Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computational 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 1,009 records · Page 56

An Improved Genetic Algorithm approach to the Unit Commitment/Economic Dispatch problem

The deployment of new technologies, the importance of accurately modeling the dynamics of the generating units and the introduction of new policies are making the solution of the Unit Commitment/Economic Dispatch problem more and more complicated.In the present scenario, traditionally followed scheduling criteria might not lead to the optimal fleet configuration any more. In addition, most of the widely used techniques have limited capabilities at modeling the nonlinear dynamics of committed power plants. When realistic power systems comprising of several tens of generating units are modeled, the resulting optimization problem turns to be computationally intensive for the current computing capabilities. In this paper, an improved version of a GA-based optimization algorithm is presented. A detailed methodology aimed at obtaining a more efficient version of the GA, and a more detailed and accurate description of the flexible operation flexibility of the power plants is described.

genetic algorithm↗

Atomistic nanoelectronic device engineering with sustained performances up to 1.44 PFlop/s

We present a multi-dimensional, atomistic, quantum transport simulation approach to investigate the performances of realistic nanoscale transistors for various geometries and material systems. The central computation consists in solving the Schrödinger equation with open boundary conditions several thousand times. To do that, a Wave Function approach is used since it can be relatively easily parallelized. To further improve the computational efficiency, three additional levels of parallelization are identified, the work load is optimally balanced between the CPUs, computational interleaving is applied where possible, and a mixed precision scheme is introduced. Using two different device types, a high electron mobility and a band-to-band tunneling transistor, sustained performances up to 1.28 PFlop/s in double precision (55% of the peak performance) and 1.44 PFlop/s in mixed precision are reached on 221,400 cores on the CRAY-XT5 Jaguar at Oak Ridge National Lab.

Luisier, Mathieu↗

Component-to-Optimization Workflow Demonstration

This report aims to demonstrate workflow-generating algorithms for optimizing dispatch across a broad range of Integrated Energy System applications using the Framework for Optimization of Resources and Economics (FORCE) tool suite. The optimization is performed at two different time scales. In the coarse time scale, the optimization focuses on a class of energy sources and consumers and aims to find the optimal combinations and flows of energy based on real-time price data information. In the fine time scale, the optimization focuses on a specific thermal energy delivery system and aims to find the optimal setpoints of components in order to meet the energy demands from coarse-time-scale optimizations. In this demonstration, the coarse-scale optimization is implemented using the newly developed Dispatch Optimization Variable Engine (DOVE), while the fine-scale optimization used Optimization of Real-Time Capacity Allocation (ORCA).

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Position Papers for the ASCR Workshop on the Science of Scientific-Software Development and Use

Software is an increasingly important component in the pursuit of scientific discovery. Both its development and use are essential activities for many scientific teams. At the same time, very little scientific study has been conducted to understand, characterize, and improve the development and use of software for science. Computational science teams have diversified over time to include contributions from domain scientists who provide expertise in scientific and engineering disciplines, applied mathematicians and computer scientists who provide optimal algorithms and data structures, and software and data engineers who provide methodologies and tools adapted and adopted from other software domains. These diverse contributions have enabled tremendous advances in the pursuit of scientific discovery, even as models, computer architectures, and software environments have become more complicated. With this increasing diversity, we believe the next opportunity for qualitative improvement comes from applying the scientific method to understanding, characterizing, and improving how scientific software is developed and used. We believe that this pursuit requires expertise from computational scientists themselves, and from the cognitive and social sciences as well as the software engineering research community. As we look to increase the productivity and sustainability of the scientific-software-development-and-use cycle, a more systematic application of the scientific method to understand processes for software development and use will be a valuable tool to guide future work and result in more usable and sustainable software. This workshop will bring together computer scientists, software engineering researchers, computational scientists, applied mathematicians, social scientists, cognitive scientists, and others, to explore how we can conduct such systematic investigations, what can be learned, and how doing so will benefit the scientific enterprise. The workshop will be structured around a set of breakout sessions, with every attendee expected to participate actively in the discussions. Afterward, workshop attendees — from DOE, industry, and academia — will produce a report for ASCR that summarizes the findings of the workshop.

