☆ 4.6 Article

Improving Ultrasonic Testing by Using Machine Learning Framework Based on Model Interpretation Strategy

CHINESE JOURNAL OF MECHANICAL ENGINEERING (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Multidisciplinary

Bearing fault diagnosis and prognosis using data fusion based feature extraction and feature selection

Sandaram Buchaiah et al.

Summary: This paper presents a method for extracting significant features from bearing vibration data through data fusion and dimensionality reduction techniques. The accuracy of fault diagnosis is verified using the Random Forest method and Support Vector Machine. A new index is proposed for selecting the suitable prognosis health indicator, and the remaining useful life of bearing is predicted using the Long Short-Term Memory technique.

MEASUREMENT (2022)

添加到收藏夹

Article Engineering, Mechanical

Simplified Matrix Focusing Imaging Algorithm for Ultrasonic Nondestructive Testing

Xinyu Zhao et al.

Summary: The advantages and limitations of the full matrix focusing method of ultrasonic phased array in Ultrasonic NDT are discussed in this paper. Two simplified matrix focusing methods, the triangular matrix focusing algorithm and the trapezoidal matrix focusing algorithm, are proposed to address the problem of time-consuming data acquisition and processing. Experimental results show that both algorithms significantly improve the imaging quality and efficiency compared to the original full matrix focusing method.

CHINESE JOURNAL OF MECHANICAL ENGINEERING (2022)

添加到收藏夹

Article Acoustics

Deep learning inversion with supervision: A rapid and cascaded imaging technique

Junkai Tong et al.

Summary: In this article, a new deep learning inversion method called DLIS is proposed and applied for corrosion mapping. The results show that DLIS can effectively reduce the scale of training set and provide reliable reconstruction accuracy when dealing with multiple defects of complex shape.

ULTRASONICS (2022)

添加到收藏夹

Article Engineering, Mechanical

Resolution Enhancement in Ultrasonic TOFD Imaging by Combining Sparse Deconvolution and Synthetic Aperture Focusing Technique (Sparse-SAFT)

Xu Sun et al.

Summary: In this paper, Sparse-SAFT is proposed to improve the time resolution and lateral resolution in ultrasonic time-of-flight diffraction (TOFD) imaging. The method combines sparse deconvolution and synthetic aperture focusing technique (SAFT). Simulated and experimental results show that Sparse-SAFT can effectively decouple lateral waves and tip-diffracted waves, and quantitatively detect shallow subsurface defects.

CHINESE JOURNAL OF MECHANICAL ENGINEERING (2022)

添加到收藏夹

Review Acoustics

A review of ultrasonic sensing and machine learning methods to monitor industrial processes

Alexander L. Bowler et al.

Summary: This article introduces the implementation and application of combining ultrasonic measurements with machine learning techniques for industrial process monitoring. It also reviews relevant literature and emphasizes key issues in the implementation process, such as feature extraction, algorithm selection, and hyperparameter selection.

ULTRASONICS (2022)

添加到收藏夹

Article Engineering, Mechanical

Modeling and Experimental Analysis of Roughness Effect on Ultrasonic Nondestructive Evaluation of Micro-crack

Zhe Wang et al.

Summary: A high-precision evaluation of ultrasonic detection sensitivity for a micro-crack can be constrained by a corroded rough surface if the surface microtopography is similar to the crack depth. In this study, a back-surface micro-crack is studied using a roughness-modified ultrasonic testing model, showing that the echo signal amplitude of the micro-crack decreases significantly with an increase in roughness, while noise amplitude slightly increases. The effect of rough front surface on the echo signal of the micro-crack is greater than that of rough back surface.

CHINESE JOURNAL OF MECHANICAL ENGINEERING (2021)

添加到收藏夹

Article Construction & Building Technology

Wood hole-damage detection and classification via contact ultrasonic testing

Mohsen Mousavi et al.

Summary: This study investigated hole-defect classification in hard and soft wood using a naive Bayes classification technique based on contact ultrasonic tests conducted in different directions. By implementing 50 replicates of each test and utilizing the Variational Mode Decomposition (VMD) algorithm, features from the ultrasonic signals were derived for classification, resulting in nearly 100% 10-fold cross-validation accuracy. However, when cases from different wood types and test directions were mixed, a 93.6% accuracy was achieved using a kernel naive Bayes classifier with a mixture of features.

