Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “defect detection”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Novel Solar Panel Defect Detection Hardware and Defect Analysis Software (CRADA Final Report)

The CRADA work involved 1) the development of a machine learning software architecture to automatically detect defects within Electroluminescence images of solar panels, and 2) demonstrations of the usefulness of UV Fluorescence (UVF) defect detection for a wide variety of defect types across many different solar panel technologies with different field or environmental chamber histories.

14 SOLAR ENERGY↗
DOE OSTI2025

Novel Solar Panel Defect Detection Hardware and Defect Analysis Software (CRADA Final Report)

The CRADA work involved 1) the development of a machine learning software architecture to automatically detect defects within Electroluminescence images of solar panels, and 2) demonstrations of the usefulness of UV Fluorescence (UVF) defect detection for a wide variety of defect types across many different solar panel technologies with different field or environmental chamber histories.

14 SOLAR ENERGY↗
DOE OSTI2025

You Only Look Once v5 and Multi-Template Matching for Small-Crack Defect Detection on Metal Surfaces

This paper compares the performance of Deep Learning (DL) and multi-template matching (MTM) models for detecting small defects. DL models extract distinguishing features of objects but require a large dataset of images. In contrast, alternative computer vision techniques like MTM need a relatively small dataset. The lack of large datasets for small metal-surface defects has inhibited the adoption of automation in small-defect detection in remanufacturing settings. This motivated this preliminary study to compare template-based approaches, like MTM, with feature-based approaches, such as DL models, for small-defect detection on an initial laboratory and remanufacturing industry dataset. This study used You Only Look Once v5 (YOLOv5) as the DL model and compared its performance against the MTM model for small-crack detection. The findings of our preliminary investigation are as follows: (i) YOLOv5 demonstrated higher performance than MTM in detecting small cracks; (ii) an extra-large variant of YOLOv5 outperformed a small-size variant; (iii) the size and object variety of the data are crucial in achieving robust pre-trained weights for use in transfer learning; and (iv) enhanced image resolution contributes to precise object detection.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Towards deep computer vision for in-line defect detection in polymer electrolyte membrane fuel cell materials

Polymer Electrolyte Membrane (PEM) fuel cells are a promising source of alternative energy. However, their production is limited by a lack of well-established methods for quality control of their constituent materials like the membrane-electrode assembly during roll-to-roll manufacturing. One potential solution is the implementation of deep learning methods to detect unwanted defects through their detection in scanned images. Here we explore the detection of defects like scratches, pinholes, and scuffs in a sample dataset of PEM optical images using two deep learning algorithms: Patch Distribution Modeling (PaDiM) for unsupervised anomaly detection and Faster-RCNN for supervised object detection. Both methods achieve scores on performance metrics (ROC-AUC and PRO-AUC for PaDiM and AP for Faster-RCNN) that are comparable to their scores on benchmark datasets. These methods also have the potential to detect a wider range of defects compared to IR thermography and previous optical inspection methods. Overall, deep learning shows promise at detecting relevant defects of interest and has the potential to achieve real-time defect detection.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2025

Utilization of Data Augmentation Techniques in Automated Inspection Systems for Defect Detection in Metals With Limited Data

Accurate identification of defects on metal surfaces is of great interest to many industry sectors, such as the automotive and aerospace industries. In contrast to conventional manual inspection techniques, recent automated inspection systems employ deep learning models trained to detect defects rapidly and precisely. The development of these models often requires a substantial image dataset to acquire adequate knowledge of defect features and enhance their predictive accuracy. When data is limited, augmentation techniques are often used to improve the precision and accuracy of defect detection systems. This study examined the prediction performance of two object detection models, namely Faster Region‐based Convolutional Neural Network (Faster R‐CNN) and You Only Look Once version 8 (YOLOv8), to identify dent defects in limited images of cast iron cylinder head surfaces. The original image set contains 46 images with 563 dents. To overcome limited data availability, common image augmentation techniques along with a copy‐paste method were applied. Results show that standard augmentation improved YOLOv8 accuracy by 8.00% and average precision (AP) by 3.00%. On the other hand, the copy‐paste technique achieved a 20.00% increase in accuracy and a 1% increase in AP with just 200 synthetic dents. Furthermore, these results provide support for using the copy‐paste augmentation strategy to enhance defect detection performance, with a limited dataset, contributing to more accurate defect identification in remanufacturing processes.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Improved guided-wave acoustic defect detection and localization in pipes under varying temperature conditions using deep learning

