Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Complex Network Data”

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 955 records · Page 53
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems

Constructing surrogate models for uncertainty quantification (UQ) on complex partial differential equations (PDEs) having inherently high-dimensional O(10 n ), n ≥ 2, stochastic inputs (e.g., forcing terms, boundary conditions, initial conditions) poses tremendous challenges. The “curse of dimensionality” can be addressed with suitable unsupervised learning techniques used as a pre-processing tool to encode inputs onto lower-dimensional subspaces while retaining its structural information and meaningful properties. In this work, we review and investigate thirteen dimension reduction methods including linear and nonlinear, spectral, blind source separation, convex and non-convex methods and utilize the resulting embeddings to construct a mapping to quantities of interest via polynomial chaos expansions (PCE). Here, we refer to the general proposed approach as manifold PCE (m-PCE), where manifold corresponds to the latent space resulting from any of the studied dimension reduction methods. To investigate the capabilities and limitations of these methods we conduct numerical tests for three physics-based systems (treated as black-boxes) having high-dimensional stochastic inputs of varying complexity modeled as both Gaussian and non-Gaussian random fields to investigate the effect of the intrinsic dimensionality of input data. We demonstrate both the advantages and limitations of the unsupervised learning methods and we conclude that a suitable m-PCE model provides a cost-effective approach compared to alternative algorithms proposed in the literature, including recently proposed expensive deep neural network-based surrogates and can be readily applied for high-dimensional UQ in stochastic PDEs.

42 ENGINEERING↗
DOE OSTI2021

Living on the edge: A continental-scale assessment of forest vulnerability to drought

Globally, forests are facing an increasing risk of mass tree mortality events associated with extreme droughts and higher temperatures. Hydraulic dysfunction is considered a key mechanism of drought-triggered dieback. By leveraging the climate breadth of the Australian landscape and a national network of research sites (Terrestrial Ecosystem Research Network), we conducted a continental-scale study of physiological and hydraulic traits of 33 native tree species from contrasting environments to disentangle the complexities of plant response to drought across communities. Here, we found strong relationships between key plant hydraulic traits and site aridity. Leaf turgor loss point and xylem embolism resistance were correlated with minimum water potential experienced by each species. Across the data set, there was a strong coordination between hydraulic traits, including those linked to hydraulic safety, stomatal regulation and the cost of carbon investment into woody tissue. These results illustrate that aridity has acted as a strong selective pressure, shaping hydraulic traits of tree species across the Australian landscape. Hydraulic safety margins were constrained across sites, with species from wetter sites tending to have smaller safety margin compared with species at drier sites, suggesting trees are operating close to their hydraulic thresholds and forest biomes across the spectrum may be susceptible to shifts in climate that result in the intensification of drought.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1988

Finite-dimensional modeling of network-induced delays for real-time control systems

In integrated control systems (ICS), a feedback loop is closed by the common communication channel, which multiplexes digital data from the sensor to the controller and from the controller to the actuator along with the data traffic from other control loops and management functions. Due to asynchronous time-division multiplexing in the network access protocols, time-varying delays are introduced in the control loop, which degrade the system dynamic performance and are a potential source of instability. The delayed control system is represented by a finite-dimensional, time-varying, discrete-time model which is less complex than the existing continuous-time models for time-varying delays; this approach allows for simpler schemes for analysis and simulation of the ICS.

Ray, Asok↗
NASA NTRS2006

Instrument Remote Control Application Framework

The Instrument Remote Control (IRC) architecture is a flexible, platform-independent application framework that is well suited for the control and monitoring of remote devices and sensors. IRC enables significant savings in development costs by utilizing extensible Markup Language (XML) descriptions to configure the framework for a specific application. The Instrument Markup Language (IML) is used to describe the commands used by an instrument, the data streams produced, the rules for formatting commands and parsing the data, and the method of communication. Often no custom code is needed to communicate with a new instrument or device. An IRC instance can advertise and publish a description about a device or subscribe to another device's description on a network. This simple capability of dynamically publishing and subscribing to interfaces enables a very flexible, self-adapting architecture for monitoring and control of complex instruments in diverse environments.

