SEARCH · Engineering Papers

Results for “Machine”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 487 records · Page 27

All sources NASA NTRS DOE OSTI

DOE OSTI2022

A New Shape Optimization Approach for Lightweighting Electric Machines Inspired by Additive Manufacturing

Minimizing the mass in electric machines while maintaining superior performance is a new requirement for the advancement of drivetrains used in wind energy and electric mobility. Topology optimization (TO) for lightweighting electric machines using traditional approaches typically explores a restricted design space allowed by standard parametrizable geometry and manufacturing, while advanced methods, such as cell-based density approaches, suffer from a lack of robust manufacturability constraints during the optimization process. To overcome these drawbacks, we explore a grid-independent, boundary optimization where the outer shape of the magnet is parameterized using Bezier curves. We conduct a design of experiments (DOE) to study the effect of different magnet shapes on machine performance by varying the control points on the Bezier curves. A machine-learning-based surrogate model is constructed using the data from the DOE to quantify the relationship between the control points, air-gap torque, and mass. The control points are then optimized to maximize the torque density. The approach is used for minimizing electrical steel mass in the International Energy Agency (IEA) 15-MW radial flux direct-drive wind turbine generator. The new approach to shape optimization resulted in smooth and concise shapes that can be easily additively manufactured with up to a 20-ton reduction in electrical steel mass.

additive manufacturing↗

DOE OSTI2021

Co-design of Advanced Architectures for Graph Analytics using Machine Learning

A graph is an excellent way of representing relationships among entities. We can use graph analytics to synthesize and analyze such relational data, and extract relevant features that are useful for various tasks such as machine learning. Considering the crucial role of graph analytics in various domains, it is important and timely to investigate the right hardware configurations that can achieve optimal performance for graph workloads on future high-performance computing systems. Design space exploration studies facilitate the selection of appropriate configurations (e.g. memory) to achieve a desired system performance. Recently, the approach of accelerating graph analytics using persistent non-volatile memory has gained a lot of attention. Traditional system simulators such as Gem5 and NVMain can be used to explore the design space of these advanced memory architectures for graph workloads. However, these simulators are slow in execution thus limiting the efficiency of design space exploration studies. To overcome this challenge, we proposed a machine learning based approach to co-design advanced memory architectures for graph workloads. We tested our approach with DRAM, non-volatile memory, and hybrid memory (DRAM+NVM) using a breadth first search benchmark algorithm. Our results showed the applicability of the proposed machine learning based approach to the co-design of the advanced memory architectures. In this paper, we provide recommendations on selecting advanced memory architectures to achieve desired performance for graph workloads. We also discuss the performances of different machine learning models that were considered in this study.

Kurte, Kuldeep↗

DOE OSTI2018

Optimizing Kernel Machines Using Deep Learning

Building highly non-linear and non-parametric models is central to several state-of-the-art machine learning systems. Kernel methods form an important class of techniques that induce a reproducing kernel Hilbert space (RKHS) for inferring non-linear models through the construction of similarity functions from data. These methods are particularly preferred in cases where the training data sizes are limited and when prior knowledge of the data similarities is available. Despite their usefulness, they are limited by the computational complexity and their inability to support end-to-end learning with a task specific objective. On the other hand, deep neural networks have become the de facto solution for end-to-end inference in several learning paradigms. In this article, we explore the idea of using deep architectures to perform kernel machine optimization, for both computational efficiency and end-to-end inferencing. To this end, we develop the DKMO (Deep Kernel Machine Optimization) framework, that creates an ensemble of dense embeddings using Nystrõm kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings. Intuitively, the filters of the network are trained to fuse information from an ensemble of linear subspaces in the RKHS. Furthermore, we introduce the kernel dropout regularization to enable improved training convergence. Finally, we extend this framework to the multiple kernel case, by coupling a global fusion layer with pre-trained deep kernel machines for each of the constituent kernels. Using case studies with limited training data, and lack of explicit feature sources, we demonstrate the effectiveness of our framework over conventional model inferencing techniques.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2014

TU-C-12A-12: Differentiating Bone Lesions and Degenerative Joint Disease in NaF PET/CT Scans Using Machine Learning

