Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “computational intelligence”

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 1,045 records · Page 58

Toward resilient high performance applications through real time reliability metric generaion and autonomous failure correction

One predominant barrier encountered in furthering research and development efforts aimed at facilitating resilient HPC applications is a substantial lack of existing reliability and performance data originating from extreme-scale computing distributions. In order to develop an understanding of how and why highly scaled HPC applications are encountering increasingly frequent performance interruptions, one must conduct extensive trending and analysis on contemporary machines and their associated programs. However, existing HPC application log files are labyrinthine documents that, even with the assistance of intelligent data mining algorithms, translate poorly to human discern. In addition, conventional log filtering, processes are limited to execution within a post-mortem, reactive time period, as the enormous size of these documents prevents efficient real time interaction. Thus, there exists a strong need within the HPC field for the provision of accurate-yet-concise real time application information. Moreover, the means of reporting this data must be sufficiently lightweight and non-intrusive, as to successfully-yet-discretely attach itself to the multiple processes running on multiple cores within tens (or in some cases, hundreds) of thousands of compute nodes. Furthermore, this information should in turn be used to facilitate the autonomous correction of application-threatening faults, suspensions, and interruptions. This paper describes a dynamic application instrumentation module (utilizing a combination of Open/SpeedShop software and custom scripting) aimed at successfully achieving these goals.

97 MATHEMATICS AND COMPUTING↗

Green AI: Insights Into Deep Learning's Looming Energy Efficiency Crisis

As demands grow to integrate artificial intelligence into every aspect of industry, commerce, and life, deep learning's exploding energy cost has become a looming crisis, making AI systems a salient energy-efficiency challenge. One might expect that doubling a neural network's size would halve its error rate, or at least allow it to achieve greater performance given the same amount of time and energy. I will present clear and substantial scientific evidence which indicates that not only is this intuition wildly wrong, but that neural networks scale so poorly that to increase deep learning performance by only a small fraction can easily require an order of magnitude or more increase in computational resources and energy. Further, the marginal trade-off price of to increase model performance rapidly explodes as performance targets are increased. To address this challenge, I will provide a toolkit of techniques that can be applied today to mitigate the inefficiency of modern deep learning. And, I will conclude by illuminating a practical path forward towards efficient, Green AI.

artificial intelligence↗

Distilling particle knowledge for fast reconstruction at high-energy physics experiments

Knowledge distillation is a form of model compression that allows artificial neural networks of different sizes to learn from one another. Its main application is the compactification of large deep neural networks to free up computational resources, in particular on edge devices. In this article, we consider proton-proton collisions at the High-Luminosity Large Hadron Collider (HL-LHC) and demonstrate a successful knowledge transfer from an event-level graph neural network (GNN) to a particle-level small deep neural network (DNN). Our algorithm, DistillNet, is a DNN that is trained to learn about the provenance of particles, as provided by the soft labels that are the GNN outputs, to predict whether or not a particle originates from the primary interaction vertex. The results indicate that for this problem, which is one of the main challenges at the HL-LHC, there is minimal loss during the transfer of knowledge to the small student network, while improving significantly the computational resource needs compared to the teacher. This is demonstrated for the distilled student network on a CPU, as well as for a quantized and pruned student network deployed on a field programmable gate array. Our study proves that knowledge transfer between networks of different complexity can be used for fast artificial intelligence (AI) in high-energy physics that improves the expressiveness of observables over non-AI-based reconstruction algorithms. Such an approach can become essential at the HL-LHC experiments, e.g. to comply with the resource budget of their trigger stages.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Directed Energy Deposition Process Modeling, Validation, and Process-Informed Optimization