Ames, Troy↗
NASA NTRS2020

Battery Health Quantification for TDRS Spacecraft by Using Signature Discriminability Measurement

The NASA/GSFC Space Network Project Office (SN) currently operates a constellation of ten geosynchronous TDRS spacecraft launched over the past 30 years. The SN project collects up to 16.5 Gigabytes of telemetry every month. Generally, the spacecraft health and functionality are obtained by the use of real-time telemetry data for the multiple spacecraft subsystems, which are transmitted to the main ground station at the White Sands Complex in Las Cruces, NM. Recently, the SN has instituted a program of Big Data to analyze the large amounts of data using a variety of tools including Machine Learning, Artificial Intelligence, development of training sets, and a variety of mathematical modeling tools. The goal is to improve spacecraft management and obtain a more accurate prediction of the spacecraft end of life. The combination of these efforts with those of the Aerospace Corporation, which has a contract with the SN to produce yearly reliability estimates for the TDRS fleet, will be performed. This paper presents a new concept called telemetry quality quantification (TQQ) and discusses the progress that has been made in battery performance estimation for the second-generation TDRS spacecraft using a signature discriminability measures (SDM) algorithm combined with the Aerospace Corp. battery life estimation models. This activity is important because many of the TDRS fleet of spacecraft have exceeded their on-orbit design lifetime and, therefore, NASA must carefully manage the spacecraft to continue operations while avoiding an end-of-mission scenario that leaves a non-functioning spacecraft in geosynchronous orbit.

Ma, Kenneth Y.↗
NASA NTRS2022

A Generalized Approach to Aircraft Trajectory Prediction via Supervised Deep Learning

As research advances diverse forms and missions of aircraft, the National Airspace System (NAS) will become increasingly crowded, limiting current communications resources to accommodate aviation operations. Ongoing research proposes a paradigm of airspace communications, such that resources are autonomously and dynamically allocated via intelligent agents; this allocation requires accurate representations of the NAS, including the predicted positions of aircraft. State-of-the-art research emphasizes the importance of a hybrid-recurrent framework for trajectory prediction and compares the impact of commonly considered weather data on prediction accuracy. However, current research has been limited in its scope of efforts, frequently utilizing a unique flight route, architecture, set of weather data, and date range. This article considers the challenges of generalizing hybrid-recurrent predictive models for flight trajectories. Results illustrate an increase in error variance when identical models are trained over a generalized set of flights; this may be mitigated with careful tuning of hyperparameters, both in the network structure and optimization algorithms. Even so, an irreducible vertical error was identified, resulting from the complex takeoff and landing procedures which can not be correlated to functions of weather or additional assumptions of aircraft behavior. Finally, the use of a test route indicates that generalized models still do not possess sufficient knowledge for general aircraft predictions, with mean error increases ranging from 70-500%. These results illustrate the need for continued efforts on improving model versatility, as well as potential limitations for spectrum allocation near airports and other centers.

Nathan Schimpf↗
NASA NTRSDate not supplied

Towards Surrogate Modeling of Subgrid Turbulent Transport for 3D Radiative Hydrodynamic Simulations of the Quiet Sun

In this work, we investigate the use of deep learn-ing techniques as surrogate models, to enhance the estimationof effects of subgrid turbulent transport for 3D radiatuve hy-drodynamic simulations of the quiet Sun. We develop two dis-tinct 3D Convolutional Neural Networks (3DCNNs) to capturespatio-temporal dependencies in 3D velocity fields, leveragingdifferent activation functions and architectural designs. Thesemodels integrate both averaged velocity vector components andscalar features such as plasma density to enhance predictionaccuracy. Additionally, a Multilayer Perceptron (MLP) modelis employed to approximate complex nonlinear relationships,offering a comparison in performance between convolutionaland fully connected architectures. Logarithmic transformationis applied to the targets to handle heavily skewed data, im-proving model performance. All models are compared againsta physics-based Gradient Model. Results show that the 3DCNNmodels excel at approximating Reynolds stress tensors, makingthem a candidate for assisting in producing reduced resolutionsimulations, and thereby reducing computational overheadwhile maintaining higher accuracy than the baseline. Thesefindings demonstrate the potential of deep learning, particu-larly CNNs, to advance scalable and accurate simulations ofsolar dynamics, offering a promising alternative to traditionalturbulence models.

