Search NASA⌕ Search

SEARCH · Search NASA

Results for “prediction algorithms”

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 757 records · Page 42

Application of linear multiple model predictive control (MMPC) framework towards dynamic maximazation of oxygen yield in an elevated-pressure air separation unit

In a typical air separation unit (ASU) utilizing either a simple gaseous oxygen (GOX) cycle or a pumped liquid oxygen (PLOX) cycle, the flowrate of liquid nitrogen (LN2) stream connecting high-pressure and low-pressure ASU columns plays an important role in the total oxygen yield. It has been observed that this yield reaches a maximum at a certain optimal flowrate of LN2 stream. At nominal full-load operation, the flowrate of LN2 stream is maintained near this optimum value, whereas at part-load conditions this flowrate is typically modified in proportion with the load-change (oxygen demand) through a ratio/feed-forward controller. Due to nonlinearity in the entire ASU process, the ratio-modified LN2 flowrate does not guarantee an optimal oxygen yield at part-load conditions. This is further exacerbated when process disturbances in form of “cold-box” heat-leaks enter the system. To address this problem of dynamically maximizing the oxygen yield while the ASU undergoes a load-change and/or a process disturbance, a multiple model predictive control (MMPC) algorithm is proposed. This approach has been used in previous studies to handle large ramp-rates of oxygen demand posed by the gasifier in an IGCC plant. In this study, the proposed algorithm uses linear step-response “blackbox” models surrounding the operating points corresponding to maximum oxygen yield points at different loads. It has been shown that at any operating point of the ASU, the MMPC algorithm, through model-weight calculation based on plant measurements, naturally and continuously selects the dominant model(s) corresponding to the current plant state, while making control-move decisions that approach the maximum oxygen yield point. This dynamically facilitates less energy consumption in form of compressed feed-air compared to a simple ratio control during load-swings. In addition, since a linear optimization problem is solved at each time step, the approach involves much less computational cost compared to a firstprinciple based nonlinear MPC. Introduction

97 MATHEMATICS AND COMPUTING↗

A Machine Learning Approach for Business Intelligence Analysis using Commercial Shipping Transaction Data

Business intelligence problems are particularly challenging due to the use of large volume and high velocity data in attempts to model and explain complex underlying phenomena. Incremental machine learning based approaches for summarizing trends and identifying anomalous behavior are often desirable in such conditions to assist domain experts in characterizing their data. The overall goal of this research is to develop a machine learning algorithm that enables predictive analysis on streaming data, detects changes and anomalies in the data, and can evolve based on the dynamic behavior of the data. Commercial shipping transaction data for the U.S. is used to develop and test a Naïve Bayes model that classifies several companies into lines of businesses and demonstrates an ability to predict when the behavior of these companies changes by venturing into other lines of businesses.

Bramer, Lisa M.↗

Stochastic Model Predictive Control for Demand Response in a Home Energy Management System: Preprint

This paper presents a chance constrained, model predictive control (MPC) algorithm for demand response (DR) in a home energy management system (HEMS). The HEMS optimally schedules controllable appliances given user preferences such as thermal comfort and energy cost sensitivity, and available residentially-owned power sources such as photovoltaic (PV) generation and home battery systems. The proposed control architecture ensures both the DR event and indoor thermal comfort are satisfied with a high probability given the uncertainty in available PV generation and the outdoor temperature forecast. The uncertainties are incorporated into the MPC formulation using probabilistic constraints instead of computationally limiting sampling-based approaches. Simulation results for various user preferences and probabilistic model parameters show the effectiveness of the HEMS algorithm response to DR requests.

47 OTHER INSTRUMENTATION↗

Enhancing nanoscale SEM image segmentation and reconstruction with crystallographic orientation data and machine learning

Current methods of image segmentation and reconstructions from scanning electron micrographs can be inadequate for resolving nanoscale gaps in composite materials (1–20 nm). Such information is critical to both accurate material characterizations and models of piezoresistive response. The current work proposes the use of crystallographic orientation data and machine learning for enhancing this process. It is first shown how a machine learning algorithm can be used to predict the connectivity of nanoscale grains in a Nickel nanostrand/epoxy composite. This results in 71.9% accuracy for a 2D algorithm and 62.4% accuracy in 3D. Finally, it is demonstrated how these algorithms can be used to predict the location of gaps between distinct nanostrands — gaps which would otherwise not be detected with the sole use of a scanning electron microscope. - Highlights: • A method is proposed for enhancing the segmentation/reconstruction of SEM images. • 3D crystallographic orientation data from a nickel nanocomposite is collected. • A machine learning algorithm is used to detect trends in adjacent grains. • This algorithm is then applied to predict likely regions of nanoscale gaps. • These gaps would otherwise be unresolved with the sole use of an SEM.

