Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Automatic Differentiation”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Differentiable Neural Architecture, Mixed Precision and Accelerator Co-Search

Quantization, effective Neural Network architecture, and efficient accelerator hardware are three important design paradigms to maximize accuracy and efficiency. Mixed Precision Quantization is a process of assigning different precision to different Neural Network layers for optimized inference. Neural Architecture Search (NAS) is a process of automatically designing the neural network for a task and can also be extended to search for the precision of each weight and activation matrix. In this paper, we develop the following three methods: (i) Fast Differentiable Hardware-aware Mixed Precision Quantization Search method to find optimal precision, (ii) Joint Differentiable hardware-aware Architecture and Mixed Precision Quantization Co-search, (iii) Joint Accelerator, Architecture, and Precision triple co-search to find best possibilities in all the three worlds. We demonstrate the effectiveness of our proposed methods targeting Bitfusion accelerator by searching mixed precision models on MobilenetV2. We achieve better accuracy-latency trade-off models than the manually designed and previously proposed search methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Regularized Differentiation for Bioburden Density Estimation in Planetary Protection

In this paper, we propose and investigate the performance of two novel shrinkage estimators for bioburden density estimation in planetary protection. The estimators are based on the regularized differentiation of a cumulative count of colony forming units collected throughout the data collecting session or the life cycle of the entire mission. The regularized differentiation recasts the problem of bioburden density estimation as a linear least squares problem. The least squares problem is then solved through regularization techniques, such as truncated singular value decomposition and penalized least squares. The regularization is necessary to avoid noise amplification during the differentiation of noisy data. The two regularization estimators are compared with four other commonly used estimators to simultaneously evaluate the means of multivariable independent Poisson distributions: the maximum likelihood, noninformative Bayes estimator with Jeffreys prior, Empirical Bayes using conjugate gamma-Poisson model with gamma parameters selected by method of moments, and the Clevenson-Zidek estimator. It is shown through computer-simulated data that the regularized differentiation based on ridge regression has the smallest mean-squared error among all estimators. The analysis of shrinkage mechanism implemented by regularized differentiation is performed, and it is shown that the regularized differentiation amounts to performing a weighted averaging of all the samples. The weights are determined by the regularization parameter automatically selected by the L-curve technique. Since the method of least squares makes no distributional assumptions about the data, it presents an attractive technique for bioburden density estimation when there are concerns about the misspecification of the distributional model. The paper concludes with the analysis of the bioburden data collected during InSight mission and directions for future work.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Applying Physics-Informed Neural Networks to Solve Navier–Stokes Equations for Laminar Flow around a Particle

In recent years, Physics-Informed Neural Networks (PINNs) have drawn great interest among researchers as a tool to solve computational physics problems. Unlike conventional neural networks, which are black-box models that “blindly” establish a correlation between input and output variables using a large quantity of labeled data, PINNs directly embed physical laws (primarily partial differential equations) within the loss function of neural networks. By minimizing the loss function, this approach allows the output variables to automatically satisfy physical equations without the need for labeled data. The Navier–Stokes equation is one of the most classic governing equations in thermal fluid engineering. This study constructs a PINN to solve the Navier–Stokes equations for a 2D incompressible laminar flow problem. Flows passing around a 2D circular particle are chosen as the benchmark case, and an elliptical particle is also examined to enrich the research. The velocity and pressure fields are predicted by the PINNs, and the results are compared with those derived from Computational Fluid Dynamics (CFD). Additionally, the particle drag force coefficient is calculated to quantify the discrepancy in the results of the PINNs as compared to CFD outcomes. The drag coefficient maintained an error within 10% across all test scenarios.

Hu, Beichao (ORCID:0009000163215151)↗
DOE OSTI2020

DDxNet: a deep learning model for automatic interpretation of electronic health records, electrocardiograms and electroencephalograms

Effective patient care mandates rapid, yet accurate, diagnosis. With the abundance of non-invasive diagnostic measurements and electronic health records (EHR), manual interpretation for differential diagnosis has become time-consuming and challenging. This has led to wide-spread adoption of AI-powered tools, in pursuit of improving accuracy and efficiency of this process. While the unique challenges presented by each modality and clinical task demand customized tools, the cumbersome process of making problem-specific choices has triggered the critical need for a generic solution to enable rapid development of models in practice. In this spirit, we develop DDxNet, a deep architecture for time-varying clinical data, which we demonstrate to be well-suited for diagnostic tasks involving different modalities (ECG/EEG/EHR), required level of characterization (abnormality detection/phenotyping) and data fidelity (single-lead ECG/22-channel EEG). Using multiple benchmark problems, we show that DDxNet produces high-fidelity predictive models, and sometimes even provides significant performance gains over problem-specific solutions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Mitigate: An Adaptive Network Data Anonymization Tool Using Condensation-Based Differential Privacy

