National Institute Of Standards And Technology Research Articles

Navigating cybersecurity challenges: Legal implications and organizational strategies

The increasing frequency and sophistication of cybersecurity incidents—such as data breaches, ransomware attacks, and system violations—highlight significant legal and organizational challenges. Despite rising investments in cybersecurity, these incidents continue to evolve, presenting complex issues for both corporations and regulators. Traditional legal frameworks, primarily focused on financial damages, fail to address non-financial harms like emotional and psychological impacts on consumers. Studies by Teichmann and Wittmann (2022) and Kilovaty (2021) reveal gaps in current cybersecurity laws, emphasizing the need to incorporate psychological damages and enhance corporate liability standards. Research by Frank, Grenier, and Pyzoha (2021) demonstrates the increasing litigation risks for boards of directors following cybersecurity incidents. Their findings suggest that prior cyberattacks raise the likelihood of being held liable, though implementing frameworks like the American Institute of Certified Public Accountants’ (AICPA) risk management guidelines can mitigate these risks. Additionally, Eijkelenboom and Nieuwesteeg (2020) analyze the disclosure of cybersecurity information in Dutch annual reports, finding a lack of transparency despite legal requirements. Their study underscores the need for better self-regulation or potential legal mandates to improve cybersecurity reporting. Falowo et al. (2022) examine the impact of digital interconnectedness on cybersecurity risks, noting that malware and phishing attacks are prevalent. Their research highlights the importance of organizational preparedness and adherence to frameworks such as the National Institute of Standards and Technology (NIST) guidelines for effective incident response. Sen (2018) identifies ongoing technical, economic, legal, and behavioral challenges that hinder effective cybersecurity, advocating for new strategies to overcome these barriers. Overall, enhancing cybersecurity resilience requires a comprehensive approach, integrating improved legal frameworks, organizational transparency, and proactive risk management.

VOC emission rates from an indoor surface using a flux chamber and PTR-MS

Arising from the Chemical Assessment of Surfaces and Air (CASA) 2022 study at the National Institute of Standards and Technology (NIST) Net-Zero Energy Residential Test Facility (NZERTF), this paper presents the first evaluation of indoor surface emissions to a house measured with a surface flux chamber coupled to an online, non-targeted volatile organic compound (VOC) mass spectrometric detection. These surface emissions are compared to those assessed using ambient, whole house indoor VOC measurements and the outdoor air change rate. Chamber emission rates varied by almost four orders of magnitude across 35 quantified VOCs. The whole house emissions measured by campaign-long ambient measurements and the flux chamber emissions (when scaled to the painted surface area of the house) are similar, with an average ratio between the two of 1.3 ± 1.0. The general agreement between these two approaches indicates that the flux chamber was not solely measuring primary emissions from building materials located below the chamber. Rather, the results suggest that over the 12-year house lifetime, VOCs have been widely distributed around the house, migrating from their primary sources to secondary surface reservoirs. With the house in a quasi-steady state, the thermodynamic activities (i.e., the vapor pressures) of the VOCs within the different reservoirs become similar. Emissions of aromatics and monoterpenes have declined since the house was built, whereas aldehyde emissions have remained relatively constant.

In-line rate encrypted links using pre-shared post-quantum keys and DPUs

The development of quantum computers poses a risk to the cryptographic algorithms utilized by current public key infrastructure (PKI). High performance computing (HPC), inter- and intra-datacenter communications, and governmental communications are particularly vulnerable to security attacks by quantum computers. In response, there are on-going efforts on implementing post-quantum cryptography (PQC) despite the considerable overhead involved in processing PQC encrypted data packets in comparison with their classical counterparts. This work aims to help with the transition to quantum resistant cryptographic schemes by means of providing a thorough experimental performance comparison of the four algorithms selected by the National Institute of Standards and Technology (NIST) for standardization when implemented in a data processing unit (DPU). The experiments are conducted at line-rate, demonstrating for the first time operation at almost 100 Gbit/s and hence suitability for high-capacity data center environments.

