., higher temperatures, different coolants, etc.) and unique plant configurations (e.g., multiunit plants with shared systems, balance of plant architectures with reconfigurable co-generation options) that increase the need for enhanced ICHMI capabilities to fully achieve industry goals related to economic competitiveness, safety and reliability, sustainability, and proliferation resistance and physical protection. As a result, significant challenges remain to be addressed to enable the nuclear power industry to complete the transition to safe and comprehensive use of modern ICHMI technology. The U.S. Department of Energy (DOE) has recognized that ICHMI research, development, and demonstration (RD&D) is needed to resolve the technical challenges that may compromise the effective and efficient utilization of modern ICHMI technology and consequently inhibit realization of the benefits offered by expanded utilization of nuclear power. Consequently, several DOE programs have substantial ICHMI RD&D elements within their respective research portfolios. This paper describes current ICHMI research in support of advanced small modular reactors. The objectives that can be achieved through execution of the defined RD&D are to provide optimal technical solutions to critical ICHMI issues, resolve technology gaps arising from the unique measurement and control characteristics of advanced reactor concepts, provide demonstration of needed technologies and methodologies in the nuclear power application domain, mature emerging technologies to facilitate commercialization, and establish necessary technical evidence and application experience to enable timely and predictable licensing. 1 Introduction Instrumentation, controls, and human-machine interfaces are essential enabling technologies that strongly influence nuclear power plant performance and operational costs. The nuclear power industry is currently engaged in a transition from traditional analog-based instrumentation, controls, and human-machine interface (ICHMI) systems to implementations employing digital technologies. This transition has primarily occurred in an ad hoc fashion through individual system upgrades at existing plants and has been constrained by licenseability concerns. Although the recent progress in constructing new plants has spurred design of more fully digital plant-wide ICHMI systems, the experience base in the nuclear power application domain is limited. Additionally, development of advanced reactor concepts, such as Generation IV designs and small modular reactors, introduces different plant conditions (e.g., higher temperatures, different coolants, etc.) and unique plant configurations (e.g., multiunit plants with shared systems, balance of plant architectures with reconfigurable co-generation options) that increase the need for enhanced ICHMI capabilities to fully achieve industry goals related to economic competitiveness, safety and reliability, sustainability, and proliferation resistance and physical protection. As a result, significant challenges remain to be addressed to enable the nuclear power industry to complete the transition to safe and comprehensive use of modern ICHMI technology. The U.S. Department of Energy (DOE) has recognized that ICHMI research, development, and demonstration (RD&D) is needed to resolve the technical challenges that may compromise the effective and efficient utilization of modern ICHMI technology and consequently inhibit realization of the benefits offered by expanded utilization of nuclear power. Consequently, several DOE programs have substantial ICHMI RD&D elements to their respective research portfolio. The objectives that can be achieved through execution of the defined RD&D are to provide optimal technical solutions to critical ICHMI issues, resolve technology gaps arising from the unique measurement and control characteristics of advanced reactor concepts, provide demonstration of needed technologies and methodologies in the nuclear power application domain, mature emerging technologies to facilitate...

Digital I&C↗

Techno-Economic Implications of Electrical Machine Scaling for Wave Energy Converters: Preprint

The sizing of an electrical machine for a Wave Energy Converter (WEC) can have a substantial impact on the overall sizing, cost, and rating of the device. An electrical generator is typically part of the power take-off (PTO) system, which is the mechanism by which the energy absorbed by the prime mover is transformed into useable electrical. For practically all WECs, the rate of change of actuation is predominantly determined by the wave resource (i.e., the wave height and frequency) and devices will see a sinusoidally varying velocity according to the wave conditions. The same can then be said for both directly and indirectly coupled PTOs with electrical generators. This techno-economic study investigates electrical machine scaling and associated cost implications through core machine design theory, manufacturer data, supporting literature, and the DOE sponsored Reference Model Project (RMP). The RMP was a partnered effort to develop open-source marine energy (ME) point designs as reference models (RMs) to benchmark ME technology performance and costs, methods for design and analysis of ME technologies, estimations for capital costs, operational costs, and levelized costs of energy (LCOE). The results from this study show torque is directly related to (1) the physical size of the machine required to increase the airgap sheer stresses, (2) the amount of active material, (3) the support structure, (4) bearing size and rating, and (5) offshore cable rating, all of which have a significant effect on overall system costs in terms of both CAPEX and OPEX. This paper aims to be a critical benchmark in helping determine an “optimal” nameplate rating for wave energy devices and their associated PTO. With an optimized rating and sizing process, WEC costs can be reduced, and overall performance can be improved.

cables↗

Techno-Economic Implications of Electrical Machine Scaling for Wave Energy Converters

