Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “optimal accuracy”

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 343 records · Page 19

Experimental demonstration of a single-spike hard-X-ray free-electron laser starting from noise

In this letter, we report the experimental demonstration of single-spike hard-X-ray free-electron laser pulses starting from noise with multi-eV bandwidth. Here, this is accomplished by shaping a low-charge electron beam with a slotted emittance spoiler and by adjusting the transport optics to optimize the beam-shaping accuracy. Based on elementary free-electron laser scaling laws, we estimate the pulse duration to be less than 1 fs full-width at half-maximum.

43 PARTICLE ACCELERATORS↗

Accurate, rapid identification of dislocation lines in coherent diffractive imaging via a min-max optimization formulation

Defects such as dislocations impact materials properties and their response during external stimuli. Imaging these defects in their native operating conditions to establish the structure-function relationship and, ultimately, to improve performance via defect engineering has remained a considerable challenge for both electron-based and x-ray-based imaging techniques. While Bragg coherent x-ray diffractive imaging (BCDI) is successful in many cases, nuances in identifying the dislocations has left manual identification as the preferred method. Derivative-based methods are also used, but they can be inaccurate and are computationally inefficient. Here we demonstrate a derivative-free method that is both more accurate and more computationally efficient than either derivative-or human-based methods for identifying 3D dislocation lines in nanocrystal images produced by BCDI. We formulate the problem as a min-max optimization problem and show exceptional accuracy for experimental images. We demonstrate a 227x speedup for a typical experimental dataset with higher accuracy over current methods. We discuss the possibility of using this algorithm as part of a sparsity-based phase retrieval process. Here, we also provide MATLAB code for use by other researchers.

47 OTHER INSTRUMENTATION↗

Rapid 3D nanoscale coherent imaging via physics-aware deep learning

Phase retrieval, the problem of recovering lost phase information from measured intensity alone, is an inverse problem that is widely faced in various imaging modalities ranging from astronomy to nanoscale imaging. The current process of phase recovery is iterative in nature. As a result, the image formation is time consuming and computationally expensive, precluding real-time imaging. Here, we use 3D nanoscale X-ray imaging as a representative example to develop a deep learning model to address this phase retrieval problem. We introduce 3D-CDI-NN, a deep convolutional neural network and differential programing framework trained to predict 3D structure and strain, solely from input 3D X-ray coherent scattering data. Our networks are designed to be “physics-aware” in multiple aspects; in that the physics of the X-ray scattering process is explicitly enforced in the training of the network, and the training data are drawn from atomistic simulations that are representative of the physics of the material. We further refine the neural network prediction through a physics-based optimization procedure to enable maximum accuracy at lowest computational cost. 3D-CDI-NN can invert a 3D coherent diffraction pattern to real-space structure and strain hundreds of times faster than traditional iterative phase retrieval methods. Our integrated machine learning and differential programing solution to the phase retrieval problem is broadly applicable across inverse problems in other application areas.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Toward quantum Monte Carlo forces on heavier ions: Scaling properties

Quantum Monte Carlo (QMC) forces have been studied extensively in recent decades because of their importance with spectroscopic observables and geometry optimization. Here, we benchmark the accuracy and computational cost of QMC forces. The zero-variance zero-bias (ZVZB) force estimator is used in standard variational and diffusion Monte Carlo simulations with mean-field based trial wavefunctions and atomic pseudopotentials. Statistical force uncertainties are obtained with a recently developed regression technique for heavy tailed QMC data [P. Lopez Rios and G. J. Conduit, Phys. Rev. E 99, 063312 (2019)]. By considering selected atoms and dimers with elements ranging from H to Zn (1 ≤ Z eff ≤ 20), we assess the accuracy and the computational cost of ZVZB forces as the effective pseudopotential valence charge, Z eff , increases. We find that the costs of QMC energies and forces approximately follow simple power laws in Zeff. The force uncertainty grows more rapidly, leading to a best case cost scaling relationship of approximately Z e ff 6.5 ( 3 ) for diffusion Monte Carlo. We find that the accessible system size at fixed computational cost scales as Z e ff − 2 , insensitive to model assumptions or the use of the “space warp” variance-reduction technique. Our results predict the practical cost of obtaining forces for a range of materials, such as transition metal oxides where QMC forces have yet to be applied, and underscore the importance of further developing force variance-reduction techniques, particularly for atoms with high Z eff .