Unified, Integral Approach to Modeling and Design of High-Pressure Pipelines: Assessment of Various Flow and Temperature Models for Supercritical Fluids

Abstract A unified one-dimensional, steady-state flow and heat transfer model is presented for the pipeline transport of fluids at high pressures, including the supercritical conditions. The model includes a generalized temperature equation, presented here for the first time, and accounts for all of the important effects, including the property variation, viscous dissipation, Joule-Thomson (J-T) cooling, and heat exchange with the surrounding. With appropriate approximations, this model can yield all isothermal and non-isothermal pipe flow solutions reported thus far. A generalized multi-zone integral method is developed which solves the two resulting algebraic equations for pressure and temperature in conjunction with a property database, such as the National Institute of Standard and Technology (NIST) Reference Fluid Thermodynamic and Transport Properties (REFPROP). With appropriately selected number and size of the zones and using property values at the mean temperature and pressure within each zone, this integral method can accurately predict the complex effects of the governing parameters, such as the pipe diameter and length, inlet and exit pressures, mass flow rate, J-T cooling, and inlet and surrounding temperatures. Its accuracy for small-to-large diameter pipes has been ascertained by a comparison with the numerical solutions of the differential form of governing equations that requires a large number of small grids along the pipe and the values of mean properties within each grid. Indeed, this integral model can be used for the pipeline transport at both subcritical and supercritical pressures as long as the fluid does not encounter its anomalous states and the phase-change.

Incident Response and Threat Intelligence in Healthcare: A Study on Cybersecurity Incident Management

India and other Asian nations are seeing an unparalleled pace of advancement in the modernisation of their healthcare systems. In this endeavour, information technology is crucial. Though the healthcare industry has made great progress, information security is still lagging behind the protection requirements attained in technologically developed nations such as the United States and the United Kingdom. This study is an honest attempt to pinpoint vulnerabilities and dangers in the field of cybersecurity and offers a few targeted remedies in three main domains: risks, vulnerabilities, and IoMT. Using a qualitative research methodology, this research culminates in the creation of a security maturity model for Indian healthcare. Furthermore, in light of these attacks, the well-known National Institute of Standards and Technology (NIST) risk assessment system and its guiding principles are examined. Evaluating the risks intrinsic to these hacks analytically becomes crucial given the comparatively low information risk management maturity levels in Asian healthcare organisations. While several nations in Asia and throughout the world are battling the COVID-19 outbreak, cybercriminals have been attempting to spread misinformation about vaccines. Additionally, some people and organisations are attempting to undermine specific vaccines in order to promote their COVID-19 treatments. Hacking research data, virus testing, and clinical studies that reveal side effects or possible issues are of particular interest to profit-seeking businesses. The secure methodology for identifying network attacks is suggested by this study.

Automatic identification of breech face impressions based on deep local features

Breech face impressions are an essential type of physical evidence in forensic investigations. However, their surface morphology is complex and varies based on the machining method used on the gun’s breech face, making traditional handcrafted local feature-based methods exhibit high false rates and are unsuitable for striated impressions. We proposed a deep local feature-based method for firearm identification utilizing Detector-Free Local Feature Matching with Transformers (LoFTR). This method removes the module of feature point detection and directly utilizes self and cross-attention layers in the Transformer to transform the convolved coarse-level feature maps into a series of dense feature descriptors. Subsequently, matches with high confidence scores are filtered based on the score matrix calculated from the dense descriptors. Finally, the screened initial matches are refined into the convolved fine-level features, and a correlation-based approach is used to obtain the exact location of the match. Validation tests were conducted using three authoritative sets of the breech face impressions datasets provided by the National Institute of Standards and Technology (NIST). The validation results show that, compared with the traditional handcrafted local-feature based methods, the proposed method in this paper yields a lower identification error rate. Notably, the method can not only deal with granular impressions, but can also be applied to the striated impressions. The results indicate that the method proposed in this paper can be utilized for comparative analysis of breech face impressions, and provide a new automatic identification method for forensic investigations.