The directed energy deposition (DED) process, one of the most popular additive manufacturing techniques in use today, involves various complex physical mechanisms that are not yet well understood. In this regard, computational tools show promise for elucidating the manufacturing process and enabling nondestructive performance evaluations of manufactured parts. To better control and optimize the DED process?thereby improving the manufactured product? the present work develops and demonstrates a novel artificial intelligence (AI)-based process control and optimization technique. Specifically, a geometry-free thermo-mechanical model with adaptive subdomain construction is developed to accurately capture the material?s thermo-mechanical response under cyclical reheating and high cooling rates [1]. The model is demonstrated and validated with experimental measurements, in light of various geometries and processing parameters. Moreover, based on this thermo-mechanical model, a physics-informed reduced-order model is developed to enable quick predictions of the temperature field at every time step. Furthermore, an AI-based controller is developed that can adapt to the ever-changing system states by automatically adjusting the manufacturing process parameters. This entire work is based on the open-source Multiphysics Object-Oriented Simulation Environment (MOOSE) [2] and its recent integration with Libtorch (the C++ frontend of PyTorch [3]). The combined development of the adaptive material deposition scheme, thermo-mechanical model, associated reduced-order model, and AI-based process controller carries great potential for improving advanced manufacturing processes.

36 MATERIALS SCIENCE↗

Computational optimal transport for molecular spectra: The fully discrete case

In this study, the use of computational optimal transport is investigated as a tool for comparing two molecular spectra. Unlike other techniques for comparing molecular spectra in a pattern-recognition framework, transport distances simultaneously encode information about line positions and intensities. In addition, it is shown that transport distances are a useful alternative to Euclidean distances as Euclidean distances are based on line-by-line comparisons, while transport distances reflect broader features of molecular spectra and adequately compare spectra with different resolutions. This paper includes a tutorial on the use of optimal transport and investigates several well-chosen examples to illustrate the utility of computational optimal transport for comparing molecular spectra.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

SIRIUS: Science-Driven Data Management for Multi-Tiered Storage

The data sets being generated by large applications on very large-scale systems are increasing in both size and complexity. At the same time, there are new ways available to store and access these data sets. The goal in this project is to develop software that applications can use to make use of new and existing storage technologies in more sophisticated ways. One challenge in scientific data management is handling ‘hot’ vs ‘cold’ data. Data that is hot is data that is needed (or will be needed soon) in order for the program to continue progressing, while cold data is either output (and so will not be need further during the life of the program) or will not be needed until significantly later in the program’s run. Hot data should be stored in a way that allows fast access. On most systems, economic factors lead to an inverse relationship between storage performance and storage capacity and so fast access storage is limited. This makes it important to correctly place hot and cold data and avoid cold data unnecessarily consuming precious resources. In this reporting period, we addressed this challenge in various ways and at various levels. Data management frameworks offer only limited control to applications in how data is stored. We have added software capabilities for seamlessly moving data between layers of the storage technology using promote and demote functions to existing software frameworks. This gives direct control to applications in deciding what priority data receives. Additionally, we integrated different storage layer management frameworks in order to allow data to be exchanged and moved between storage layers in a consistent way across the application. Further, applications are not always able to directly decide what storage level makes sense for a given piece of data without an understanding of the underlying storage technologies. Data storage frameworks are often positioned to make these sorts of decisions in service of the application. We have added machine-learning based capabilities to data staging frameworks in order to make intelligent decisions about where data should be stored given learning about patterns in previous usage of similar data.

97 MATHEMATICS AND COMPUTING↗

Application of Learning Machines and Combinatorial Algorithms in Water Resources Management and Hydrologic Sciences

Contemporary and water resources engineering and management rely increasingly on pattern recognition techniques that have the ability to capitalize on the unrelenting accumulation of data that is made possible by modern information technology and remote sensing methods. In response to the growing information needs of modern water systems, advanced computational models and tools have been devised to identify and extract relevant information from the mass of data that is now available. This chapter presents innovative applications from computational learning science within the fields of hydrology, hydrogeology, hydroclimatology, and water management. The success of machine learning is evident from the growing number of studies involving the application of Artificial Neural Networks (ANN), Support Vector Machines (SVM), Relevance Vector Machines (RVM), and Locally Weighted Projection Regression (LWPR) to address various issues in hydrologic sciences. The applications that will be discussed within the chapter employ the abovementioned machine learning techniques for intelligent modeling of reservoir operations, temporal downscaling of precipitation, spatial downscaling of soil moisture and evapotranspiration, comparisons of various techniques for groundwater quality modeling, and forecasting of chaotic time series behavior. Combinatorial algorithms to capture the intrinsic complexities in the modeled phenomena and to overcome disparate scales are developed; for example, learning machines have been coupled with geostatistical techniques, non-homogenous hidden Markov models, wavelets, and evolutionary computing techniques. This chapter does not intend to be exhaustive; it reviews the progress that has been made over the past decade in the use of learning machines in applied hydrologic sciences and presents a summary of future needs and challenges for further advancement of these methods.

