Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep generative models”

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 829 records · Page 46
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Uncertainty quantification for deep learning in particle accelerator applications

With the advent of increased computational resources and improved algorithms, machine learning-based models are being increasingly applied to complex problems in particle accelerators. However, such data-driven models may provide overly confident predictions with unknown errors and uncertainties. For reliable deployment of machine learning models in high-regret and safety-critical systems such as particle accelerators, estimates of prediction uncertainty are needed along with accurate point predictions. In this investigation, we evaluate Bayesian neural networks (BNN) as an approach that can provide accurate predictions along with reliably quantified uncertainties for particle accelerator problems, and compare their performance with bootstrapped ensembles of neural networks. We select three accelerator setups for this evaluation: a storage ring, a photoinjector, and a linac. The problems span different data volumes and dimensionalities (e.g., scalar predictions as well as image outputs). It is found that BNN provide accurate predictions of the mean along with reliable estimates of predictive uncertainty across the test cases. In this vein, BNN may offer an attractive alternative to deterministic deep learning tools to generate accurate predictions with quantified uncertainties in particle accelerator applications.

43 PARTICLE ACCELERATORS↗
DOE OSTI2020

Weak structure functions in $\nu_l-N$ and $\nu_l-A$ scattering with nonperturbative and higher order perturbative QCD effects

We study the effect of various perturbative and nonperturbative QCD corrections on the free nucleon structure functions [FiNWI(x,Q2);i=1–3] and their implications in the determination of nuclear structure functions. The evaluation of the nucleon structure functions has been performed by using the MMHT 2014 parton distribution functions (PDFs) parametrization, and the target mass correction (TMC) and higher twist (HT) effects are incorporated following the works of Schienbein et al. and Dasgupta et al., respectively. These nucleon structure functions are taken as input in the determination of nuclear structure functions. The numerical calculations for the νl/ν¯l-A deep inelastic scattering (DIS) process have been performed by incorporating the nuclear medium effects like Fermi motion, binding energy, nucleon correlations, mesonic contributions, shadowing, and antishadowing in several nuclear targets such as carbon, polystyrene scintillator, iron, and lead, which are being used in MINERνA, and in argon nuclei, which is relevant for the ArgoNeuT and DUNE experiments. The differential scattering cross sections d2σAWIdxdy and (dσAWIdx/dσCHWIdx) have also been studied in the kinematic region of the MINERνA experiment. The theoretical results are compared with the recent experimental data of MINERνA and the earlier data of the NuTeV, CCFR, CDHSW, and CHORUS Collaborations. Moreover, a comparative analysis of the present results for the ratio (dσAWIdx/dσCHWIdx), and the results from the Monte Carlo (MC) generator GENIE and other phenomenological models of Bodek and Yang, and Cloet et al., has been performed in the context of the MINERνA experiment. The predictions have also been made for the ν¯l-A cross section relevant for the MINERνA experiment.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Electricity Pricing aware Deep Reinforcement Learning based Intelligent HVAC Control

Recently, deep reinforcement learning (DRL) based intelligent control of Heating, Ventilation, and Air Conditioning (HVAC) has gained a lot of attention due to DRL's ability to optimally control HVAC for minimizing operational cost while maintaining resident's comfort. The success of such DRL-based techniques largely depends on the articulation of the problem in terms of states, actions, and reward function. Inclusion of the electricity pricing information in the problem formulation can play an important role in saving the cost of HVAC operation. However, less attention has been given in the literature on formulating well-crafted state features based on electricity pricing. In this work, we propose an approach for training the DRL model with a specific focus on feature engineering based on electricity pricing. During training, we generate random but sufficiently realistic electricity price signals so that the pre-trained DRL model is robust and adaptive to the dynamic and variable electricity prices. The validation results are encouraging and show the potential of ≈12%-15% savings in the one day cost of HVAC operation, proving the usefulness of including electricity pricing related features as state features.