Averrhoa carambola Leaf Extract Induces Apoptosis-Like Death with Increased ROS Generation in Leishmania donovani.

The parasitic disease leishmaniasis is responsible for high mortality and morbidity rates worldwide. The visceral form is the most severe form of leishmaniasis (or leishmaniosis), which is caused predominantly by Leishmania donovani. Currently, clinically recommended antileishmanial drugs are not convenient because of several medical complications and resistance issues. Phytocompounds are the best candidates in this regard. The present study aimed to evaluate the antileishmanial activity of Averrhoa carambola leaf extract. The antipromastigote activity and cytotoxicity were assessed using the MTT assay. Morphological distortions were determined using phase contrast microscopy and scanning electron microscopy (SEM). Reactive oxygen species (ROS) production, nonprotein thiol depletion and apoptotic death in promastigotes were determined via flow cytometry. UV-visible spectroscopy and energy dispersive X-ray (EDX) spectroscopy was performed for elemental analysis. Fourier-transform infrared spectroscopy (FTIR) and liquid chromatography‒mass spectrometry (LCMS) were used to characterize the phytocomponent(s) present in the extract. The chloroform extract of Averrhoa carambola leaf (ACCEX) (IC50 = 50.76 ± 1.7µg/mL) exhibited the highest activity, followed by the ethyl acetate, hexane, and methanol extracts. ACCEX has also exhibited lower toxicity towards host macrophages. ACCEX also induced morphological distortions in promastigotes, with significant generation of ROS and the concomitant apoptosis initiation followed by a decrease in the nonprotein thiol level. The major phytometabolites present in ACCEX were identified from the National Institute of Standards and Technology (NIST) database and from a literature review. This study suggested that Averrhoa carambola leaf extracts are rich in some classes of biologically active phytocompounds and exhibit good antileishmanial activity.

Identification and characterization of phytochemicals in methanolic extract of roots of Datura fastuosa using various techniques

BackgroundPlant extracts have attracted significant interest among researchers due to their potential bioactivity and crucial contribution to the production of pharmaceutical compounds. In this study, the primary objective was to extract, analyze and characterize the bioactive compounds found in the methanol root extract of Datura fastuosa (D. fastuosa). This was achieved using various analytical techniques such as gas chromatography/mass spectrometry (GC–MS), ultra-violet visible spectrophotometry, Fourier-transform infrared (FT-IR), nuclear magnetic radiation spectrometry (NMR) and DPPH free radical scavenging activity assay.ResultsGC–MS analysis of the methanol root crude extract identified 49 compounds. Three compounds were isolated via column chromatography; one was pure, with a sharp melting point and clean IR spectrum, while the other two showed broad melting points and IR interferences. Comprehensive investigation of the pure extract revealed a UV profile with two distinct bands (300–800 nm) and confirmed functional groups (alcohol, alkanes, alkenes, carbonyl, methylene, and methyl) through FT-IR analysis. The 1HNMR (proton nuclear magnetic resonance spectroscopy) signal confirmed the presence of forty-nine non-equivalent protons, 13CNMR (Carbon-13 nuclear magnetic resonance spectroscopy) signal confirmed the presence of 32 non-equivalent carbons and DEPT-135 (distortionless enhancement by polarization transfer-135) signal confirmed the presence of 24 carbons (17 for odd and 7 for even) which are protons containing carbons in the compound. Combining the above mentioned analyses with data obtained from the GC/MS analysis of National Institute of Standards and Technology (NIST) library, the isolated pure compound exhibited a structural similarity to 1-(7-(3-hydroxyphenyl)-1,1,4a,5,6,9,10a,10b-octamethyl-1,2,3,4,4a,4b,6a,7,8,9,10,10a,10b,11,12,12a-hexadecahydrochrysen-2-yl)propan-1-one, with a chemical formula of C35H50O2.ConclusionsThe presence of various notable compounds, including phenolics, flavonoids, alkaloids, steroids etc., within the methanol root extract of D. fastuosa signifies its pharmacological potential. The methanol crude extract demonstrated antioxidant potential compared to standard ascorbic acid, exhibiting DPPH scavenging activity. Previous research has demonstrated the bioactivity of some of these compounds, further elucidating the plant’s medicinal properties. These findings not only suggest opportunities for developing synthetic drugs but also underscore its direct therapeutic potential in addressing diverse ailments.