42 ENGINEERING↗

A Decomposition-Based Learn-To-Optimize Approach with Feasibility Layer Assistance for Sub-Hourly Unit Commitment

Sub-hourly unit commitment (UC) with 15-min intervals is gaining significant attention as a way to respond rapidly to the fluctuations in electricity supply and demand introduced by renewable resources. However, the increased temporal resolution and complex inter-temporal dependencies pose substantial computational challenges for traditional optimization methods. To this end, this paper explores a decomposition-based learn-to-optimize approach. Building on recent advances in machine learning, our method revisits the long- overlooked Lagrangian relaxation framework, which is a classical decomposition technique that enables tractable subproblem solving. These smaller subproblems are inherently well-suited for machine learning, as their reduced dimensionality and structural regularity allow predictive models to efficiently learn and generalize solution patterns. We thus propose a generic predictive model, which embeds Gated Recurrent Units (GRUs) and Attention in the encoder-decoder structure, and integrate a rule-based feasibility layer to capture temporal dependencies, reduce training effort, and improve feasibility w.r.t. unit-level constraints. Our method has been validated on the IEEE 118-bus system, demonstrating promising performance in solving sub-hourly UC problems efficiently and feasibly.

97 MATHEMATICS AND COMPUTING↗

Modeling approaches for addressing unrelaxable bound constraints with unconstrained optimization methods

We explore novel approaches for solving nonlinear optimization problems with unrelaxable bound constraints, which must be satisfied before the objective function can be evaluated. Our method reformulates the unrelaxable bound-constrained problem as an unconstrained optimization problem that is amenable to existing unconstrained optimization methods. The reformulation relies on a domain warping to form a merit function; the choice of the warping determines the level of exactness with which the unconstrained problem can be used to find solutions to the bound-constrained problem, as well as key properties of the unconstrained formulation such as smoothness. We develop theory when the domain warping is a multioutput sigmoidal warping, and we explore the practical elements of applying unconstrained optimization methods to the formulation. Here, we develop an algorithm that exploits the structure of the sigmoidal warping to guarantee that unconstrained optimization algorithms applied to the merit function will find a stationary point to the desired tolerance.

97 MATHEMATICS AND COMPUTING↗

Predictive drug dosage control through a Fokker–Planck observer

During the years, various techniques have been presented for optimal control of tumor growth for which its stochastic behavior has rarely been considered. This article uses the well-known Gompertz stochastic model, for describing tumor growth, and by receding horizon model predictive control (RH-MPC) scheme computes the drug dosage for minimizing the tumor-cell population. To do this, a predictive control problem is defined based on the difference between the probability density function of tumor-cell population and the desired probability density function. In the model, both the drug dosage limitation and the Fokker–Planck equation have been considered as constraints. By solving this problem, the drug dosage which is considered as an external input to tumor model, is computed. In this article, the Fokker–Planck equation is used (1) as a nonlinear observer of probability density function of tumor-cell population and (2) a mapping vehicle from stochastic to deterministic domain. The Fokker–Planck equation is written for the Gompertz stochastic model of tumor growth. The equation is then solved through the path integral method. In this way, the probability density function of tumor-cell population, which contains the entire stochastic characteristics of the tumor growth, is obtained for any instance of time. The simulation results have also been presented for the evaluation of the suggested approach. The results show that the tumor-cell population can be controlled within a number of time windows (15 time windows in our case study) if an appropriate desired PDF is selected.

97 MATHEMATICS AND COMPUTING↗

Collaborative Decision Approach for Electricity Pricing-demand Response Stackelberg Game

Demand response programs are considered as a valuable resource in smart grids that provide several advantages of load shifting, peak load reduction, mediating intermittency of renewable energy integration, etc. Flexible price-based incentives have been recognized as a critical strategy in motivating and compensating consumers' load adjustment actions for successful implementation of demand response. Game theoretical approaches, especially Stackelberg games are popularly adopted to model the relationship between electricity price and customers' demand response and solved by the classical centralized backward induction (BI) method. However, the BI method generally requires convexity of the follower's model for necessary optimality conditions, and the computational time of any centralized approach increases sharply with larger problem instances. In this paper, the Stackelberg game of electricity pricing-demand response between a distribution system operator (DSO) and load aggregators (LAs) is decomposed based on a collaborative optimization (CO) framework, where each LA is treated as a discipline with its own domain constraints (e.g. building temperature control), while the DSO at the system level tries to reduce the solution discrepancy and guide the searching towards optimality. Several groups of comparison experiments have demonstrated the effectiveness of the proposed collaborative decision approach in solving the demand response game.

