Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “factorization 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.

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

At least 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2014

TH-E-BRE-09: TrueBeam Monte Carlo Absolute Dose Calculations Using Monitor Chamber Backscatter Simulations and Linac-Logged Target Current

Purpose: To simulate and measure radiation backscattered into the monitor chamber of a TrueBeam linac; establish a rigorous framework for absolute dose calculations for TrueBeam Monte Carlo (MC) simulations through a novel approach, taking into account the backscattered radiation and the actual machine output during beam delivery; improve agreement between measured and simulated relative output factors. Methods: The ‘monitor backscatter factor’ is an essential ingredient of a well-established MC absolute dose formalism (the MC equivalent of the TG-51 protocol). This quantity was determined for the 6 MV, 6X FFF, and 10X FFF beams by two independent Methods: (1) MC simulations in the monitor chamber of the TrueBeam linac; (2) linac-generated beam record data for target current, logged for each beam delivery. Upper head MC simulations used a freelyavailable manufacturer-provided interface to a cloud-based platform, allowing use of the same head model as that used to generate the publicly-available TrueBeam phase spaces, without revealing the upper head design. The MC absolute dose formalism was expanded to allow direct use of target current data. Results: The relation between backscatter, number of electrons incident on the target for one monitor unit, and MC absolute dose was analyzed for open fields, as well as a jaw-tracking VMAT plan. The agreement between the two methods was better than 0.15%. It was demonstrated that the agreement between measured and simulated relative output factors improves across all field sizes when backscatter is taken into account. Conclusion: For the first time, simulated monitor chamber dose and measured target current for an actual TrueBeam linac were incorporated in the MC absolute dose formalism. In conjunction with the use of MC inputs generated from post-delivery trajectory-log files, the present method allows accurate MC dose calculations, without resorting to any of the simplifying assumptions previously made in the TrueBeam MC literature. This work has been partially funded by Varian Medical Systems.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2018

Validating quantum-classical programming models with tensor network simulations

The exploration of hybrid quantum-classical algorithms and programming models on noisy near-term quantum hardware has begun. As hybrid programs scale towards classical intractability, validation and benchmarking are critical to understanding the utility of the hybrid computational model. In this paper, we demonstrate a newly developed quantum circuit simulator based on tensor network theory that enables intermediate-scale verification and validation of hybrid quantum-classical computing frameworks and programming models. We present our tensor-network quantum virtual machine (TNQVM) simulator which stores a multi-qubit wavefunction in a compressed (factorized) form as a matrix product state, thus enabling single-node simulations of larger qubit registers, as compared to brute-force statevector simulators. Our simulator is designed to be extensible in both the tensor network form and the classical hardware used to run the simulation (multicore, GPU, distributed). The extensibility of the TNQVM simulator with respect to the simulation hardware type is achieved via a pluggable interface for different numerical backends (e.g., ITensor and ExaTENSOR numerical libraries). We demonstrate the utility of our TNQVM quantum circuit simulator through the verification of randomized quantum circuits and the variational quantum eigensolver algorithm, both expressed within the eXtreme-scale ACCelerator (XACC) programming model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Depot Charging Schedule Optimization for Medium- and Heavy-Duty Battery-Electric Trucks

Charge management, which lowers charging costs for fleets and prevents straining the electrical grid, is critical to the successful deployment of medium- and heavy-duty battery-electric trucks (MHD BETs). This study introduces an energy demand and cost management framework that optimizes depot charging for MHD BETs by combining an energy consumption machine learning model and a linear program optimization model. The framework considers key factors impacting real-world MHD BET operations, including vehicle and charger configurations, duty cycles, use cases, geographic and climate conditions, operation schedules, and utilities’ time-of-use (TOU) rates and demand charges. The framework was applied to a hypothetical fleet of 100 MHD BETs in California under three different utilities for 365 days, with results compared to unmanaged charging. The optimized charging solution avoided more than 90% of on-peak charging, reduced fleet charging peak load by 64–75%, and lowered fleet energy variable costs by 54–64%. This study concluded that the proposed charge management framework significantly reduces energy costs and peak loads for MHD BET fleets while making recommendations for fleet electrification infrastructure planning and the design of utility TOU rates and demand charges.

