Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Multi-Objective Optimization”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Holistic fleet optimization incorporating system design considerations

The methodology described in this article enables a type of holistic fleet optimization that simultaneously considers the composition and activity of a fleet through time as well as the design of individual systems within the fleet. Often, real-world system design optimization and fleet-level acquisition optimization are treated separately due to the prohibitive scale and complexity of each problem. Importantly, this means that fleet-level schedules are typically limited to the inclusion of predefined system configurations and are blind to a rich spectrum of system design alternatives. Similarly, system design optimization often considers a system in isolation from the fleet and is blind to numerous, complex portfolio-level considerations. In reality, these two problems are highly interconnected. To properly address this system-fleet design interdependence, we present a general method for efficiently incorporating multi-objective system design trade-off information into a mixed-integer linear programming (MILP) fleet-level optimization. This work is motivated by the authors' experience with large-scale DOD acquisition portfolios. However, the methodology is general to any application where the fleet-level problem is a MILP and there exists at least one system having a design trade space in which two or more design objectives are parameters in the fleet-level MILP.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Deep reinforcement learning assisted co-optimization of Volt-VAR grid service in distribution networks

With the increasing penetration of distributed energy resources in distribution networks, Volt-VAR control and optimization (VVC/VVO) have become very important to ensure an acceptable quality of service to all customers. System operators can rely on slow-responding utility devices, including capacitor banks and on-load tap changing transformers, along with fast-responding battery and photovoltaic (PV) inverters for the VVC/VVO implementation. Because of variations in response time of these two classes of devices, and different control actions (discrete versus continuous), coordinated and optimal scheduling and operation have become of utmost importance. Here, this paper develops a look-ahead deep reinforcement learning (DRL)-based multi-objective VVO technique to improve the voltage profile of active distribution networks, decrease network and inverter power loss, and save the operational cost of the grid. It proposes a deep deterministic policy gradient (DDPG)-based approach to schedule the optimal reactive and/or active power set-points of fast-responding inverters, and a deep Q-network (DQN)-based DRL agent to schedule the discrete decisions variables of slow-responding assets. The reactive power output of PV and battery smart inverters are scheduled at 30-minute intervals and the capacitors’ commitment status is scheduled with several hour intervals. The proposed framework is validated on the modified IEEE 34-bus and 123-bus test cases with embedded PV and PV-plus-storage. To validate the efficacy of the proposed VVO, it is compared with several scenarios, including the base case without VVO, localized droop control of DERs, DDPG-only, and twin delayed DDPG (TD3) agent-based DRL techniques. The results justify the superior performance of the proposed method to improve the voltage profile, reduce network power loss, and minimize the look-ahead grid operational cost while minimizing the undesirable power losses in inverters as a result of power factor adjustments.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

A Two-Stage Quantum Reinforcement Learning Method for Multi-Objective Transmission Switching

Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Improving the Quasi‐Biennial Oscillation via a Surrogate‐Accelerated Multi‐Objective Optimization

Accurate simulation of the quasi-biennial oscillation (QBO) is challenging due to uncertainties in representing convectively generated gravity waves. We develop an end-to-end uncertainty quantification workflow that calibrates these gravity wave processes in E3SM for a realistic QBO. Central to our approach is a domain knowledge-informed, compressed representation of high-dimensional spatio-temporal wind fields. By employing a parsimonious statistical model that learns the fundamental frequency from complex observations, we extract interpretable and physically meaningful quantities capturing key attributes. Building on this, we train a probabilistic surrogate model that approximates the fundamental characteristics of the QBO as functions of critical physics parameters governing gravity wave generation. Leveraging the Karhunen–Loève decomposition, our surrogate efficiently represents these characteristics as a set of orthogonal features, capturing cross-correlations among multiple physics quantities evaluated at different pressure levels and enabling rapid surrogate-based inference at a fraction of the computational cost of full-scale simulations. Finally, we analyze the inverse problem using a multi-objective approach. Our study reveals a tension between amplitude and period that constrains the QBO representation, precluding a single optimal solution. To navigate this, we quantify the bi-criteria trade-off and generate a set of Pareto optimal parameter values that balance the conflicting objectives. This integrated workflow improves the fidelity of QBO simulations and offers a versatile template for uncertainty quantification in complex geophysical models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Data Repository for Multi-Objective Urban Observational Strategies: A risk-based framework for expanding flood sensor networks.