Chen, Yang↗

PRACTICAL METHODS FOR CONTINUOUS GRAVITATIONAL WAVE DETECTION USING PULSAR TIMING DATA

Gravitational waves (GWs) are tiny ripples in the fabric of space time predicted by Einstein's general relativity. Pulsar timing arrays (PTAs) are well poised to detect low-frequency (10{sup -9}-10{sup -7} Hz) GWs in the near future. There has been a significant amount of research into the detection of a stochastic background of GWs from supermassive black hole binaries (SMBHBs). Recent work has shown that single continuous sources standing out above the background may be detectable by PTAs operating at a sensitivity sufficient to detect the stochastic background. The most likely sources of continuous GWs in the pulsar timing frequency band are extremely massive and/or nearby SMBHBs. In this paper we present detection strategies including various forms of matched filtering and power spectral summing. We determine the efficacy and computational cost of such strategies. It is shown that using an optimal matched filter explicitly including the poorly constrained pulsar distances with a grid-based method is computationally infeasible. We show that an Earth-term-matched filter constructed using only the correlated signal terms is robust, computationally viable and highly sensitive to GW signals. We further show that a simple power spectral summing technique is nearly equivalent to the Earth-term-matched filter in terms of the minimum detectable amplitude. Both of these techniques are only a factor of two less sensitive than the computationally unrealizable optimal matched filter. We also show that a pairwise matched filter, taking the pulsar distances into account, is comparable to the optimal matched filter for the single template case and comparable to the Earth-term-matched filter for many search templates. Finally, using simulated data optimal quality, we place a theoretical minimum detectable strain amplitude of h > 2 Multiplication-Sign 10{sup -15} from continuous GWs at frequencies on the order {approx}1/T{sub obs}.

79 ASTRONOMY AND ASTROPHYSICS↗

Optimization of a dual-energy contrast-enhanced technique for a photon-counting digital breast tomosynthesis system: I. A theoretical model

Purpose: Dual-energy (DE) iodine contrast-enhanced x-ray imaging of the breast has been shown to identify cancers that would otherwise be mammographically occult. In this article, theoretical modeling was performed to obtain optimally enhanced iodine images for a photon-counting digital breast tomosynthesis (DBT) system using a DE acquisition technique. Methods: In the system examined, the breast is scanned with a multislit prepatient collimator aligned with a multidetector camera. Each detector collects a projection image at a unique angle during the scan. Low-energy (LE) and high-energy (HE) projection images are acquired simultaneously in a single scan by covering alternate collimator slits with Sn and Cu filters, respectively. Sn filters ranging from 0.08 to 0.22 mm thickness and Cu filters from 0.11 to 0.27 mm thickness were investigated. A tube voltage of 49 kV was selected. Tomographic images, hereafter referred to as DBT images, were reconstructed using a shift-and-add algorithm. Iodine-enhanced DBT images were acquired by performing a weighted logarithmic subtraction of the HE and LE DBT images. The DE technique was evaluated for 20-80 mm thick breasts. Weighting factors, w{sub t}, that optimally cancel breast tissue were computed. Signal-difference-to-noise ratios (SDNRs) between iodine-enhanced and nonenhanced breast tissue normalized to the square root of the mean glandular dose (MGD) were computed as a function of the fraction of the MGD allocated to the HE images. Peak SDNR/{radical}(MGD) and optimal dose allocations were identified. SDNR/{radical}(MGD) and dose allocations were computed for several practical feasible system configurations (i.e., determined by the number of collimator slits covered by Sn and Cu). A practical system configuration and Sn-Cu filter pair that accounts for the trade-off between SDNR, tube-output, and MGD were selected. Results: w{sub t} depends on the Sn-Cu filter combination used, as well as on the breast thickness; to optimally cancel 0% with 50% glandular breast tissue, w{sub t} values were found to range from 0.46 to 0.72 for all breast thicknesses and Sn-Cu filter pairs studied. The optimal w{sub t} values needed to cancel all possible breast tissue glandularites vary by less than 1% for 20 mm thick breasts and 18% for 80 mm breasts. The system configuration where one collimator slit covered by Sn is alternated with two collimator slits covered by Cu delivers SDNR/{radical}(MGD) nearest to the peak value. A reasonable compromise is a 0.16 mm Sn-0.23 mm Cu filter pair, resulting in SDNR values between 1.64 and 0.61 and MGD between 0.70 and 0.53 mGy for 20-80 mm thick breasts at the maximum tube current. Conclusions: A DE acquisition technique for a photon-counting DBT imaging system has been developed and optimized.

