Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Convolutional Neural Networks”

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 1,135 records · Page 63
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Applying Machine Learning to the Classification of DC-DC Converters (Milestone 2 Deliverable Report)

Since extending the Autodetector to a convolutional neural network (CNN) machine learning classifier model, an effort has been executed to demonstrate its ability to distinguish not only a switching DC-DC converter as high voltage, but identify the make and model of a converter on which it was trained. This was achieved by collecting data in a noisy environment, pre-processing the time domain data to obtain composite images using a method that improves upon that of the prior research, then validating a trained CNN model to an accuracy of 100% on a selected candidate converter.

42 ENGINEERING↗
DOE OSTI2020

How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection

Deep convolutional neural networks (DCNNs) currently provide state-of-the-art performance on image classification and object detection tasks, and there are many global security mission areas where such models could be extremely useful. Crucially, the success of these models is driven in large part by the widespread availability of high-quality open source data sets such as Image Net, Common Objects in Context (COCO), and KITTI, which contain millions of images with thousands of unique labels. However, global security relevant objects-of-interest can be difficult to obtain: relevant events are low frequency and high consequence; the content of relevant images is sensitive; and adversaries and proliferators seek to obscure their activities. For these cases where exemplar data is hard to come-by, even fine-tuning an existing model with available data can be effectively impossible. Recent work demonstrated that models can be trained using a combination of real-world and synthetic images generated from 3D representations; that such models can exceed the performance of models trained using real-world data alone; and that the generated images need not be perfectly realistic (Tremblay, et al., 2018). However, this approach still required hundreds to thousands of real-world images for training and fine tuning, which for sparse, global security-relevant datasets can be an unrealistic hurdle. In this research, we validate the performance and behavior of DCNN models as we drive the number of real-world images used for training object detection tasks down to a minimal set. We perform multiple experiments to identify the best approach to train DCNNs from an extremely small set of real-world images. In doing so, we: Develop state-of-the-art, parameterized 3D models based on real-world images and sample from their parameters to increase the variance in synthetic image training data; Use machine learning explainability techniques to highlight and correct through targeted training the biases that result from training using completely synthetic images; and Validate our results by comparing the performance of the models trained on synthetic data to one another, and to a control model created by fine-tuning an existing ImageNet-trained model with a limited number (hundreds) of real-world images.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Reification of latent microstructures: On supervised unsupervised and semi-supervised deep learning applications for microstructures in materials informatics

Machine learning (ML), including deep learning (DL), has become increasingly popular in the last few years due to its continually outstanding performance. In this context, we apply machine learning techniques to "learn" the microstructure using both supervised and unsupervised DL techniques. In particular, we focus (1) on the localization problem bridging (micro)structure (localized) property using supervised DL and (2) on the microstructure reconstruction problem in latent space using unsupervised DL. The goal of supervised and semi-supervised DL is to replace crystal plasticity finite element model (CPFEM) that maps from (micro)structure (localized) property, and implicitly the (micro)structure (homogenized) property relationships, while the goal of unsupervised DL is (1) to represent high-dimensional microstructure images in a non-linear low-dimensional manifold, and (2) to discover a way to interpolate microstructures via latent space associating with latent microstructure variables. At the heart of this report is the applications of several common DL architectures, including convolutional neural networks (CNN), autoencoder (AE), and generative adversarial network (GAN), to multiple microstructure datasets, and the quest of neural architecture search for optimal DL architectures.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Microseismic Event Denoising: Removal of Borehole Waves

The vertical borehole array at Farnsworth Unit, TX is used to monitor microseismic activity in the subsurface around the Carbon Capture and Sequestration (CCS) reservoir. The array consists of 16 3-component seismometers spaced vertically in a single borehole. Tube or borehole waves traveling up or down the borehole can corrupt signals of interest, such as microseismic events. A denoising convolutional neural network (DCNN) was trained to remove borehole waves from seismic waveforms of microseismic events for the purpose of reducing unwanted signal detections and better characterizing events of interest. This R&D leverages the work of Sandia colleague Rigo Tibi, who used a DCNN developed by Greg Beroza at Stanford University to improve the signal-to-noise ratio (SNR) of teleseismic events detected by the International Monitoring System.