Purpose: [F-18]NaF PET can be used to image bone metastases; however, tracer uptake in degenerative joint disease (DJD) often appears similar to metastases. This study aims to develop and compare different machine learning algorithms to automatically identify regions of [F-18]NaF scans that correspond to DJD. Methods: 10 metastatic prostate cancer patients received whole body [F-18]NaF PET/CT scans prior to treatment. Image segmentation resulted in 852 ROIs, 69 of which were identified by a nuclear medicine physician as DJD. For all ROIs, various PET and CT textural features were computed. ROIs were divided into training and testing sets used to train eight different machine learning classifiers. Classifiers were evaluated based on receiver operating characteristics area under the curve (AUC), sensitivity, specificity, and positive predictive value (PPV). We also assessed the added value of including CT features in addition to PET features for training classifiers. Results: The training set consisted of 37 DJD ROIs with 475 non-DJD ROIs, and the testing set consisted of 32 DJD ROIs with 308 non-DJD ROIs. Of all classifiers, generalized linear models (GLM), decision forests (DF), and support vector machines (SVM) had the best performance. AUCs of GLM (0.929), DF (0.921), and SVM (0.889) were significantly higher than the other models (p<0.001). GLM and DF, overall, had the best sensitivity, specificity, and PPV, and gave a significantly better performance (p<0.01) than all other models. PET/CT GLM classifiers had higher AUC than just PET or just CT. GLMs built using PET/CT information had superior or comparable sensitivities, specificities and PPVs to just PET or just CT. Conclusion: Machine learning algorithms trained with PET/CT features were able to identify some cases of DJD. GLM outperformed the other classification algorithms. Using PET and CT information together was shown to be superior to using PET or CT features alone. Research supported by the Prostate Cancer Foundation.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2015

SU-C-BRB-05: Investigation of Conformal Arc Therapy Utilizing Newly Designed Cobalt 60 Machine

Purpose: A new modernized design for cobalt 60 (Co-60) machines is being developed with a ring type gantry. In this study we investigate the beneficial outcome of the new design for conformal arc therapy for various clinical sites. The new modality was evaluated based on isodose distributions and dose volume histograms as compared to 6MV photon beams from conventional linear accelerators. Methods: Computed tomographic images of seven different SBRT patients were selected from our patient database. All of these cases were previously planned on the Eclipse treatment planning system. New plans for these patients were generated with a modified conformal arc technique using both 6MV and Co-60 beams. The conformal arc was created by the delivery of treatment fields conformal to the target cross-section at every 5 or 10 degrees. The field shape was modified or turned off when it initially passed through a critical structure. Monte Carlo codes, MCBEAM and MCPLAN, were used for the machine head simulation and phantom/patient dose calculation, respectively. In the new Co-60 machine design, the source-to-isocenter distance was 60cm and the treatment head included the Co-60 source, primary collimator, jaws and MLC. Results: For all cases investigated, conformal arc plans utilizing Co-60 beams achieved similar conformity (mean conformity index=1.19) comparing to 6MV photon beams. Isodose distributions were tailored similarly around the PTV; both Co-60 and 6MV plans met our clinical acceptance criteria for the target coverage, and the maximum and minimum target doses. The DVH for the Co-60 plans showed slightly lower doses to the critical structures although the differences were small in most cases. Conclusion: There were no significant dosimetric differences between 6MV and Co-60 plans. Our results confirmed that this new Co-60 design could be a cost-effective machine for advanced radiotherapy due to its low cost, low maintenance and high up time.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2016

SU-F-T-459: ArcCHECK Machine QA : Highly Efficient Quality Assurance Tool for VMAT, SRS & SBRT Linear Accelerator Delivery