Kurte, Kuldeep↗
DOE OSTI2022

Progress in Understanding Short-Range Structure in Nuclei: An Experimental Perspective

High-energy electron scattering is a clean, precise probe for measurements of hadronic and nuclear structure and plays a key role in understanding the role of high-momentum nucleons (and quarks) in nuclei. Jefferson Lab has dramatically expanded our knowledge of the high-momentum nucleons generated by short-range correlations, providing sufficient insight to model much of their impact on nuclear structure in neutron stars and in low- to medium-energy scattering observables, including neutrino oscillation measurements. These short-range correlations also seem related to the modification of the quark distributions in nuclei, and efforts to improve our understanding of the internal structure of these short-distance and high-momentum configurations in nuclei will provide important input on a wide range of high-energy observables.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2020

Remaining Useful Strength (RUS) Prediction of SiCf-SiCm Composite Materials Using Deep Learning and Acoustic Emission

Prognosis techniques for prediction of remaining useful life (RUL) are of crucial importance to the management of complex systems for they can lead to appropriate maintenance interventions and improvements in reliability. While various data-driven methods have been introduced to predict the remaining useful life (RUL) of machinery systems or batteries, no research has been reported on the remaining useful strength (RUS) prediction of silicon carbide fiber reinforced silicon carbide matrix (SiCf-SiCm) materials with pivotal role in its potential usage as a structural material in nuclear reactors and turbine engines. Knowledge of its degradation process is of the utmost importance to the manufacturers. For this purpose, two approaches based on the machine-learning techniques of random-forest (RF) and convolutional neural network (CNN) are proposed to predict the RUS of SiCf-SiCm using only acoustic emission (AE) signals generated during the material’s stress applying process. Experimental results show that the CNN models achieved better predictive performance than the RF models but the latter with expert-engineered features achieves better prediction for AE signals in the early stage of degradation. Additionally, our results demonstrate that both models can correctly predict the SiCf-SiCm RUS as evaluated by our robust testing method from which the best average root mean square error (RMSE) and Pearson correlation coefficient of 3.55 ksi units and 0.85 were obtained.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Controls From Above and Below: Snow, Soil, and Steepness Drive Diverging Trends of Subsurface Water and Streamflow Dynamics

ABSTRACT The importance of subsurface water dynamics, such as water storage and flow partitioning, is well recognised. Yet, our understanding of their drivers and links to streamflow generation has remained elusive, especially in small headwater streams that are often data‐limited but crucial for downstream water quantity and quality. Large‐scale analyses have focused on streamflow characteristics across rivers with varying drainage areas, often overlooking the subsurface water dynamics that shape streamflow behaviour. Here we ask the question: What are the climate and landscape characteristics that regulate subsurface dynamic storage, flow path partitioning, and dynamics of streamflow generation in headwater streams? To answer this question, we used streamflow data and a widely‐used hydrological model (HBV) for 15 headwater catchments across the contiguous United States. Results show that climate characteristics such as aridity and precipitation phase (snow or rain) and land attributes such as topography and soil texture are key drivers of streamflow generation dynamics. In particular, steeper slopes generally promoted more streamflow, regardless of aridity. Streams in flat, rainy sites (< 30% precipitation as snow) with finer soils exhibited flashier regimes than those in snowy sites (> 30% precipitation as snow) or sites with coarse soils and deeper flow paths. In snowy sites, less weathered, thinner soils promoted shallower flow paths such that discharge was more sensitive to changes in storage, but snow dampened streamflow flashiness overall. Results here indicate that land characteristics such as steepness and soil texture modify subsurface water storage and shallow and deep flow partitioning, ultimately regulating streamflow response to climate forcing. As climate change increases uncertainty in water availability, understanding the interacting climate and landscape features that regulate streamflow will be essential to predict hydrological shifts in headwater catchments and improve water resources management.