Song, Shuhan↗
DOE OSTI2017

Uncertainty in counting ice nucleating particles with continuous flow diffusion chambers

Abstract. This study investigates the measurement of ice nucleating particle (INP) concentrations and sizing of crystals using continuous flow diffusion chambers (CFDCs). CFDCs have been deployed for decades to measure the formation of INPs under controlled humidity and temperature conditions in laboratory studies and by ambient aerosol populations. These measurements have, in turn, been used to construct parameterizations for use in models by relating the formation of ice crystals to state variables such as temperature and humidity as well as aerosol particle properties such as composition and number. We show here that assumptions of ideal instrument behavior are not supported by measurements made with a commercially available CFDC, the SPectrometer for Ice Nucleation (SPIN), and the instrument on which it is based, the Zurich Ice Nucleation Chamber (ZINC). Non-ideal instrument behavior, which is likely inherent to varying degrees in all CFDCs, is caused by exposure of particles to different humidities and/or temperatures than predicated from instrument theory of operation. This can result in a systematic, and variable, underestimation of reported INP concentrations. We find here variable correction factors from 1.5 to 9.5, consistent with previous literature values. We use a machine learning approach to show that non-ideality is most likely due to small-scale flow features where the aerosols are combined with sheath flows. Machine learning is also used to minimize the uncertainty in measured INP concentrations. We suggest that detailed measurement, on an instrument-by-instrument basis, be performed to characterize this uncertainty.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

ELM2.1-XGBfire1.0: improving wildfire prediction by integrating a machine learning fire model in a land surface model

Wildfires have shown increasing trends in both frequency and severity across the contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth system models (ESMs). Alternatively, fire models based on machine learning (ML), which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ELM2.1-XGBFire1.0) that integrates an eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran–C–Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001–2019, the ELM2.1-XGBFire1.0 outperforms process-based fire models in terms of spatial distribution and seasonal variations. The ELM2.1-XGBFire1.0 has proven to be a new tool for studying vegetation–fire interactions and, more importantly, enables seamless exploration of climate–fire feedback, working as an active component of E3SM.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2017

Application of eye tracking for measurement and evaluation in human factors studies in control room modernization - 309

An important element of human factors engineering (HFE) pertains to measurement and evaluation (M and E). The role of HFE-M and E should be integrated throughout the entire control room modernization (CRM) process and be used for human-system performance evaluation and diagnostic purposes with resolving potential human engineering deficiencies (HEDs) and other human machine interface (HMI) design issues. NUREG-0711 describes how HFE in CRM should employ a hierarchical set of measures, particularly during integrated system validation (ISV), including plant performance, personnel task performance, situation awareness, cognitive workload, and anthropometric/ physiological factors. Historically, subjective measures have been primarily used since they are easier to collect and do not require specialized equipment. However, there are pitfalls with relying solely on subjective measures in M and E such that negatively impact reliability, sensitivity, and objectivity. As part of comprehensively capturing a diverse set of measures that strengthen findings and inferences made of the benefits from emerging technologies like advanced displays, this paper discusses the value of using eye tracking as an objective method that can be used in M and E. A brief description of eye tracking technology and relevant eye tracking measures is provided. Additionally, technical considerations and the unique challenges with using eye tracking in full-scaled simulations are addressed. Finally, this paper shares preliminary findings regarding the use of a wearable eye tracking system in a full-scale simulator study. These findings should help guide future full-scale simulator studies using eye tracking as a methodology to evaluate human-system performance. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