Designing a Scalable and Area-Efficient Hardware Accelerator Supporting Multiple PQC Schemes

This study introduces a hardware accelerator to support various Post-Quantum Cryptosystem (PQC) schemes, addressing the quantum computing threat to cryptographic security. PQCs, while more secure, also bring significant computational demands, which are especially problematic for lightweight devices. Previous hardware accelerators are typically scheme-specific, which is inefficient given the National Institute of Standards and Technology (NIST)’s multiple finalists. Our approach focuses on the shared operations among these schemes, allowing a single design to accelerate multiple candidate PQCs at the same time. This is further enhanced by allocating resources according to performance profiling results. Our compact, scalable hardware accelerator supports four of NIST PQC finalists, achieving an area efficiency of up to 81.85% compared to the current state-of-the-art multi-scheme accelerator while supporting twice as many schemes. The design demonstrates average throughput improvements ranging from 0.97× to 35.97× across the four schemes and their main operations, offering an efficient solution for implementing multiple PQC schemes within constrained hardware environments.

The Use of Fire Dynamics System (NIST) in Determining The Architecture of Educational Spaces for Children and Young People

Objective: This study aims to investigate the potential of the Fire Dynamics Simulator (FDS) software, developed by the National Institute of Standards and Technology (NIST), as a tool to assess and improve Fire Safety (FS) in educational environments, specifically in the classrooms of CEFET in Araxá (MG), Brazil. Theoretical Framework: The research is based on the importance of fire safety in educational environments, highlighting the vulnerability of children and young people. Concepts of fire behavior, smoke propagation, and thermal conditions in buildings are addressed. Method: The methodology adopted for this research involves detailed computer simulations using FDS to analyze different fire scenarios. The simulation results were validated with the PyroSim software. Data collection was conducted through these simulations, generating robust empirical data that support the review and development of specific regulations. Results and Discussion: The results indicate that FDS is an important ally in promoting fire safety in educational buildings. The simulations showed the effectiveness of FDS in predicting fire behavior, smoke propagation, and thermal conditions, helping to prevent and minimize potential damages. The discussion contextualizes these results, highlighting the need for accurate empirical data to strengthen Brazilian fire safety legislation. Research Implications: The practical and theoretical implications of this research are discussed, providing insights into how the results can be applied to positively influence legislation, optimize architectural designs, and promote safety guidelines in educational institutions in Brazil. Originality/Value: This study significantly contributes to the advancement of knowledge and practices in FS. The originality of the research lies in the application of FDS for simulations in educational environments, offering a robust tool for evaluating and improving fire safety.

The impact of cybersecurity risk management strategy disclosure on investors’ judgments and decisions

In March 2022, the Securities and Exchange Commission (SEC) proposed the mandatory reporting of cybersecurity risk management policies for public companies. This study aims to explore the potential impact of cybersecurity risk management strategy disclosure on nonprofessional investors. Using a 4 x 1 between-participants experimental design, we examine whether nonprofessional investors’ perceptions and decisions differ between disclosed cybersecurity risk management strategies of self-assessment, self-assessment referencing the National Institute of Standards and Technology (NIST) framework, third-party assurance, and insurance. We find that nonprofessional investors’ willingness to invest is significantly higher for the insurance strategy compared to the third-party cybersecurity examination and self-assessment (without reference to NIST) strategies. Moderated mediation analysis reveals that investors’ perceptions of financial risk moderates the mediating effect of perceived cybersecurity risk management strategy effectiveness on the relation between cybersecurity risk management strategy and likelihood of investment. Our study contributes to regulators, practitioners, and stakeholders concerned about the potential impact of cybersecurity risk management strategy disclosures on nonprofessional investors.