60 APPLIED LIFE SCIENCES↗

Sensitivity Analyses for Monte Carlo Sampling-Based Particle Simulations

Computational design-based optimization is a well-used tool in science and engineering. Our report documents the successful use of a particle sensitivity analysis for design-based optimization within Monte Carlo sampling-based particle simulation—a currently unavailable capability. Such a capability enables the particle simulation communities to go beyond forward simulation and promises to reduce the burden on overworked analysts by getting more done with less computation.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Snowflake: A Lightweight Portable Stencil DSL

Stencil computations are not well optimized by general-purpose production compilers and the increased use of multicore, manycore, and accelerator-based systems makes the optimization problem even more challenging. In this paper we present Snowflake, a Domain Specific Language (DSL) for stencils that uses a 'micro-compiler' approach, i.e., small, focused, domain-specific code generators. The approach is similar to that used in image processing stencils, but Snowflake handles the much more complex stencils that arise in scientific computing, including complex boundary conditions, higher-order operators (larger stencils), higher dimensions, variable coefficients, non-unit-stride iteration spaces, and multiple input or output meshes. Snowflake is embedded in the Python language, allowing it to interoperate with popular scientific tools like SciPy and iPython; it also takes advantage of built-in Python libraries for powerful dependence analysis as part of a just-in-time compiler. We demonstrate the power of the Snowflake language and the micro-compiler approach with a complex scientific benchmark, HPGMG, that exercises the generality of stencil support in Snowflake. By generating OpenMP comparable to, and OpenCL within a factor of 2x of hand-optimized HPGMG, Snowflake demonstrates that a micro-compiler can support diverse processor architectures and is performance-competitive whilst preserving a high-level Python implementation.

97 MATHEMATICS AND COMPUTING↗

Optimal experiment design for time-lapse traveltime tomography

Geophysical monitoring techniques offer the only noninvasive approach capable of assessing both the spatial and temporal dynamics of subsurface fluid processes. Increasingly, permanent sensor arrays in boreholes and on the ocean floor are being deployed to improve the repeatability and increase the temporal sampling of monitoring surveys. Because permanent arrays require a large up-front capital investment and are difficult (or impossible) to re-configure once installed, a premium is placed on selecting a geometry capable of imaging the desired target at minimum cost. We present a simple approach to optimizing downhole sensor configurations for monitoring experiments making use of differential seismic traveltimes. In our case, we use a design quality metric based on the accuracy of tomographic reconstructions for a suite of imaging targets. By not requiring an explicit singular value decomposition of the forward operator, evaluation of this objective function scales to problems with a large number of unknowns. We also restrict the design problem by recasting the array geometry into a low dimensional form more suitable for optimization at a reasonable computational cost. We test two search algorithms on the design problem: the Nelder-Mead downhill simplex method and the Multilevel Coordinate Search algorithm. The algorithm is tested for four crosswell acquisition scenarios relevant to continuous seismic monitoring, a two parameter array optimization, several scenarios involving four parameter length/offset optimizations, and a comparison of optimal multi-source designs. In the last case, we also examine trade-offs between source sparsity and the quality of tomographic reconstructions. One general observation is that asymmetric array lengths improve localized image quality in crosswell experiments with a small number of sources and a large number of receivers. Preliminary results also suggest that high-quality differential images can be generated using only a small number of optimally positioned sources.

54 ENVIRONMENTAL SCIENCES↗

Spherical fitting for oscilloscope film trace reading

This report describes a spherical fitting algorithm that can be used for estimating the oscilloscope film trace coordinates. This algorithm was adopted from a least square algebraic spherical fitting algorithm developed by the author earlier for photovoltaic velocimetry applications. Preliminary assessment suggests that the algorithm may be used for optimizing the coordinates manually digitized by the user, or may be used as an uncertainty estimator for the user’s film reading uncertainties.