Modern network devices collect a large amount of data that can be analyzed to identify bottlenecks, anomalies, cyber-attacks, etc. Therefore, there is often a need to analyze such collections of network data quite often by an external expert or by the research community. However, these collections of data contain sensitive, proprietary information. In order for the network data to be shared, it must first be anonymized. The overall objective of this project is to develop an innovative privacy management tool to anonymize network data and achieve sufficient privacy, acceptable data utility, and efficient data analysis at the same time. No existing anonymization methods can achieve all of these at the same time. The core of this technology is a differential private clustering algorithm that provides strong privacy protection, preserves data properties important for subsequent analysis, and allows the party receiving the anonymized data to conduct analysis directly on anonymized data without the need of decryption or any extra processing. The research carried out was to design, implement and verify a solution to this problem by completing the following tasks: 1) developing the core technology; 2) developing a context based method that automatically recommends fields that must be anonymized; 3) conducted experiments showing superior results using our approach compared to existing tools, and 4) developed an intuitive but basic user interface. The research that was conducted generated novel algorithmic techniques that utilize state-of-the-art methods such as condensation, differential privacy preservation, clustering, automated tuning based on contextual awareness, and recommendation techniques to specify columns to users for anonymization leading to optimal privacy that allows research analysis on the dataset. Experiments were conducted to evaluate the efficacy of these novel algorithmic techniques by performing analysis on original non-anonymized datasets, then conducting analysis on the same yet anonymized datasets and comparing the results of the analyses. Overall, the anonymized analysis results were within 1% of the original results, verifying that the generated technology not only guarantees a high level of privacy but also enables research analysis as if it were conducted on the original dataset. Potential applications of this technology include anonymization of any type of structured network datasets that contain sensitive identifiers, such as IP addresses, that can be used in multiple applications. For example, to create an AI or machine learning model for cyber security, e.g., to detect attacks, or for performance analysis, e.g., identify bottlenecks or predict performance. In addition, a market analysis that was conducted for potential applications of this technology identified a broader range of applications of our anonymization technology beyond the network sector that includes healthcare, banking, insurance, securities, finance (FISB), data brokering, cloud services, ad sales, and government.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Feature‐shared adaptive‐boost deep learning for invasiveness classification of pulmonary subsolid nodules in CT images

Purpose In clinical practice, invasiveness is an important reference indicator for differentiating the malignant degree of subsolid pulmonary nodules. These nodules can be classified as atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC). The automatic determination of a nodule's invasiveness based on chest CT scans can guide treatment planning. However, it is challenging, owing to the insufficiency of training data and their interclass similarity and intraclass variation. To address these challenges, we propose a two‐stage deep learning strategy for this task: prior‐feature learning followed by adaptive‐boost deep learning. Methods The adaptive‐boost deep learning is proposed to train a strong classifier for invasiveness classification of subsolid nodules in chest CT images, using multiple 3D convolutional neural network (CNN)‐based weak classifiers. Because ensembles of multiple deep 3D CNN models have a huge number of parameters and require large computing resources along with more training and testing time, the prior‐feature learning is proposed to reduce the computations by sharing the CNN layers between all weak classifiers. Using this strategy, all weak classifiers can be integrated into a single network. Results Tenfold cross validation of binary classification was conducted on a total of 1357 nodules, including 765 noninvasive (AAH and AIS) and 592 invasive nodules (MIA and IAC). Ablation experimental results indicated that the proposed binary classifier achieved an accuracy of with an AUC of 81.3 . These results are superior compared to those achieved by three experienced chest imaging specialists who achieved an accuracy of , , and , respectively. About 200 additional nodules were also collected. These nodules covered 50 cases for each category (AAH, AIS, MIA, and IAC, respectively). Both binary and multiple classifications were performed on these data and the results demonstrated that the proposed method definitely achieves better performance than the performance achieved by nonensemble deep learning methods. Conclusions It can be concluded that the proposed adaptive‐boost deep learning can significantly improve the performance of invasiveness classification of pulmonary subsolid nodules in CT images, while the prior‐feature learning can significantly reduce the total size of deep models. The promising results on clinical data show that the trained models can be used as an effective lung cancer screening tool in hospitals. Moreover, the proposed strategy can be easily extended to other similar classification tasks in 3D medical images.