58 GEOSCIENCES↗
DOE OSTI2019

GMLS-Nets: A Framework for Learning from Unstructured Data

Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gaining benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a nonparametric technique for estimating linear bounded functionals from scattered data, and has recently been used in the literature for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators and to regress quantities of interest. The results suggest the architectures to be an attractive foundation for data-driven model development in scientific machine learning applications.

42 ENGINEERING↗
DOE OSTI2021

Identifying precursors of daily to seasonal hydrological extremes over the USA using deep learning techniques and climate model ensembles

Focal Area(s): We focus on two areas of crosscutting interest for DOE: 1) predictability of extreme precipitation and drought in the USA and 2) the integration of climate models with new AI tools, such as convolutional neural networks (CNN) and methods to understand their output (e.g. layer-wise relevance propagation; LRP). This project fits into focus area 3 of this call for white paper using AI to gain insight from complex data, including explainable AI tools. Science Challenge: Predicting hydrological extremes is important due to their impacts on people, agriculture and infrastructure. This prediction is difficult due to the infrequent occurrence of extremes and their complexity. However, extreme events can be related to more predictable conditions in the ocean, such as El Nino, long-term soil moisture or large scale modes of climate variability, such as the North Atlantic Oscillation (NAO).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Insights into cosmological structure formation with machine learning.

Our modern understanding of cosmological structure formation posits that small matter density fluctuations present in the early Universe, as traced by the cosmic microwave background, grow via gravitational instability to form extended haloes of dark matter. A theoretical understanding of the structure, evolution and formation of dark matter haloes is an essential step towards unravelling the intricate connection between halo and galaxy formation, needed to test our cosmological model against data from upcoming galaxy surveys. Physical understanding of the process of dark matter halo formation is made difficult by the highly non-linear nature of the haloes' evolution. I describe a new approach to gain physical insight into cosmological structure formation based on machine learning. This approach combines the ability of machine learning algorithms to learn non-linear relationships, with techniques that enable us to physically interpret the learnt mapping. I describe applicatio ns of th e method, with the aim of investigating which aspects of the early universe density field impact the later formation of dark matter haloes. First I present a case where the process of halo formation is turned into a binary classification problem; the algorithm predicts whether or not dark matter `particles' in the initial conditions of a simulation will collapse into haloes of a given mass range. Second, I present its generalization to regression, where the algorithm infers the final mass of the halo to which each particle will later belong. I show that the initial tidal shear does not play a significant role compared to the initial density field in establishing final halo masses. Finally, I demonstrate that extending the framework to deep learning algorithms such as convolutional neural networks allows us to explore connections between the early universe and late time haloes beyond those studied by existing analytic approximations of halo collapse.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Bridging Power System Protection Gaps with Data-driven Approaches

Protection is a critical function in power systems to avoid equipment damage, maintain personnel safety, and support system reliability. However, current protective relay technology cannot adequately protect equipment and personnel from effects of some events; these deficiencies are termed protection gaps. In this research, a data-driven approach is proposed to complement traditional protection technology and distinguish fault conditions from transients caused by normal operations. A convolutional neural network (CNN) based fault detection approach is implemented to achieve data translation invariance of the time-series input data. As a result, the data-driven method can accurately detect system faults despite variation and noise in the input data. In addition, using the CNN–based method avoids the complicated manual feature extraction procedure required by many traditional data-driven methods. The effectiveness of the proposed approach is tested on four kinds of protection gaps: high impedance faults, transformer/generator inter-turn faults, distribution system PV circuit faults, and the mis-operation situations of Zone 3 line protection relays operating under system stress. Finally, a transfer learning method is also proposed to address the common issue of data-driven methods for which real-world training data are scarce. Extensive study results demonstrate that the proposed approach can accurately bridge power system protection gaps.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Scaling Inference Using Triton to Accelerate Particle Physics at the LHC and DUNE