97 MATHEMATICS AND COMPUTING↗

OPTIMIZATION OF A NUCLEAR VESSEL OUTLET FOR INCIDENT MONITORING

Classical nuclear core fluidic design techniques require improvement to better align with modern technological innovations. The US Department of Energy’s Office of Nuclear Energy (DOE-NE) Transformational Challenge Reactor (TCR) program is deploying additive manufacturing and advanced modeling and simulation to reimagine these designs. With the aid of modern computing power, computerized design optimization can be implemented to remove unwanted pressure drop while simultaneously optimizing flow structures, resulting in new opportunities to enable advanced instrumentation and monitoring capabilities.Previous development of geometric specifications for the TCR pressure vessel’s outlet plenum used design optimization to (1) limit pressure losses below 3.5 kPa (~0.5 psi) and (2) create a fluidic plane in which the temperature variation would not exceed ±5°C. This significant limit of the allowable pressure drop stems from the overarching goal of the TCR program to apply cutting edge techniques and unconventional thinking to demonstrate potential opportunities in additive manufacturing (AM).This paper expands the previous work by optimizing thermowell locations for robust measurements by explicitly modeling them and the resulting flow impacts. Additionally, a single core coolant channel was chosen to represent an event that causes an increased bulk flow temperature increase of 100°C.High fidelity unsteady Reynolds-averaged Navier-Stokes (URANS) simulations of the conjugate heat transfer problem were run in Siemen’s Star-CCM+ for this study. Next, the bulk flow temperature of a single coolant channel was increased by 100°C and was allowed to converge again. Finally, statistical analysis using a sequential probability ratio test (SPRT) was used to determine the elapsed time the thermocouples took to discover the increased bulk flow temperature.

See, Nate↗

Classical-Quantum Algorithm for Solving Stochastic Programs

Stochastic programming provides a rigorous mathematical framework for making decisions under uncertainty in a risk-aware manner. Two-stage stochastic programming is, perhaps, the simplest form of this framework. Here the first-stage variables represent decisions that must be made "here and now" in the face of uncertainty, while the second-stage variables are decisions made after uncertain events. However, the broad adoption of stochastic programming has been hindered by computational challenges caused by the two-stage stochastic programming formulation which requires solving an ensemble of optimization problems. Using quantum amplitude estimation (QAE), quantum computers have shown the theoretic ability to compute expectations with Monte-Carlo methods with quadratically fewer samples than classical methods. In this work, we present a quantum algorithm for computing the expectation term using QAE for given first-stage decisions. Further, we detail methods of computing gradient information from the quantum calculation enabling the application of classical gradient-based optimization techniques. The result is a classical-quantum hybrid method of solving two-stage stochastic programs. These techniques are demonstrated with computational experiments based an engineering optimization problem.

97 MATHEMATICS AND COMPUTING↗

Scalable Parallel Methods for Analyzing Metagenomics Data at Extreme Scale

The field of bioinformatics and computational biology is currently experiencing a data revolution. The exciting prospect of making fundamental biological discoveries is fueling the rapid development and deployment of numerous cost-effective, high-throughput next-generation sequencing technologies. The result is that the DNA and protein sequence repositories are being bombarded with new sequence information. Databases are continuing to report a Moore’s law-like growth trajectory in their database sizes, roughly doubling every 18 months. In what seems to be a paradigm-shift, individual projects are now capable of generating billions of raw sequence data that need to be analyzed in the presence of already annotated sequence information. While it is clear that data-driven methods, such as sequencing homology detection, are becoming the mainstay in the field of computational life sciences, the algorithmic advancements essential for implementing complex data analytics at scale have mostly lagged behind. Sequence homology detection is central to a number of bioinformatics applications including genome sequencing and protein family characterization. Given millions of sequences, the goal is to identify all pairs of sequences that are highly similar (or “homologous”) on the basis of alignment criteria. While there are optimal alignment algorithms to compute pairwise homology, their deployment for large-scale is currently not feasible; instead, heuristic methods are used at the expense of quality. In this dissertation, we present the design and evaluation of a parallel implementation for conducting optimal homology detection on distributed memory supercomputers. Our approach uses a combination of techniques from asynchronous load balancing (viz. work stealing, dynamic task counters), data replication, and exact-matching filters to achieve homology detection at scale. Results for a collection of 2.56M sequences show parallel efficiencies of ~75-100% on up to 8K cores, representing a time-to-solution of 33 seconds. We extend this work with a detailed analysis of single-node sequence alignment performance using the latest CPU vector instruction set extensions. Preliminary results reveal that current sequence alignment algorithms are unable to fully utilize widening vector registers.

