Crack Detection in "As-Cast" Steel Using Laser Triangulation and Machine Learning

Veitch-Michaelis, Joshua; Tao, Yu; Walton, David R.; Müller, Jan-Peter; Crutchley, Benjamin; Storey, Jonathan; Paterson, Carl; Chown, A.

doi:10.1109/crv.2016.55

Cited by 12 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2016, Veitch-Michaelis et al [ 29 ] combined the principle of laser triangulation with machine learning to detect surface defects on cast steel plates. This project (high-temperature process control (HTP-C)) uses a striped laser transmitter that can emit 405 nm.…”

Section: Laser Scanning Measurement Methodsmentioning

confidence: 99%

Three-Dimensional Morphology and Size Measurement of High-Temperature Metal Components Based on Machine Vision Technology: A Review

Wen

Wang

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

The three-dimensional (3D) size and morphology of high-temperature metal components need to be measured in real time during manufacturing processes, such as forging and rolling. Since the surface temperature of a metal component is very high during the forming and manufacturing process, manually measuring the size of a metal component at a close distance is difficult; hence, a non-contact measurement technology is required to complete the measurement. Recently, machine vision technology has been developed, which is a non-contact measurement technology that only needs to capture multiple images of a measured object to obtain the 3D size and morphology information, and this technology can be used in some extreme conditions. Machine vision technology has been widely used in industrial, agricultural, military and other fields, especially fields involving various high-temperature metal components. This paper provides a comprehensive review of the application of machine vision technology in measuring the 3D size and morphology of high-temperature metal components. Furthermore, according to the principle and method of measuring equipment structures, this review highlights two aspects in detail: laser scanning measurement and multi-view stereo vision technology. Special attention is paid to each method through comparisons and analyses to provide essential technical references for subsequent researchers.

show abstract

Section: Laser Scanning Measurement Methodsmentioning

confidence: 99%

Three-Dimensional Morphology and Size Measurement of High-Temperature Metal Components Based on Machine Vision Technology: A Review

Wen

Wang

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…However, this is not applicable for processes with samples of high temperature due to the thermal emission of the molten material at this wavelength. Therefore, it is necessary to move to wavelengths where there is no significant emission, as demonstrated with a laser with a wavelength of 405 nm for crack detection in metal production [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

2D and 3D Triangulation Are Suitable In Situ Measurement Tools for High-Power Large Spot Laser Penetration Processes to Visualize Depressions and Protrusions before Perforating

et al. 2022

View full text Add to dashboard Cite

During laser penetration, the irradiated samples form a melt pool before perforation. Knowledge of the dynamics of this melt pool is of interest for the correct physical description of the process and leads to improved simulations. However, a direct investigation, especially at the location of high-power laser interaction with large spot diameters in the centimeter range is missing until now. Here, the applicability of 2D triangulation for surface topology observations is demonstrated. With the designed bidirectional 2D triangulation setup, the material cross-section is measured by profile detection at the front and back side. This allows a comprehensive description of the penetration process to be established, which is important for a detailed explanation of the process. Specific steps such as surface melting, indentations, protrusions during melt pool development and their dynamics, and the perforation are visualized, which were unknown until now. Furthermore, a scanning 3D triangulation setup is developed to obtain more information about the entire melt pool at the front side, and not just a single intersection line. The measurements exhibit a mirror-symmetric melt pool and the possibility to extrapolate from the central profile to the outer regions in most cases.

show abstract

“…ML algorithms can also be used for clustering to detect cracks on the scanned surface of steel slabs [21], where the support vector machine (SVM) was used as a classifier. In a study by Tootooni et al [22] the researchers used a novel method to invoke a spectral graph of Laplacian eigenvalues as a function derived from the laser-scanned 3D point cloud data in combination with various ML techniques.…”

Section: Introductionmentioning

confidence: 99%

Machine learning method for predicting the influence of scanning parameters on random measurement error

Urbas

Vlah

Vukašinović

2021

Meas. Sci. Technol.

View full text Add to dashboard Cite

Measurements of technical objects can be done with contact and non-contact approaches. Contact methods are accurate but slow. On the other hand, non-contact methods deliver rapid point acquisition and are increasingly being used as their precision mounts. However, multiple scanning parameters such as the incident angle, object colour and scanning distance influence the measurement error and uncertainty when capturing the geometry of the object. With the aim of creating a generalised model that considers the influence of the aforementioned scanning parameters with satisfactory accuracy, a model for predicting the random measurement error based on machine learning (ML) is proposed in this study. Data acquired from measurements with varying scanning distances, incident angles and surface colours were used to train ML models. The tested ML methods included linear regression, support vector machine, neural network, k-nearest neighbour, AdaBoost and random forest. The best-performing trained model was the random forest, with a standard deviation of relative differences of 1.46% for the case of red surfaces, and 5.2% for the case of an arbitrarily coloured surface, which is comparable to results achieved with model-based methods. The trained models and the data are available online.

show abstract

Crack Detection in "As-Cast" Steel Using Laser Triangulation and Machine Learning

Cited by 12 publications

References 20 publications

Three-Dimensional Morphology and Size Measurement of High-Temperature Metal Components Based on Machine Vision Technology: A Review

Three-Dimensional Morphology and Size Measurement of High-Temperature Metal Components Based on Machine Vision Technology: A Review

2D and 3D Triangulation Are Suitable In Situ Measurement Tools for High-Power Large Spot Laser Penetration Processes to Visualize Depressions and Protrusions before Perforating

Machine learning method for predicting the influence of scanning parameters on random measurement error

Contact Info

Product

Resources

About