Wang, Jun↗
DOE OSTI2022

Learning emergent partial differential equations in a learned emergent space

We propose an approach to learn effective evolution equations for large systems of interacting agents. This is demonstrated on two examples, a well-studied system of coupled normal form oscillators and a biologically motivated example of coupled Hodgkin-Huxley-like neurons. For such types of systems there is no obvious space coordinate in which to learn effective evolution laws in the form of partial differential equations. In our approach, we accomplish this by learning embedding coordinates from the time series data of the system using manifold learning as a first step. In these emergent coordinates, we then show how one can learn effective partial differential equations, using neural networks, that do not only reproduce the dynamics of the oscillator ensemble, but also capture the collective bifurcations when system parameters vary. The proposed approach thus integrates the automatic, data-driven extraction of emergent space coordinates parametrizing the agent dynamics, with machine-learning assisted identification of an emergent PDE description of the dynamics in this parametrization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Image Classification Using Convolutional Neural Networks to Automate Visual Inspection of CCO Containers (Rev. 1)

The Savannah River Site is automating the receipt and inspection of Criticality Control Overpack drums to aid in nuclear waste disposal. The Advanced Engineering group is automating this receipt and inspection process to assist the site’s goals. Part of this process includes visually inspecting CCO drums to ensure that no defects or security risks are present. This research focuses on developing a machine learning model to automatically classify drums as passing or failing inspection. The machine learning model was implemented using the open-source Tensorflow library and uses a Convolutional Neural Network architecture to extract features and differentiate between images. The model was able to achieve an average of 85% accuracy on a dataset of 288 drums. This project’s goal was to prove the validity of computer vision in an automation process and provide a starting place for continued research.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2022

Data-Driven Discovery of Active Nematic Hydrodynamics

Active nematics can be modeled using phenomenological continuum theories that account for the dynamics of the nematic director and fluid velocity through partial differential equations (PDEs). While these models provide a statistical description of the experiments, the relevant terms in the PDEs and their parameters are usually identified indirectly. We adapt a recently developed method to automatically identify optimal continuum models for active nematics directly from spatio-temporal data, via sparse regression of the coarse-grained fields onto generic low order PDEs. After extensive benchmarking, we apply the method to experiments with microtubule-based active nematics, finding a surprisingly minimal description of the system. Furthermore, our approach can be generalized to gain insights into active gels, microswimmers, and diverse other experimental active matter systems.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2025

Cartesian equivariant representations for learning and understanding molecular orbitals

Qualitative and quantitative orbital properties such as bonding/antibonding character, localization, and orbital energies are critical to how chemists understand reactivity, catalysis, and excited-state behavior. Despite this, representations of orbitals in deep learning models have been very underdeveloped relative to representations of molecular geometries and Hamiltonians. Here, we apply state-of-the-art equivariant deep learning architectures to the task of assigning global labels to orbitals, namely energies characterizations, given the molecular coefficients from Hartree–Fock or density functional theory. The architecture we have developed, the Cartesian Equivariant Orbital Network (CEONET), shows how molecular orbital coefficients are readily featurized as equivariant node features common to all graph-based machine-learned potentials. We find that CEONET performs well at predicting difficult quantitative labels such as the orbital energy and orbital entropy. Furthermore, we find that the CEONET representation provides an intuitive latent space for differentiating orbital character for the qualitative assignment of e.g. bonding or antibonding character. In addition to providing a useful representation for further integrating deep learning with electronic structure theory, we expect CEONET to be useful for automatizing and interpreting the results of advanced electronic structure methods such as complete active space self-consistent field theory. In particular, the ability of CEONET to infer multireference character via the orbital entropy paves the way toward the machine-learned selection of active spaces.

chemical reactions↗
DOE OSTI2026

Data and scripts associated with a manuscript modeling microbial regulation of priming effects