Purpose: Quality assurance (QA) of complex linear accelerators is critical and highly time consuming. ArcCHECK Machine QA tool is used to test geometric and delivery aspects of linear accelerator. In this study we evaluated the performance of this tool. Methods: Machine QA feature allows user to perform quality assurance tests using ArcCHECK phantom. Following tests were performed 1) Gantry Speed 2) Gantry Rotation 3) Gantry Angle 4)MLC/Collimator QA 5)Beam Profile Flatness & Symmetry. Data was collected on trueBEAM stX machine for 6 MV for a period of one year. The Gantry QA test allows to view errors in gantry angle, rotation & assess how accurately the gantry moves around the isocentre. The MLC/Collimator QA tool is used to analyze & locate the differences between leaf bank & jaw position of linac. The flatness & Symmetry test quantifies beam flatness & symmetry in IEC-y & x direction. The Gantry & Flatness/Symmetry test can be performed for static & dynamic delivery. Results: The Gantry speed was 3.9 deg/sec with speed maximum deviation around 0.3 deg/sec. The Gantry Isocentre for arc delivery was 0.9mm & static delivery was 0.4mm. The maximum percent positive & negative difference was found to be 1.9 % & – 0.25 % & maximum distance positive & negative diff was 0.4mm & – 0.3 mm for MLC/Collimator QA. The Flatness for Arc delivery was 1.8 % & Symmetry for Y was 0.8 % & X was 1.8 %. The Flatness for gantry 0°,270°,90° & 180° was 1.75,1.9,1.8 & 1.6% respectively & Symmetry for X & Y was 0.8,0.6% for 0°, 0.6,0.7% for 270°, 0.6,1% for 90° & 0.6,0.7% for 180°. Conclusion: ArcCHECK Machine QA is an useful tool for QA of Modern linear accelerators as it tests both geometric & delivery aspects. This is very important for VMAT, SRS & SBRT treatments.

43 PARTICLE ACCELERATORS↗

DOE OSTI2016

TU-H-CAMPUS-JeP2-03: Machine-Learning-Based Delineation Framework of GTV Regions of Solid and Ground Glass Opacity Lung Tumors at Datasets of Planning CT and PET/CT Images

Purpose: In radiation treatment planning, delineation of gross tumor volume (GTV) is very important, because the GTVs affect the accuracies of radiation therapy procedure. To assist radiation oncologists in the delineation of GTV regions while treatment planning for lung cancer, we have proposed a machine-learning-based delineation framework of GTV regions of solid and ground glass opacity (GGO) lung tumors following by optimum contour selection (OCS) method. Methods: Our basic idea was to feed voxel-based image features around GTV contours determined by radiation oncologists into a machine learning classifier in the training step, after which the classifier produced the degree of GTV for each voxel in the testing step. Ten data sets of planning CT and PET/CT images were selected for this study. The support vector machine (SVM), which learned voxel-based features which include voxel value and magnitudes of image gradient vector that obtained from each voxel in the planning CT and PET/CT images, extracted initial GTV regions. The final GTV regions were determined using the OCS method that was able to select a global optimum object contour based on multiple active delineations with a level set method around the GTV. To evaluate the results of proposed framework for ten cases (solid:6, GGO:4), we used the three-dimensional Dice similarity coefficient (DSC), which denoted the degree of region similarity between the GTVs delineated by radiation oncologists and the proposed framework. Results: The proposed method achieved an average three-dimensional DSC of 0.81 for ten lung cancer patients, while a standardized uptake value-based method segmented GTV regions with the DSC of 0.43. The average DSCs for solid and GGO were 0.84 and 0.76, respectively, obtained by the proposed framework. Conclusion: The proposed framework with the support vector machine may be useful for assisting radiation oncologists in delineating solid and GGO lung tumors.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

Machine Learning for Sustainable Energy Systems

In recent years, machine learning has proven to be a powerful tool for deriving insights from data. In this review, we describe ways in which machine learning has been leveraged to facilitate the development and operation of sustainable energy systems. We first provide a taxonomy of machine learning paradigms and techniques, along with a discussion of their strengths and limitations. We then provide an overview of existing research using machine learning for sustainable energy production, delivery, and storage. Finally, we identify gaps in this literature, propose future research directions, and discuss important considerations for deployment.

Environmental Sciences & Ecology↗

DOE OSTI2023

Robust Machine Learning

UQ4ML is a code repository for a set of tools for the development of robust machine learning methods, uncertainty quantification and explainability of machine learning methods. The goal of these tools is to develop more robust and statistically rigorous machine learning methods for scientific applications. These tools are developed in Python, a high-level programming language that takes advantage of the Python ecosystem of high-quality open-source packages for machine learning.