36 MATERIALS SCIENCE↗

Machine learning strategy for accelerated design of polymer dielectrics

The ability to efficiently design new and advanced dielectric polymers is hampered by the lack of sufficient, reliable data on wide polymer chemical spaces, and the difficulty of generating such data given time and computational/experimental constraints. Here, we address the issue of accelerating polymer dielectrics design by extracting learning models from data generated by accurate state-of-the-art first principles computations for polymers occupying an important part of the chemical subspace. The polymers are ‘fingerprinted’ as simple, easily attainable numerical representations, which are mapped to the properties of interest using a machine learning algorithm to develop an on-demand property prediction model. Further, a genetic algorithm is utilised to optimise polymer constituent blocks in an evolutionary manner, thus directly leading to the design of polymers with given target properties. Furthermore, while this philosophy of learning to make instant predictions and design is demonstrated here for the example of polymer dielectrics, it is equally applicable to other classes of materials as well.

36 MATERIALS SCIENCE↗

Reducing Urban Traffic Congestion Using Deep Learning and Model Predictive Control

This article proposes a deep learning (DL)-based control algorithm—DL velocity-based model predictive control (VMPC)—for reducing traffic congestion with slowly time-varying traffic signal controls. This control algorithm consists of system identification using DL and traffic signal control using VMPC. For the training process of DL, we established a modeling error entropy loss as the criteria inspired by the theory of stochastic distribution control (SDC) originated by the fourth author. Herein, simulation results show that the proposed algorithm can reduce traffic congestion with a slowly varying traffic signal control input. Results of an ablation study demonstrate that this algorithm compares favorably to other model-based controllers in terms of prediction error, signal varying speed, and control effectiveness.

97 MATHEMATICS AND COMPUTING↗

Predicting images for the dynamics of stellar clusters ( π-DOC ): a deep learning framework to predict mass, distance, and age of globular clusters

ABSTRACT Dynamical mass estimates of simple systems such as globular clusters (GCs) still suffer from up to a factor of 2 uncertainty. This is primarily due to the oversimplifications of standard dynamical models that often neglect the effects of the long-term evolution of GCs. Here, we introduce a new approach to measure the dynamical properties of GCs, based on the combination of a deep-learning framework and the large amount of data from direct N-body simulations. Our algorithm, π-DOC (Predicting Images for the Dynamics Of stellar Clusters) is composed of two convolutional networks, trained to learn the non-trivial transformation between an observed GC luminosity map and its associated mass distribution, age, and distance. The training set is made of V-band luminosity and mass maps constructed as mock observations from N-body simulations. The tests on π-DOC demonstrate that we can predict the mass distribution with a mean error per pixel of 27 per cent, and the age and distance with an accuracy of 1.5 Gyr and 6 kpc, respectively. In turn, we recover the shape of the mass-to-light profile and its global value with a mean error of 12 per cent, which implies that we efficiently trace mass segregation. A preliminary comparison with observations indicates that our algorithm is able to predict the dynamical properties of GCs within the limits of the training set. These encouraging results demonstrate that our deep-learning framework and its forward modelling approach can offer a rapid and adaptable tool competitive with standard dynamical models.

Chardin, Jonathan↗

ECNet is an evolutionary context-integrated deep learning framework for protein engineering

Abstract Machine learning has been increasingly used for protein engineering. However, because the general sequence contexts they capture are not specific to the protein being engineered, the accuracy of existing machine learning algorithms is rather limited. Here, we report ECNet (evolutionary context-integrated neural network), a deep-learning algorithm that exploits evolutionary contexts to predict functional fitness for protein engineering. This algorithm integrates local evolutionary context from homologous sequences that explicitly model residue-residue epistasis for the protein of interest with the global evolutionary context that encodes rich semantic and structural features from the enormous protein sequence universe. As such, it enables accurate mapping from sequence to function and provides generalization from low-order mutants to higher-order mutants. We show that ECNet predicts the sequence-function relationship more accurately as compared to existing machine learning algorithms by using ~50 deep mutational scanning and random mutagenesis datasets. Moreover, we used ECNet to guide the engineering of TEM-1 β-lactamase and identified variants with improved ampicillin resistance with high success rates.