Prediction of condition-specific regulatory genes using machine learning

Recent advances in genomic technologies have generated data on large-scale protein–DNA interactions and open chromatin regions for many eukaryotic species. How to identify condition-specific functions of transcription factors using these data has become a major challenge in genomic research. To solve this problem, we have developed a method called ConSReg, which provides a novel approach to integrate regulatory genomic data into predictive machine learning models of key regulatory genes. Using Arabidopsis as a model system, we tested our approach to identify regulatory genes in data sets from single cell gene expression and from abiotic stress treatments. Our results showed that ConSReg accurately predicted transcription factors that regulate differentially expressed genes with an average auROC of 0.84, which is 23.5–25% better than enrichment-based approaches. To further validate the performance of ConSReg, we analyzed an independent data set related to plant nitrogen responses. ConSReg provided better rankings of the correct transcription factors in 61.7% of cases, which is three times better than other plant tools. We applied ConSReg to Arabidopsis single cell RNA-seq data, successfully identifying candidate regulatory genes that control cell wall formation. Our methods provide a new approach to define candidate regulatory genes using integrated genomic data in plants.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Trustworthiness and Trust: Identifying Factors that Drive Successful Human-AI Interaction in Nuclear Power Plant Applications

Emerging technologies such as artificial intelligence (AI) and machine learning (ML) are rapidly evolving and considered a promising tool for efficient and continued safe operations of the U.S. nuclear power plants (NPPs). Emerging AI techniques like large language models (LLMs) are one such technology that may support personnel at existing NPPs perform work more efficiently. For example, operators may query the current operational status of a power plant via a chat interface leveraging LLMs to access plant-related information in an interactive manner rather than manually collecting various sensor data for tasks such as surveillances or completing work orders. This is a fundamental shift in the way operators currently perform their tasks today. The literature of human-automation interaction indicates that trust is a crucial factor that drives successful interaction between a human operator and an automated system, like an AI-infused NPP application. This work presents the results of a literature review on key factors that relate to trust in AI/LLM technologies for NPP applications. The relevant literature of human factors and cognitive engineering has identified various factors related to trust including trustworthiness, performance characteristics, operator skill and perceived risk. This preliminary literature review will guide development and evaluation of models involving the identified factors influencing trust in AI and develop a framework for human-centered design for interface between humans and AI. By addressing trust, this work supports developing a technical basis for designing key characteristics of AI/LLM to support calibrated trust, which will ultimately support wide-scale adoption of AI/LLM technologies, as well as ensure safe, effective, and reliable use.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2016

Insights into twinning in $\mathrm{Mg AZ31: A}$ combined $\mathrm{EBSD}$ and machine learning study

To explore the driving forces behind deformation twinning in Mg AZ31, a machine learning framework is utilized to mine data obtained from electron backscatter diffraction (EBSD) scans in order to extract correlations in physical characteristics that cause twinning. The results are intended to inform physics-based models of twin nucleation and growth. A decision tree learning environment is selected to capture the relationships between microstructure and twin formation; this type of model effectively highlights the more influential characteristics of the local microstructure. Trees are assembled to analyze both twin nucleation in a given grain, and twin propagation across grain boundaries. Each model reveals a unique combination of crystallographic attributes that affect twinning in the Mg. Twin nucleation is found to be mostly controlled by a combination of grain size, basal Schmid factor, and bulk dislocation density while twin propagation is affected most by grain boundary length, basal Schmid factor, angle from grain boundary plane to the RD plane, and grain boundary misorientation. The machine learning framework can be readily adapted to investigate other relationships between microstructure and material response.

36 MATERIALS SCIENCE↗
DOE OSTI2025

NETL RDE Image Classification Dataset 2020 - 10 Classes

Dataset including high-speed down-axis RDE images used for updated image classification study. This dataset includes 100,000 images with 10 classifications: 1CW, 1CCW, 2CW, 2CCW, 3CW, 3CCW, and Deflagration. Images are cropped to center annulus, and resized to 301x301 pixels. Images are filtered using the AFRL Beta correction factor.

AS↗
DOE OSTI2024

Identification of carbohydrate gene clusters obtained from in vitro fermentations as predictive biomarkers of prebiotic responses