CONSTRUCTION AND BUILDING MATERIALS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Multi-source data fusion for economic data analysis

Menggang Li et al.

Summary: This paper proposes an economic data analysis and prediction method based on machine learning, which uses convolutional auto-encoder and extreme gradient boosting algorithms to improve the prediction accuracy of economic development and effectively integrate multi-source data to achieve predictive goals.

NEURAL COMPUTING & APPLICATIONS (2021)

添加到收藏夹

Article Acoustics

Enhancement of Time Resolution in Ultrasonic Time-of-Flight Diffraction Technique With Frequency-Domain Sparsity-Decomposability Inversion (FDSDI) Method

Xu Sun et al.

Summary: This study introduces a frequency-domain sparsity-decomposability inversion method to enhance the time resolution in ultrasonic time-of-flight diffraction (TOFD) technique. By formulating an optimization problem with l(1)- and l(2)-norm constraints in the frequency domain, the method successfully improves the detection of shallow subsurface defects in simulations and experiments with high accuracy and feasibility.

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL (2021)

添加到收藏夹

Article Acoustics

Ultrasonic Defect Characterization Using the Scattering Matrix: A Performance Comparison Study of Bayesian Inversion and Machine Learning Schemas

Long Bai et al.

Summary: Characterizing small surface-breaking notches can be achieved using two approaches: one based on a general coherent noise model within a Bayesian framework, and the other relying on supervised machine learning with a scattering matrix database. Convolutional neural networks (CNNs) show the best characterization accuracy among the machine learning approaches, and have similar characterization uncertainty to the Bayesian approach for favorably oriented notches. The performance of both approaches varies for unfavorably oriented notches, with the machine learning approach showing higher variance and lower biases.

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL (2021)

添加到收藏夹

Article Engineering, Manufacturing

Online tool condition monitoring for ultrasonic metal welding via sensor fusion and machine learning

Qasim Nazir et al.

Summary: This paper presents a completely online tool condition monitoring system for ultrasonic metal welding using sensor fusion and machine learning techniques. The system not only provides real-time monitoring for UMW tools, but also supports optimal maintenance decisions and can predict the remaining life of tools.

JOURNAL OF MANUFACTURING PROCESSES (2021)

添加到收藏夹

Article Materials Science, Characterization & Testing

Reduction of Layered Dead Zone in Time-of-Flight Diffraction (TOFD) for Pipeline with Spectrum Analysis Method

S. J. Jin et al.

Summary: This paper presents a quantitative flaw depth detection method based on spectrum analysis in TOFD B-scan, which reduces the dead zone in the pipeline effectively and maintains the relative quantitative error of flaw depths within 11%. Additionally, the formation mechanism of extreme values for the tip-diffracted waves in B-scan image is discussed through theoretical analysis.

JOURNAL OF NONDESTRUCTIVE EVALUATION (2021)

添加到收藏夹

Article Materials Science, Characterization & Testing

Automatic Recognition and Positioning of Wheel Defects in Ultrasonic B-Scan Image Using Artificial Neural Network and Image Processing

Meng Yuan et al.

JOURNAL OF TESTING AND EVALUATION (2020)

添加到收藏夹

Article Acoustics

Segmented analysis of time-of-flight diffraction ultrasound for flaw detection in welded steel plates using extreme learning machines

Lucas C. Silva et al.

ULTRASONICS (2020)

添加到收藏夹

Article Biochemistry & Molecular Biology

Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions

Raquel Rodriguez-Perez et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2020)

添加到收藏夹

Article Materials Science, Characterization & Testing

Feature extraction of wood-hole defects using empirical mode decomposition of ultrasonic signals

Mohsen Mousavi et al.

NDT & E INTERNATIONAL (2020)

添加到收藏夹

Article Green & Sustainable Science & Technology

Machine learning method for energy consumption prediction of ships in port considering green ports

Yun Peng et al.