54 ENVIRONMENTAL SCIENCES↗

Scalable Knowledge Graph Analytics at 136 Petaflop/s

We are motivated by newly proposed methods for data mining large-scale corpora of scholarly publications, such as the full biomedical literature, which may consist of tens of millions of papers spanning decades of research. In this setting, analysts seek to discover how concepts relate to one another. They construct graph representations from annotated text databases and then formulate the relationship-mining problem as one of computing all-pairs shortest paths (APSP), which becomes a significant bottleneck. In this context, we present a new high-performance algorithm and implementation of the Floyd-Warshall algorithm for distributed-memory parallel computers accelerated by GPUs, which we call DSNAPSHOT (Distributed Accelerated Semiring All-Pairs Shortest Path). For our largest experiments, we ran DSNAPSHOT on a connected input graph with millions of vertices using 4, 096nodes (24,576GPUs) of the Oak Ridge National Laboratory's Summit supercomputer system. We find DSNAPSHOT achieves a sustained performance of 136×1015 floating-point operations per second (136petaflop/s) at a parallel efficiency of 90% under weak scaling and, in absolute speed, 70% of the best possible performance given our computation (in the single-precision tropical semiring or “min-plus” algebra). Looking forward, we believe this novel capability will enable the mining of scholarly knowledge corpora when embedded and integrated into artificial intelligence-driven natural language processing workflows at scale.

Kannan, Ramakrishnan {ramki}↗

Understanding checkpointing overheads on massive-scale systems : analysis of the IBM Blue Gene/P system.

Providing fault tolerance in high-end petascale systems, consisting of millions of hardware components and complex software stacks, is becoming an increasingly challenging task. Checkpointing continues to be the most prevalent technique for providing fault tolerance in such high-end systems. Considerable research has focussed on optimizing checkpointing; however, in practice, checkpointing still involves a high-cost overhead for users. In this paper, we study the checkpointing overhead seen by various applications running on leadership-class machines like the IBM Blue Gene/P at Argonne National Laboratory. In addition to studying popular applications, we design a methodology to help users understand and intelligently choose an optimal checkpointing frequency to reduce the overall checkpointing overhead incurred. In particular, we study the Grid-Based Projector-Augmented Wave application, the Carr-Parrinello Molecular Dynamics application, the Nek5000 computational fluid dynamics application and the Parallel Ocean Program application-and analyze their memory usage and possible checkpointing trends on 65,536 processors of the Blue Gene/P system.

99 GENERAL AND MISCELLANEOUS↗

An Artificial Intelligence-Assisted Method for Dementia Detection Using Images from the Clock Drawing Test

Background: Widespread dementia detection could increase clinical trial candidates and enable appropriate interventions. Since the Clock Drawing Test (CDT) can be potentially used for diagnosing dementia-related disorders, it can be leveraged to develop a computer-aided screening tool. Objective: To evaluate if a machine learning model that uses images from the CDT can predict mild cognitive impairment or dementia. Methods: Images of an analog clock drawn by 3,263 cognitively intact and 160 impaired subjects were collected during in-person dementia evaluations by the Framingham Heart Study. We processed the CDT images, participant’s age, and education level using a deep learning algorithm to predict dementia status. Results: When only the CDT images were used, the deep learning model predicted dementia status with an area under the receiver operating characteristic curve (AUC) of 81.3% ± 4.3%. A composite logistic regression model using age, level of education, and the predictions from the CDT-only model, yielded an average AUC and average F1 score of 91.9% ±1.1% and 94.6% ±0.4%, respectively. Conclusion: Our modeling framework establishes a proof-of-principle that deep learning can be applied on images derived from the CDT to predict dementia status. When fully validated, this approach can offer a cost-effective and easily deployable mechanism for detecting cognitive impairment.