DUNE and the LHC experiments consist of unique and cutting-edge particle detectors that create massive, complex, and rich datasets with billions of events. They require sophisticated algorithms to reconstruct and interpret the data. Modern machine learning algorithms provide a powerful toolset to detect and classify particles, from familiar image processing convolutional neural networks to newer graph neural network architectures. A full reconstruction of these particle collisions requires novel approaches to handle the computing challenge of processing so much raw data. In a series of studies, physicists from Fermilab, CERN, and university groups explored how to accelerate their data processing using the Triton Inference Server.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Verification of Triso Fuel Burnup Using Machine Learning Algorithms

Pebble Bed Reactors are fueled with fuel pebbles that are circulated multiple times through the reactor vessel before discharge. During the normal operation of a PBR, ejected pebbles are returned to the reactor or discharged depending on the fuel burnup and physical condition of the pebbles. The burnup measurement is usually based on detected radiation signatures of fission products accumulated in the pebble fuel over burnup. Previous research has shown that height of photopeaks of fission products, such as 134 Cs, 137 Cs, 154 Eu, etc., can be used independently or in combination to infer or predict the level of burnup in the fuel. However, it remains challenging to measure such complex sources due to self-shielding effects, strong radiation background and intervening materials. Another operational challenge is the required high throughput of burnup measurement, which necessitates limited measurement time and thus impacts quality of measured gamma-ray spectra. Hence, advanced spectral analysis methods are needed to analyze the noisy gamma spectra and predict the burnup values. We propose to use machine learning (ML) method to interpret gamma-ray spectra and predict the burnup values of the pebbles. ML has achieved widespread success and adoption across a few domains that require pattern recognition and analysis in varied data types. In this work, we apply three proven ML approaches - multilayer perceptrons, convolutional neural networks, and transformers - to the task of predicting fuel burnup from measured gamma spectra, and compile a dataset of simulated spectra for training and validation of the ML models. In this paper, we will discuss the network architecture of these three ML approaches and compare the performance of the simplest of these (MLP) to a standard linear regression.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2020

LDMS-GPU: Lightweight Distributed Metric Service (LDMS) for NVIDIA GPGPUs

GPUs are now a fundamental accelerator for many high-performance computing applications. They are viewed by many as a technology facilitator for the surge in fields like machine learning and Convolutional Neural Networks. To deliver the best performance on a GPU, we need to create monitoring tools to ensure that we optimize the code to get the most performance and efficiency out of a GPU. Since NVIDIA GPUs are currently the most commonly implemented in HPC applications and systems, NVIDIA tools are the solution for performance monitoring. The Light-Weight Distributed Metric System (LDMS) at Sandia is an infrastructure widely adopted for large-scale systems and application monitoring. Sandia has developed CPU application monitoring capability within LDMS. Therefore, we chose to develop a GPU monitoring capability within the same framework. In this report, we discuss the current limitations in the NVIDIA monitoring tools, how we overcame such limitations, and present an overview of the tool we built to monitor GPU performance in LDMS and its capabilities. Also, we discuss our current validation results. Most of the performance counter results are the same in both vendor tools and our tool when using LDMS to collect these results. Furthermore, our tool provides these statistics during the entire runtime of the tool as a time series and not just aggregate statistics at the end of the application run. This allows the user to see the progress of the behavior of the applications during their lifetime.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Deep Learning Systems for Increased Safeguards Surveillance Review Productivity

Nuclear safeguards inspectors expend significant time and maintain intense focus in reviewing video surveillance for safeguards relevant events. To increase efficiency and reduce the time burden of safeguards inspectors performing surveillance data review, this paper presents a novel deep learning (DL) systems concept to integrate generalized DL models into the safeguards surveillance review workflow. The Agency is investigating several DL algorithms for object recognition, localization, tracking, and flagging relevant activities. The project team is working closely with nuclear safeguards inspectors to identify review use cases (based on specific safeguards objectives) and collect their associated requirements. We focused on CANDU and LWR Nuclear Power Plants (NPPs) and their associated dry storage areas as these present a particularly heavy burden on the inspector surveillance review process due to the number of these facilities under safeguards worldwide. Initial DL algorithm results on safeguards data are promising. Using a convolutional neural network, the team attained a mean average precision (mAP) of 92.9% identifying and localizing spent fuel (SF) casks from a 475 surveillance image dataset. Further, the team had initial success in training a recurrent neural network to identify reactor area activities in video clips, successfully indicating when SF casks enter or exit a pool. We discuss how such DL algorithms would be integrated into the Next Generation Surveillance Review (NGSR) software application. Another issue impacting review productivity is the long time inspectors may have to wait when running these algorithms in NGSR. We present a concept to pre-process remotely collected surveillance data with DL models as the data arrives to IAEA headquarters so that results are already available when starting a new review in NGSR. The proposed DL system concept shows a pathway and workflow for increasing an inspector’s surveillance review productivity by quickly and accurately identifying declared and undeclared safeguards relevant objects and activities in large quantities of surveillance imagery data.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2021