These data support the manuscript "Multi-Objective Urban Observational Strategies: A risk-based framework for expanding flood sensor networks." These data are generated to allow water managers to reason about optimal locations to expand a flood observation system from multiple perspectives, specifically focusing on flood hazards, and population exposure to flooding. The data included are a) a shapefile of individual sensor locations b) a shapefile of river reach catchments, c) raster of FEMA flood likelihood layers d) shapefile of population locations and population socioeconomic characteristics. The code is written in R and includes all files necessary to generate the figures for the associated manuscript. Interactive maps of the final calculated maps of hazard, vulnerability, exposure, and risk are also included as html files.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Towards automated and real-time multi-object detection of anguilliform fishes from sonar data using YOLOv8 deep learning algorithm

Eels (Anguilla spp.), including American eels (Anguilla rostrata), European eels (Anguilla anguilla), and Japanese eels (Anguilla japonica), are species of critical management and regulatory concern due to their vulnerability to various stressors during downstream migrations. Accurate and efficient detection of migrating eels can improve our understanding of fish behaviors and fish-hydraulic structure interactions, thereby facilitating the design, operation, and optimization of more effective downstream passage facilities from both biological and economic perspectives. However, a real-time, automated framework for detecting migrating eels in real-world applications is currently lacking. Leveraging imaging sonar as a reliable technology for fish passage monitoring, field data are acquired using imaging sonar and then converted to single sonar frames/images for subsequent analysis. In this study, a framework based on the You Only Look Once Version 8 (YOLOv8)-based convolutional neural network is proposed for multi-object detection of eels and non-eel fish using the sonar images after image subtraction and additional wavelet denoising. The results from both training and testing phases demonstrate that the framework's ability can successfully detect both eels and non-eel fish in preprocessed sonar images, achieving F1-scores and mAP@0.50 exceeding 0.84. Additionally, the incorporation of wavelet denoising during preprocessing slightly improve detection performance. Furthermore, the transferability of this framework from eel to lamprey detection is demonstrated to be feasible given the similar morphological characteristics of these two species. Overall, the proposed framework achieves accurate and efficient detection of migrating eels, providing reliable and real-time information that can help conserve vulnerable eel and eel-like populations.

Deep learning↗
DOE OSTI2026

Multi-Objective design of interlocking metasurfaces using conditional diffusion models

Unit cell design remains a major challenge for interlocking metasurfaces, a promising joining technology for dissimilar materials, due to the complex, competing, multivariate design space and the need for rapid adaptation to varying performance requirements. This study explores Conditional Diffusion Models as a design optimization tool for interlocking metasurfaces. Given the complex, competing, multivariate design space for interlocking metasurfaces, unit cell design remains a major challenge for this joining technology. We trained a conditional diffusion model on 25,000 finite element analysis-simulated interlocking metasurface unit cells to generate designs with tailored thermo-mechanical properties (tensile strength, shear strength, and thermal conductivity) based on specified performance criteria. The model demonstrated a success rate of approximately 72 % in producing designs that met specified property bounds. The conditional diffusion model generated both thermally resistive and conductive designs, revealing clear trends in design characteristics: taller, dendritic structures were advantageous for tensile loads, while shorter, robust designs excelled in shear applications. Our findings indicate that the model's performance is more influenced by the breadth of the design space than by the quantity of training data, highlighting the importance of expansive design domains for generating innovative solutions. This work establishes conditional diffusion models as a highly efficient and adaptable tool for rapid interlocking metasurface unit cell design, paving the way for advancements in multi-material joining technologies, as well as highlighting the justification to leverage conditional diffusion models as design tools across complex design domains.

Conditional diffusion models↗
DOE OSTI2024

A Full-scale Demonstration of Pressurized Water Reactor Core Design Optimization using Multi-Cycle Optimization Methodology

The U.S. nuclear sector encounters a difficulty in upholding essential safety standards while also securing economic viability for continued operation. Safety stands as a pivotal factor across all facets of operations within light-water reactor nuclear power plants. Achieving economic feasibility alongside safety can be facilitated through the utilization of a risk-informed framework, exemplified by the ongoing development within the Risk-Informed Systems Analysis Pathway under the auspices of the U.S. Department of Energy's LWRS Program. This initiative advocates for a diverse array of research and development endeavors aimed at optimizing both safety and economic efficacy within nuclear power plants, particularly pertinent as many plants contemplate second license renewals. The Risk-Informed Systems Analysis Pathway has two main goals: deploy methodologies and technologies that better represent safety margins and cost and safety factors and develop advanced applications that enable cost-effective plant operation. This report assesses the potential for resolving multi-cycle plant reload challenges through real-world scenarios utilizing the Plant ReLoad Optimization (PRLO) framework. This framework offers reactor core design developers analytic tools of reactor safety and fuel performance with the assistance of artificial intelligence (AI) to enhance core design solutions. Multi-objective genetic algorithm alongside acceleration techniques is explored as an enabling technology for improving fuel efficiency while upholding safety thresholds. The demonstration of multi-cycle core design optimization is performed. This report investigates the practical application of the PRLO platform in addressing real-world core design challenges, supporting AI efforts, and contrasting outcomes with those derived from heuristic or conventional algorithms.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