The sizing of an electrical machine for a Wave Energy Converter (WEC) can have a substantial impact on the overall sizing, cost, and rating of the device. An electrical generator is typically part of the power take-off (PTO) system, which is the mechanism by which the energy absorbed by the prime mover is transformed into useable electrical. For practically all WECs, the rate of change of actuation is predominantly determined by the wave resource (i.e., the wave height and frequency) and devices will see a sinusoidally varying velocity according to the wave conditions. The same can then be said for both directly and indirectly coupled PTOs with electrical generators. This techno-economic study investigates electrical machine scaling and associated cost implications through core machine design theory, manufacturer data, supporting literature, and the DOE sponsored Reference Model Project (RMP). The RMP was a partnered effort to develop open-source marine energy (ME) point designs as reference models (RMs) to benchmark ME technology performance and costs, methods for design and analysis of ME technologies, estimations for capital costs, operational costs, and levelized costs of energy (LCOE). The results from this study show torque is directly related to (1) the physical size of the machine required to increase the airgap sheer stresses, (2) the amount of active material, (3) the support structure, (4) bearing size and rating, and (5) offshore cable rating, all of which have a significant effect on overall system costs in terms of both CAPEX and OPEX. This paper aims to be a critical benchmark in helping determine an “optimal” nameplate rating for wave energy devices and their associated PTO. With an optimized rating and sizing process, WEC costs can be reduced, and overall performance can be improved.

cables↗

Health Assessment and Performance Monitoring of Large Machine Diagnostics

Diagnostic machines are a crucial component of the Stockpile Stewardship Program for data collection, toward the ultimate goal of improving our understanding of nuclear physics. These systems consist of interactions between many complex components, and require regular maintenance for acceptable performance. The Cygnus X-ray diagnostic located at the Nevada National Security Site's U1a underground facility which provides radiographic data for subcritical experiments, is a prime example of these systems. Component degradation and failures within Cygnus can result in system downtime and data loss, affecting schedules and increasing experiment costs. To evade such failures, years worth of data on machine performance has been collected on the two Cygnus axes in the form of voltage and current measurements of Cygnus' various components. Using these as input, we have developed machine learning techniques for assessing the health of Cygnus, with the ultimate goal of predicting declining performance and machine failure.

97 MATHEMATICS AND COMPUTING↗

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↗

Aluminum alloys for satellite boxes : engineering guidelines for obtaining adequate strength while minimizing residual stresses and machining distortion.

This report provides strategies for minimizing machining distortion in future designs of aluminum alloy satellite boxes, based in part on key findings from this investigation. The report outlines types of aluminum alloys and how they are heat treated, how residual stresses develop during heat treatment of age hardening alloys, ways residual stresses can be minimized, and the design of machining approaches to minimize distortion in parts that contain residual stresses. Specific recommendations are made regarding alloy selection, heat treatment, stress relieving, and machining procedures for boxes requiring various strength levels with emphasis on 6061 and 7075 aluminum alloys.

36 MATERIALS SCIENCE↗

Applying Machine‐Learning Methods to Laser Acceleration of Protons: Lessons Learned From Synthetic Data

ABSTRACT In this study, we consider three different machine‐learning methods—a three‐hidden‐layer neural network, support vector regression, and Gaussian process regression—and compare how well they can learn from a synthetic data set for proton acceleration in the Target Normal Sheath Acceleration regime. The synthetic data set was generated from a previously published theoretical model by Fuchs et al. 2005 that we modified. Once trained, these machine‐learning methods can assist with efforts to maximize the peak proton energy, or with the more general problem of configuring the laser system to produce a proton energy spectrum with desired characteristics. In our study, we focus on both the accuracy of the machine‐learning methods and the performance on one GPU including memory consumption. Although it is arguably the least sophisticated machine‐learning model we considered, support vector regression performed very well in our tests.

Desai, Ronak↗

Machine Learning Calabi–Yau Metrics

We apply machine learning to the problem of finding numerical Calabi–Yau metrics. Building on Donaldson's algorithm for calculating balanced metrics on Kähler manifolds, we combine conventional curve fitting and machine-learning techniques to numerically approximate Ricci-flat metrics. We show that machine learning is able to predict the Calabi–Yau metric and quantities associated with it, such as its determinant, having seen only a small sample of training data. Using this in conjunction with a straightforward curve fitting routine, we demonstrate that it is possible to find highly accurate numerical metrics much more quickly than by using Donaldson's algorithm alone, with our new machine-learning algorithm decreasing the time required by between one and two orders of magnitude.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Adrastea: An Efficient FPGA Design Environment for Heterogeneous Scientific Computing and Machine Learning