This data package is associated with the publication “Modeling Microbial Regulatory Feedback in Organic Matter Decomposition Identifies Copiotrophic Traits as Key Drivers of Positive Priming” published as a preprint on BioRXiv by Ahamed et al. (2026); https://doi.org/10.1101/2024.08.11.607483. The package contains MATLAB scripts and saved simulation outputs used to implement a cybernetic model of microbial regulation during complex organic matter (OM) decomposition governing priming effects. It includes models of (i) single microbial functional groups (copiotrophic or oligotrophic degraders) and (ii) binary consortia composed of degraders and non-degraders with contrasting or common growth traits. Simulation results were generated using Monte Carlo analyses, with randomized key model parameters across a range of environmental mixing fractions of complex and labile OM. The dataset was created to provide a transparent and reusable computational framework for systematically exploring how microbial growth traits, metabolic regulation, and community composition influence OM decomposition dynamics and priming effects. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. In addition to a readme, this data package also includes a file-level metadata (FLMD) file that describes each file and a data dictionary (DD) that describes the variable definitions. This package includes: (1) annotated MATLAB code implementing the system of ordinary differential equations and cybernetic control laws; (2) saved output files containing data (e.g., biomass, substrates, enzyme levels, priming metrics); and (3) scripts for processing saved outputs and regenerating figures. Specifically, the data package contains three main MATLAB scripts: runPrimingModel.m, runPlotData.m, and runPlotSuppFigS1.m, along with this readme and supporting documentation. Users should begin with runPrimingModel.m, which contains the annotated code implementing the system of ordinary differential equations and cybernetic control laws. This script runs the Monte Carlo simulations of microbial OM decomposition and allows users to modify microbial trait definitions, adjust parameter distributions, or define new community configurations. Simulation outputs are automatically saved as .mat files in the folder named SavedData, which stores all pre-generated results included in this package. The second script, runPlotData.m, reads files from the SavedData folder and processes them to regenerate the figures presented in the manuscript. The third script, runPlotSuppFigS1.m, specifically generates Figure S1 in the Supplementary Material of the manuscript. The package also includes the aforementioned files in non-proprietary .txt format. If users intend to use them, they should first save the files in their respective .m or .mat formats prior to execution in MATLAB.

Biomass concentration↗
DOE OSTI2020

Generalized Grad–Shafranov equation for non-axisymmetric MHD equilibria

The structure of static MHD equilibria that admit continuous families of Euclidean symmetries is well understood. Such field configurations are governed by the classical Grad–Shafranov equation, which is a single elliptic partial differential equation in two space dimensions. By revealing a hidden symmetry, here we show that in fact all smooth solutions of the equilibrium equations with non-vanishing pressure gradients away from the magnetic axis satisfy a generalization of the Grad–Shafranov equation. In contrast to solutions of the classical Grad–Shafranov equation, solutions of the generalized equation are not automatically equilibria, but instead only satisfy force balance averaged over the one-parameter hidden symmetry. We then explain how the generalized Grad–Shafranov equation can be used to reformulate the problem of finding exact three-dimensional smooth solutions of the equilibrium equations as finding an optimal volume-preserving symmetry.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Cluster Analysis of Combined EDS and EBSD Data to Solve Ambiguous Phase Identifications

A common problem in analytical scanning electron microscopy (SEM) using electron backscatter diffraction (EBSD) is the differentiation of phases with distinct chemistry but the same or very similar crystal structure. X-ray energy dispersive spectroscopy (EDS) is useful to help differentiate these phases of similar crystal structures but different elemental makeups. However, open, automated, and unbiased methods of differentiating phases of similar EBSD responses based on their EDS response are lacking. This paper describes a simple data analytics-based method, using a combination of singular value decomposition and cluster analysis, to merge simultaneously acquired EDS + EBSD information and automatically determine phases from both their crystal and elemental data. I use hexagonal TiB 2 ceramic contaminated with multiple crystallographically ambiguous but chemically distinct cubic phases to illustrate the method. Code, in the form of a Python 3 Jupyter Notebook, and the necessary data to replicate the analysis are provided as Supplementary material.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Automated identification of dominant physical processes

The identification of processes that locally and approximately dominate dynamical system behavior has enabled significant advances in understanding and modeling nonlinear differential dynamical systems. Conventional methods of dominant process identification involve piecemeal and ad hoc (non-rigorous, informal) scaling analyses to identify dominant balances of governing equation terms and to delineate the spatiotemporal boundaries (boundaries in space and/or time) of each dominant balance. For the first time, we present an objective global measure of the fit of dominant balances to observations, which is desirable for automation, and was previously undefined. Furthermore, we propose a formal definition of the dominant balance identification problem in the form of an optimization problem. Here, we show that the optimization can be performed by various machine learning algorithms, enabling the automatic identification of dominant balances. Our method is algorithm agnostic and it eliminates reliance upon expert knowledge to identify dominant balances which are not known beforehand.