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

CIGALEMC: GALAXY PARAMETER ESTIMATION USING A MARKOV CHAIN MONTE CARLO APPROACH WITH CIGALE

We introduce a fast Markov Chain Monte Carlo (MCMC) exploration of the astrophysical parameter space using a modified version of the publicly available code Code Investigating GALaxy Emission (CIGALE). The original CIGALE builds a grid of theoretical spectral energy distribution (SED) models and fits to photometric fluxes from ultraviolet to infrared to put constraints on parameters related to both formation and evolution of galaxies. Such a grid-based method can lead to a long and challenging parameter extraction since the computation time increases exponentially with the number of parameters considered and results can be dependent on the density of sampling points, which must be chosen in advance for each parameter. MCMC methods, on the other hand, scale approximately linearly with the number of parameters, allowing a faster and more accurate exploration of the parameter space by using a smaller number of efficiently chosen samples. We test our MCMC version of the code CIGALE (called CIGALEMC) with simulated data. After checking the ability of the code to retrieve the input parameters used to build the mock sample, we fit theoretical SEDs to real data from the well-known and -studied Spitzer Infrared Nearby Galaxy Survey sample. We discuss constraints on the parameters and show the advantages of our MCMC sampling method in terms of accuracy of the results and optimization of CPU time.

79 ASTRONOMY AND ASTROPHYSICS↗

Ptychographic phase retrieval by proximal algorithms

We derive a set of ptychography phase-retrieval iterative engines based on proximal algorithms originally developed in convex optimization theory, and discuss their connections with existing ones. The use of proximal operator creates a simple frame work that allows us to incorporate the effect of noise from a maximum-likelihood (ML) principle. We focus on three particular algorithms, namely proximal minimization, alternating direction method of multiplier and accelerated proximal gradient (APG). We benchmark their performance with numerical simulations, and discuss their optimal conditions for convergence and accuracy. An experimental dataset is used to demonstrate their effectiveness as well, in which case an array of cubic Au nanoparticles with a size of 50 nm is imaged. We show that with the presence of Poisson noise, a dataset with photon counts up to 10 4 at one detector pixel already requires ML-based methods to achieve a stable convergence. Among the three algorithms derived in this work, APG method is reported first time for its application in ptychographic reconstruction and shows superior performance in terms of both accuracy and convergence rate with a noisy dataset.

36 MATERIALS SCIENCE↗

TH-E-BRE-02: A Forward Scattering Approximation to Dose Calculation Using the Linear Boltzmann Transport Equation

Purpose: To investigate the use of the linear Boltzmann transport equation as a dose calculation tool which can account for interface effects, while still having faster computation times than Monte Carlo methods. In particular, we introduce a forward scattering approximation, in hopes of improving calculation time without a significant hindrance to accuracy. Methods: Two coupled Boltzmann transport equations were constructed, one representing the fluence of photons within the medium, and the other, the fluence of electrons. We neglect the scattering term within the electron transport equation, resulting in an extreme forward scattering approximation to reduce computational complexity. These equations were then solved using a numerical technique for solving partial differential equations, known as a finite difference scheme, where the fluence at each discrete point in space is calculated based on the fluence at the previous point in the particle's path. Using this scheme, it is possible to develop a solution to the Boltzmann transport equations by beginning with boundary conditions and iterating across the entire medium. The fluence of electrons can then be used to find the dose at any point within the medium. Results: Comparisons with Monte Carlo simulations indicate that even simplistic techniques for solving the linear Boltzmann transport equation yield expected interface effects, which many popular dose calculation algorithms are not capable of predicting. Implementation of a forward scattering approximation does not appear to drastically reduce the accuracy of this algorithm. Conclusion: Optimized implementations of this algorithm have been shown to be very accurate when compared with Monte Carlo simulations, even in build up regions where many models fail. Use of a forward scattering approximation could potentially give a reasonably accurate dose distribution in a shorter amount of time for situations where a completely accurate dose distribution is not required, such as in certain optimization algorithms.