Performance of Pulsed Thermal Tomography Imaging with Machine Learning-Based Classification of Defects in Additively Manufactured Structures

Additive manufacturing (AM) is an emerging method for cost-efficient fabrication of complex topology nuclear reactor parts from high-strength corrosion resistance alloys, such as stainless steel and Inconel. AM of metallic structures for nuclear energy applications is currently based on laser powder bed fusion (LPBF) process. Some of the challenges with using LPBF method for nuclear manufacturing include the possibility of introducing pores into metallic structures. Integrity of AM structures needs to be evaluated nondestructively because material flaws could lead to premature failures in high temperature nuclear reactor environment. Currently, there exist limited capabilities to evaluate actual AM structures non-destructively. Pulsed Thermal Tomography Imaging (PTT) provides a capability for non-destructive evaluation (NDE) of subsurface defects in arbitrary size structures. The PTT method is based on recording material surface temperature transients with infrared (IR) camera following thermal pulse delivered on material surface with flash light. The PTT method has advantages for NDE of actual AM structures because the method involves one-sided non-contact measurements and fast processing of large sample areas captured in one image. Following initial qualification of an AM component for deployment in a nuclear reactor, a PTT system can also be used for in-service nondestructive evaluation (NDE) applications. In this report, we describe recent progress in enhancing PTT capabilities in detecting and visualizing microscopic defects in metallic specimens. The thermal tomography (TT) algorithm obtains depth reconstructions of spatial effusivity from the data cube of sequentially recorded surface temperatures. However, interpretation of TT images is non-trivial because of blurring of images with increasing depth. To address this challenge, we have developed a deep learning convolutional neural network (CNN) to classify size and orientation subsurface defects in simulated TT images. CNN is trained on a database of TT images created for a set of simulated metallic structures with elliptical subsurface voids. Test of CNN performance demonstrate the ability to classify radii and angular orientation of subsurface defects in TT images. In addition, we have shown that CNN trained on elliptical defects is capable of classifying irregular-shaped defects obtained from scanning electron microscopy (SEM) of stainless steel sections printed with LPBF.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Integrating static PRA information with risk informed safety margin characterization (RISMC) simulation methods

The overall objective of the project was to develop a computationally feasible and user-friendly mechanized process to integrate traditional probabilistic risk assessment (PRA) and dynamic PRA (DPRA) results. Starting with the systematic identification of items in an existing PRA that need dynamic augmentation, the project used a generic 4-loop pressurized reactor (PWR) and 3-loop PWR as example plants. Station blackout (SBO) and large break loss of coolant accident SBLOCA) were selected as the example initiating events. Using the traditional event-tree (ET)/fault-tree (FT) methodology augmented by dynamic evet tree approach, the potential consequences of the initiating events were simulated with RELAP-3D and MELCOR/RASCAL codes to cover Level 1 through Level 3 of PRA. RAVEN and ADAPT software were used to generate Level 1 simulations with RELAP-3D and Level 2/3 simulations with MELCOR (Level 2)/RASCAL (Level 3), respectively. Example branching conditions (BCs) for SBO included AC power recovery time, valve repair failure time, reactor coolant pump leak time/break size and emergency power supply duration to a total of 9. Example BCs for LOCA included off-site power recovery time, diesel generator power recovery time, auxiliary feed water system operation time, safety relief valve failure to open upon demand, reactor coolant pump seal break time and size to a total of 21. Each RELAP-3D simulation (9,587 scenarios) was labelled OK or Core Damage based on the maximum allowed peak clad temperature (2,100oF). Each MELCOR simulation (4610 scenarios) was labeled as Bin over 10rem or Bin 0-10rem based on the dose at the site boundary. The scenarios were clustered based on the criteria above using the mean shift methodology. Classical PRA (CPRA) and DPRA results were compared to identify the ET sequences that need DPRA augmentation. Several approaches were proposed for the incorporation of these sequences into CPRA using clustering with the mean shift methodology, restructuring the CPRA ETs by adding new BCs/sequences, and using the concept of a limit surface. Procedures for decision making regarding the possible consequences of an initiating event (e.g. core damage or not, site evacuation or not) were developed using a convolutional neural network (CNN), a recurrent neural network (RNN) and a transformer neural network (TNN). The project has led to two PhD degrees, three archival journal papers and five refereed conference proceedings.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2021