Neurosciences & Neurology↗

Development of an end state vision to implement digital monitoring in nuclear plants

Transitioning from an onsite Maintenance & Diagnostics Center to cloud-based services offers many new opportunities with computing power and storage, but also new challenges in terms of networking and security. This report will cover everything required for that transition including data processing and uploading to cloud services, feature selection, model creation, and result visualization for decision making. Although there are several other cloud-based services (e.g. Amazon Web Services and Google Cloud), this report explores Microsoft Azure to simplify nomenclature and maintain a consistent focus. Many of the services offered by Microsoft Azure are also available in the other cloud-based services, and their differences have been recorded in other literature. The Azure services most important to a nuclear power plant including networking & security, storage & databases, and Artificial Intelligence (AI) are reviewed here. Networking covers all aspects related to communication to Azure resources including security, privacy, and redundancy. Storage & databases includes data storage, upgrading, patching, backups, and monitoring. The AI services allows the user access to the machine learning (ML) techniques developed with Azure including automated ML, anomaly detection, computer vision, and natural language processing. This report summaries the features, capabilities, and challenges when using cloud-based services in a user-friendly manner.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A computational pipeline to generate a synthetic dataset of metal ion sorption to oxides for AI/ML exploration

The charged mineral/electrolyte interfaces are ubiquitous in the surface and subsurface–including the surroundings of the geological disposal sites for radioactive waste. Therefore, understanding how ions interact with charged surfaces is critically important for predicting radionuclide mobility in the case of waste leakage. At present, the Surface Complexation Models (SCMs) are the most successful thermodynamic frameworks to describe ion retention by mineral surfaces. SCMs are interfacial speciation models that account for the effect of the electric field generated by charged surfaces on sorption equilibria. These models have been successfully used to analyze and interpret a broad range of experimental observations including potentiometric and electrokinetic titrations or spectroscopy. Unfortunately, many of the current procedures to solve and fit SCM to experimental data are not optimal, which leads to a non-transferable or non-unique description of interfacial electrostatics and consequently of the strength and extent of ion retention by mineral surfaces. Recent developments in Artificial Intelligence (AI) offer a new avenue to replace SCM solvers and fitting algorithms with trained AI surrogates. Unfortunately, there is a lack of a standardized dataset covering a wide range of SCM parameter values available for AI exploration and training–a gap filled by this study. Here, we described the computational pipeline to generate synthetic SCM data and discussed approaches to transform this dataset into AI-learnable input. First, we used this pipeline to generate a synthetic dataset of electrostatic properties for a broad range of the prototypical oxide/electrolyte interfaces. The next step is to extend this dataset to include complex radionuclide sorption and complexation, and finally, to provide trained AI architectures able to infer SCMs parameter values rapidly from experimental data. Here, we illustrated the AI-surrogate development using the ensemble learning algorithms, such as Random Forest and Gradient Boosting. These surrogate models allow a rapid prediction of the SCM model parameters, do not rely on an initial guess, and guarantee convergence in all cases.

Li, Chunhui↗

Tachyon: Intelligent Multi-Scale Modeling of Distributed Resilient Infrastructure and Workflows for Data Intensive HEP Analyses

The DOE High Energy Physics (HEP) program in Neutrino and Collider science drives data-intensive science and simulation on extreme-scale platforms. Modeling and optimizing the complex distributed components from experimental to leadership computing facilities are essential for HEP workflows to achieve required response times and resilience under various conditions. Tachyon proposes a framework for scalable modeling, simulation, and validation of key performance characteristics for the distributed infrastructure between FNAL and ALCF, along with associated HEP workflows.

Carothers, Chris [Rensselaer Poly.]↗

Tachyon: Intelligent Multi-Scale Modeling of Distributed Resilient Infrastructure and Workflows for Data Intensive HEP Analyses

The DOE High Energy Physics (HEP) program in Neutrino and Collider science drives data-intensive science and simulation on extreme-scale platforms. Modeling and optimizing the complex distributed components from experimental to leadership computing facilities are essential for HEP workflows to achieve required response times and resilience under various conditions. Tachyon proposes a framework for scalable modeling, simulation, and validation of key performance characteristics for the distributed infrastructure between FNAL and ALCF, along with associated HEP workflows.