The hyperplane of early-type galaxies: using stellar population properties to increase the precision and accuracy of the fundamental plane as a distance indicator

ABSTRACT We use deep spectroscopy from the SAMI (Sydney-AAO Multi-object Integral) Galaxy Survey to explore the precision of the fundamental plane (FP) of early-type galaxies as a distance indicator for future single-fibre spectroscopy surveys. We study the optimal trade-off between sample size and signal-to-noise ratio (SNR), and investigate which additional observables can be used to construct hyperplanes with smaller intrinsic scatter than the FP. We add increasing levels of random noise (parametrized as effective exposure time) to the SAMI spectra to study the effect of increasing measurement uncertainties on the FP- and hyperplane-inferred distances. We find that, using direct-fit methods, the values of the FP and hyperplane best-fitting coefficients depend on the spectral SNR, and reach asymptotic values for a mean $\langle \mathrm{ SNR} \rangle =40\, \mathrm{\mathring{\rm A}}^{-1}$. As additional variables for the FP we consider three stellar-population observables: light-weighted age, stellar mass-to-light ratio, and a novel combination of Lick indices ($I_\mathrm{age}$). For an $\langle \mathrm{ SNR} \rangle =45~\mathrm{\mathring{\rm A}}^{-1}$ (equivalent to 1-h exposure on a 4-m telescope), all three hyperplanes outperform the FP as distance indicators. Being an empirical spectral index, $I_\mathrm{age}$ avoids the model-dependent uncertainties and bias underlying age and mass-to-light ratio measurements, yet yields a 10 per cent reduction of the median distance uncertainty compared to the FP. We also find that, as a by-product, the $I_\mathrm{age}$ hyperplane removes most of the reported environment bias of the FP. After accounting for the different SNR, these conclusions also apply to a 50 times larger sample from SDSS-III (Sloan Digital Sky Survey). However, in this case, only $\mathrm{ age}$ removes the environment bias.

D’Eugenio, Francesco (ORCID:0000000323888172)↗
DOE OSTI2026

Domain Knowledge Guided Bayesian Optimization For Autonomous Alignment Of Complex Scientific Instruments

Bayesian Optimization (BO) is a powerful tool for optimizing complex non-linear systems. However, its performance degrades in high-dimensional problems with tightly coupled parameters and highly asymmetric objective landscapes, where rewards are sparse. In such needle-in-a-haystack scenarios, even advanced methods like trust-region BO (TurBO) often lead to unsatisfactory results. We propose a domain knowledge guided Bayesian Optimization approach, which leverages physical insight to fundamentally simplify the search problem by transforming coordinates to decouple input features and align the active subspaces with the primary search axes. We demonstrate this approach's efficacy on a challenging 12-dimensional, 6-crystal Split-and-Delay optical system, where conventional approaches, including standard BO, TuRBO and multi-objective BO, consistently led to unsatisfactory results. When combined with an reverse annealing exploration strategy, this approach reliably converges to the global optimum. The coordinate transformation itself is the key to this success, significantly accelerating the search by aligning input co-ordinate axes with the problem's active subspaces. As increasingly complex scientific instruments, from large telescopes to new spectrometers at X-ray Free Electron Lasers are deployed, the demand for robust high-dimensional optimization grows. Our results demonstrate a generalizable paradigm: leveraging physical insight to transform high-dimensional, coupled optimization problems into simpler representations can enable rapid and robust automated tuning for consistent high performance while still retaining current optimization algorithms.

FOS: Computer and information sciences↗
DOE OSTI2026

Optimization and stabilization of Fermilab Booster using hybrid Bayesian/RL framework

PIPII project will raise Fermilab Booster intensity and ramp rate. Beam losses will limit average power and are hard to simulate. Presently, Booster uses operator-guided empirical tuning. This task is challenging due to high dimensionality, multiple objectives, critical safety constraints, and drifts. We developed a synergistic suite of Bayesian optimization (BO) and reinforcement learning (RL) tools to optimize and stabilize beam losses. First, active learning was used to build a rough model. Data was collected parasitically using two novel safety constraint types – nonlinear input space restrictions (based on optics model), and uncertainty constraints (to stop bad steps/beam aborts). We then applied online multi-objective BO with scalarized objectives and fitting to improve/rebalance losses, increasing safety margins by 25%. Using BO model as a safety veto, we tried several on/off-policy RL agents for long term stabilization; SAC had best performance. We found that adding contextual (state) information further improved performance, eventually integrating key knobs like linac phase and temperature into the parameter space. Long term testing is ongoing to enable operational use.

