Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors

Saludes-Rodil, Sergio; Baeyens, Enrique; Rodríguez-Juan, Carlos P.

doi:10.3390/s150510100

Cited by 10 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of a combination of clustering algorithms with another method also became more frequent. The new method using the K-means clustering algorithm in combination with a self-organising map was used by Saludes-Rodil (2015) for the classification of surface defects in wire rod production. Yusof et al (2018) in his research applied the principle component analysis (PCA) as a pre-processing method for hierarchical clustering analysis on the frequency spectrum of the vibration signal.…”

Section: Data Mining Application For Defect Detectionmentioning

confidence: 99%

Early Defect Detection Using Clustering Algorithms

Bártová¹,

Bína²

2019

AOP

View full text Add to dashboard Cite

Product quality is a crucial issue for manufacturing companies, so it is essential to take note of any emerging product defects. In contrast to the use of traditional methods, the "modern" constantly evolving data mining methods are now being more frequently used. The main objective of this paper is to detect the potential cause or the area of the production process where the majority of product defects arise. The dataset from the semiconductor manufacturing process has been used for this purpose. First, it was necessary to address dataset quality. Significant multicollinearity was found in the data and to detect and delete the collinear variables, correlations and variance inflation factors have been used. The MICE-CART method has been used for the imputation because the original dataset contained more than 5% of random missing values. In further analysis, the K-means clustering method has been used to separate the failed products from the flawless ones. Following this, the hierarchical clustering method has been used for the failed product to create groups of product defects with similar properties. For the optimal number of clusters, the determination of the BIC method has been used. Five clusters of products have been made although only three can be classed as important for further analysis. These groups of products should be directly subjected to the analysis in the production process, which can assist in identifying the source of scarcity.

show abstract

Section: Data Mining Application For Defect Detectionmentioning

confidence: 99%

Early Defect Detection Using Clustering Algorithms

Bártová¹,

Bína²

2019

AOP

View full text Add to dashboard Cite

show abstract

“…The fatigue characteristic of the wire was significantly impacted by the presence of micro-defects when wires used. In a test conducted using wire rod specimens with surface defects, the behavior of steel wire was analyzed in terms of fatigue, where the presence of micro surface defects caused early wire breakage [15]. Other research efforts focused on the causes of fatigue in wire materials.…”

Section: Introductionmentioning

confidence: 99%

Detection, Verification and Analysis of Micro Surface Defects in Steel Filament Using Eddy Current Principles, Scanning Electron Microscopy and Energy-Dispersive Spectroscopy

Tran,

Shirinzadeh,

Ehrampoosh

et al. 2023

Sensors

View full text Add to dashboard Cite

In the current industrial revolution, advanced technologies and methods can be effectively utilized for the detection and verification of defects in high-speed steel filament production. This paper introduces an innovative methodology for the precise detection and verification of micro surface defects found in steel filaments through the application of the Eddy current principle. Permanent magnets are employed to generate a magnetic field with a high frequency surrounding a coil of sensors positioned at the filament’s output end. The sensor’s capacity to detect defects is validated through a meticulous rewinding process, followed by a thorough analysis involving scanning electron microscopy (SEM) and energy-dispersive spectroscopy (EDS). Artificial defects were intentionally introduced into a sample, and their amplitudes were monitored to establish a threshold value. The amplitude signal of these created defect was identified at approximately 10% FSH, which corresponds to a crack depth of about 20 µm. In the experimental production of 182 samples covering 38 km, the defect ratio was notably high, standing at 26.37%. These defects appeared randomly along the length of the samples. The verification results underscore the exceptional precision achieved in the detection of micro surface defects within steel filaments. These defects were primarily characterized by longitudinal scratches and inclusions containing physical tungsten carbide.

show abstract

“…The network model is directly applied instead of improving the network based on the actual defects of the steel strips, causing that the applicability of the YOLO network is low [9]. In addition, some other deep learning network models have also been used in the field of steel strip surface defect detection, such as CNN [10][11][12][13], Pyramid Feature Fusion and Global Context Attention Network (PGA-Net) [14], and semi-supervised convolutional neural network [15,16], generating a certain effect.…”

Section: Introductionmentioning

confidence: 99%

Surface defect detection of steel strips based on classification priority YOLOv3-dense network

Zhang

Kang

et al. 2020

Ironmaking & Steelmaking

View full text Add to dashboard Cite

The steel strip is an essential raw material in the machinery industry. Besides, the surface defects of the steel strip directly determine its performance. To achieve rapid and effective detection of the defects, a CP-YOLOv3-dense (classification priority YOLOv3 DenseNet) neural network was proposed in the present study. The model used YOLOv3 as basic network, implemented priority classification on the images, and then replaced the two residual network modules with two dense network modules. Therefore, the network can receive the multi-layer convolution features output by the dense connection block before making predictions, consequently enhancing the reuse and fusion of features. Finally, the six kinds of surface defects were detected by the improved network. According to the results, the detection precision of the CP-YOLOv3-dense network is 85.7%, the recall rate is 82.3%, the mean average precision is 82.73%, and the detection time of each image is 9.68 ms.

show abstract

Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors

Cited by 10 publications

References 20 publications

Early Defect Detection Using Clustering Algorithms

Early Defect Detection Using Clustering Algorithms

Detection, Verification and Analysis of Micro Surface Defects in Steel Filament Using Eddy Current Principles, Scanning Electron Microscopy and Energy-Dispersive Spectroscopy

Surface defect detection of steel strips based on classification priority YOLOv3-dense network

Contact Info

Product

Resources

About