Prebiotic fibers are non-digestible substrates that modulate the gut microbiome by promoting expansion of microbes having the genetic and physiological potential to utilize those molecules. Although several prebiotic substrates have been consistently shown to provide health benefits in human clinical trials, responder and non-responder phenotypes are often reported. These observations had led to interest in identifying, a priori, prebiotic responders and non-responders as a basis for personalized nutrition. In this study, we conducted in vitro fecal enrichments and applied shotgun metagenomics and machine learning tools to identify microbial gene signatures from adult subjects that could be used to predict prebiotic responders and non-responders. Using short chain fatty acids as a targeted response, we identified genetic features, consisting of carbohydrate active enzymes, transcription factors and sugar transporters, from metagenomic sequencing of in vitro fermentations for three prebiotic substrates: xylooligosacharides, fructooligosacharides, and inulin. A machine learning approach was then used to select substrate-specific gene signatures as predictive features. These features were found to be predictive for XOS responders with respect to SCFA production in an in vivo trial. Our results confirm the bifidogenic effect of commonly used prebiotic substrates along with inter-individual microbial responses towards these substrates. We successfully trained classifiers for the prediction of prebiotic responders towards XOS and inulin with robust accuracy (≥ AUC 0.9) and demonstrated its utility in a human feeding trial. Overall, the findings from this study highlight the practical implementation of pre-intervention targeted profiling of individual microbiomes to stratify responders and non-responders.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2015

Function allocation for humans and automation in the context of team dynamics

Within Human Factors Engineering, a decision-making process called function allocation (FA) is used during the design life cycle of complex systems to distribute the system functions, often identified through a functional requirements analysis, to all human and automated machine agents (or teammates) involved in controlling the system. Most FA methods make allocation decisions primarily by comparing the capabilities of humans and automation, but then also by considering secondary factors such as cost, regulations, and the health and safety of workers. The primary analysis of the strengths and weaknesses of humans and machines, however, is almost always considered in terms of individual human or machine capabilities. Yet, FA is fundamentally about teamwork in that the goal of the FA decision-making process is to determine what are the optimal allocations of functions among agents. Given this framing of FA, and the increasing use of and sophistication of automation, there are two related social psychological issues that current FA methods need to address more thoroughly. First, many principles for effective human teamwork are not considered as central decision points or in the iterative hypothesis and testing phase in most FA methods, when it is clear that social factors have numerous positive and negative effects on individual and team capabilities. Second, social psychological factors affecting team performance and can be difficult to translate to automated agents, and most FA methods currently do not account for this effect. The implications for these issues are discussed.

Automation↗
DOE OSTI2023

Synergy of semiempirical models and machine learning in computational chemistry

Catalyzed by enormous success in the industrial sector, many research programs have been exploring data-driven, machine learning approaches. Performance can be poor when the model is extrapolated to new regions of chemical space, e.g., new bonding types, new many-body interactions. Another important limitation is the spatial locality assumption in model architecture, and this limitation cannot be overcome with larger or more diverse datasets. The outlined challenges are primarily associated with the lack of electronic structure information in surrogate models such as interatomic potentials. Given the fast development of machine learning and computational chemistry methods, we expect some limitations of surrogate models to be addressed in the near future; nevertheless spatial locality assumption will likely remain a limiting factor for their transferability. Here, we suggest focusing on an equally important effort—design of physics-informed models that leverage the domain knowledge and employ machine learning only as a corrective tool. In the context of material science, we will focus on semi-empirical quantum mechanics, using machine learning to predict corrections to the reduced-order Hamiltonian model parameters. The resulting models are broadly applicable, retain the speed of semiempirical chemistry, and frequently achieve accuracy on par with much more expensive ab initio calculations. These early results indicate that future work, in which machine learning and quantum chemistry methods are developed jointly, may provide the best of all worlds for chemistry applications that demand both high accuracy and high numerical efficiency.