Kuklev, Nikita [Fermilab]↗
DOE OSTI2026

Data driven drift correction for complex optical systems

To exploit the thousand-fold increase in spectral brightness of modern light sources, increasingly intricate experiments are being conducted that demand extremely precise beam trajectory. Maintaining the optimal trajectory over several hours of an experiment with the needed precision necessitates active drift control. Here, we outline time varying Bayesian optimization (TVBO) as a data driven approach for robust drift correction, and illustrate its application for a split and delay optical system composed of six crystals and twelve input dimensions. Using numerical simulations, we exhibit the application of TVBO for linear drift, non-smooth temporal drift as well as constrained TVBO for multi-objective control settings, representing real-life operating conditions. This approach can be easily adapted to other X-ray beam conditioning and guidance systems, including multi-crystal monochromators and grazing-incidence mirrors, to maintain sub-micrometer and nanoradian beam stability over the course of an experiment spanning several hours.

Bayesian optimization↗
DOE OSTI2024

3D high-fidelity automated neutronics guided optimization of fusion blanket designs

The compact Fusion Pilot Plant (FPP) is defined in the recent National Academies of Sciences, Engineering, and Medicine report as the next step of fusion energy demonstration with a $50$ MWe peak net electricity production, $Q_e$ greater than $1$, and at least $3$ hours of continuous operation. This fusion pilot plant will be a test bed enabling materials, designs, and fuel management assessment, and it will represent an engineering challenge because of its high-fusion power and compact design targets. Previous reactor data is limited to experiments operating in different design space ranges. Therefore, design iterations and assessments should rely on high-fidelity first-principle theoretical and computational models. The high-fidelity integrated modeling of the plasma is a fundamental part of fusion energy research. However, the whole device modeling is often neglected, utilizing low-fidelity, system-level analysis. Recently, the need for high-fidelity multi-physics modeling was recognized, resulting in a selection of integrated tools. Further, autonomous design optimization requires a streamlined framework that perturbs the design point, reruns the analysis, and examines the outputs. However, high-fidelity analysis requires complex geometry specification that is difficult to perturb. This work presents the parametric CAD generation tool TRACER and a new neutronic workflow. TRACER allows the perturbation of the geometry representation, creating geometry files ready for further analysis. The streamlined neutronic workflow allows efficient and accurate calculations. The two new tools coupled together were used to perform a 3D high-fidelity multi-objective, multi-input optimization of an "ARC Class" compact tokamak design. The workflow was driven by an optimization driver for full automation.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Multi-Objective Boundary Analysis of Discrete and Integrated SiC FET Modular Non-inverting Buck and Boost Converters for Fuel Cell EVs

This paper presents a multi-objective analysis of discrete and integrated SiC FET-based non-inverting buck-boost converter modules for modular fuel cell electric vehicle (EV) systems. Two converter ratings, 60 kW and 90 kW, are evaluated for both implementations, scalable up to 420 kW and 450 kW, respectively. Performance is assessed across efficiency, volumetric and gravimetric power density, cost, thermal stress, and estimated lifetime, where lifetime is derived from SiC FET B10 power-cycling data and junction temperature variations at rated power. A normalized overall performance index combined with a Pareto-boundary framework is used to identify configurations that optimally balance competing objectives. Results show that most configurations lie on the Pareto front, providing balanced trade-offs, while certain high-power discrete (90 kW at 450 kW) and integrated (60 kW at 180−420 kW) configurations are dominated. In general, discrete modules are more favorable for lower-power modular systems due to higher power density and lower cost, whereas integrated modules become more advantageous at higher power levels due to improved thermal behavior and longer lifetime. These findings provide practical design guidance for scalable fuel cell converter architectures and highlight the importance of system-level trade-offs in modular power electronics design.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗
DOE OSTI2023