Heliophysics↗
DOE OSTI2025

Demonstrate new plasticity models for doped UO 2 that capture dislocation mechanisms

In light water reactors, fuel vendors are investigating the use of dopants to modify the properties of UO 2 pellets, with the goal of improving pellet-cladding mechanical interactions during operation. Dopants are expected to ‘soften’ the pellets; that is, the doped pellets have higher plastic deformation than conventional UO 2 . This leads to a reduction in the severity of mechanical pellet-cladding interactions, helping to reduce the hoop strain on the cladding. By minimizing the strain exerted by the pellet on the cladding, it is anticipated that cladding performance under accident conditions can be enhanced (i.e., lowering the risk of burst during a LOCA). Dopants such as chromium (Cr) promote grain growth during pellet fabrication, leading to larger grains; therefore, understanding the link between chemistry, microstructure and mechanical deformation (enhanced creep rates) behavior of UO 2 is critical to helping operators further substantiate the benefits of doping UO 2 . Historically, the nuclear energy industry has relied on empirical models to make assessments of performance. Compared to empirical models, mechanistic physics-based models provide benefits, such as, fewer data points for validation and better extrapolation where experimental data is scarce or non-existent. In this report, Bayesian inference techniques have been applied to a previously developed lower length-scale-informed diffusional creep model. The objective is to i) infer lower-length-scale parameter distributions from available experiment and then ii) determine the uncertainties in the measurable quantity (in this case creep rates) after propagating the inferred lower length scale parameter uncertainties. The approach requires many evaluations of the model, which becomes computationally insurmountable; therefore, a neural-network model is trained to data obtained by sampling the full model over the most important parameters. This neural-network is then used in the Bayesian inference approach to determine probability distributions in the parameter values that represent the uncertainty in the model given what is known from the experiments (posterior). A significant reduction compared to conservative initial (prior) uncertainties is achieved through inference against the experimental data, demonstrating the efficacy of this approach. Furthermore, by accounting for uncertainties in the experimental conditions and sample non-stoichiometry, it is possible to resolve apparent discrepancies in experimental measurements within a self-consistent grain boundary (Coble) creep model that is sensitive to chemistry. This work has been written up and submitted to Nuclear Technology for a special issue on accelerated fuel qualification (AFQ). This uncertainty quantification (UQ) work not only improves the diffusional model, while accounting for uncertainty, but also establishes a framework which can readily be applied to the mechanistic models of dislocation deformation developed in this study. The most likely values from the Bayesian analysis are incorporated into our UO 2 diffusional creep model and a lower length scale-informed irradiation UO 2 creep mechanistic model to generate a dataset. This dataset has been provided to our INL collaborators for training an artificial neural network surrogate model, which will be implemented in the BISON fuel performance code to assess how the results differ from those currently obtained using a fully empirical model and that of using the nominal (uncalibrated) atomic scale parameters in our mechanistic model. Plastic deformation (creep and glide) in UO 2 is a complex phenomenon, governed by multiple underlying processes such as local defect concentrations, applied stresses, and microstructural characteristics. Consequently, there is a need for a meso-scale model with polycrystalline resolution capable of extrapolating to large grain sizes applicable to doped UO 2 , where data is limited and the model can help bridge the knowledge gap. By integrating atomistic data into the polycrystal LApx code, it becomes possible to predict dislocation climb and glide plasticity that simple analytical models cannot accurately represent. The application of atomic-scale data within LApx demonstrated the importance of climb and glide mechanisms in reproducing high-stress UO 2 behavior. Behaviors such as this are crucial to capture and implement in BISON, as parts of the fuel pellet can reach temperatures where glide can occur before pellet cracking. This model which captures dislocation based mechanisms for UO 2 is then used to stand up the doped model accounting for larger grain sizes. It was found that larger grain sizes can lead to enhanced deformation rates in the glide regime, and therefore can help with the pellet cladding mechanical interaction. Therefore if the fuel pellet reaches conditions (stress/temperature) where glide is active, the enhanced creep rates for larger grains in the glide regime (doped UO 2 ) can help with pellet cladding mechanical interactions. Plastic deformation in UO 2 involves multiple mechanisms, including diffusional creep, dislocation climb, and glide. This milestone contains two parts: (1) UQ of a pre-existing lower length scale informed mechanistic diffusional creep model, and (2) development of a new LApx based model for dislocation-mediated creep mechanisms in UO 2 , with application to large-grain doped UO 2 .