Kerins, Devon [Department of Civil and Environment↗
DOE OSTI2025

Cross-reactive sarbecovirus antibodies induced by mosaic RBD nanoparticles

Broad immune responses are needed to mitigate viral evolution and escape. To induce antibodies against conserved receptor-binding domain (RBD) regions of SARS-like betacoronavirus (sarbecovirus) spike proteins that recognize SARS-CoV-2 variants of concern and zoonotic sarbecoviruses, we developed mosaic-8b RBD nanoparticles presenting eight sarbecovirus RBDs arranged randomly on a 60-mer nanoparticle. Mosaic-8b immunizations protected animals from challenges from viruses whose RBDs were matched or mismatched to those on nanoparticles. Here, we describe neutralizing mAbs isolated from mosaic-8b-immunized rabbits, some on par with Pemgarda, the only currently FDA-approved therapeutic mAb. Deep mutational scanning, in vitro selection of spike resistance mutations, and single-particle cryo-electron microscopy structures of spike–antibody complexes demonstrated targeting of conserved RBD epitopes. Rabbit mAbs included critical D-gene segment RBD-recognizing features in common with human anti-RBD mAbs, despite rabbit genomes lacking an equivalent human D-gene segment, thus demonstrating that the immune systems of humans and other mammals can utilize different antibody gene segments to arrive at similar modes of antigen recognition. These results suggest that animal models can be used to elicit anti-RBD mAbs with similar properties to those raised in humans, which can then be humanized for therapeutic use, and that mosaic RBD nanoparticle immunization coupled with multiplexed screening represents an efficient way to generate and select broadly cross-reactive therapeutic pan-sarbecovirus and pan-SARS-CoV-2 variant mAbs.

Science & Technology - Other Topics↗
DOE OSTI2023

Data efficiency and extrapolation trends in neural network interatomic potentials

Abstract Recently, key architectural advances have been proposed for neural network interatomic potentials (NNIPs), such as incorporating message-passing networks, equivariance, or many-body expansion terms. Although modern NNIP models exhibit small differences in test accuracy, this metric is still considered the main target when developing new NNIP architectures. In this work, we show how architectural and optimization choices influence the generalization of NNIPs, revealing trends in molecular dynamics (MD) stability, data efficiency, and loss landscapes. Using the 3BPA dataset, we uncover trends in NNIP errors and robustness to noise, showing these metrics are insufficient to predict MD stability in the high-accuracy regime. With a large-scale study on NequIP, MACE, and their optimizers, we show that our metric of loss entropy predicts out-of-distribution error and data efficiency despite being computed only on the training set. This work provides a deep learning justification for probing extrapolation and can inform the development of next-generation NNIPs.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Machine Learning for Joint Quality Control

The use of lightweight material combinations has been highly demanded in manufacturing automotive structures. However, making robust dissimilar material joints of such lightweight materials is still challenging. A significant barrier to achieving high-quality and repeatable joint performance is a deficient understanding of the relationship between the welding process, joint attributes, and joint performance. In this context, welding factors refer to material, equipment, environment, and process parameters, while joint features comprise specific microstructural attributes of the weld such as nugget size, heat affected zone (HAZ) topology, intermetallic layer thickness, and sheet thickness reduction. Joint performance is quantified in terms of strength (e.g., tensile shear, coach peel, cross-tension), weld size, and hardness, among other factors. While there have been many attempts to establish this process-structure-property relationship by developing a model derived from the associated physics and first principles, the complexity of the joining processes compounded by the complex interactions with different materials in an automotive assembly line environment, has hindered the usefulness of such attempts. The complexity is further exacerbated using different stacking materials, especially comprising dissimilar material combinations. In practice, the common approach has been the laborious process of creating welds, characterizing them, and then physically testing them through experimentation. With the emergence of artificial intelligence (AI) methods, an alternative pathway to eliciting the desired process-structure-property relationship at an accelerated pace is to use a data-driven approach by employing machine-learning (ML) techniques. This approach is benefitted by the availability of large streams of data, generated through years of research and testing by original equipment manufacturers, in the form of material, process, environmental, equipment, microstructural, and bulk-scale performance information from multimodal, multiscale sensors making measurements from laboratory-scale to production-scale processes. During Phase I efforts, which ended in fiscal year (FY) 2021, the Oak Ridge National Laboratory and Pacific Northwest National Laboratory (ORNL/PNNL) team demonstrated the effectiveness of different ML/AI frameworks in modeling complex relationships between resistance spot welding (RSW) process parameters, weld attributes, and joint properties using a subset of data from General Motors (GM). In FY 2022, the project team further refined and expanded their respective ML models to analyze additional welds with new weld stack-ups and materials to enhance the ML model predictive capability. ORNL extended its unified deep neural networks (DNN) ML training and prediction framework with new data streams of process parameters, and PNNL extended its model describing RSW process parameters’ associations with weld attributes. In FY 2023, the project team completed the development of the AI/ML architecture for analyzing aluminum/steel joints manufactured by GM via RSW and transitioned into the inline welding quality monitoring task for steel/steel RSW joints provided by GM.