Multi-Objective Adaptive Mesh Refinement Using Reinforcement Learning

Finite element methods approximate the solution to a partial differential equation (PDE) on a mesh consisting of many elements. In general, using more, smaller elements results in a lower error in the approximation. However, it is often possible to lower the error substantially by only refining, or decreasing the size of, the few elements in the mesh that have the highest error. Adaptive mesh refinement (AMR) is a process that selectively refines regions of a mesh with high error to achieve a desired accuracy in as few degrees of freedom (DOFs) as possible. AMR is favorable compared to uniform refinement, which refines all elements of the mesh equally, because it can often achieve the same accuracy without wasting extra computation time on refinement of elements that already have low error. However, it is difficult to know which elements to refine. In this report we explore ways to choose which elements to refine such that we minimize both the resulting error and the cumulative DOFs used in computation. In particular, we introduce a Pareto-front learning algorithm that trains a policy to give the optimal refinement actions to minimize the cumulative DOFs used to achieve a given target error. Such a policy is useful because it can be deployed on many different problem types where different accuracy levels are desired. Furthermore, training a single policy for a range of target errors allows us to use transfer learning to reduce the required training time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A neural-network-enhanced parameter-varying framework for multi-objective model predictive control applied to buildings

Management of the electrical grid is becoming more complex due to the increased penetration of alternative energy generation technologies and a broadening diversity of electric loads. This complexity creates challenges in balancing demand and generation that can increase the potential for grid instabilities. One effective way to address this issue is to leverage previously unexploited demand flexibility through advanced control strategies. In this work, we propose an advanced control method, called adaptive neural parameter-varying model predictive control (ANPV-MPC), to control the temperature and energy consumption of a building via its Heating, Ventilation, and Air Conditioning system. ANPV-MPC combines key ideas in parameter-varying control, adaptive control, and online learning strategies to bridge the gap between computationally efficient linear model predictive control and more accurate nonlinear model predictive control. The novelty in ANPV-MPC is the use of a physics-inspired Bayesian neural network to estimate the coefficients of the parameter-varying linear control model. The Bayesian neural network additionally provides uncertainty estimates, triggering online training to capture evolving building system conditions. We show that ANPV-MPC can approximate the building system dynamics with a 28.39% higher accuracy than traditional linear model predictive control, resulting in 36.23% better control performance without increasing complexity of the optimal control problem. ANPV-MPC also adapts in real time to previously unseen conditions using online learning, further improving its performance.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Bayesian optimization with active learning of design constraints using an entropy-based approach

Abstract The design of alloys for use in gas turbine engine blades is a complex task that involves balancing multiple objectives and constraints. Candidate alloys must be ductile at room temperature and retain their yield strength at high temperatures, as well as possess low density, high thermal conductivity, narrow solidification range, high solidus temperature, and a small linear thermal expansion coefficient. Traditional Integrated Computational Materials Engineering (ICME) methods are not sufficient for exploring combinatorially-vast alloy design spaces, optimizing for multiple objectives, nor ensuring that multiple constraints are met. In this work, we propose an approach for solving a constrained multi-objective materials design problem over a large composition space, specifically focusing on the Mo-Nb-Ti-V-W system as a representative Multi-Principal Element Alloy (MPEA) for potential use in next-generation gas turbine blades. Our approach is able to learn and adapt to unknown constraints in the design space, making decisions about the best course of action at each stage of the process. As a result, we identify 21 Pareto-optimal alloys that satisfy all constraints. Our proposed framework is significantly more efficient and faster than a brute force approach.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Co-Simulation Model for Optimal Wind-Hydro Coordination Using Wind Farm Control Dynamics

The growing share of Variable Renewable Energy sources (VRES) in power systems presents challenges for regula- tors, grid operators and energy producers. The VRES’ operation has limited flexibility in their operations, as they are highly dependent on ambient environments. To address these challenges, decision-makers must consider multiple objectives, among these are revenue, power system services and mechanical load on wind turbines. Coordinated operation of power plants and different wind farm control strategies are examples of measures that can benefit these objectives. This study proposes a Multi-Objective Linear Programming (MOLP) model to simulate the optimum operation of wind and hydropower plants that share limited transmission capacity. Further, wind farm control dynamics are included to obtain realistic output power and accumulated damage. From this, a case study based on a relevant location in Norway is presented to analyze the improved effect of wind- hydro coordination and wind farm control in achieving the objectives of accumulated wind turbine damage and total revenue of the hybrid power system. In addition, the study considers the potential advantages of adding a variable-speed pump to the hydropower plant. The results demonstrate that by considering multiple objectives in the optimization, one may achieve better overall performance of the objectives. By utilizing the flexibility of hydro storage, the decision maker may adjust to obtain the most desired outcome. Moreover, the added flexibility of utilizing a pump for hydro storage shows great improvements for the combined revenue of the power plants and reduced curtailment of the wind farm. However, less impact is observed from using a variable speed pump compared to a fixed speed pump.

13 HYDRO ENERGY↗