42 ENGINEERING↗
DOE OSTI2022

FLASSH 1.0: Thermal scattering law evaluation and cross section generation for reactor physics applications

The Full Law Analysis Scattering System Hub (FLASSH) is a modern, advanced code which evaluates the thermal scattering law (TSL) along with accompanying cross sections. FLASSH features generalized methods which accommodate any material structure. Historical approximations including the incoherent and cubic approximations have been removed. Instead, the latest release of FLASSH features advanced physics options including distinct corrections (1-phonon contributions) and non-cubic formulations. The non-cubic elastic and inelastic contributions are necessary to accurately evaluate 1-phonon contributions. Both non-cubic and 1-phonon calculations require high-density sampling of the various scattering directions. Optimization and parallelization of these routines were therefore necessary to produce results in a reasonable timeframe. With these notable improvements to the generalized TSL, FLASSH 1.0 meets benchmark requirements, demonstrating noticeable agreement with experiment for both TSLs and the resulting integrated cross sections. Additional features including a graphical user interface (GUI), plotting diagnostics, and formatted output options including ACE files allow users to complete a TSL evaluation with minimal input and maximum flexibility. The user GUI creates input files for FLASSH, reducing user error and also providing built-in error checks. Autofill options and suggested input values help make TSL evaluation accessible to novice users. The FLASSH code is compiled to run on both Windows and Linux platforms with automatic parallelization. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

DEEPER: An Intergrated Platform for Deeper Roots

Crops with deeper roots would have multiple benefits, including better drought tolerance, reduced requirement for nitrogen fertilizer, and better sequestration of atmospheric CO 2 . DEEPER is an integrated platform of phenomic, genomic, and in silico technologies to generate maize lines with deeper roots. DEEPER is: LEADER (Leaf Elemental Accumulation from Deep Roots) is a breakthrough technology to nondestructively measure rooting depth by using the plant itself as a sensor. LEADER uses handheld X-ray Fluorescence spectrometry to quantify foliar accumulation of elements that are differentially distributed in the soil profile. LEADER is nondestructive and is orders of magnitude cheaper, faster, and more precise than any competing assay of rooting depth in the field. LEADER is able to distinguish deep-rooted from shallow-rooted maize lines in the field without the need for costly and noisy soil coring. RootRobot/DIRT3D, to automatically phenotype root architecture in any field, combining RootRobot, a mechatronics platform to excavate, clean, section, and image mature root crowns, with DIRT3D, software to quantify architectural traits in 3D. Anatomics, a high-throughput platform to phenotype root anatomy, combining LAT 2.0, a technology for 3D imaging of root anatomy and composition, with RootScan3D, software to automatically extract 3D anatomical and cell wall composition metrics from LAT 2.0 output. Using this platform we discovered two novel root traits, parenchyma cell wall thickness and multiseriate cortical sclerenchyma, that improve rooting depth and drought tolerance in maize and wheat. OpenSimRoot/Deep, software to simulate root interaction with hard subsoils. Using this platform we discovered novel concepts regarding how to increase crop rooting depth by modulating how individual root axes respond to hard soil. DeepGenes, a toolkit of genes, parent lines, and genomic selection strategies to enable breeding hybrids with deeper roots. We discovered 3 novel root genes that increase rooting depth in maize and wheat. DEEPER discovered novel root phenotypes for deeper rooting, and delivered validated ideotypes for deeper-rooted maize; novel technologies to rapidly assess root depth, root architecture and anatomy in field-grown plants; novel software tools for root modeling and 3D image analysis of root architecture and anatomy; and validated genes and genomic selection models to deploy traits for deeper rooting in maize breeding. Each DEEPER technology is transformative in its own right, and exceeds existing technologies. They are mutually synergistic, deployable for field-grown plants, and are ready for application. The phenotyping and modeling technologies are readily applicable to many crops, and genetic leads in maize may have utility in other grasses. Taken as a whole they represent a transformative platform to develop deeper-rooted crops, with greater drought tolerance, reduced fertilizer requirement, and greater carbon sequestration.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Large Vessel Activity and Low-Frequency Underwater Sound Benchmarks in United States Waters