59 BASIC BIOLOGICAL SCIENCES↗

Towards Predictive Plasma Science and Engineering through Revolutionary Multi-Scale Algorithms and Models (Final Report)

This report describes the high-level accomplishments from the Plasma Science and Engineering Grand Challenge LDRD at Sandia National Laboratories. The Laboratory has a need to demonstrate predictive capabilities to model plasma phenomena in order to rapidly accelerate engineering development in several mission areas. The purpose of this Grand Challenge LDRD was to advance the fundamental models, methods, and algorithms along with supporting electrode science foundation to enable a revolutionary shift towards predictive plasma engineering design principles. This project integrated the SNL knowledge base in computer science, plasma physics, materials science, applied mathematics, and relevant application engineering to establish new cross-laboratory collaborations on these topics. As an initial exemplar, this project focused efforts on improving multi-scale modeling capabilities that are utilized to predict the electrical power delivery on large-scale pulsed power accelerators. Specifically, this LDRD was structured into three primary research thrusts that, when integrated, enable complex simulations of these devices: (1) the exploration of multi-scale models describing the desorption of contaminants from pulsed power electrodes, (2) the development of improved algorithms and code technologies to treat the multi-physics phenomena required to predict device performance, and (3) the creation of a rigorous verification and validation infrastructure to evaluate the codes and models across a range of challenge problems. These components were integrated into initial demonstrations of the largest simulations of multi-level vacuum power flow completed to-date, executed on the leading HPC computing machines available in the NNSA complex today. These preliminary studies indicate relevant pulsed power engineering design simulations can now be completed in (of order) several days, a significant improvement over pre-LDRD levels of performance.

42 ENGINEERING↗

A Methodology for Determining Statistical Performance Compliance for Airborne Doppler Radar with Forward-Looking Turbulence Detection Capability

The objective of the research developed and presented in this document was to statistically assess turbulence hazard detection performance employing airborne pulse Doppler radar systems. The FAA certification methodology for forward looking airborne turbulence radars will require estimating the probabilities of missed and false hazard indications under operational conditions. Analytical approaches must be used due to the near impossibility of obtaining sufficient statistics experimentally. This report describes an end-to-end analytical technique for estimating these probabilities for Enhanced Turbulence (E-Turb) Radar systems under noise-limited conditions, for a variety of aircraft types, as defined in FAA TSO-C134. This technique provides for one means, but not the only means, by which an applicant can demonstrate compliance to the FAA directed ATDS Working Group performance requirements. Turbulence hazard algorithms were developed that derived predictive estimates of aircraft hazards from basic radar observables. These algorithms were designed to prevent false turbulence indications while accurately predicting areas of elevated turbulence risks to aircraft, passengers, and crew; and were successfully flight tested on a NASA B757-200 and a Delta Air Lines B737-800. Application of this defined methodology for calculating the probability of missed and false hazard indications taking into account the effect of the various algorithms used, is demonstrated for representative transport aircraft and radar performance characteristics.

Bowles, Roland L.↗

Numerical prediction of three-dimensional juncture region flow using the parabolic Navier-Stokes equations

A numerical solution algorithm is established for prediction of subsonic turbulent three-dimensional flows in aerodynamic configuration juncture regions. A turbulence closure model is established using the complete Reynolds stress. Pressure coupling is accomplished using the concepts of complementary and particular solutions to a Poisson equation. Specifications for data input juncture geometry modification are presented.

Baker, A. J.↗

Video compression using conditional replenishment and motion prediction

A study of a low-rate monochrome video compression system is presentd in this paper. This system is a conditional-replenishment coder that uses two-dimensional Walsh-transform coding within each video frame. The conditional-replenishment algorithm works by transmitting only the portions of an image that are changing in time. This system is augmented with a motn-prediction algorithm that measures spatial dispalcement parameters from frame to frame, and codes the data using these parameters. A comparison is made between the conditional-replenishment system with, and without, the motion-predictinalgorthm. Subsampling in time is ued to maintain the data rate rate at a fixed value. Average bit rates of 1 bit/picture element (pel) to 1/16 bit/pel are considered. The resultant performance of the compression simulations is presented in terms of the average frame rates produced.

Hein, D. N.↗

Incorporating polar field data for improved solar flare prediction

In this paper, we consider incorporating data associated with the sun’s north and south polar field strengths to improve solar flare prediction performance using machine learning models. When used to supplement local data from active regions on the photospheric magnetic field of the sun, the polar field data provides global information to the predictor. While such global features have been previously proposed for predicting the next solar cycle’s intensity, in this paper we propose using them to help classify individual solar flares. We conduct experiments using HMI data employing four different machine learning algorithms that can exploit polar field information. Additionally, we propose a novel probabilistic mixture of experts model that can simply and effectively incorporate polar field data and provide on-par prediction performance with state-of-the-art solar flare prediction algorithms such as the Recurrent Neural Network (RNN). Our experimental results indicate the usefulness of the polar field data for solar flare prediction, which can improve Heidke Skill Score (HSS2) by as much as 10.1%.