59 BASIC BIOLOGICAL SCIENCES↗

Multi-Source Machine Learning and Thermoplastics Enhanced Aerostructure Manufacturing (mTEAM)

RTX Technology Research Center (RTRC), together with Collins Aerospace (Collins) and Oak Ridge National Laboratory (ORNL) has developed an Artificial Intelligence (AI) / Machine Learning (ML) guided solution to advance the manufacturing and assembly of high performance and lightweight thermoplastic composite (TPC) aerospace products. The solution aims to lower risk, cost and lead time for induction heating based welding and consolidation processes for TPC structure. The cost and lead time of part and material specific process development for induction welding (IW) and induction consolidation will be reduced by replacing traditional empirical methods with optimization methods that merge AI/ML and physics-based process simulations and process experiments with sensing and controls. TPC-IW process development is empirical in nature, and uncertainties in material & process behavior exist near & far from the induction coil. Physics-based simulations can be leveraged directly for process optimization but can be too computationally expensive to run in high fidelity and real time to do robust process optimization. The key impact of successful TPC induction consolidation and welding is cost & lead time reduction for part & material specific consolidation and welding recipes. This is an enabler for more rapid deployment of TPC structures via joining assembly, which can reduce energy & cost intensive usage of autoclaves & ovens. The solution aimed to advance the U.S. Department of Energy’s interests in using thermoplastics and automation in composite manufacturing for improvement of products for existing markets via increased production speeds, reduced costs, and lowered use of energy. Welded TPC structures can offer significant weight & energy savings for high-value commercial aerospace & industrial applications compared to metal & thermoset composite structures assembled by mechanical fastening and/or adhesive bonding. The project was organized into two Budget Periods. Budget Period 1 (BP1) was 15 months and its goal was to perform ML process optimization framework development & deployment on lab-coupon aerostructure components. A Go/No-Go Review was performed at the end of BP1 to verify fulfilment of key tasks & milestones to justify a Go Decision to move into the next Budget Period. Budget Period 2 (BP2) was 12 months and its goal was the deployment of the ML framework for ML process optimization of pilot industrial scale aerostructure components. The overall project aim was to develop & demonstrate ML-enhanced modeling framework that learns process-property mapping from multiple data sources at different fidelities. During BP1, the team accomplished key tasks & milestones to demonstrate the concept of multi-source ML for TPC aerostructure consolidation and assembly. First, the team completed documentation of induction based TPC heating requirements including baseline metrics to compare measured results against. Next the team completed demonstration of data generation from physics-based simulations for ML surrogate model generation and demonstrated the integration of physics-based simulation data into multi-source AI/ML algorithms. In parallel, the team established the lab-coupon scale induction welding system and completed a process to label and reduce generated data from physics-based simulation and experiments for ML surrogate models to enable multi-source ML model training & testing. To complete BP1, the team integrated physics-based simulation data and experimental data into multi-source ML algorithms. This was based on the team completing ML deployment of the induction welding on a lab system at RTRC and AI/ML deployment on existing induction welding line at Collins. ORNL visited both Collins and RTRC sites to witness the TPC induction welding process. Then, ORNL designed and constructed a new version of their vision-based sensing system better adapted to acquire process signals of the TPC induction welding process for process anomaly and defect detection. In BP2, the team accomplished key tasks & milestones to scale up multi-source ML for TPC aerostructure consolidation and assembly from the lab-coupon scale to the pilot-industrial scale. In BP2, the team demonstrated real time anomaly & defect detection via experiments performed by ORNL & RTRC. The team completed ML-optimization heating trials for TPC induction consolidation at Collins, and the team confirmed pilot industrial scale experimental data from Collins was compatible with the developed ML pipeline from RTRC. The team completed sub-element scale ML process optimization demonstration at RTRC, where the team leveraged RTRC’s robotic TPC welding setup to de-risk the ML process optimization by performing ML analysis of recorded temperatures to account for complex part features. Then, the team applied its ML-derived control strategies and ML process optimization framework at Collins to the pilot-industrial scale on a demo skin-stiffener part representative of a nacelle aerostructure fan cowl section. The key innovation is the AI/ML framework enabling effective process development of high performance, lightweight, energy efficient TPCs for composite aircraft structures.

36 MATERIALS SCIENCE↗