Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Machine learning for ultrasonic nondestructive examination of welding defects: A systematic review

Journal Article · · Ultrasonics
 [1];  [1];  [2]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  2. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
+ Show Author Affiliations

Recent years have seen a substantial increase in the application of machine learning (ML) for automated analysis of nondestructive examination (NDE) data. One of the applications of interest is the use of ML for the analysis of data from in-service inspection of welds in nuclear power and other industries. These types of inspections are performed in accordance with criteria described in the ASME Boiler and Pressure Vessel Code and require the use of reliable NDE techniques. The rapid growth in ML methods and the diversity of possible approaches indicate a need to assess the current capabilities of ML and automated data analysis for NDE and identify any gaps or shortcomings in current ML technologies as applied to the automated analysis of NDE data. In particular, there is a need to determine the impact of ML on the NDE reliability. This paper discusses the findings from a literature survey on the current state of ML for the automated analysis of data from ultrasonic NDE of weld flaws. It discusses an overview of ultrasonic NDE as used for weld inspections in nuclear power and other industries. Herein, data sets and ML models used in the literature are summarized, along with a generally applicable workflow for ML. Findings on the capabilities, limitations and potential gaps in feature selection, data selection, and ML model optimization are discussed. The paper identified several needs for quantifying and validating the performance of ML methods for ultrasonic NDE, including the need for common data sets.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE; USNRC
Grant/Contract Number:
AC05-00OR22725
OSTI ID:
1892427
Alternate ID(s):
OSTI ID: 1896703
Journal Information:
Ultrasonics, Journal Name: Ultrasonics Journal Issue: 1 Vol. 127; ISSN 0041-624X
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (83)