Carothers, Chris [Rensselaer Poly.]↗

SPECTER: efficient evaluation of the spectral EMD

The Energy Mover’s Distance (EMD) has seen use in collider physics as a metric between events and as a geometric method of defining infrared and collinear safe observables. Recently, the Spectral Energy Mover’s Distance (SEMD) has been proposed as a more analytically tractable alternative to the EMD. In this work, we obtain a closed-form expression for the Riemannian-like p = 2 SEMD metric between events, eliminating the need to numerically solve an optimal transport problem. Additionally, we show how the SEMD can be used to define event and jet shape observables by minimizing the distance between events and parameterized energy flows (similar to the EMD), and we obtain closed-form expressions for several of these observables. We also present the Specter framework, an efficient and highly parallelized implementation of the SEMD metric and SEMD-derived shape observables as an analogue of the previously-introduced Shaper for EMD-based computations. We demonstrate that computing the SEMD with Specter can be up to a thousand times faster than computing the EMD with standard optimal transport libraries.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Development of intelligent instruments with embedded HTTP servers for control and data acquisition in a cryogenic setup—The hardware, firmware, and software implementation

The power of Ethernet for control and automation technology is being largely understood by the automation industry in recent times. Ethernet with HTTP (Hypertext Transfer Protocol) is one of the most widely accepted communication standards today. Ethernet is best known for being able to control through internet from anywhere in the globe. The Ethernet interface with built-in on-chip embedded servers ensures global connections for crate-less model of control and data acquisition systems which have several advantages over traditional crate-based control architectures for slow applications. This architecture will completely eliminate the use of any extra PLC (Programmable Logic Controller) or similar control hardware in any automation network as the control functions are firmware coded inside intelligent meters itself. Here, we describe the indigenously built project of a cryogenic control system built for linear accelerator at Inter University Accelerator Centre, known as “CADS,” which stands for “Complete Automation of Distribution System.” CADS deals with complete hardware, firmware, and software implementation of the automated linac cryogenic distribution system using many Ethernet based embedded cryogenic instruments developed in-house. Each instrument works as an intelligent meter called device-server which has the control functions and control loops built inside the firmware itself. Dedicated meters with built-in servers were designed out of ARM (Acorn RISC (Reduced Instruction Set Computer) Machine) and ATMEL processors and COTS (Commercially Off-the-Shelf) SMD (Surface Mount Devices) components, with analog sensor front-end and a digital back-end web server implementing remote procedure call over HTTP for digital control and readout functions. At present, 24 instruments which run 58 embedded servers inside, each specific to a particular type of sensor-actuator combination for closed loop operations, are now deployed and distributed across control LAN (Local Area Network). A group of six categories of such instruments have been identified for all cryogenic applications required for linac operation which were designed to build this medium-scale cryogenic automation setup. These devices have special features like remote rebooters, daughter boards for PIDs (Proportional Integral Derivative), etc., to operate them remotely in radiation areas and also have emergency switches by which each device can be taken to emergency mode temporarily. Finally, all the data are monitored, logged, controlled, and analyzed online at a central control room which has a user-friendly control interface developed using LabVIEW{sup ®}. This paper discusses the overall hardware, firmware, software design, and implementation for the cryogenics setup.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

2020 Workplace and the Evolution of Business Intelligence

The work place is rapidly changing and will continue to change as the decade proceeds to 2020. Business Intelligence (BI) has many of the tools that will ensure that employees in this future work place can be successful and deal with these environmental changes. Ideas such as “swarming”, “hyper-connectedness”, “de-routinization of work” and “the collective” will morph employee engagement and those organizations with mature Business Intelligence practices will be prepared to support the success of their employees.

99 GENERAL AND MISCELLANEOUS↗

Energy-Efficient Cruise Control Using Optimal Control for a Hybrid Electric Vehicle

Increasing connectivity in passenger vehicles provides for a large amount of look-ahead information about driving conditions. An intelligent control algorithm is presented that takes advantage of this information to obtain the operation strategy for the powertrain of a parallel hybrid electric vehicle, in an uncongested highway cruising situation. In order to guarantee sufficient computational efficiency to meet future online requirements, the algorithm is based on Pontryagin’s Minimum Principle. The whole driving/operation strategy is composed of a series of solutions to the optimal control sub-problem for each separate route segment. The control sequence computed offline is then evaluated in Autonomie. The simulation result shows 6% fuel savings compared to a baseline rule-based controller with no speed optimization.

Shen, Daliang↗