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
NASA NTRSDate not supplied

Extending the Life of NASA’s Tracking and Data Relay Satellite (TDRS)-8: TDRS-8 Power Challenges And Planning for End of Mission

The United States National Aeronautics and Space Administration (NASA) Near Space Network’s Space Relay (SR) System provides communication relay services to a number of scientific and manned space missions with its Tracking and Data Relay Satellite (TDRS) constellation. NASA’s eighth Tracking and Data Relay Satellite (TDRS) has been experiencing a decline in the health of its power subsystem, and recent reliability analyses indicate that the end of its mission serving the Space Relay is imminent. Launched in 2000, TDRS-8 is the oldest TDRS built upon a Boeing 601 platform, and as such it is the first TDRS to experience these age-related failures. The most prevalent elements of the power subsystem to decline are the solar array circuitry and the Bus Voltage Limiters (BVLs), which prevent too much power from the solar arrays being transferred to the bus by shunting excess current. This means that while the loss of solar array circuits introduces concerns that the solar arrays will continue providing the spacecraft with enough current to remain power positive, the loss of BVLs introduces a concern that the bus may not be adequately protected from overvoltage events. Spacecraft engineers at the TDRS primary ground terminal, the White Sands Complex (WSC) in Las Cruces, New Mexico, and at NASA's Goddard Space Flight Center (GSFC) have also been working in collaboration with Boeing to develop innovative techniques to extend the serviceable life of TDRS-8.

tdrs↗
NASA NTRSDate not supplied

Multigraph-based Routing in Delay Tolerant Networks: An Alternative to Contact Graph Routing

Satellites are leaving the realms of niche use, extending our day-to-day networked infrastructure to space – thereby forcing a generalization of network architectures. The Delay Tolerant Networking (DTN) protocol is being developed to give rise to this new Solar System Internet. Predominantly, DTNs in space use globally-distributed contact tables to compute routes. In this paper, we propose and analyze a novel optimized approach for route computations that improves upon traditional approaches. As the general DTN will always include some scheduled links, our new algorithm enables greater scalability and practicality of DTN routing. These contact tables include windows when two nodes can communicate and were classically organized into a contact graph, where the vertices represent contact opportunities. Because the complexity of a contact graph grows with the number of contacts, pathfinding on it does not scale. A new structure using multigraphs with the same data is proposed. We show that a multigraph-based approach, which we call contact multigraph routing, exhibits performance superior to routing based on contact graphs, allowing greater scaling to schedule-based routing. In this paper, the multigraph-based algorithm is detailed and a proof is included showing it outperforms the previous algorithm given the same input. Pseudocode is included, as are simulation results. We conclude with suggested future work.

Delay Tolerant Networking↗
DOE OSTI2025

Machine Learning‐Guided Discovery of High‐Entropy Perovskite Oxide Electrocatalysts via Oxygen Vacancy Engineering

Abstract High‐entropy perovskite oxides (HEPOs) have recently emerged as multifunctional catalysts. However, the HEPOs’ structural and compositional complexity hinders the easy and accurate extrapolation of activity indicators, which are essential for establishing structure‐property correlations. Here, OxiGraphX, is introduced as a novel graph neural network (GNN) model designed to capture the complex relationships among structure, composition, and atomic chemical environments for accurate prediction of oxygen vacancy formation energies (OVFEs) in HEPOs. By integrating machine learning (ML), density functional theory (DFT), and experimental validation, this work demonstrates an efficient framework for rapidly and accurately screening HEPO electrocatalysts for oxygen evolution reaction (OER). The OxiGraphX predicts OVFEs with a precision exceeding existing data, enabling the identification of compositions of higher oxygen vacancy content (OVC) and, thus, higher catalytic activity. Furthermore, the model explores latent spaces that translate effectively into experimental domains, bridging computational predictions with real‐world applications. This approach accelerates the discovery of high‐performance HEPO catalysts while providing deeper insights into their catalytic mechanisms.

Chemistry↗
DOE OSTI2021

RISE: Reducing I/O Contention in Staging-based Extreme-Scale In-situ Workflows

While in-situ workflow formulations have addressed some of the data-related challenges associated with extreme-scale scientific workflows, these workflows involve complex interactions and different modes of data exchange. In the context of increasing system complexity, such workflows present significant resource management challenges, requiring complex cost-performance tradeoffs. This paper presents RISE, an intelligent staging-based data management middleware, which builds on the DataSpaces framework and performs intelligent scheduling of data management operations to reduce I/O contention. In RISE, data are always written immediately to local buffers to reduce the effect of the transfer impact upon application performance. RISE identifies applications’ data access patterns and moves data towards data consumers only when the network is expected to be idle, reducing the impact of asynchronous background data movement upon critical data read/write requests. Here, we experimentally demonstrate that RISE can take advantage of staging nodes to offload data during writes without degrading application data movement performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Model-Based Framework to Optimize Charger Station Deployment for Battery Electric Vehicles