Early defect detection in pipelines is critical across industries, particularly in the oil and gas sector, where failures result in significant maintenance costs and operational disruptions. Acoustic guided-wave techniques are widely used for nondestructive evaluation of pipeline defects due to their long-distance propagation capability. However, environmental variations, sensitivity limitations, and complex signal interpretation challenges limit the effectiveness of traditional signal processing approaches with guided-wave signals. Recent advances in deep learning methods have demonstrated remarkable success in solving complex real-world problems in many fields. In particular, deep-learning-based signal processing holds substantial promise to overcome limitations and challenges of conventional signal processing. This study presents a deep learning framework for pipeline inspection using acoustic guided-wave signals under temperature varying environments. The proposed framework employs a dual-path one-dimensional convolutional autoencoder that combines defect detection, localization, and temperature prediction functions. The proposed system utilizes multi-mode and broadband acoustic waves with an optimized number of sensors that provide high accuracy while retaining practical simplicity. Experimental validation is performed on a carbon steel pipe. The results indicate exceptional defect detection accuracy and precise defect localization with a mean absolute error of 66 mm. The proposed technique also predicts the effective average temperature of the pipe with a mean absolute error of 0.2°C. Comparative analysis shows superior performance of the proposed method over a traditional method previously developed by the authors' team. These results highlight the potential of integrating deep learning methods into guided-wave pipeline inspection systems to improve reliability under varying environmental conditions.

42 ENGINEERING↗
DOE OSTI2024

Critical Review of LPBF Metal Print Defects Detection: Roles of Selective Sensing Technology

The integrative potential of LPBF-printed parts for various innovative applications depends upon the robustness and infallibility of the part quality. Eliminating or sufficiently reducing factors contributing to the formation of defects is an integral step to achieving satisfiable part quality. Significant research efforts have been conducted to understand and quantify the triggers and origins of LPBF defects by investigating the material properties and process parameters for LPBF-printed geometries using various sensing technologies and techniques. Frequently, combinations of sensing techniques are applied to deepen the understanding of the investigated phenomena. The main objectives of this review are to cover the roles of selective sensing technologies by (1) providing a summary of LPBF metal print defects and their corresponding causes, (2) informing readers of the vast number and types of technologies and methodologies available to detect defects in LPBF-printed parts, and (3) equipping readers with publications geared towards defect detection using combinations of sensing technologies. Due to the large pool of developed sensing technology in the last few years for LPBF-printed parts that may be designed for targeting a specific defect in metal alloys, the article herein focuses on sensing technology that is common and applicable to most common defects and has been utilized in characterization for an extended period with proven efficiency and applicability to LPBF metal parts defect detection.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Acoustics-based noninvasive wafer defect detection

Techniques are provided for detecting wafer defects. Example techniques include exciting a wafer using an acoustic signal to cause the wafer to exhibit vibrations, measuring one or more of linear frequency response metrics or nonlinear frequency responses metrics associated with the vibrations, and identifying any defects in the wafer based at least in part on one or more of the linear frequency response metrics or nonlinear frequency responses metrics. In embodiments, the wafer includes bismuth telluride (Bi 2 Te 3 ).

Pantea, Cristian↗
DOE OSTI2022

Multi-scan computed tomography defect detectability

Systems and methods for representing internal defects of an object to determine defect detectability using a multi-scan computed tomography (CT) approach are disclosed. A defect-free object may be scanned using a CT machine. In one or more separate scans, phantom defects may be imaged and the resulting projections combined and reconstructed to represent internal defects. The air-normalized intensities of the object and the phantom defect may be used to represent voids and inclusions. Subtraction of materials may be represented by the quotient of the air-normalized intensities thereof, and the addition of materials may be represented by the product of the air-normalized intensities thereof. A void may be represented by subtracting a phantom defect scan from the object scan. An inclusion may be represented by creating a void, scanning an additional phantom defect, and adding the additional phantom defect in the volume created by the void.