97 MATHEMATICS AND COMPUTING↗

MO-DE-BRA-05: Developing Effective Medical Physics Knowledge Structures: Models and Methods

Purpose: Develop a method and supporting online resources to be used by medical physics educators for teaching medical imaging professionals and trainees so they develop highly-effective physics knowledge structures that can contribute to improved diagnostic image quality on a global basis. Methods: The different types of mental knowledge structures were analyzed and modeled with respect to both the learning and teaching process for their development and the functions or tasks that can be performed with the knowledge. While symbolic verbal and mathematical knowledge structures are very important in medical physics for many purposes, the tasks of applying physics in clinical imaging--especially to optimize image quality and diagnostic accuracy--requires a sensory conceptual knowledge structure, specifically, an interconnected network of visually based concepts. This type of knowledge supports tasks such as analysis, evaluation, problem solving, interacting, and creating solutions. Traditional educational methods including lectures, online modules, and many texts are serial procedures and limited with respect to developing interconnected conceptual networks. A method consisting of the synergistic combination of on-site medical physics teachers and the online resource, CONET (Concept network developer), has been developed and made available for the topic Radiographic Image Quality. This was selected as the inaugural topic, others to follow, because it can be used by medical physicists teaching the large population of medical imaging professionals, such as radiology residents, who can apply the knowledge. Results: Tutorials for medical physics educators on developing effective knowledge structures are being presented and published and CONET is available with open access for all to use. Conclusion: An adjunct to traditional medical physics educational methods with the added focus on sensory concept development provides opportunities for medical physics teachers to share their knowledge and experience at a higher cognitive level and produce medical professionals with the enhanced ability to apply physics to clinical procedures.

60 APPLIED LIFE SCIENCES↗

WE-EF-207-09: Single-Scan Dual-Energy CT Using Primary Modulation

Purpose: Compared with conventional CT, dual energy CT (DECT) provides better material differentiation but requires projection data with two different effective x-ray spectra. Current DECT scanners use either a two-scan setting or costly imaging components, which are not feasible or available on open-gantry cone-beam CT systems. We propose a hardware-based method which utilizes primary modulation to enable single-scan DECT on a conventional CT scanner. The CT imaging geometry of primary modulation is identical to that used in our previous method for scatter removal, making it possible for future combination with effective scatter correction on the same CT scanner. Methods: We insert an attenuation sheet with a spatially-varying pattern - primary modulator-between the x-ray source and the imaged object. During the CT scan, the modulator selectively hardens the x-ray beam at specific detector locations. Thus, the proposed method simultaneously acquires high and low energy data. High and low energy CT images are then reconstructed from projections with missing data via an iterative CT reconstruction algorithm with gradient weighting. Proof-of-concept studies are performed using a copper modulator on a cone-beam CT system. Results: Our preliminary results on the Catphan(c) 600 phantom indicate that the proposed method for single-scan DECT is able to successfully generate high-quality high and low energy CT images and distinguish different materials through basis material decomposition. By applying correction algorithms and using all of the acquired projection data, we can reconstruct a single CT image of comparable image quality to conventional CT images, i.e., without primary modulation. Conclusion: This work shows great promise in using a primary modulator to perform high-quality single-scan DECT imaging. Future studies will test method performance on anthropomorphic phantoms and perform quantitative analyses on image qualities and DECT decomposition accuracy. We will use simulations to optimize the modulator material and geometry parameters.

60 APPLIED LIFE SCIENCES↗

TU-H-CAMPUS-JeP1-04: Deformable Image Registration Performances in Pelvis Patients: Impact of CBCT Image Quality

Purpose: To investigate the accuracy and robustness, against image noise and artifacts (typical of CBCT images), of a commercial algorithm for deformable image registration (DIR), to propagate regions of interest (ROIs) in computational phantoms based on real prostate patient images. Methods: The Anaconda DIR algorithm, implemented in RayStation was tested. Two specific Deformation Vector Fields (DVFs) were applied to the reference data set (CTref) using the ImSimQA software, obtaining two deformed CTs. For each dataset twenty-four different level of noise and/or capping artifacts were applied to simulate CBCT images. DIR was performed between CTref and each deformed CTs and CBCTs. In order to investigate the relationship between image quality parameters and the DIR results (expressed by a logit transform of the Dice Index) a bilinear regression was defined. Results: More than 550 DIR-mapped ROIs were analyzed. The Statistical analysis states that deformation strenght and artifacts were significant prognostic factors of DIR performances, while noise appeared to have a minor role in DIR process as implemented in RayStation as expected by the image similarity metric built in the registration algorithm. Capping artifacts reveals a determinant role for the accuracy of DIR results. Two optimal values for capping artifacts were found to obtain acceptable DIR results (DICE> 075/ 0.85). Various clinical CBCT acquisition protocol were reported to evaluate the significance of the study. Conclusion: This work illustrates the impact of image quality on DIR performance. Clinical issues like Adaptive Radiation Therapy (ART) and Dose Accumulation need accurate and robust DIR software. The RayStation DIR algorithm resulted robust against noise, but sensitive to image artifacts. This result highlights the need of robustness quality assurance against image noise and artifacts in the commissioning of a DIR commercial system and underlines the importance to adopt optimized protocols for CBCT image acquisitions in ART clinical implementation.