Chronic low-frequency noise from commercial shipping is a worldwide threat to marine animals that rely on sound for essential life functions. Although the U.S. National Oceanic and Atmospheric Administration recognizes the potential negative impacts of shipping noise in marine environments, there are currently no standard metrics to monitor and quantify shipping noise in U.S. marine waters. However, one-third octave band acoustic measurements centered at 63 and 125 Hz are used as international (European Union Marine Strategy Framework Directive) indicators for underwater ambient noise levels driven by shipping activity. We apply these metrics to passive acoustic monitoring data collected over 20 months in 2016–2017 at five dispersed sites throughout the U.S. Exclusive Economic Zone: Alaskan Arctic, Hawaii, Gulf of Mexico, Northeast Canyons and Seamounts Marine National Monument (Northwest Atlantic), and Cordell Bank National Marine Sanctuary (Northeast Pacific). To verify the relationship between shipping activity and underwater sound levels, vessel movement data from the Automatic Identification System (AIS) were paired to each passive acoustic monitoring site. Daily average sound levels were consistently near to or higher than 100 dB re 1 μPa in both the 63 and 125 Hz one-third octave bands at sites with high levels of shipping traffic (Gulf of Mexico, Northeast Canyons and Seamounts, and Cordell Bank). Where cargo vessels were less common (the Arctic and Hawaii), daily average sound levels were comparatively lower. Specifically, sound levels were ~20 dB lower year-round in Hawaii and ~10-20 dB lower in the Alaskan Arctic, depending on the season. Although these band-level measurements can only generally facilitate differentiation of sound sources, these results demonstrate that international acoustic indicators of commercial shipping can be applied to data collected in U.S. waters as a unified metric to approximate the influence of shipping as a driver of ambient noise levels, provide critical information to managers and policy makers about the status of marine environments, and to identify places and times for more detailed investigation regarding environmental impacts.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Emulation and detection of physical faults and cyber-attacks on building energy systems through real-time hardware-in-the-loop experiments

The increasing use of remote or mobile access, integrated wearable technologies, data exchange, and cloud-based data analytics in modern smart buildings is steering the building industry towards open communication technologies. The increased connectivity and accessibility could lead to more cyber-attacks in smart buildings. On the other hand, physical faults (e.g., HVAC -heating, ventilation, and air-conditioning faults) may have similar adverse impacts as those from the cyber-attacks on building energy systems, such as occupant discomfort, energy wastage, and equipment downtime. However, current physical behavior-based anomaly detection methods fail to differentiate between cyber-attacks and physical faults in building energy systems. Moreover, the challenge in collecting real-world threat data with ground truth has led researchers to rely on numerical models with user-defined assumptions, which may not accurately reflect real-world conditions due to the lack of in-situ experimental datasets. To address these challenges and gaps, this paper presents a flexible hardware-in-the-loop (HIL) testbed for generating cyber-attack and physical fault datasets and demonstrating threat detection algorithms in a real building automation system (BAS) environment. This testbed combines hardware (i.e., real BAS with local HVAC controllers and a physical network) with software (i.e., high-fidelity models to represent behaviors of building envelope and HVAC energy systems), enabling emulations of realistic threats. Five HIL experiments, including one baseline without any threats, two with physical faults, and two with cyber-attacks, were conducted to generate datasets containing detailed network traffic and system states. A joint classification framework, incorporating a network analyzer and a physical HVAC fault detector, was proposed to automatically detect cyber-physical abnormalities on BAS at both the network and the physical HVAC levels. The network analyzer comprises a conditional random fields (CRF) based command validator and a statistics-based detection strategy. The fault detector employs a weather and schedule-based pattern matching and feature-based principal component analysis (WPM-FPCA) method. Evaluation of the classification using four metrics from the multi-class confusion matrix revealed an average accuracy of 90.2%, recall of 89.7%, precision of 88.5% and F1-score of 89.2%. Finally, these results demonstrate that the proposed joint classification framework can effectively differentiate between specific types of cyber-attacks (e.g., device reinitialization attack, network Denial-of-Service attack) and physical faults (e.g., air handling unit operational fault, cooling coil valve stuck) in real time for improved building energy management.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