Online Monitoring System for Concrete Structures Affected by Alkali-Silica Reaction

This report presents a comprehensive study of developing ultrasonic wave and acoustic emission (AE) techniques for long-term monitoring of alkali-silica reaction (ASR) development in concrete. Small, medium, and full-scale concrete specimens were cast, conditioned, and monitored for various periods, from at least one year to 2.4 years. The reactive concrete specimens contain coarse or fine reactive aggregates to study the effects of different types of reactive aggregates. Confinements were also designed to simulate the 2-dimensional confinement effects of reinforcement in the shield building of nuclear power plants. The concrete specimens were stored in a environmental chamber with high humidity and high temperature to accelerate the ASR development. The ultrasonic monitoring data shows high sensitivity to ASR development and could detect cracking initiation well before visible surface cracks occurred. However, the linear ultrasonic analysis based on wave velocity is strongly affected by temperature variation. Therefore, a nonlinear ultrasonic method was proposed to measure thermally induced nonlinear acoustic responses of concrete (thermal modulation of ultrasonic wave). The measured nonlinear acoustic parameter shows a high correlation with ASR expansion across specimens with different reactive aggregates and confinement conditions. The same conclusion was obtained from nonlinear resonance tests on small concrete prisms. Compared to the linear acoustic methods, the nonlinear tests show high sensitivities to ASR damage from internal microcracking initiation at the early stage to visible cracks at the late stage of ASR. The attributes of the thermal modulation of nonlinear ultrasonic method include high sensitivity, immunity to temperature effects, and strong correlation with ASR expansion, which demonstrate great potentials of the nonlinear ultrasonic method for diagnosis of ASR damage and prediction of concrete deterioration process. Acoustic emission is a passive sensing technique for damage assessment, and access to only one surface is needed even for thick and heavily reinforced elements such as the walls utilized for nuclear shield building. Additionally, relatively few sensors are required to monitor the progression of the damage process. Results indicate that the AE data can be related to the damage rating index, which is a petrography-based means of assessing damage due to ASR in reinforced concrete. Furthermore, AE is capable of detecting ASR damage long before surface cracking is visually noticeable. Boundary conditions play in important role in the progression of ASR damage and differences in boundary conditions are reflected in the AE data. Entropy based data assessment methods provide a means to assess the damage state, and convolutional neural network based data assessment provided a means to assess the damage state in real-time. Results indicate that artificial neural network models may be used as a means to predict volumetric expansion based on AE data.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Pulsed Thermal Tomography Nondestructive Examination of Additively Manufactured Reactor Materials and Components. Third Annual Progress Report