36 MATERIALS SCIENCE↗
DOE OSTI2016

Neutronics of Advanced-Fuel Fusion Experiments with DT Triggering

Nuclear fusion studies are currently devoted to the Deuterium-Tritium (DT) fuel cycle, the easiest way to reach ignition. The recent stress on safety by the world community has stimulated the research on other fuel cycles, based on advanced reactions, such as Deuterium-Helium-3 (DHe). With DHe, it is not necessary to breed and fuel tritium. The DHe cycle has a very low presence of energetic fusion neutrons, due to DD and DT side reactions, and it has the possibility to obtain electrical power by direct energy conversion of the protons produced by the fusion reactions. DHe fusion has its own set of problems, such as the availability of {sup 3}He and the attainment of the higher plasma parameters. To explore the possibilities of DHe plasmas, a burning plasma experiment at high magnetic field and high plasma densities is particularly attractive. Ignitor is a proposed compact high-magnetic field tokamak, aimed at studying plasma-burning conditions in Deuterium-Tritium plasmas. The Ignitor experiment is designed to reach ignition under controlled DT burning conditions. The machine parameters have been established, on the basis of existing knowledge of the confinement properties of high density plasmas. The scientific goal of the Ignitor experiment is to approach, for the first time, the ignition conditions of a magnetically confined D-T plasma. However, the plasma density limit in Ignitor being well above the optimal density for DT ignition, is potentially suitable to the higher densities required for DHe burning. In fact, Ignitor has been designed also to explore conditions where 14.7-MeV protons and 3.6-MeV alpha particles produced by the DHe reactions can supply a significant amount of thermal energy to a well-confined plasma. In particular, Ignitor can sustain plasma currents exceeding those required to confine proton orbits at birth, and has more than sufficiently high densities so that the slowing-down time of both the protons and the DT alpha particles is shorter than the electron energy replacement time of the thermal plasma in which they are produced. Preliminary analyses show that a fusion power PF around 2 MW, may be reached. As a start, Ignitor can perform initial studies at the level of approximately 1 MW of power in charged particles from the DHe reaction in a mostly DT plasma. CANDOR, a design evolution of Ignitor in the direction of a reactor using a DHe fuel cycle, has been proposed; it is a feasibility study of a high-field DHe experiment of larger dimensions and higher fusion power than Ignitor, however still based on the core Ignitor technologies. The main characteristics of the CANDOR machine are the following: the major radius Ro is about double than Ignitor, plasma currents up to 25 MA with toroidal magnetic fields B{sub T} = 13 T can be produced. Unlike Ignitor, CANDOR would operate with higher values of poloidal beta around unity and the central part of the plasma column in the Second Stability region. The characteristic times over which the plasma discharge can be sustained are longer by more than a factor of 4 than those of Ignitor. To produce such a strong magnetic field in a larger machine, the toroidal field coils have been divided into two sets of coils and the central solenoid (air core transformer) is placed between them in the inboard part. In CANDOR, the DHe burning regime can be reached, by a combination of ICRF heating and alpha particle heating due to DT fusion reactions, which take the role of a sort of trigger. Thanks to this fact, and unlike other proposed DHe fusion experiments, CANDOR is capable of reaching DHe ignition using the existing technologies, and present knowledge of plasma confinement phenomena. With the initial use of DT, where tritium comprises some 50% of an initial lower density DT plasma, but is not added thereafter, the need for an intense auxiliary heating, which is one of the main technological drawbacks of DHe ignition, would be considerably alleviated, becoming feasible with the present technology. However, this method has the disadvantage of using tritium and of presenting a higher neutron flux (due to DT reactions) than 'pure' DHe plasmas, generating a neutron flux transient when passing from the initial DT trigger reaction to the final DHe burning plasma. However, for an experimental machine one-of-a-kind of relatively small dimensions, this is not an issue. (authors)

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Adsorbate chemical environment-based machine learning framework for heterogeneous catalysis

Abstract Heterogeneous catalytic reactions are influenced by a subtle interplay of atomic-scale factors, ranging from the catalysts’ local morphology to the presence of high adsorbate coverages. Describing such phenomena via computational models requires generation and analysis of a large space of atomic configurations. To address this challenge, we present Adsorbate Chemical Environment-based Graph Convolution Neural Network (ACE-GCN), a screening workflow that accounts for atomistic configurations comprising diverse adsorbates, binding locations, coordination environments, and substrate morphologies. Using this workflow, we develop catalyst surface models for two illustrative systems: (i) NO adsorbed on a Pt 3 Sn(111) alloy surface, of interest for nitrate electroreduction processes, where high adsorbate coverages combined with low symmetry of the alloy substrate produce a large configurational space, and (ii) OH* adsorbed on a stepped Pt(221) facet, of relevance to the Oxygen Reduction Reaction, where configurational complexity results from the presence of irregular crystal surfaces, high adsorbate coverages, and directionally-dependent adsorbate-adsorbate interactions. In both cases, the ACE-GCN model, trained on a fraction (~10%) of the total DFT-relaxed configurations, successfully describes trends in the relative stabilities of unrelaxed atomic configurations sampled from a large configurational space. This approach is expected to accelerate development of rigorous descriptions of catalyst surfaces under in-situ conditions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Spaced Orthocyclic Winding Pattern for Improved Die Compressed Coils