Oyen, Diane↗

DOE OSTI2021

Application of an automated machine learning-genetic algorithm (AutoML-GA) coupled with computational fluid dynamics simulations for rapid engine design optimization

In recent years, the use of machine learning-based surrogate models for computational fluid dynamics (CFD) simulations has emerged as a promising technique for reducing the computational cost associated with engine design optimization. However, such methods still suffer from drawbacks. One main disadvantage is that the default machine learning (ML) hyperparameters are often severely suboptimal for a given problem. This has often been addressed by manually trying out different hyperparameter settings, but this solution is ineffective in case of a high-dimensional hyperparameter space. Besides this problem, the amount of data needed for training is also not known a priori. In response to these issues that need to be addressed, the present work describes and validates an automated active learning approach, AutoML-GA, for surrogate-based optimization of internal combustion engines. In this approach, a Bayesian optimization technique is used to find the best machine learning hyperparameters based on an initial dataset obtained from a small number of CFD simulations. Subsequently, a genetic algorithm is employed to locate the design optimum on the ML surrogate surface. In the vicinity of the design optimum, the solution is refined by repeatedly running CFD simulations at the projected optima and adding the newly obtained data to the training dataset. It is demonstrated that AutoML-GA leads to a better optimum with a lower number of CFD simulations, compared to the use of default hyperparameters. The proposed framework offers the advantage of being a more hands-off approach that can be readily utilized by researchers and engineers in industry who do not have extensive machine learning expertise.

Owoyele, Opeoluwa↗

DOE OSTI2016

Process Development and Micro-Machining of MARBLE Foam-Cored Rexolite Hemi-Shell Ablator Capsules

For this study, machined CH hemi-shell ablator capsules have been successfully produced by the MST-7 Target Fabrication Team at Los Alamos National Laboratory. Process development and micro-machining techniques have been developed to produce capsules for both the Omega and National Ignition Facility (NIF) campaigns. These capsules are gas filled up to 10 atm and consist of a machined plastic hemi-shell outer layer that accommodates various specially engineered low-density polystyrene foam cores. Machining and assembly of the two-part, step-jointed plastic hemi-shell outer layer required development of new techniques, processes, and tooling while still meeting very aggressive shot schedules for both campaigns. Finally, problems encountered and process improvements will be discussed that describe this very unique, complex capsule design approach through the first Omega proof-of-concept version to the larger NIF version.

42 ENGINEERING↗

DOE OSTI2020

Optical matter machines: angular momentum conversion by collective modes in optically bound nanoparticle arrays

The creation of optically powered self-assembling nano-to-meso-scale machines that do work is a long-standing goal in photonics. We demonstrate an optical matter (OM) machine that converts the spin angular momentum (SAM) of light into orbital angular momentum (OAM) to do mechanical work. The specific OM machine we study is based on a sixfold symmetric hexagonally ordered nanoparticle array that operates as an OM “gear” that is assembled and made to rotate in a circularly polarized Gaussian beam. The rotational symmetry of the OM gear leads to a selection rule for the allowed scattering modes based on their angular momentum. Electrodynamics calculations show that the collective scattering modes with the largest angular momentum scatter strongly in the transverse direction. Simulations and experiments show that the angular momentum that accompanies the scattered light causes a “negative torque” response on the OM gear and drives a “probe” particle placed outside the OM gear around the gear in an asymmetric force field analogously to Brownian ratchets. The gear–probe OM machine concept can be expanded to applications in nanofluidics and particle sorting.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2019

Complexity and entropy representation for machine component diagnostics

The Complexity-entropy causality plane (CECP) is a parsimonious representation space for time series. It has only two dimensions: normalized permutation entropy and Jensen-Shannon complexity of a time series. This two-dimensional representation allows for detection of slow or rapid drifts in the condition of mechanical components monitored through sensor measurements. The CECP representation can be used for both predictive analytics and visual monitoring of changes in component condition. This method requires minimal pre-processing of raw signals. Furthermore, it is insensitive to noise, stationarity, and trends. These desirable properties make CECP a good candidate for machine condition monitoring and fault diagnostics. In this work we study the effectiveness of CECP on three rotary component condition assessment applications. We use CECP representation of vibration signals to differentiate various machine component health conditions for rotary machine components, namely roller bearing and gears. The results confirm that the CECP representation is able to detect, with high accuracy, changes in underlying dynamics of machine component degradation states. From class separability perspective, the CECP representation is able to generate linearly separable classes for the classification of different fault states. This classification performance improves with increasing signal length. For signal length of 16,384 data points, the fault classification accuracy varies from 90% to 100% for bearing applications, and from 85% to 100% for gear applications. We observed that the optimum parameter for CECP representating depends on the application. For bearing applications we found that embedding dimension D = 4, 5, 6, and embedding delay τ = 1, 2, 3 are suitable for good fault classification. For gear applications we find that embedding dimension D = 4, 5, and embedding delay τ = 1, 5 are suitable for fault classification.

