23 Jul 2024

A/E/C Computer-Aided Design (CAD) Standard: Release 6.2

Abstract: The A/E/C Computer-Aided Design (CAD) Standard has been developed by the CAD/Building Information Modeling (BIM) Technology Center for Facilities, Infrastructure, and Environment to eliminate redundant CAD standardization efforts within DoD and the Federal Government. This manual is part of an initiative to develop a nonproprietary CAD standard that incorporates existing industry, national, and international standards and to develop data standards that address the entire life cycle of facilities within DoD. The material addressed in the A/E/C CAD Standard includes level/layer assignments, digital file naming, and standard symbology. The CAD/BIM Center’s primary goal is to develop a CAD standard that is generic enough to operate under various CAD software packages (such as Bentley’s MicroStation and Autodesk’s AutoCAD) while incorporating existing industry standards when possible. While this Standard encompasses many CAD concepts and practices, it is not intended to limit the capabilities of other advanced modeling software. Ultimately, a BIM / Civil Information Modeling standard will be developed to standardize the additional capabilities of other software.

31 May 2024

Hydraulic Load Definitions for Use in Load and Resistance Factor Design (LRFD) Analysis, Including Probabilistic Load Characterization, of 10 Hydraulic Steel Structures: Report Number 1

Abstract: In the past, allowable stress design (ASD) was used to design steel structures. The allowable stresses used were determined from previous practice, with limited understanding of the reliability and risk performance provided by the structure. Engineering methods based on Load and Resistance Factor Design (LRFD) provide more accurate lifetime models of structures by providing risk-based load factors. Besides improved safety, cost savings can be provided through improved performance and, in some cases, by delaying rehabilitation. This research project develops LRFD-based engineering procedures for the evaluation and design of hydraulic steel structures (HSS). Hydraulic loads are a key element to the LRFD analysis. This report identifies the primary hydraulic loads and describes procedures that can be used to determine these hydraulic loads. Existing design guidance for HSS is described and presented in the individual chapters. The appendixes to the report provide examples of the procedures used to compute the hydrostatic, wave, and hydrodynamic loads. A new approach for determining wind-induced wave loads was developed. Design guidance for computing the hydrodynamic load was limited for many of the HSS. Additional research is recommended to improve capabilities for computing hydraulic loads. Details on these recommendations can be found in this report.

29 May 2024

Encryption for Edge Computing Applications

Purpose: As smart sensors and the Internet of Things (IoT) exponentially expand, there is an increased need for effective processing solutions for sensor node data located in the operational arena where it can be leveraged for immediate decision support. Current developments reveal that edge computing, where processing and storage are performed close to data generation locations, can meet this need (Ahmed and Ahmed 2016). Edge computing imparts greater flexibility than that experienced in cloud computing architectures (Khan et al. 2019). Despite these benefits, the literature highlights open security issues in edge computing, particularly in the realm of encryption. A prominent limitation of edge devices is the hardware’s ability to support the computational complexity of traditional encryption methodologies (Alwarafy et al. 2020). Furthermore, encryption on the edge poses challenges in key management, the process by which cryptographic keys are transferred and stored among devices (Zeyu et al. 2020). Though edge computing provides reduced latency in data processing, encryption mechanism utilization reintroduces delay and can hinder achieving real-time results (Yu et al. 2018). The IoT is composed of a wide range of devices with a diverse set of computational capabilities, rendering a homogeneous solution for encryption impractical (Dar et al. 2019). Edge devices are often deployed in operational locations that are vulnerable to physical tampering and attacks. Sensitive data may be compromised if not sufficiently encrypted or if keys are not managed properly. Furthermore, the distributed nature and quantity of edge devices create a vast attack surface that can be compromised in other ways (Xiao et al. 2019). Understanding established mechanisms and exploring emerging methodologies for encryption reveals potential solutions for developing a robust solution for edge computing applications. The purpose of this document is to detail the current research for encryption methods in the edge computing space and highlight the major challenges associated with executing successful encryption on the edge.

29 May 2024

Mesoscale Multiphysics Simulations of the Fused Deposition Additive Manufacturing Process

Abstract: As part of an ongoing effort to better understand the multiscale effects of fused deposition additive manufacturing, this work centers on a multiphysics, mesoscale approach for the simulation of the extrusion and solidification processes associated with fused deposition modeling. Restricting the work to a single line scan, we focus on the application of polylactic acid. In addition to heat, momentum, and mass transfer, the solid-liquid–vapor interface is simulated using a front-tracking, level-set method. The results focus on the evolving temperature, viscosity, and volume fraction and are cast within a set of parametric studies to include the nozzle and extrusion velocities as well as the extrusion temperature. Among other findings, it was observed that fused deposition modeling can be effectively modeled using a front-tracking method (i.e., the level-set method) in concert with a moving mesh and temperature-dependent porosity function.

29 May 2024

Publications of the U.S. Army Engineer Research and Development Center; Appendix H : FY23 (October 2022-September 2023)

Abstract: Each year, the US Army Engineer Research and Development Center (ERDC) publishes more than 200 reports through the Information Technology Laboratory’s Information Science and Knowledge Management (ISKM) Branch, the publishing authority for ERDC. Annually since 2017, ISKM has compiled a list of the last fiscal year’s publications. This Appendix H to the original collection includes ERDC publications issued October 2022 through September 2023. The publications are grouped according to the technical laboratories or technical program for which they were prepared, and the preface includes procedures for obtaining ERDC reports. Through this compilation, online distribution, and physical collections, ISKM continues to support ERDC, the Army, and the nation.