A High-Performance FPGA PRNG Based on Multiple Deep-Dynamic Transformations.

Pseudo-random number generators (PRNGs) are important cornerstones of many fields, such as statistical analysis and cryptography, and the need for PRNGs for information security (in fields such as blockchain, big data, and artificial intelligence) is becoming increasingly prominent, resulting in a steadily growing demand for high-speed, high-quality random number generators. To meet this demand, the multiple deep-dynamic transformation (MDDT) algorithm is innovatively developed. This algorithm is incorporated into the skewed tent map, endowing it with more complex dynamical properties. The improved one-dimensional discrete chaotic mapping method is effectively realized on a field-programmable gate array (FPGA), specifically the Xilinx xc7k325tffg900-2 model. The proposed pseudo-random number generator (PRNG) successfully passes all evaluations of the National Institute of Standards and Technology (NIST) SP800-22, diehard, and TestU01 test suites. Additional experimental results show that the PRNG, possessing high novelty performance, operates efficiently at a clock frequency of 150 MHz, achieving a maximum throughput of 14.4 Gbps. This performance not only surpasses that of most related studies but also makes it exceptionally suitable for embedded applications.

Reconfigurable Image Confusion Scheme Using Large Period Pseudorandom Bit Generator Based on Coupled-Variable Input LCG and Clock Divider

This paper presents a reconfigurable image confusion scheme, which uses Linear Congruential Generators (LCGs)-based Pseudorandom Bits Generator (PRBG). The PRBG is based on the variable input-coupled LCG with a reconfigurable clock divider. The proposed algorithm encrypts the input image up to four times successively using different random sequences in every attempt. This new scheme aims to efficiently extract statistically strong pseudorandom sequences from a proposed PRBG with a large keyspace and simultaneously increase the security level of the encrypted image. This PRBG was initially designed on Virtex-5 (XC5VLX110T), Virtex-7 (XC7VX330T) and Artix-7 (XC7A100T) Field Programmable Gate Arrays (FPGAs). The statistical properties of the proposed PRBG for four different configurations are verified by the National Institute of Standards and Technology (NIST) tests. Thereafter, a reconfigurable encryption/decryption algorithm that uses the proposed PRBG is developed for secure image encryption. The encryption process was accomplished using the MATLAB tool after obtaining the PRBG keys from the FPGA. To show the quality and strength of the encryption process, security analysis [correlations and Number of Pixels Change Rate (NPCR)] is performed. Security analysis results are compared with the conventional encryption algorithm to show that the developed reconfigurable encryption scheme provides better results in security tests.

Thermal expansion calculation using FBGS in cryogenic applications

This study presents the measurement of the thermal expansion of aluminum alloy 6061 at cryogenic temperatures using Helium as the cooling medium. Three distinct tests were conducted to evaluate thermal expansion: two with gradual and natural heating of the material, and a third with temperature stabilization at key points. Measurements were carried out using Fiber Bragg Grating Sensors (FBGS), which provided precise and reliable data on the material's thermal behavior. The obtained results were compared with reference curves from the National Institute of Standards and Technology (NIST), showing good agreement and validation of the employed methods. This research highlights the effectiveness of using FBGS in measuring thermal expansion under cryogenic conditions and the importance of heating procedures in obtaining accurate data.