Schiefelbein, Bryan E.↗
DOE OSTI2021

Acoustic Wafer Defect Detection System

Researchers at Los Alamos have developed the Acoustic Wafer Defect Detection System, a technology that enables rapid diagnosis of critical defects during wafer production. This technology is capable of both efficient and accurate detection of defects in wafers, including defects that are undetectable through current optical techniques. The system identifies the wafer defects by exciting resonant vibrations in the wafers and by exciting “crack breathing” modes. These vibrations cause the crack to periodically open and close. Specific resonance characteristics, combined with acoustic signatures resulting from crack breathing, result in a technique that is highly sensitive to cracked wafers. There are minimal custom parts used to build the system, and it can be easily implemented in nearly any wafer production plant with minimal modifications. We are seeking a commercialization partner to license the technology or partner through a Cooperative Research and Development Agreement (CRADA) to develop into a usable product for commercial purposes.

42 ENGINEERING↗
DOE OSTI2024

Crystalline Si Surface Passivation with Nafion for Bulk Defects Detection with Electron Paramagnetic Resonance

Here, in monocrystalline Si (c-Si) solar cells, identification and mitigation of bulk defects are crucial to achieving a high photoconversion efficiency. To spectroscopically detect defects in the c-Si bulk, it is desirable to passivate the surface defects. Passivation of the c-Si surface with dielectrics such as Al 2 O 3 and SiNx requires deposition at elevated temperatures, which can influence defects in the bulk. Herein, we report on the passivation of different Czochralski (Cz) Si wafer surfaces by an organic copolymer, Nafion. We test the efficacy of the surface passivation at temperatures ranging from 6 to 473 K to detect bulk defects using electron paramagnetic resonance (EPR) spectroscopy. By comparing with state-of-the-art passivation layers, including Al 2 O 3 and liquid HF/HCl, we found that at room temperature, Nafion can provide comparable passivation of n-type Cz Si with an implied open-circuit voltage (iV oc ) of 713 mV and a recombination current prefactor J o of 5 fA/cm 2 . For p-type Cz Si, we obtained an iV oc of 682 mV with a J o of 22.4 fA/cm 2 . Scanning electron microscopy and photoluminescence reveal that Nafion can also be used to passivate the surface of c-Si solar cell fragments scribed from a solar cell module by using a laser. Consistent with previous studies, analysis of the EPR spectroscopy data confirms that the H-terminated surface is necessary, and fixed negative charge in Nafion is responsible for the field-effect passivation. While the surface passivation quality was maintained for almost 24 h, which is sufficient for spectroscopic measurements, the passivation degraded over longer durations, which can be attributed to surface SiO x growth. These results show that Nafion is a promising room-temperature surface passivation technique to study bulk defects in c-Si.

14 SOLAR ENERGY↗
DOE OSTI2026

Infrared thermography NDT for in-situ defect detection in sandwich composite panel manufacturing

Composite manufacturing presents numerous challenges, as defects can arise from various sources throughout the process. In sandwich composite structures, the integration of a foam core introduces additional complexity and increases the likelihood of defect formation like delamination. To mitigate these issues and reduce the risk of future structural failures, in-situ monitoring during manufacturing is essential. This study investigates infrared (IR) thermography as a non-destructive technique for detecting manufacturing defects in foam-core sandwich composite panels under thermally excited conditions representative of in-situ processing. A stationary FLIR A8590 IR camera (640 × 512 pixels, 30Hz, 17mm lens, 9 ft stand-off distance) was used to monitor prefabricated panels subjected to controlled external heating simulating compression molding and resin cure exotherm. Interlaminar delamination defects with characteristic sizes ranging from 0.25 × 0.25in² to 5 × 5in² produced measurable surface temperature depressions of approximately 4–10°C during transient cooling, exceeding the effective noise floor of the camera by more than two standard deviations. Thicker laminates exhibited prolonged defect detectability windows due to increased thermal diffusion time. In contrast, embedded Teflon inclusions generated weak thermal contrasts of ≤ 3°C, approaching the measurement noise floor, due to limited thermal property contrast with the surrounding glass fiber composite. These results establish quantitative detectability limits for stationary thermographic inspection of sandwich composite panels under manufacturing-representative thermal cycles.