79 ASTRONOMY AND ASTROPHYSICS↗

Predicting Solar Flares Using SDO /HMI Vector Magnetic Data Products and the Random Forest Algorithm

Adverse space-weather effects can often be traced to solar flares, the prediction of which has drawn significant research interests. The Helioseismic and Magnetic Imager (HMI) produces full-disk vector magnetograms with continuous high cadence, while flare prediction efforts utilizing this unprecedented data source are still limited. Here we report results of flare prediction using physical parameters provided by the Space-weather HMI Active Region Patches (SHARP) and related data products. We survey X-ray flares that occurred from 2010 May to 2016 December and categorize their source regions into four classes (B, C, M, and X) according to the maximum GOES magnitude of flares they generated. We then retrieve SHARP-related parameters for each selected region at the beginning of its flare date to build a database. Finally, we train a machine-learning algorithm, called random forest (RF), to predict the occurrence of a certain class of flares in a given active region within 24 hr, evaluate the classifier performance using the 10-fold cross-validation scheme, and characterize the results using standard performance metrics. Compared to previous works, our experiments indicate that using the HMI parameters and RF is a valid method for flare forecasting with fairly reasonable prediction performance. To our knowledge, this is the first time that RF has been used to make multiclass predictions of solar flares. We also find that the total unsigned quantities of vertical current, current helicity, and flux near the polarity inversion line are among the most important parameters for classifying flaring regions into different classes.

79 ASTRONOMY AND ASTROPHYSICS↗

Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection

Purpose: Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very time-consuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correct the segmentations from any type of automatic or interactive segmentation methods. Methods: The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, location-adaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm. Results: The proposed interactive segmentation method was applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to evaluate both the efficiency and the robustness. The automatic segmentation results with the original average Dice similarity coefficient of 0.78 were improved to 0.865–0.872 after conducting 55–59 interactions by using the proposed method, where each editing procedure took less than 3 s. In addition, the proposed method obtained the most consistent editing results with respect to different user interactions, compared to other methods. Conclusions: The proposed method obtains robust editing results with few interactions for various wrong segmentation cases, by selecting the location-adaptive features and further imposing the manifold regularization. The authors expect the proposed method to largely reduce the laborious burdens of manual editing, as well as both the intra- and interobserver variability across clinicians.

07 ISOTOPE AND RADIATION SOURCES↗

Analytical investigation of adaptive control of radiated inlet noise from turbofan engines

An analytical model has been developed to predict the resulting far field radiation from a turbofan engine inlet. A feedforward control algorithm was simulated to predict the controlled far field radiation from the destructive combination of fan noise and secondary control sources. Numerical results were developed for two system configurations, with the resulting controlled far field radiation patterns showing varying degrees of attenuation and spillover. With one axial station of twelve control sources and error sensors with equal relative angular positions, nearly global attenuation is achieved. Shifting the angular position of one error sensor resulted in an increase of spillover to the extreme sidelines. The complex control inputs for each configuration was investigated to identify the structure of the wave pattern created by the control sources, giving an indication of performance of the system configuration. It is deduced that the locations of the error sensors and the control source configuration are equally critical to the operation of the active noise control system.

Risi, John D.↗

GNN-based end-to-end reconstruction in the CMS Phase 2 High-Granularity Calorimeter

We present the current stage of research progress towards a one-pass, completely Machine Learning (ML) based imaging calorimeter reconstruction. The model used is based on Graph Neural Networks (GNNs) and directly analyzes the hits in each HGCAL endcap. The ML algorithm is trained to predict clusters of hits originating from the same incident particle by labeling the hits with the same cluster index. We impose simple criteria to assess whether the hits associated as a cluster by the prediction are matched to those hits resulting from any particular individual incident particles. The algorithm is studied by simulating two tau leptons in each of the two HGCAL endcaps, where each tau may decay according to its measured standard model branching probabilities. The simulation includes the material interaction of the tau decay products which may create additional particles incident upon the calorimeter. Using this varied multiparticle environment we can investigate the application of this reconstruction technique and begin to characterize energy containment and performance.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Performance prediction: A case study using a multi-ring KSR-1 machine

While computers with tens of thousands of processors have successfully delivered high performance power for solving some of the so-called 'grand-challenge' applications, the notion of scalability is becoming an important metric in the evaluation of parallel machine architectures and algorithms. In this study, the prediction of scalability and its application are carefully investigated. A simple formula is presented to show the relation between scalability, single processor computing power, and degradation of parallelism. A case study is conducted on a multi-ring KSR1 shared virtual memory machine. Experimental and theoretical results show that the influence of topology variation of an architecture is predictable. Therefore, the performance of an algorithm on a sophisticated, heirarchical architecture can be predicted and the best algorithm-machine combination can be selected for a given application.

Sun, Xian-He↗