JOURNAL OF CLEANER PRODUCTION (2020)

添加到收藏夹

Article Materials Science, Characterization & Testing

An Improved Ultrasonic Imaging Method for Austenitic Welds Based on Grain Orientation Distribution Inversion Algorithm

Haipeng Zhou et al.

JOURNAL OF NONDESTRUCTIVE EVALUATION (2020)

添加到收藏夹

Article Acoustics

An Inverse Approach for Ultrasonic Imaging From Full Matrix Capture Data: Application to Resolution Enhancement in NDT

Nans Laroche et al.

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL (2020)

添加到收藏夹

Article Environmental Sciences

Crop Classification Method Based on Optimal Feature Selection and Hybrid CNN-RF Networks for Multi-Temporal Remote Sensing Imagery

Shuting Yang et al.

REMOTE SENSING (2020)

添加到收藏夹

Article Environmental Sciences

Comparative evaluation of machine learning models for groundwater quality assessment

Shine Bedi et al.

ENVIRONMENTAL MONITORING AND ASSESSMENT (2020)

添加到收藏夹

Article Acoustics

Axial super-resolution in ultrasound imaging with application to non-destructive evaluation

Saurav K. Shastri et al.

ULTRASONICS (2020)

添加到收藏夹

Article Materials Science, Characterization & Testing

Quantitative evaluation of crack depths and angles for pulsed eddy current non-destructive testing

Faris Nafiah et al.

NDT & E INTERNATIONAL (2019)

添加到收藏夹

Article Acoustics

Enhancing ultrasonic time-of-flight diffraction measurement through an adaptive deconvolution method

Jian Chen et al.

ULTRASONICS (2019)

添加到收藏夹

Article Geochemistry & Geophysics

CNN-Based Polarimetric Decomposition Feature Selection for PolSAR Image Classification

Chen Yang et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

添加到收藏夹

Article Materials Science, Characterization & Testing

System identification-based frequency domain feature extraction for defect detection and characterization

Ping Li et al.

NDT & E INTERNATIONAL (2018)

添加到收藏夹

Article Automation & Control Systems

Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network

Jing Liu et al.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks

Min Meng et al.

NEUROCOMPUTING (2017)

添加到收藏夹

Article Computer Science, Information Systems

Data Mining and Analytics in the Process Industry: The Role of Machine Learning

Zhiqiang Ge et al.

IEEE ACCESS (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Study of image retrieval and classification based on adaptive features using genetic algorithm feature selection

Chuen-Horng Lin et al.

EXPERT SYSTEMS WITH APPLICATIONS (2014)

添加到收藏夹

Article Acoustics

A comparison between ultrasonic array beamforming and super resolution imaging algorithms for non-destructive evaluation

Chengguang Fan et al.

ULTRASONICS (2014)

添加到收藏夹

Article Materials Science, Characterization & Testing

High resolution non-destructive evaluation of defects using artificial neural networks and wavelets

S. J. Farley et al.

NDT & E INTERNATIONAL (2012)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Feature selection for high-dimensional machinery fault diagnosis data using multiple models and Radial Basis Function networks

Kui Zhang et al.

NEUROCOMPUTING (2011)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Feature selection using factor analysis for Alzheimer's diagnosis using 18F-FDG PET images

D. Salas-Gonzalez et al.

MEDICAL PHYSICS (2010)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Feature subset selection in large dimensionality domains

Iffat A. Gheyas et al.

PATTERN RECOGNITION (2010)

添加到收藏夹

Article Statistics & Probability

Principal component analysis

Herve Abdi et al.

WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS (2010)

添加到收藏夹

Article Acoustics

Improving the time-resolution and signal-to-noise ratio of ultrasonic NDE signals

F Honarvar et al.

ULTRASONICS (2004)

添加到收藏夹

Article Automation & Control Systems

Statistical process monitoring with independent component analysis

JM Lee et al.

JOURNAL OF PROCESS CONTROL (2004)

添加到收藏夹

Article Engineering, Electrical & Electronic

Backward sequential elimination for sparse vector subset selection

SF Cotter et al.

SIGNAL PROCESSING (2001)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.