2 May 2024

Data-Driven Modeling of Groundwater Level Using Machine Learning

Purpose: This US Army Engineer Research and Development Center (ERDC), Coastal and Hydraulics Laboratory engineering technical note (CHETN) documents a preliminary study on the use of specialized machine learning (ML) methods to model the variations in groundwater level (GWL) with time. This approach uses historical groundwater observation data at seven gage locations in Wyoming, USA, available from the USGS database and historical data on several relevant meteorological variables obtained from the ERA5 reanalysis dataset produced by the Copernicus Climate Change Service (usually referred to as C3S) at the European Center for Medium-Range Weather Forecasts to predict future GWL values for a desired period of time. The results presented in this report indicate that the ML method has the potential to predict both short-term (4-hourly) as well as daily variations in GWL several days into the future for the chosen study region, thus alleviating the need for employing sophisticated process-based numerical models with complicated model structure configurations.

18 Apr 2024

Neural Ordinary Differential Equations for Rotorcraft Aerodynamics

Abstract: High-fidelity computational simulations of aerodynamics and structural dynamics on rotorcraft are essential for helicopter design, testing, and evaluation. These simulations usually entail a high computational cost even with modern high-performance computing resources. Reduced order models can significantly reduce the computational cost of simulating rotor revolutions. However, reduced order models are less accurate than traditional numerical modeling approaches, making them unsuitable for research and design purposes. This study explores the use of a new modified Neural Ordinary Differential Equation (NODE) approach as a machine learning alternative to reduced order models in rotorcraft applications—specifically to predict the pitching moment on a rotor blade section from an initial condition, mach number, chord velocity and normal velocity. The results indicate that NODEs cannot outperform traditional reduced order models, but in some cases they can outperform simple multilayer perceptron networks. Additionally, the mathematical structure provided by NODEs seems to favor time-dependent predictions. We demonstrate how this mathematical structure can be easily modified to tackle more complex problems. The work presented in this report is intended to establish an initial evaluation of the usability of the modified NODE approach for time-dependent modeling of complex dynamics over seen and unseen domains.

18 Apr 2024

Artificial Intelligence (AI)–Enabled Wargaming Agent Training

Abstract: Fiscal Year 2021 (FY21) work from the Engineer Research and Development Center Institute for Systems Engineering Research lever-aged deep reinforcement learning to develop intelligent systems (red team agents) capable of exhibiting credible behavior within a military course of action wargaming maritime framework infrastructure. Building from the FY21 research, this research effort sought to explore options to improve upon the wargaming framework infrastructure and to investigate opportunities to improve artificial intelligence (AI) agent behavior. Wargaming framework infrastructure enhancements included updates related to supporting agent training, leveraging high-performance computing resources, and developing infrastructure to support AI versus AI agent training and gameplay. After evaluating agent training across different algorithm options, Deep Q-Network–trained agents performed better compared to those trained with Advantage Actor Critic or Proximal Policy Optimization algorithms. Experimentation in varying scenarios revealed acceptable performance from agents trained in the original baseline scenario. By training a blue agent against a previously trained red agent, researchers successfully demonstrated the AI versus AI training and gameplay capability. Observing results from agent gameplay revealed the emergence of behavior indicative of two principles of war, which were economy of force and mass.

17 Apr 2024

Enabling Understanding of Artificial Intelligence (AI) Agent Wargaming Decisions through Visualizations

Abstract: The process to develop options for military planning course of action (COA) development and analysis relies on human subject matter expertise. Analyzing COAs requires examining several factors and understanding complex interactions and dependencies associated with actions, reactions, proposed counteractions, and multiple reasonable outcomes. In Fiscal Year 2021, the Institute for Systems Engineering Research team completed efforts resulting in a wargaming maritime framework capable of training an artificial intelligence (AI) agent with deep reinforcement learning (DRL) techniques within a maritime scenario where the AI agent credibly competes against blue agents in gameplay. However, a limitation of using DRL for agent training relates to the transparency of how the AI agent makes decisions. If leaders were to rely on AI agents for COA development or analysis, they would want to understand those decisions. In or-der to support increased understanding, researchers engaged with stakeholders to determine visualization requirements and developed initial prototypes for stakeholder feedback in order to support increased understanding of AI-generated decisions and recommendations. This report describes the prototype visualizations developed to support the use case of a mission planner and an AI agent trainer. The prototypes include training results charts, heat map visualizations of agent paths, weight matrix visualizations, and ablation testing graphs.

26 Mar 2024

Risk-Based Prioritization of Operational Condition Assessments: Trinity River and Willamette River Case Studies

Abstract: The US Army Corps of Engineers (USACE) operates, maintains, and man-ages over 700 dams and 4,000 miles of levees, providing approximately $257 billion worth of economic benefit to the Nation. USACE employs the Operational Condition Assessment (OCA) process to understand the condition of those assets and allocate resources to minimize risk associated with performance degradation. Understanding risk in flood risk management (FRM) assets requires an understanding of consequence of asset failure from a systemwide FRM watershed perspective and an understanding of likelihood of degradation based on the condition of the low-level components derived from OCA ratings. This research demonstrates a case-study application of a scalable methodology to model the likelihood of a dam performing as expected given the state of its gates and their components. The research team combines this likelihood of degradation with consequences generated by the application of designed simulation experiments with hydrological models to develop risk measures. These risk measures can be developed for all FRM gate assets in order to enable traceable, consistent resource allocation decisions. Two case study applications are provided.