Ultrasonic flaw classification in weldments using probabilistic neural networks journal June 1992
Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network journal October 2016
Sample size selection in optimization methods for machine learning journal June 2012
Pattern Recognition of Weld Defects in Preprocessed TOFD Signals Using Linear Classifiers journal December 2004
Automatic Defect Classification in Ultrasonic NDT Using Artificial Intelligence journal December 2010
Hybrid Ultrasonic TOFD Imaging of Weld Flaws Using Wavelet Transforms and Image Registration journal March 2018
Welding Defect Classification from Simulated Ultrasonic Signals journal May 2018
Performance Based Modifications of Random Forest to Perform Automated Defect Detection for Fluorescent Penetrant Inspection journal March 2019
Augmented Ultrasonic Data for Machine Learning journal January 2021
The Effect of Different Flaw Data to Machine Learning Powered Ultrasonic Inspection journal February 2021
Automated Defect Recognition for Welds Using Simulation Assisted TFM Imaging with Artificial Intelligence journal February 2021
Machine Learning Algorithms in Civil Structural Health Monitoring: A Systematic Review journal July 2020
Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments journal July 2018
Silhouettes: A graphical aid to the interpretation and validation of cluster analysis journal November 1987
Neural network classification of flaws detected by ultrasonic means journal April 1996
Development of an intelligent system for ultrasonic flaw classification in weldments journal March 2002
The use of neural networks in ultrasonic flaw detection journal March 1999
Review on automated condition assessment of pipelines with machine learning journal August 2022
Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products journal September 2006
A survey on feature selection methods journal January 2014
Embedded decision support system for ultrasound nondestructive evaluation based on extreme learning machines journal March 2021
Automatic microstructural characterization and classification using artificial intelligence techniques on ultrasound signals journal June 2013
Evaluation on defect in the weld of stainless steel materials using nondestructive technique journal October 2014
Acoustic emission method for defect detection and identification in carbon steel welded joints journal July 2017
Random forest-based real-time defect detection of Al alloy in robotic arc welding using optical spectrum journal June 2019
Applications of ultrasonic testing and machine learning methods to predict the static & fatigue behavior of spot-welded joints journal April 2020
A tutorial on deep learning-based data analytics in manufacturing through a welding case study journal March 2021
Artificial neural networks for quality control by ultrasonic testing in resistance spot welding journal March 2007
Assessment of resistance spot welding quality based on ultrasonic testing and tree-based techniques journal November 2014
Monitoring of friction stir welding based on vision system coupled with Machine learning algorithm journal October 2019
MFL signals and artificial neural networks applied to detection and classification of pipe weld defects journal December 2006
An alternative Ultrasonic Time of Flight Diffraction (TOFD) method journal December 2018
Automated defect detection for Fluorescent Penetrant Inspection using Random Forest journal January 2019
Visual inspection and characterization of external corrosion in pipelines using deep neural network journal October 2019
Automated defect classification in infrared thermography based on a neural network journal October 2019
Temporal and spatial deep learning network for infrared thermal defect detection journal December 2019
Performance enhancement of convolutional neural network for ultrasonic flaw classification by adopting autoencoder journal April 2020
Defects identification using the improved ultrasonic measurement model and support vector machines journal April 2020
Feature selection in machine learning: A new perspective journal July 2018
A novel hybrid CNN–SVM classifier for recognizing handwritten digits journal April 2012
A novel ensemble method for classifying imbalanced data journal May 2015
Identification of weld geometry from ultrasound scan data using deep learning journal January 2021
An improved automated ultrasonic NDE system by wavelet and neuron networks journal April 2004
Active incremental Support Vector Machine for oil and gas pipeline defects prediction system using long range ultrasonic transducers journal August 2014
Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing journal January 2017
Measurement of weld penetration depths in thin structures using transmission coefficients of laser-generated Lamb waves and neural network journal July 2017
Classification of spot-welded joint strength using ultrasonic signal time-frequency features and PSO-SVM method journal January 2019
Carburization level identification in industrial HP pipes using ultrasonic evaluation and machine learning journal April 2019
Convolutional neural network for ultrasonic weldment flaw classification in noisy conditions journal April 2019
Segmented analysis of time-of-flight diffraction ultrasound for flaw detection in welded steel plates using extreme learning machines journal March 2020
Towards using convolutional neural network to locate, identify and size defects in phased array ultrasonic testing journal August 2021
Ultrasonic signal enhancement for coarse grain materials by machine learning analysis journal December 2021
A review of ultrasonic sensing and machine learning methods to monitor industrial processes journal August 2022
A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load journal February 2018
Detection and assessment of flaws in friction stir welded joints using ultrasonic guided waves: experimental and finite element analysis journal February 2018
Detection of damage in welded joints using high order feature guided ultrasonic waves journal July 2019
The FAIR Guiding Principles for scientific data management and stewardship journal March 2016
Ultrasonic signal denoising based on autoencoder journal April 2020
A support vector machine approach for classification of welding defects from ultrasonic signals journal April 2014
Development of an ultrasonic weld inspection system based on image processing and neural networks journal September 2017
Estimating Dataset Size Requirements for Classifying DNA Microarray Data journal April 2003
Neural classification of Lamb wave ultrasonic weld testing signals using wavelet coefficients journal June 2001
Frequency invariant classification of ultrasonic weld inspection signals journal May 1998
Laser Welding Quality Monitoring via Graph Support Vector Machine With Data Adaptive Kernel journal January 2019
A Deep Learning-Based Ultrasonic Pattern Recognition Method for Inspecting Girth Weld Cracking of Gas Pipeline journal July 2020
NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion journal May 2018
A Cluster Separation Measure journal April 1979
An incremental learning algorithm with confidence estimation for automated identification of NDE signals journal August 2004
Overview of the Impact of Ultrasonic Examination Performance Demonstration on the ASME Boiler and Pressure Vessel Code journal July 2002
Deep Learning Techniques for Flaw Characterization in Weld Pieces from Ultrasonic Signals journal October 2020
How Large a Training Set is Needed to Develop a Classifier for Microarray Data? journal January 2008
Guided wave–based condition assessment of in situ timber utility poles using machine learning algorithms journal February 2014
Predicting sample size required for classification performance journal February 2012
Machine learning algorithm validation with a limited sample size journal November 2019
Classification of ultrasonic signals journal January 2006
Automatic Recognition of Weld Defects in TOFD D-Scan Images Based on Faster R-CNN journal August 2018
The use of artificial neural network in the classification of pulse-echo and TOFD ultra-sonic signals journal December 2005
Automatic classification of welding defects from ultrasonic signals using an SVM-based RBF neural network approach journal April 2018
Ultrasonic Noise Sources in a Work Environment journal June 2013
Performance Evaluation of Neural Network Based Pulse-Echo Weld Defect Classifiers journal January 2012
System Invariant Method for Ultrasonic Flaw Classification in Weldments Using Residual Neural Network journal January 2022
Deep Learning-Based Classification of Weld Surface Defects journal August 2019
Vision-Based Corrosion Detection Assisted by a Micro-Aerial Vehicle in a Vessel Inspection Application journal December 2016

Similar Records

An Assessment of Machine Learning Applied to Ultrasonic Nondestructive Evaluation
Technical Report · Thu Nov 30 23:00:00 EST 2023 · OSTI ID:2320378
Evaluation of Machine Learning Models for Automated Data Analysis in In-Service Nuclear Power Plant Inspections
Other · Tue Jun 24 00:00:00 EDT 2025 · OSTI ID:2571749

Related Subjects

36 MATERIALS SCIENCE
Machine learning
Model performance
Nondestructive examination
Ultrasound
Welding defect