We present Adrastea, an efficient FPGA design environment for developing scientific machine learning applications. FPGA development is challenging, from deployment, proper toolchain setup, programming methods, interfacing FPGA kernels, and more importantly, the need to explore design space choices to get the best performance and area usage from the FPGA kernel design. Adrastea provides an automated and scalable design flow to parameterize, implement, and optimize complex FPGA kernels and associated interfaces. We show how virtualization of the development environment via virtual machines is leveraged to simplify the setup of the FPGA toolchain while deploying the FPGA boards and while scaling up the automated design space exploration to leverage multiple machines concurrently. Adrastea provides an automated build and test environment of FPGA kernels. By exposing design space hyper-parameters, Adrastea can automatically search the design space in parallel to optimize the FPGA design for a given metric, usually performance or area. Adrastea simplifies the task of interfacing with the FPGA kernels with a simplified interface API. To demonstrate the capabilities of Adrastea, we implement a complex random forest machine learning kernel with 10,000 input features while achieving extremely low computing latency without loss of prediction accuracy, which is required by a scientific edge application at SNS. We also demonstrate Adrastea using an FFT kernel and show that for both applications Adrastea is able to systematically and efficiently evaluate different design options, which reduced the time and effort required to develop the kernel from months of manual work to days of automatic builds.

Young, Aaron↗

Control of machining-induced residual stress via tool geometry and process parameter modification

Distortion generated in machined, monolithic, thin-walled aerospace components due to residual stresses leads to significant material and economic waste in the manufacturing industry. Inherent residual stress (IRS) present in stock materials combines with machining-induced residual stress (MIRS) to influence the final machined part distortion. It is hypothesized that MIRS can be controlled, based on the part geometry, through deliberate cutting tool geometry and process parameter modifications to negate the effect of IRS on distortion, consequently resulting in distortion-free parts. A finite element (FE) orthogonal cutting model is developed to study how tool geometry and process parameters influence machining-induced residual stress (MIRS). Orthogonal cutting experiments are performed on Al 7075-T651 samples to measure cutting forces and MIRS. A cutting force dynamometer is used to measure forces during cutting and a novel digital image correlation (DIC) based hole drilling technique is employed to measure the near-surface residual stress (RS) in the cut samples. These data are subsequently utilized to validate the FE prediction model. Various cases of cutting simulations involving different depths of cut, tool tip radii, and rake angles are performed to study their effects on RS. Similar to prior literature, increasing the depth of cut, tool tip radius, or rake angle is found to promote the formation of near-surface tensile stresses. The competing effects of material plowing and temperature are shown to determine the type of RS at the end of the cut. Moreover, a window of variation of RS (up to ± 400 MPa) is estimated within the given range of conditions, allowing for the control of MIRS through tool and process modification.

Mathews, Ritin [ORNL] (ORCID:0000000301440828)↗

Machine learning-based jet and event classification at the Electron-Ion Collider with applications to hadron structure and spin physics

We explore machine learning-based jet and event identification at the future Electron-Ion Collider (EIC). We study the effectiveness of machine learning-based classifiers at relatively low EIC energies, focusing on (i) identifying the flavor of the jet and (ii) identifying the underlying hard process of the event. We propose applications of our machine learning-based jet identification in the key research areas at the future EIC and current Relativistic Heavy Ion Collider program, including enhancing constraints on (transverse momentum dependent) parton distribution functions, improving experimental access to transverse spin asymmetries, studying photon structure, and quantifying the modification of hadrons and jets in the cold nuclear matter environment in electron-nucleus collisions. We establish first benchmarks and contrast the estimated performance of flavor tagging at the EIC with that at the Large Hadron Collider. We perform studies relevant to aspects of detector design including particle identification, charge information, and minimum transverse momentum capabilities. Additionally, we study the impact of using full event information instead of using only information associated with the identified jet. These methods can be deployed either on suitably accurate Monte Carlo event generators, or, for several applications, directly on experimental data. We provide an outlook for ultimately connecting these machine learning-based methods with first principles calculations in quantum chromodynamics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Performance of a machine learning-based decision model to help clinicians decide the extent of lymphadenectomy (D1 vs. D2) in gastric cancer before surgical resection