The development of battery electric vehicles (BEVs) is accelerating due to their environmental advantages over gasoline and diesel-powered vehicles, including a decrease in air pollution and an increase in energy efficiency. The deployment of charging infrastructure will need to increase to keep pace with demand, especially for large commercial vehicles for which few public chargers currently exist. In this paper, a new flexible framework is proposed for optimizing the placement of charging stations for BEVs, within which different physical models and optimization techniques may be used. Furthermore, a set of metrics is suggested to help enforce complex constraints and facilitate direct comparison between different optimization techniques. Unlike many existing charger placement techniques, the proposed method directly considers the historical driving patterns on a vehicle-by-vehicle basis, using transparent models to assess impacts of candidate charger placements, thus improving the explainability of the results. In the developed framework, modeled BEVs are first generated along the road network to mimic historical traffic data and are simulated traveling along a given route according to a simplified vehicle model. During the simulation, the charger placement problem is initially relaxed to allow vehicles to charge at any node along the road network, and vehicle states are tracked to assess areas of high charging demand. Charging stations are then placed based on the results of the relaxed simulation, and suggested placements are evaluated via road network simulation with fixed charger locations. This proposed framework is applied to a sample problem of placing charging stations along five major highway corridors for Class 8 over-the-road electric trucks. A novel mixed integer programming (MIP) formulation is proposed to optimize charger placements based upon the expected charging demand. Constraints were imposed on the final placement results to limit expected wait times at each station and ensure a minimum threshold of trucking routes are viable for BEVs. The results demonstrate the flexibility and potential effectiveness of the developed model-based framework for scalable charger station deployment.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
NASA NTRS1988

Knowledge-based operation and management of communications systems

Expert systems techniques are being applied in operation and control of the Defense Communications System (DCS), which has the mission of providing reliable worldwide voice, data and message services for U.S. forces and commands. Thousands of personnel operate DCS facilities, and many of their functions match the classical expert system scenario: complex, skill-intensive environments with a full spectrum of problems in training and retention, cost containment, modernization, and so on. Two of these functions are: (1) fault isolation and restoral of dedicated circuits at Tech Control Centers, and (2) network management for the Defense Switched Network (the modernized dial-up voice system currently replacing AUTOVON). An expert system for the first of these is deployed for evaluation purposes at Andrews Air Force Base, and plans are being made for procurement of operational systems. In the second area, knowledge obtained with a sophisticated simulator is being embedded in an expert system. The background, design and status of both projects are described.

Heggestad, Harold M.↗
NASA NTRS1990

Expert systems and advanced automation for space missions operations

Increased complexity of space missions during the 1980s led to the introduction of expert systems and advanced automation techniques in mission operations. This paper describes several technologies in operational use or under development at the National Aeronautics and Space Administration's Goddard Space Flight Center. Several expert systems are described that diagnose faults, analyze spacecraft operations and onboard subsystem performance (in conjunction with neural networks), and perform data quality and data accounting functions. The design of customized user interfaces is discussed, with examples of their application to space missions. Displays, which allow mission operators to see the spacecraft position, orientation, and configuration under a variety of operating conditions, are described. Automated systems for scheduling are discussed, and a testbed that allows tests and demonstrations of the associated architectures, interface protocols, and operations concepts is described. Lessons learned are summarized.

Durrani, Sajjad H.↗
NASA NTRS1993

A new technology for manufacturing scheduling derived from space system operations

A new technology for producing finite capacity schedules has been developed in response to complex requirements for operating space systems such as the Space Shuttle, the Space Station, and the Deep Space Network for telecommunications. This technology has proven its effectiveness in manufacturing environments where popular scheduling techniques associated with Materials Resources Planning (MRPII) and with factory simulation are not adequate for shop-floor work planning and control. The technology has three components. The first is a set of data structures that accommodate an extremely general description of a factory's resources, its manufacturing activities, and the constraints imposed by the environment. The second component is a language and set of software utilities that enable a rapid synthesis of functional capabilities. The third component is an algorithmic architecture called the Five Ruleset Model which accommodates the unique needs of each factory. Using the new technology, systems can model activities that generate, consume, and/or obligate resources. This allows work-in-process (WIP) to be generated and used; it permits constraints to be imposed or intermediate as well as finished goods inventories. It is also possible to match as closely as possible both the current factory state and future conditions such as promise dates. Schedule revisions can be accommodated without impacting the entire production schedule. Applications have been successful in both discrete and process manufacturing environments. The availability of a high-quality finite capacity production planning capability enhances the data management capabilities of MRP II systems. These schedules can be integrated with shop-floor data collection systems and accounting systems. Using the new technology, semi-custom systems can be developed at costs that are comparable to products that do not have equivalent functional capabilities and/or extensibility.