60 APPLIED LIFE SCIENCES↗

Reduced Order Modeling for Prediction and Control of Large-Scale Systems.

This report describes work performed from June 2012 through May 2014 as a part of a Sandia Early Career Laboratory Directed Research and Development (LDRD) project led by the first author. The objective of the project is to investigate methods for building stable and efficient proper orthogonal decomposition (POD)/Galerkin reduced order models (ROMs): models derived from a sequence of high-fidelity simulations but having a much lower computational cost. Since they are, by construction, small and fast, ROMs can enable real-time simulations of complex systems for onthe- spot analysis, control and decision-making in the presence of uncertainty. Of particular interest to Sandia is the use of ROMs for the quantification of the compressible captive-carry environment, simulated for the design and qualification of nuclear weapons systems. It is an unfortunate reality that many ROM techniques are computationally intractable or lack an a priori stability guarantee for compressible flows. For this reason, this LDRD project focuses on the development of techniques for building provably stable projection-based ROMs. Model reduction approaches based on continuous as well as discrete projection are considered. In the first part of this report, an approach for building energy-stable Galerkin ROMs for linear hyperbolic or incompletely parabolic systems of partial differential equations (PDEs) using continuous projection is developed. The key idea is to apply a transformation induced by the Lyapunov function for the system, and to build the ROM in the transformed variables. It is shown that, for many PDE systems including the linearized compressible Euler and linearized compressible Navier-Stokes equations, the desired transformation is induced by a special inner product, termed the “symmetry inner product”. Attention is then turned to nonlinear conservation laws. A new transformation and corresponding energy-based inner product for the full nonlinear compressible Navier-Stokes equations is derived, and it is demonstrated that if a Galerkin ROM is constructed in this inner product, the ROM system energy will be bounded in a way that is consistent with the behavior of the exact solution to these PDEs, i.e., the ROM will be energy-stable. The viability of the linear as well as nonlinear continuous projection model reduction approaches developed as a part of this project is evaluated on several test cases, including the cavity configuration of interest in the targeted application area. In the second part of this report, some POD/Galerkin approaches for building stable ROMs using discrete projection are explored. It is shown that, for generic linear time-invariant (LTI) systems, a discrete counterpart of the continuous symmetry inner product is a weighted L2 inner product obtained by solving a Lyapunov equation. This inner product was first proposed by Rowley et al., and is termed herein the “Lyapunov inner product“. Comparisons between the symmetry inner product and the Lyapunov inner product are made, and the performance of ROMs constructed using these inner products is evaluated on several benchmark test cases. Also in the second part of this report, a new ROM stabilization approach, termed “ROM stabilization via optimization-based eigenvalue reassignment“, is developed for generic LTI systems. At the heart of this method is a constrained nonlinear least-squares optimization problem that is formulated and solved numerically to ensure accuracy of the stabilized ROM. Numerical studies reveal that the optimization problem is computationally inexpensive to solve, and that the new stabilization approach delivers ROMs that are stable as well as accurate. Summaries of “lessons learned“ and perspectives for future work motivated by this LDRD project are provided at the end of each of the two main chapters.

97 MATHEMATICS AND COMPUTING↗

Numerical experiments with the extended virtual element method for the Laplace problem with strong discontinuities

The virtual element method (VEM) is a stabilized Galerkin formulation on arbitrary polytopal meshes. In the VEM, the basis functions are implicit (virtual) — they are not known nor do they need to be computed within the problem domain. Suitable projection operators are used to decompose the bilinear form at the element-level into two parts: a consistent term that reproduces a given polynomial space and a correction term that ensures stability. In this study, we consider a low-order extended virtual element method (X-VEM) that is in the spirit of the extended finite element method for crack problems. Herein, we focus on the two-dimensional Laplace crack problem. In the X-VEM, we enrich the standard virtual element space with additional discontinuous functions through the framework of partition-of-unity. The nodal basis functions in the VEM are chosen as the partition-of-unity functions, and we study means to stabilize the standard and enriched sub-matrices that constitute the element stiffness matrix. Numerical experiments are performed on the problem of a cracked membrane under mode III loading to affirm the accuracy, and to establish the optimal convergence in energy of the method.