Barakat, Abdallah [ORNL] (ORCID:0000000296141398)↗
DOE OSTI2021

Localized Defect Detection from Spatially Mapped, In-Situ Process Data With Machine Learning

In powder bed fusion additive manufacturing, machines are often equipped with in-situ sensors to monitor the build environment as well as machine actuators and subsystems. The data from these sensors offer rich information about the consistency of the fabrication process within a build and across builds. This information may be used for process monitoring and defect detection; however, little has been done to leverage this data from the machines for more than just coarse-grained process monitoring. In this work we demonstrate how these inherently temporal data may be mapped spatially by leveraging scan path information. We then train a XGBoost machine learning model to predict localized defects—specifically soot–using only the mapped process data of builds from a laser powder bed fusion process as input features. The XGBoost model offers a feature importance metric that will help to elucidate possible relationships between the process data and observed defects. Finally, we analyze the model performance spatially and rationalize areas of greater and lesser performance.

3D printing↗
DOE OSTI2021

Defect detection in atomic-resolution images via unsupervised learning with translational invariance

Abstract Crystallographic defects can now be routinely imaged at atomic resolution with aberration-corrected scanning transmission electron microscopy (STEM) at high speed, with the potential for vast volumes of data to be acquired in relatively short times or through autonomous experiments that can continue over very long periods. Automatic detection and classification of defects in the STEM images are needed in order to handle the data in an efficient way. However, like many other tasks related to object detection and identification in artificial intelligence, it is challenging to detect and identify defects from STEM images. Furthermore, it is difficult to deal with crystal structures that have many atoms and low symmetries. Previous methods used for defect detection and classification were based on supervised learning, which requires human-labeled data. In this work, we develop an approach for defect detection with unsupervised machine learning based on a one-class support vector machine (OCSVM). We introduce two schemes of image segmentation and data preprocessing, both of which involve taking the Patterson function of each segment as inputs. We demonstrate that this method can be applied to various defects, such as point and line defects in 2D materials and twin boundaries in 3D nanocrystals.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Multi defect detection and analysis of electron microscopy images with deep learning

Electron microscopy is widely used to explore defects in crystal structures, but human detecting of defects is often time-consuming, error-prone, and unreliable, and is not scalable to large numbers of images or real-time analysis. In this work, we discuss the application of machine learning approaches to find the location and geometry of different defect clusters in irradiated steels. We show that a deep learning based Faster R-CNN analysis system has a performance comparable to human analysis with relatively small training data sets. Furthermore, this study proves the promising ability to apply deep learning to assist the development of automated microscopy data analysis even when multiple features are present and paves the way for fast, scalable, and reliable analysis systems for massive amounts of modern electron microscopy data.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Frequency domain assurance criterion for defect detection in additively manufactured parts

Additive manufacturing (AM) is a very desirable manufacturing method for industries such as aerospace and automotive due to its ability to create internal features and complex geometries, however, these characteristics also present challenges for nondestructive evaluation (NDE) and defect detection. Dynamic analysis and modal analysis have shown promise for NDE and identifying flaws in AM parts. Frequency Domain Assurance Criterion (FDAC) is a method of dynamic evaluation that represents the degree of correlation between two sets of operational deflection shapes (ODS) at each spectral line. Using colormaps to display the results allows for quick and easy interpretation of parts’ similarities and differences. This method appears to show promise in identifying parts with minor defects and can be used to differentiate nominal and defective parts. This paper explores the use of FDAC on various AM parts with and without intentional defects.

Deonarain, G↗
DOE OSTI2022

DEFECT DETECTION USING DYNAMIC ANALYSIS FOR ADDITIVE MANUFACTURED METALS

Additive manufacturing (AM) has the ability to produce parts with complex geometries and internal features, however, for demanding applications such as the automotive and aerospace industries, it is crucial that the parts can meet the demanding functional and geometric requirements. Quality control for AM parts focuses on nondestructive methods of testing, but many of the current methods are expensive and time-consuming. The research presented in this report explores various methods of nondestructive evaluation (NDE) using dynamic analysis on stainless steel parts produced with selective laser melting (SLM). Methods include, but are not limited to, frequency response functions (FRF), impedance-based measurements, and scanning laser doppler vibrometry. Additionally, mode shape analysis was performed in MATLAB and FEA simulations were used for comparison with experimental results. The results indicate that dynamic analysis has the potential to be a feasible method of defect detection and NDE in AM parts and future work should focus on refining these methods, such as optimizing test parameters to improve sensitivity to defects.

Deonarain, Gita↗