Additive manufacturing (AM) of high-strength corrosion resistance alloys for nuclear energy applications, such as stainless steel and Inconel, is currently based on laser powder bed fusion (LPBF) process. Some of the challenges with using LPBF method for nuclear manufacturing include the possibility of introducing pores into metallic structures. Probability of crack initiation at the pore depends on size, shape, and orientation of the defect. Pulsed Infrared Thermography Imaging (PIT) provides a capability for non-destructive evaluation (NDE) of sub-surface defects in arbitrary size structures. The PIT method is based on recording material surface temperature transients with infrared (IR) camera following thermal pulse delivered on material surface with flash light. The PIT method has advantages for NDE of actual AM structures because the method involves one-sided non-contact measurements and fast processing of large sample areas captured in one image. Following initial qualification of an AM component for deployment in a nuclear reactor, a PIT system can also be used for in-service nondestructive evaluation (NDE) applications. In this report, we describe recent progress in enhancing PIT capabilities in detecting microscopic subsurface defects in metals, and classifying shapes and orientation of pores in thermal images. For detection of microscopic defects in PIT imaging data, we have developed Spatial Temporal Denoised Thermal Source Separation (STDTSS) unsupervised machine learning (ML) image processing algorithm. We show that flat bottom hole (FBH) defects as small as 200µm in SS316 and IN718 specimens, can be detected with STDTSS algorithm. To the best of our knowledge, these are the smallest detected defects which are reported in literature. For classification of defects shapes, we have previously developed thermal tomography (TT) algorithm to obtain depth reconstructions of material defects from data cube of sequentially recorded surface temperatures. However, interpretation of TT images is non-trivial because of blurring with increasing depth. To address this challenge, we have developed a deep learning convolutional neural network (CNN) to classify size and orientation subsurface defects in simulated TT images.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Deep Learning for Fish Identification from Sonar Data: CRADA 481 [Abstract only]

To help solve the challenges of hydropower energy production related to the potential for eel injury and mortality from passage through hydropower turbines, we will develop a deep learning method for identifying migrating eels from imaging sonar. This project continues with a prior project conducted by the Pacific Northwest National Laboratory (PNNL) and the Electric Power Research Institute (EPRI) in FY2018-2019. The proposed method employs Convolution Neural Network (CNN), a powerful deep learning method for image classification, to distinguish between images of eels and non-eel moving objects. We propose to collect more laboratory data and add more existing field data to train a powerful deep learning model. In addition to eels and sticks as classified in previous studies, we will add images containing several non-eel fish species and macrophyte mats to the training data. A multi-class classification model will be developed to distinguish these objects. Object detection algorithm will be explored and developed to locate and identify multiple objects in each sonar frame. Motion analysis will be performed to track the movement of objects in sonar video clips. We will also improve the data conversion algorithm so that it can read in both DIDSON and ARIS (both are imaging sonars developed by Sound Metrics Corp) data files and convert them to images with comparably high resolution, regardless of the varying detection ranges in different environments. The developed algorithms will be packaged as a software with a graphic user interface. The software will be evaluated by external collaborators in the field. The developed framework can be generalized for automatic monitoring of fish passage and migration using other imaging sonars like ARIS and will benefit the design and operation of ecologically friendly hydroelectric projects. The developed wavelet and CNN model configuration parameters can potentially be transferred to lamprey detection in similar riverine environments.

13 HYDRO ENERGY↗
DOE OSTI2022

Analysis of Defects in Metal Additive Manufacturing with Augmented Data Generation

Laser powder bed fusion (LPBF) is a method of additive manufacturing (AM) that selectively melts and fuses together microscopic metallic powder. LPBF offers the benefit of producing custom structures out of high strength metals that can be difficult to fabricate with conventional methods. The challenge of LPBF is that 3D printed structures often have internal pores due to process flaws. Pulsed thermal tomography (PTT) is a method for reconstructing the depth profile of materials, allowing the visualization internal voids in solids. In prior work, we developed a convolutional neural network (CNN) which, having been trained on simulated 2D PTT images of subsurface elliptical defects, was able to classify the semi-major radii, semi-minor radii, and angular orientation of the best-fit ellipses in previously unseen PTT images. The unseen PTT images contained subsurface irregular defect shapes imported from scanning electron microscopy (SEM) images of metallic LPBF-printed specimens. Training the CNN on irregular defect shapes instead of on elliptical shapes would make the resulting classifications more descriptive of actual defect shapes. However, this requires a much higher volume of SEM images of material defects, which are difficult to obtain because of random occurrence of defects in LPBF. To address this challenge, we developed a generative adversarial network (GAN) to augment the existing dataset of SEM defect images. The GAN model is demonstrated to create novel yet realistic defect shapes that can be used as input for simulated PTT images to train CNN.

36 MATERIALS SCIENCE↗