97 MATHEMATICS AND COMPUTING↗

Solid-State Mixed-Potential Electrochemical Sensors for Natural Gas Leak Detection and Quality Control (Final Technical Report)

Mitigation of methane emissions are a critical factor to limiting the impact of the natural gas industry on global climate change. Throughout the period of 2020-2024, the University of New Mexico and its commercialization partner and subcontractor, SensorComm Technologies, Inc. (SCT), have worked together to develop a low-cost Artificial Intelligence (AI)-driven Internet of Things (IoT)-based multi-gas sensor platform for methane emissions detection. In the final year of the project, we extended this work to include hydrogen detection in support of a transition to a hydrogen economy where hydrogen could be transported through existing natural gas infrastructure. Mixed potential electrochemical sensors were first prototyped by ceramic additive manufacturing and then transitioned to conventional ceramic manufacturing tape casting and screen-printing technologies in preparation for mass production. Demonstrated limits of detection of 5 ppm of methane in natural gas and 1 ppm of hydrogen were measured. These limits of detection are among the lowest of solid-state electrochemical sensors that have been reported in the literature or available in the industry. Machine learning algorithms were developed to identify natural gas mixtures with > 98% accuracy level and quantify methane concentrations at 97% accuracy. The presence of hydrogen could also be identified, and its concentration quantified at these accuracy levels. These algorithms were optimized for running on portable computing hardware which enabled > 1 Hz processing rates. A portable packaged IoT system was integrated with the electrochemical sensor in collaboration with SCT. The package consists of readout electronics with < 1 mV resolution, sensor temperature control, and data transmission over cellular wireless and/or Wi-Fi networks. Field testing was performed in two rounds at Colorado State University’s Methane Emissions Technology Evaluation Center (CSU METEC). The first round of testing demonstrated successful measurements of methane from an underground natural gas leak of 20 standard liters per minute (SLPM), which agreed with previously published literature using more sophisticated and expensive analytical equipment. The second round of testing showed that an above ground leak of 2 SLPM of hydrogen could be detected at 32 ft. This project has resulted in six published peer reviewed journal articles, over ten presentations at professional conferences, and one full patent application filed in 2023. Future work on this project includes increased sensitivity, higher production yields, and applications in the hydrogen safety and flare emissions monitoring spaces.

03 NATURAL GAS↗

Acceleration of Thermochemistry Solves in MOOSE and Pronghorn

This work focuses on the development and implementation of strategies to accelerate thermochemical calculations within MOOSE-based multiphysics simulations, particularly for applications in MSRs. We highlight the inherent complexity of nuclear materials, which require a multiscale approach to accurately model their behavior across various physical domains, including mechanical, chemical, and thermal phenomena. Thermochemical equilibrium calculations are crucial for predicting material properties and enhancing the fidelity of these simulations. The integration of Thermochimica, a Gibbs energy minimizer, into MOOSE allows for the direct minimization of Gibbs energy at every point on the mesh. However, the computational cost of such integration is significant. To address this, we explored acceleration strategies such as multi-threading support and the use of a thermodynamic ValueCache to reduce redundant calculations. Additionally, we investigated modifications to Thermochimica to enable phase constraints and improve its coupling with phase-field models, which are essential for simulating microstructural evolution and corrosion in MSR. These efforts aim to optimize the computational efficiency and accuracy of multiphysics simulations, thereby supporting the development of reliable and efficient nuclear materials for next-generation reactor technologies.