47 OTHER INSTRUMENTATION↗

DOE OSTI2021

Anomaly Detection in Accelerator Facilities Using Machine Learning

Synchrotron light sources are user facilities and usually run about 5000 hours per year to support many beamlines operations in parallel. Reliability is a key parameter to evaluate machine performance. Even many facilities have achieved >95% beam reliability, there are still many hours of unscheduled downtime and every hour lost is a waste of operation costs along with a big impact on individual scheduled user experiments. Preventive maintenance on subsystems and quick recovery from machine trips are the basic strategies to achieve high reliability, which heavily depends on experts’ dedication. Recently, SLAC, APS, and NSLS-II collaborated to develop machine-learning-based approaches aiming to solve both situations, hardware failure prediction and machine failure diagnosis to find the root sources. In this paper, we report our facility operation status, development progress, and plans.

Accelerator Physics↗

DOE OSTI2013

Hot Coordinate Measuring Machine Technology Assessment (U)

The goal of this report is to document a technology assessment performed following the guidance created by LA-UR-13-22870, “Hot Coordinate Measuring Machine Technical Specifications and Requirements (U)”. The intent was to capture specific values for technical specifications and requirements listed by the guide and assign a weight factors based on TA-55 importance. After the information was obtained, an optimal coordinate measuring machine for TA-55 was revealed – Hexagon’s Leitz Reference Xi 15.9.7. An internal look at on-site technology revealed that the current Hot CMM (Xcel 765) has the worst performance specification or accuracy statement of all CMMs currently at LANL. A look at Quindos license file options revealed that while most machines appear to have a standard set of options, some machines appear to be missing options and may contain unneeded ones. Controller firmware versions also appear to not be standardized at this time.

42 ENGINEERING↗

DOE OSTI2015

Business Case Analysis for Replacing the Mazak 30Y Mill-Turn Machine in SM-39. Summary

Business case studies are being looked at to support procurement of new machines and capital equipment in the SM-39 and TA-03-0102 machine shops. The first effort conducted economic analysis of replacing the Mazak 30Y Mill-Turn Machine located in SM-39. To determine the value of switching machinery, a baseline scenario was compared with a future scenario where new machinery was purchased and installed. The conditions under the two scenarios were defined via interviews with subject matter experts in terms of one-time and periodic costs. The results of the analysis were compiled in a life-cycle cost/benefit table. The costs of procuring, installing, and maintaining a new machine were balanced against the costs avoided by replacing older machinery. Productivity savings were included as a measure to show the costs avoided by being able to produce parts at a quicker and more efficient pace.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2016

Assisting the Tooling and Machining Industry to Become Energy Efficient

The Arizona Commerce Authority (ACA) conducted an Innovation in Advanced Manufacturing Grant Competition to support and grow southern and central Arizona’s Aerospace and Defense (A&D) industry and its supply chain. The problem statement for this grant challenge was that many A&D machining processes utilize older generation CNC machine tool technologies that can result an inefficient use of resources – energy, time and materials – compared to the latest state-of-the-art CNC machines. Competitive awards funded projects to develop innovative new tools and technologies that reduce energy consumption for older generation machine tools and foster working relationships between industry small to medium-sized manufacturing enterprises and third-party solution providers. During the 42-month term of this grant, 12 competitive awards were made. Final reports have been included with this submission.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2015

Machine Learning and Understanding for Intelligent Extreme Scale Scientific Computing and Discovery. DOE Workshop Report, January 7–9, 2015, Rockville, MD

Large-scale parallel simulations and data analysis drive scientific discovery across many disciplines. To drive larger and more detailed simulations, and deal with larger data volumes, exascale machines capable of 1018 operations per second are expected within the next five to ten years. However, the complexity of developing and adapting modern simulation codes for these architectures is increasing rapidly. Workloads on exascale machines will be billion-way parallel. Exploiting the full capability of the machine will require carefully assigning application tasks to cores, accelerators, deep memories, and other heterogeneous compute resources, while simultaneously optimizing for time to solution, data movement, power, and resilience. Optimizations that improve performance on one machine may slow down another. Worse, applications themselves are dauntingly complex. Production simulations comprise millions of lines of code and use sophisticated, adaptive algorithms whose performance is input-dependent. Complex workflows can couple multi-physics simulation with data preprocessing and post-processing modules.

97 MATHEMATICS AND COMPUTING↗