36 MATERIALS SCIENCE↗
DOE OSTI2020

FALCON: Framework for Anomaly Detection in Industrial Control Systems

Industrial Control Systems (ICS) are used to control physical processes in critical infrastructure. These systems are used in a wide variety of operations such as water treatment, power generation and distribution, and manufacturing. While the safety and security of these systems are of serious concern, recent reports have shown an increase in targeted attacks aimed at manipulating physical processes to cause catastrophic consequences. This trend emphasizes the need for algorithms and tools that provide resilient and smart attack detection mechanisms to protect ICS. In this paper, we propose an anomaly detection framework for ICS based on a deep neural network. The proposed methodology uses dilated convolution and long short-term memory (LSTM) layers to learn temporal as well as long term dependencies within sensor and actuator data in an ICS. The sensor/actuator data are passed through a unique feature engineering pipeline where wavelet transformation is applied to the sensor signals to extract features that are fed into the model. Additionally, this paper explores four variations of supervised deep learning models, as well as an unsupervised support vector machine (SVM) model for this problem. The proposed framework is validated on Secure Water Treatment testbed results. This framework detects more attacks in a shorter period of time than previously published methods.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2020

New opportunities at the next-generation neutrino experiments I: BSM neutrino physics and dark matter

The combination of the high intensity proton beam facilities and massive detectors for precision measurements of neutrino oscillation parameters including the charge-parity violating (CPV) phase will open the door to help make beyond the standard model (BSM) physics reachable even in low energy regimes in the accelerator-based experiments. Large-mass detectors with highly precise tracking and energy measurements, excellent timing resolution, and low energy thresholds will enable the searches for BSM phenomena from cosmogenic origin, as well. Therefore, it is also conceivable that BSM topics in the next-generation neutrino experiments could be the dominant physics topics in the foreseeable future, as the precision of the neutrino oscillation parameter and CPV measurements continue to improve. This paper reviews the current landscape of BSM theory in neutrino experiments in two selected areas of the BSM topics-dark matter and neutrino related BSM-and summarizes the current results from existing neutrino experiments to set benchmarks for both theory and experiment. This paper then provides a review of upcoming neutrino experiments throughout the next 10 to 15 year time scale and their capabilities to set the foundation for potential reach in BSM physics in the two aforementioned themes. An important outcome of this paper is to ensure theoretical and simulation tools exist to carry out studies of these new areas of physics, from the first day of the experiments, such as Deep Underground Neutrino Experiment in the U.S. and Hyper-Kamiokande Experiment in Japan.

dark sector↗
DOE OSTI2026

Uncertainty guided online ensemble for non-stationary data streams in fusion science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.

AI↗
DOE OSTI2022

Exploring the Use of Novel Spatial Accelerators in Scientific Applications

Driven by the need to find alternative accelerators which can viably replace GPUs in next-generation Supercomputing systems, this paper proposes a methodology to enable agile application/hardware co-design. The application-first methodology provides the ability to come up with design of accelerators while working with real-world workloads, available accelerators, and system software. The iterative design process targets a set of kernels in a workload for performance estimates that can prune the design space for later phases of detailed architectural evaluations. To this effect, in this paper, a novel data-parallel device model is introduced that simulates the latency of performance-sensitive operations in an accelerator including data transfers and kernel computation using multi-core CPUs. The use of off-the-shelf simulators, such as pre-RTL simulator Aladdin or multiple tools available for exploring the design of deep neural network accelerators (e.g., Timeloop) is demonstrated for evaluation of various accelerator designs using applications with realistic inputs. Examples of multiple device configurations that are instantiable in a system are explored to evaluate the performance benefit of deploying novel accelerators. The proposed device is integrated with a programming model and system software to potentially explore the impacts of high-level programming languages/compilers and low-level effects such as task scheduling on multiple accelerators. We analyze our methodology for a set of applications that represent high-performance computing (HPC) and graph analytics. The applications include a computational chemistry kernel realized using tensor contractions, triangle counting, GraphSAGE and Breadth-first Search. These applications include kernels such as dense matrix-dense matrix multiplication, sparse matrix-spare matrix multiplication, and sparse matrix-dense vector multiplication. Our results indicate potential performance benefits and insights for system design by including accelerators that realize these kernels along-side general purpose accelerators.