Winding fill, coil fill, or packing factor, is critical to the performance of many types of electromagnetic devices from electric machines to actuators, transformers, inductors, etc. One technique to increase the packing of conductors in the winding area is to compress round magnet wire conductors in a die, so that they deform and air voids between coil turns are removed. The winding layout of the coil turns on a bobbin before compression has a direct impact on the achievable coil fill and the damage to the coil insulation or conductors after compression. It is thought that winding the turns in an orthocyclic pattern on the bobbin before compression would minimize damage to the turns. This however causes turns to displace during the winding compression process. A new pre-compression winding pattern is proposed, a spaced orthocyclic winding, to minimize turn displacement and damage. A design of experiments study has been carried out to optimize this winding method and to compare it to the traditional orthocyclic winding.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2019

Preservation of the distribution of beam particles with respect to longitudinal oscillation amplitude in a 3 to 1 bunch merge

In the work presented here we show in detail how the 3 to 1 bunch merge can be set up so that it preserves the distribution of beam particles with respect to longitudinal oscillation amplitude. This is an elaboration based on the work presented in reference 1. The desired merge is achieved by slowly reducing the area inside the three-lobed separatrix that contains the beam while keeping the areas of the three lobes equal to one another. A sequence of RF voltages that does the job is found by employing a numerical integration routine and a search algorithm. The integration routine calculates the areas of the three lobes for given voltages. This is used by the search algorithm to nd voltages that give three lobes of equal area. The resulting voltages are listed in Section 12 in order of decreasing lobe area. These may be multiplied by a common scaling factor to make the scheme work for any given longitudinal emittance in any given machine. The analytic basis of the scheme is presented in Sections 2 through 13. (These sections may be treated as appendices.) Demonstration of the merge is done by simulation. The results are shown in Figures 1 through 39 and are discussed in Section 1. References [1] through [10] and those cited therein provide a history of bunch merging (and splitting) relevant to the present work. Refs. [1] and [2] record the early work done at CERN. Refs. [3] through [10] record the setup and study of the 2 to 1 and 3 to 1 merges used in Booster and AGS. In particular, Refs. [9] and [10] record the recent work of K. Zeno who proposed and developed the 3 to 1 bunch merge in Booster. It is this merge that is studied in the present work.

43 PARTICLE ACCELERATORS↗
DOE OSTI2021

Evaluating Offshore Infrastructure Integrity

Drilling in the offshore environment involves a complex network of infrastructure including pipelines, platforms, rigs, subsea installations, ports, and terminals. Government and industry partners have developed this network over many decades and it remains a critical part of the United States (U.S.) energy portfolio. Many of the major components of this system have been designed with a 20- to 30-year lifespan, yet consistent and growing energy demands support the need to extend the design life of existing infrastructure or repurpose it for secondary needs (i.e. enhanced oil recovery, carbon storage, and new wells). As a result, a growing portion of the offshore infrastructure in the U.S. is approaching or has exceeded its original design life. A critical step in ensuring the continued safe and effective operation of offshore infrastructure is developing a comprehensive understanding of the state of offshore infrastructure and the factors that effect it. The purpose of this project is to assess the current state of existing infrastructure and identify the factors involved in infrastructure degradation through the development and application of big data analytics, machine learning, and advanced spatio-temporal analysis. The project leverages existing data at NETL and combines it with new information on offshore oil and gas structures and the ambient offshore environment in an effort to identify patterns associated with infrastructure integrity. Building on the identified trends and patterns, this project incorporates exploratory analytics and spatial analysis tools in conjunction with machine learning and statistical models to characterize the condition of existing platforms in the offshore environment and predict their risk of failure.

02 PETROLEUM↗