Hornstein, R. S.↗
NASA NTRSDate not supplied

Exploring Lightning and Convective Processes Using the Ground-Radar Multiplatform Precipitation Feature Database

The Multiplatform Precipitation Feature (MPF) database synthesizes coincident spaceborne and ground-based lightning and radar data in a framework of storm-based features, fusing broader spaceborne detection capabilities with process-based, storm-level analysis practices. The MPF database was designed to extend the scale and scope of investigations into the complex connections between precipitation, updrafts, and lightning. The NASA International Space Station Lightning Imaging Sensor (ISS LIS) serves as the source of lightning information for the database. The first iteration of the MPF database leveraged the NASA Global Precipitation Measurement (GPM) mission spaceborne Dual-frequency Precipitation Radar (DPR) to define features, along with contributions of microphysics data and vertical wind retrievals from the GPM Validation Network (VN) of ground-based radar data. The dependency on coincident ISS and GPM satellite overpasses of radars in a dual-Doppler configuration significantly limited the size of the initial database of features, referred to as VNMPFs, but established the database infrastructure and feasibility. We present here a second iteration of the MPF database that omits the GPM DPR and VN, instead incorporating data directly from selected proximal installations of the operational Next Generation Radar (NEXRAD) network that facilitate vertical wind retrievals via dual-Doppler analysis. These features based exclusively on ground-based polarimetric Doppler radar are hereafter referred to as Ground-Radar MPFs (GRMPFs). Removing the restriction of a coincident GPM overpass appreciably increases the size of the GRMPF database while incorporating more detailed information from higher-resolution radar data and retrievals. This expansion allows for unprecedented broad, robust statistical analyses of the electrical, kinematic, and microphysical characteristics of deep convective processes. These results highlight the potential for advancements in lightning meteorology made possible by combining multiple perspectives from global lightning measurements and ground-based radar data.

Lightning↗
DOE OSTI2023

Explainable AI (XAI)-driven vibration sensing scheme for surface quality monitoring in a smart surface grinding process

Local Interpretable and Model-agnostic Explanation (LIME), an explainable artificial intelligence (XAI) approach is adapted to identify the globally important time-frequency bands for predicting average surface roughness (Ra) in a smart grinding process. The smart grinding setup consisted of a Supertech CNC precision surface grinding machine, instrumented with a Dytran piezoelectric accelerometer attached to the tailstock quill along the tangential direction (Y-axis). For every grinding pass, vibration signatures were captured, and the ground truth surface roughness values were recorded using a Mahr Marsurf M300C portable surface roughness profilometer. The roughness values ranged from 0.06 to 0.14 microns over the complete set of experiments. Time-frequency domain spectrogram frames were extracted for each of the vibration signals collected during the grinding process. Convolutional Neural Networks (CNNs) were modeled to predict the surface roughness based on these spectrogram frames and their image augmentations. The best CNN model was able to predict the roughness values with an overall R2-score of 0.95, training R2-score of 0.99, and testing R2-score of 0.81 with only 80 sets of vibration signals corresponding to 4 experiments with 20 trials each. Although the data size is not large enough to guarantee such performance metrics in real-world scenarios, one can extract statistically consistent explanations underlying the relationships these complex deep learning models capture. Further, the LIME methodology was implemented on the developed surface roughness CNN model to identify the important time-frequency bands (i.e., the superpixels of a spectrogram) influencing the predictions. Based on the identified important regions on the spectrogram frames, the corresponding frequency characteristics were determined that influence the surface roughness predictions. The important frequency range based on LIME results was approximately 11.7 to 19.1 kHz. The power of XAI was demonstrated by cutting down the sampling rate from 160 kHz to 30, 20, 10, and 5 kHz based on the important frequency range and considering Nyquist criteria. Separate CNN models were developed for these ranges by only extracting time-frequency contents below their corresponding Nyquist cut-offs. A proper data acquisition strategy is proposed by comparing the model performances to argue the selection of a sufficient sampling rate to capture the grinding process successfully and robustly.

42 ENGINEERING↗