36 - MATERIALS SCIENCE↗

Digital Modeling on Large Kernel Metamaterial Neural Network

Deep neural networks (DNNs) utilized recently are physically deployed with computational units (e.g., CPUs and GPUs). Such a design might lead to a heavy computational burden, significant latency, and intensive power consumption, which are critical limitations in applications such as Internet of Things (IoT), edge computing, and usage of drones. Recent advances in optical computational units (e.g., metamaterial) have shed light on energy-free and light-speed neural networks. However, the digital design of the metamaterial neural network (MNN) is fundamentally limited by its physical limitations, such as precision, noise, and bandwidth during fabrication. Moreover, the unique advantages of MNN’s (e.g., light-speed computation) are not fully explored via standard 3×3 convolution kernels. In this paper, we propose a novel large kernel metamaterial neural network (LMNN) that maximizes the digital capacity of the state-of-the-art (SOTA) MNN with model re-parametrization and network compression, while also considering the optical limitation explicitly. The new digital learning scheme can maximize the learning capacity of MNN while modeling the physical restrictions of meta-optics. With the proposed LMNN, the computation cost of the convolutional front-end can be offloaded to fabricated optical hardware. The experimental results on two publicly available datasets demonstrate that the optimized hybrid design improved classification accuracy while reducing computational latency. In conclusion, the development of the proposed LMNN is a promising step towards the ultimate goal of energy-free and light-speed AI.

97 MATHEMATICS AND COMPUTING↗

Prediction of Dielectric Constant in Series of Polymers by Quantitative Structure-Property Relationship (QSPR)

This work is devoted to the investigation of dielectric permittivity which is influenced by electronic, ionic, and dipolar polarization mechanisms, contributing to the material’s capacity to store electrical energy. In this study, an extended dataset of 86 polymers was analyzed, and two quantitative structure–property relationship (QSPR) models were developed to predict dielectric permittivity. From an initial set of 1273 descriptors, the most relevant ones were selected using a genetic algorithm, and machine learning models were built using the Gradient Boosting Regressor (GBR). In contrast to Multiple Linear Regression (MLR)- and Partial Least Squares (PLS)-based models, the gradient boosting models excel in handling nonlinear relationships and multicollinearity, iteratively optimizing decision trees to improve accuracy without overfitting. The developed GBR models showed high R2 coefficients of 0.938 and 0.822, for the training and test sets, respectively. An Accumulated Local Effect (ALE) technique was applied to assess the relationship between the selected descriptors—eight for the GB_A model and six for the GB_B model, and their impact on target property. ALE analysis revealed that descriptors such as TDB09m had a strong positive effect on permittivity, while MLOGP2 showed a negative effect. These results highlight the effectiveness of the GBR approach in predicting the dielectric properties of polymers, offering improved accuracy and interpretability.

Ascencio-Medina, Estefania↗

A Machine Learning-Genetic Algorithm (ML-GA) Approach for Rapid Optimization Using High-Performance Computing

A Machine Learning-Genetic Algorithm (ML-GA) approach was developed to virtually discover optimum designs using training data generated from multi-dimensional simulations. Machine learning (ML) presents a pathway to transform complex physical processes that occur in a combustion engine into compact informational processes. In the present work, a total of over 2000 sector-mesh computational fluid dynamics (CFD) simulations of a heavy-duty engine were performed. These were run concurrently on a supercomputer to reduce overall turnaround time. The engine being optimized was run on a low-octane (RON70) gasoline fuel under partially premixed compression ignition (PPCI) mode. A total of nine input parameters were varied, and the CFD simulation cases were generated by randomly sampling points from this nine-dimensional input space. These input parameters included fuel injection strategy, injector design, and various in-cylinder flow and thermodynamic conditions at intake valve closure (IVC). The outputs (targets) of interest from these simulations included five metrics related to engine performance and emissions. Over 2000 samples generated from CFD were then used to train an ML model that could predict these five targets based on the nine input features. A robust super learner approach was employed to build the ML model, where results from a collection of different ML algorithms were pooled together. Thereafter, a stochastic global optimization genetic algorithm (GA) was used, with the ML model as the objective function, to optimize the input parameters based on a merit function so as to minimize fuel consumption while satisfying CO and NOx emissions constraints. The optimized configuration from ML-GA was found to be very close to that obtained from a sequentially performed CFD-GA approach, where a CFD simulation served as the objective function. In addition, the overall turnaround time was (at least) 75% lower with the ML-GA approach, as the training data was generated from concurrent CFD simulations and employing the ML model as the objective function significantly accelerated the GA optimization. Finally, this study demonstrates the potential of ML-GA and high-performance computing (HPC) to reduce the number of CFD simulations to be performed for optimization problems without loss in accuracy, thereby providing significant cost savings compared to traditional approaches.

97 MATHEMATICS AND COMPUTING↗