Background: Controversy still exists on the optimal surgical resection for potentially curable gastric cancer (GC). Use of radiologic evaluation and machine learning algorithms might predict extent of lymphadenectomy to limit unnecessary surgical treatment. We purposed to design a machine learning-based clinical decision-support model for predicting extent of lymphadenectomy (D1 vs. D2) in local advanced GC. Methods: Clinicoradiologic features available from routine clinical assignments in 557 patients with GCs were retrospectively interpreted by an expert panel blinded to all histopathologic information. All patients underwent surgery using standard D2 resection. Decision models were developed with a logistic regression (LR), support vector machine (SVM) and auto-encoder (AE) algorithm in 371 training and tested in 186 test data, respectively. The primary end point was to measure diagnostic performance of decision model and a Japanese gastric cancer treatment guideline version 4th (JPN 4th) criteria for discriminate D1 (pT1 + pN0) versus D2 (≥ pT1 + ≥ pN1) lymphadenectomy. Results: The decision model with AE analysis produced highest area under ROC curve (train: 0.965, 95% confidence interval (CI) 0.948–0.978; test: 0.946, 95% CI 0.925–0.978), followed by SVM (train: 0.925, 95% CI 0.902–0.944; test: 0.942, 95% CI 0.922–0.973) and LR (train: 0.886, 95% CI 0.858–0.910; test: 0.891, 95% CI 0.891–0.952). By this improvement, overtreatment was reduced from 21.7% (121/557) by treat-all pattern, to 15.1% (84/557) by JPN 4th criteria, and to 0.7–0.9% (4–5/557) by the new approach. Conclusions: The decision model with machine learning analysis demonstrates high accuracy for identifying patients who are candidates for D1 versus D2 resection. Its approximate 14–20% improvements in overtreatment compared to treat-all pattern and JPN 4th criteria potentially increase the number of patients with local advanced GCs who can safely avoid unnecessary lymphadenectomy.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Failure prediction using machine learning in a virtualised HPC system and application

Failure is an increasingly important issue in high performance computing and cloud systems. As large-scale systems continue to grow in scale and complexity, mitigating the impact of failure and providing accurate predictions with sufficient lead time remains a challenging research problem. Traditional existing fault-tolerance strategies such as regular check-pointing and replication are not adequate because of the emerging complexities of high performance computing systems. This necessitates the importance of having an effective as well as proactive failure management approach in place aimed at minimizing the effect of failure within the system. With the advent of machine learning techniques, the ability to learn from past information to predict future pattern of behaviours makes it possible to predict potential system failure more accurately. Thus, in this paper, we explore the predictive abilities of machine learning by applying a number of algorithms to improve the accuracy of failure prediction. We have developed a failure prediction model using time series and machine learning, and performed comparison based tests on the prediction accuracy. The primary algorithms we considered are the support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN), classification and regression trees (CART) and linear discriminant analysis (LDA). Experimental results indicates that the average prediction accuracy of our model using SVM when predicting failure is 90% accurate and effective compared to other algorithms. This finding implies that our method can effectively predict all possible future system and application failures within the system.

Mohammed, Bashir↗

Machine Learning Aided Modeling of Granular Materials: A Review

Artificial intelligence (AI) has become a buzzy word since Google’s AlphaGo beat a world champion in 2017. In the past five years, machine learning as a subset of the broader category of AI has obtained considerable attention in the research community of granular materials. This work offers a detailed review of the recent advances in machine learning-aided studies of granular materials from the particle-particle interaction at the grain level to the macroscopic simulations of granular flow. This work will start with the application of machine learning in the microscopic particle-particle interaction and associated contact models. Then, different neural networks for learning the constitutive behaviour of granular materials will be reviewed and compared. Finally, the macroscopic simulations of practical engineering or boundary value problems based on the combination of neural networks and numerical methods are discussed. We hope readers will have a clear idea of the development of machine learning-aided modelling of granular materials via this comprehensive review work.

42 ENGINEERING↗

Towards robust surrogate models: Benchmarking machine learning approaches to expediting phase field simulations of brittle fracture

Data-driven approaches have the potential to make modeling complex, nonlinear physical phenomena significantly more computationally tractable. For example, computational modeling of fracture is a core challenge where machine learning techniques have the potential to provide a much needed speedup that would enable progress in areas such as multi-scale modeling and uncertainty quantification. Currently, phase field modeling (PFM) of fracture is one such approach that offers a convenient variational formulation to model crack nucleation, branching and propagation. To date, machine learning techniques have shown promise in approximating PFM simulations. While standard fracture benchmarks represent realistic scenarios frequently observed in practice, they typically do not provide sufficiently challenging tests for data-driven methods. Here, to address this gap, we introduce a challenging dataset based on PFM simulations designed to benchmark and advance ML methods for fracture modeling. This dataset includes three energy decomposition methods, two boundary conditions, and 1000 random initial crack configurations for a total of 6000 simulations. Each sample contains 100 time steps capturing the temporal evolution of the crack field. Alongside this dataset, we also implement and evaluate Physics Informed Neural Networks (PINN), Fourier Neural Operators (FNO), and UNet models as baselines, and explore the impact of ensembling strategies on prediction accuracy. With this combination of our dataset and baseline models drawn from the literature we aim to provide a standardized and challenging benchmark for evaluating machine learning approaches to solid mechanics. Our results highlight both the promise and limitations of popular current models, and demonstrate the utility of this dataset as a testbed for advancing machine learning in fracture mechanics research.

Benchmark dataset↗