AI, codesign, Accelerated Computing, Modeling and ↗
DOE OSTI2024

Decode the Workload: Training Deep Learning Models for Efficient Compute Cluster Representation

Monitoring the status of a high throughput computing cluster running computationally intensive production jobs is a crucial yet challenging system administration task due to the complexity of such systems. To this end, we train autoencoders using the Linux kernel CPU metrics of the cluster. Additionally, we explore assisting these models with graph neural networks to share information across threads within a compute node. The models are compared in terms of their ability to: 1) Produce a compressed latent representation that captures the salient features of the input, 2) Detect anomalous activity, and 3) Make distinction between different kinds of jobs run at Jefferson Lab. The goal is to have a robust encoder whose compressed embeddings are used for several downstream tasks. We extend this study further by deploying these models in a human-in-the-loop production-based setting for the anomaly detection task and discuss the associated implementation aspects such as continual learning and the criterion to generate alarms. This study represents a first step in the endeavor towards building self-supervised large-scale foundation models for computing centers.

Mohammed, Ahmed↗
DOE OSTI2023

Graph neural networks predict energetic and mechanical properties for models of solid solution metal alloy phases

Here, we developed a PyTorch-based architecture called HydraGNN that implements graph convolutional neural networks (GCNNs) to predict the formation energy and the bulk modulus for models of solid solution alloys for various atomic crystal structures and relaxed volumes. We trained the GCNN surrogate model on a dataset for nickel–niobium (NiNb) generated by the embedded atom model (EAM) empirical interatomic potential for demonstration purposes. The dataset was generated by calculating the formation energy and the bulk modulus as a prototypical elastic property for optimized geometries starting from initial body-centered cubic (BCC), face-centered cubic (FCC), and hexagonal compact packed (HCP) crystal structures, with configurations spanning the possible compositional range for each of the three types of initial crystal structures. Numerical results show that the GCNN model effectively predicts both the formation energy and the bulk modulus as function of the optimized crystal structure, relaxed volume, and configurational entropy of the model structures for solid solution alloys.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Field-Scale Lysimeter Studies of Glass and Cementitious Waste Forms at the Hanford Site - 20392

The Hanford site Integrated Disposal Facility (IDF) will receive waste forms from vitrification activities at the Hanford Waste Treatment and Immobilization Plant (WTP). The waste form inventory to be disposed of at the IDF will consist of vitrified low-activity waste (LAW) in glass forms and solidified (or encapsulated) secondary wastes in cementitious forms. The IDF is a near-surface burial facility located near Hanford's Waste Treatment and Immobilization Plant in the 200 East Area of the site's Central Plateau. An extensive set of laboratory experimental data has been collected to support IDF performance assessment calculations of the eventual degradation of waste forms and mobility of contaminants. This paper describes the start of a field experiment to generate waste-form performance data on a larger scale (tens of centimeters), over a longer duration (five years or more), and under field conditions representative of the IDF. Results from this study are expected to improve model descriptions of contaminant mobility, reduce uncertainties about the representativeness of laboratory results in the IDF performance assessment, improve stakeholder confidence in the safe disposal of treated waste at the IDF, and facilitate the adoption of informed facility designs with the potential to reduce operational costs. A lysimeter test facility near Hanford's 200 West Area has been repurposed to carry out long-term assessments of waste forms buried in sediments excavated from the IDF. The waste forms are buried in large drainage lysimeters, open caissons that are two meters in diameter and three meters deep. Waste forms are buried in up to six locations in each lysimeter. Samplers collect pore water and drainage water beneath the waste forms and air from the pore space adjacent to waste forms. Sensors measure temperature, soil water content, soil water tension, and drainage flux. One lysimeter containing cementitious waste forms and one containing glass waste forms have been completed, along with a control lysimeter (without waste forms). The cementitious waste forms are Cast Stone grout formulations using a liquid secondary waste simulant and a generic Hanford high-salt simulant, as well as a hydrated lime-based grout formulation using a liquid secondary waste simulant. Technetium-99 and iodine-127 were added as tracers to monitor contaminant mobility. Glass waste forms were fabricated in two formulations (LAWA44 and ORLEC28), with rhenium and molybdenum tracers to monitor waste form degradation. The predicted performance of the waste forms in the lysimeters was modeled prior to installation to determine waste form size, tracer concentration/activity, and locations of sensors and samplers. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