Ranking the states most at risk of healthcare data breaches: an application of integrated multicriteria framework for prioritization in risk management

PurposeData breaches in the US healthcare sector have more than tripled in the last decade across all states. However, to this day, no established framework ranks all states from most to least at risk for healthcare data breaches. This gap has led to a lack of proper risk identification and understanding of cyber environments at state levels.Design/methodology/approachBased on the security action cycle, the National Institute of Standards and Technology (NIST) cybersecurity framework, the risk-planning model, and the multicriteria decision-making (MCDM) literature, the paper offers an integrated multicriteria framework for prioritization in cybersecurity to address this lack and other prioritization issues in risk management in the field. The study used historical breach data between 2015 and 2021.FindingsThe findings showed that California, Texas, New York, Florida, Indiana, Pennsylvania, Massachusetts, Minnesota, Ohio, and Georgia are the states most at risk for healthcare data breaches.Practical implicationsThe findings highlight each US state faces a different level of healthcare risk. The findings are informative for patients, crucial for privacy officers in understanding the nuances of their risk environment, and important for policy-makers who must grasp the grave disconnect between existing issues and legislative practices. Furthermore, the study suggests an association between positioning state risk and such factors as population and wealth, both avenues for future research.Originality/valueTheoretically, the paper offers an integrated framework, whose basis in established security models in both academia and industry practice enables utilizing it in various prioritization scenarios in the field of cybersecurity. It further emphasizes the importance of risk identification and brings attention to different healthcare cybersecurity environments among the different US states.

Technical note: Determination of for a miniature x-ray source using a soft x-ray ionization chamber calibrated in NIST reference beam qualities.

The formalism proposed by Watson etal. allows users of the INTRABEAM (Carl Zeiss Medical AG, Jena, Germany) electronic brachytherapy system to accurately determine the absorbed dose to water, in the absence of a primary dosimetry standard. However, all published values are for PTW 34013 ionization chambers calibrated in a TW30 reference beam, traceable to PTB (Germany). For North American users, it would be advantageous to have data for chambers calibrated in a kV reference beam maintained by the National Institute of Standards and Technology (NIST). In this work, we determine for a PTW 34013 chamber calibrated in three NIST-traceable reference beams: M30, L40, andL50. Using available photon spectra data for M30, L40, and L50 reference beam qualities, Monte Carlo simulations using EGSnrc were performed to calculate the ratio of the absorbed dose to the PTW 34013 chamber air cavity to air-kerma ( ) for these beams. From this ratio, as a function of depth in water was determined. The effect of the use of a buildup foil was also investigated. An uncertainty analysis considering both the Type A and Type B uncertainties in the calculation of was performed. The largest difference in was found between L50 and TW30, with a relative decrease of 1.4% (no buildup) to 1.6% (buildup). For M30 and L40, the differences were minimal compared with measurementuncertainties. We report values for three NIST-traceable kV reference beams. This study reinforces the feasibility of adapting the Watson etal. methodology using different kV reference beams, facilitating the use of INTRABEAM in North America and ensuring the continuity and accuracy of dosimetry standards in intraoperative radiationtherapy.

SecSAGE: NIST Cybersecurity Framework Visualization on SAGE2

Cybersecurity has been an area of great interest for an organization, given the significance of data and the increasing cybersecurity threats. The National Institute of Standards and Technology (NIST) has developed a cybersecurity framework intended for voluntary utilization by critical infrastructure owners and operators. Its primary purpose is to aid in the effective management of cybersecurity risks. This framework, similar to many other security standards, comprises a substantial volume of textual information that can be challenging to grasp comprehensively in a limited timeframe. In response to this challenge, we designed and developed an interactive visualization of the NIST Cybersecurity Framework using the SAGE2 platform. Our objective is to facilitate a better understanding of the framework. In addition, using SAGE2 enhances collaborative working. In our project, we analyze the content within the NIST document and map the framework's five core functions into a rich visualization workflow. Each function includes categories, sub-categories, and references that users can interactively explore. Our experiments show that our visualization can help participants correctly find the information about the NIST Cybersecurity Framework faster than manually finding the information in the document. For all tasks, participants can complete the tasks around 4.25 times faster than the manual method on average.