PHASE: Personalized Head-based Automatic Simulation for Electromagnetic properties in 7T MRI

Accurate and individualized human head models are becoming increasingly important for electromagnetic (EM) simulations. These simulations depend on precise anatomical representations to realistically model electric and magnetic field distributions, particularly when evaluating Specific Absorption Rate (SAR) within safety guidelines. State of the art simulations use the Virtual Population due to limited public resources and the impracticality of manually annotating patient data at scale. Here, this paper introduces Personalized Head-based Automatic Simulation for EM properties (PHASE), an automated open-source toolbox that generates high-resolution, patient-specific head models for EM simulations using paired T1-weighted (T1w) magnetic resonance imaging (MRI) and computed tomography (CT) scans with 14 tissue labels. To evaluate the performance of PHASE models, we conduct semi-automated segmentation and EM simulations on 15 real human patients, serving as the gold standard reference. The PHASE model achieved comparable global SAR and localized SAR averaged over 10 grams of tissue (SAR-10g), demonstrating its potential as a promising tool for generating large-scale human model datasets in the future. The code and models of PHASE toolbox have been made publicly available: https://github.com/hrlblab/PHASE.

Deep learning↗
DOE OSTI2021

Deep Analysis Net with Causal Embedding for Coal-fired Power Plant Fault Detection and Diagnosis (DANCE4CFDD)

Fault detection and diagnosis is critical to power plant operation to ensure attaining high reliability while reducing operation cost. As more renewable power is introduced to the power grid, traditional fossil power plants take on the extra burden of excessive load cycling to compensate the generation variability from renewable power. Such load cycling will pose more reliability challenges to power plant operation. There are a number of challenges faced by today’s asset health management system in coal- fired (or gas) power plants: 1) high-dimensional nonlinear interaction among multiple time series measurements; 2) high measurement variance induced by operational conditions/modes; 3) variation among asset types and plant configurations; and 4) a small number of faulty events to learn from. To cope with these challenges, today’s fielded asset health management systems rely heavily on manual efforts from domain experts and hand-crafted features or rules based on domain knowledge. Despite its role in plant reliability, such a practice is costly and hinders its scalability and sustainability, particularly when a plant undergoes modifications. The objective of this project is to develop a novel end-to-end AI learning system that is trainable (i.e., the AI representation of a complex system behavior can be directly learned from properly labeled data) for accurate fault detection and root cause analysis. The ability to create a fault detection model directly from time series could alleviate the efforts associated with today’s asset management solution development. In the course of this project, we have achieved the following: Created an AI model development environment incorporating state-of-the-art neural network architectures for rapid model development and evaluation; Developed novel learning strategies for training of fault detection model; Developed special-purpose neural network architecture embedded with variable association graph aiming for better interpretability; Developed a learning strategy to leverage a small number of faulty events for enhanced fault detection capability; Conducted detailed experimental study based on public benchmark datasets and demonstrated the effectiveness of the proposed solution; and Validated the developed system with data from both a coal-fired plant boiler dynamic simulation model and real-world coal-fired power plant covering multiple asset and fault types. Overall, the project attained a technology readiness level of TRL 5 from TRL 2 at the beginning of the project.

20 FOSSIL-FUELED POWER PLANTS↗