Diffraction order penalization to improve spectrometer calibrations

Wavelength calibration in diffraction spectroscopy typically depends on identifying strong, well-known lines in the recorded spectra and fitting a calibration function to them. In this paper, we outline a novel method (order penalization) for improving spectroscopic calibrations by extending non-linear least squares fitting of the calibration curve. The method introduces an extra term into the minimized quantity that penalizes disagreement in the positions of spectral lines observed in multiple diffraction orders. The primary advantage of this method is that the lines used do not have to be identified, except for establishing the fact that they are different orders of the same line. This increases the number of constraints on the calibration curve, potentially in spectral regions where no regular calibration lines are available. The mathematical basis of this method is described, and the performance of this method is evaluated on simulated data and experimental data from the National Institute of Standards and Technology (NIST) Electron Beam Ion Trap. We demonstrate the effectiveness of the method on the spectra of highly charged Ag-like Re28+ and nearby charge state ions.

Advancing cryptography: a novel hybrid cipher design merging Feistel and SPN structures

In the dynamic field of cryptography, lightweight ciphers play a pivotal role in overcoming resource constraints in modern applications. This paper introduces a lightweight cryptographic algorithm by seamlessly merging the proven characteristics of the Feistel cipher CLEFIA with the advanced substitution-permutation network (SPN) framework of RECTANGLE for key generation. The algorithm incorporates a specially optimized feather S-box, balancing efficiency and security in both CLEFIA and RECTANGLE components. The RECTANGLE key generation, vital for the proposed lightweight technique, enhances overall cryptographic security and efficiency. Meticulous consideration of resource limitations maintains the algorithm's lightweight nature, making it well-suited for applications with restricted computational resources. To validate the efficacy of the lightweight algorithm, extensive evaluation on encrypted data is conducted using National Institute of Standards and Technology (NIST) tools, known for assessing cryptographic algorithm quality. Results reveal a high degree of randomness, indicative of robust resistance against cryptographic attacks. This manuscript provides a comprehensive examination of the lightweight algorithm, emphasizing key attributes, security enhancements, and successful integration of the optimized feather S-box. Rigorous testing, particularly NIST tool-based randomness analysis, offers empirical evidence of the algorithm's resilience against attacks, establishing its suitability for secure data encryption in resource-limited environments.<p> </p>

Data-driven prediction of future melt pool from built parts during metal additive manufacturing

Smart manufacturing in metal additive manufacturing (MAM) relies on real-time process optimization through the prediction of unbuilt parts using data from built parts. Melt pool dynamics are intimately associated with the development of various microstructures during the MAM. In this paper, we demonstrate the idea by establishing a machine learning (ML) model to predict the melt pool of future parts, based on the experimental data from the National Institute of Standards and Technology (NIST) where 80 % is used for the training (built parts) and 20 % for testing (future parts). The ML model integrates both data denoising and predictive modeling. First, a convolutional neural network (CNN) is used to process a large dataset of raw melt pool images, enabling the automatic removal of noises (e.g., splash and plume) and thereof extraction of high-quality melt pool data. Following that, a novel data-driven melt pool model based on multi-layer perceptron (MLP) is trained by incorporating raw, long scanning history as input features, which best accounts for the effects of printing history (e.g., intertrack heating) on melt pool development. It takes complete advantage of MLP in handling high-dimensional regression problems in conjunction with a large dataset. Upon testing under various manufacturing conditions, the average relative error magnitude (AREM) of predicting melt pool size drops to 2.8 %, compared to 14.8 % of the prior art – the Neighboring Effect Modeling Method model (NBEM). This research thus represents a significant step towards reliable melt-pool-guided AM process optimization for smart manufacturing, enabled by advanced, flexible, and maximum use of ML techniques.