Implementing an ultrasonic inspection system to find surface and internal defects in hot, moving steel using EMATs

Baillie, Iain; Griffith, P.; Jian, X.; Dixon, S.

doi:10.1784/insi.2007.49.2.87

Cited by 25 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Real-time X-ray imaging technology is widely used in defect detection systems in industry, such as on-line weld defect inspection [5]. Ultrasonic inspection and magnetic particle inspection can also be used to measure the size and position of casting defects in cast components [6,7]. X-ray Computed Tomography (CT) can be used to visualize the internal structure of materials.…”

Section: Introductionmentioning

confidence: 99%

Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

Ferguson

Lee

et al. 2018

Smart and Sustainable Manufacturing Systems

188

View full text Add to dashboard Cite

Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based on the Mask Region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation, results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large openly-available image datasets before finetuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds state-of-the art performance on the GRIMA database of X-ray images (GDXray) Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multi-task learning, and multi-class learning influence the performance of the trained system.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

Ferguson

Lee

et al. 2018

Smart and Sustainable Manufacturing Systems

188

View full text Add to dashboard Cite

show abstract

“…They generate ultrasound directly in surface near zones of electrically conductive materials, allowing them to function without couplant and without con-Email address: r.s.edwards@warwick.ac.uk (R. S. Edwards) tacting the sample, allowing for fast scanning [2][3][4]. EMATs can be used at high temperatures, with the temperature of operation limited by the Curie temperature of the magnet needed for detection and/or any cooling mechanisms [5,6]. However, the generation mechanism is inefficient, and EMATs can suffer from low signal to noise ratios (SNR) [7].…”

Section: Introductionmentioning

confidence: 99%

The effect of EMAT coil geometry on the Rayleigh wave frequency behaviour

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The ability to inspect defects or classify them without shutdown of industry for unscheduled time is an important economic consideration, and therefore, a monitoring method with temperature compensation ability is highly desirable. Many NDT&E methods can be used for high-temperature inspection and monitoring such as laser ultrasonic [3,4], thermal infrared imaging technology [5] and laser electromagnetic acoustic transducer (EMAT) configurations [6][7][8]. However, these inspection techniques come with complexity and cost and for long-term measurements in condition monitoring applications.…”

Section: Introductionmentioning

confidence: 99%

Temperature Independent Defect Monitoring Using Passive Wireless RFID Sensing System

et al. 2019

View full text Add to dashboard Cite

A significant requirement of low-cost sensing systems for defect detection is essential to bridge the gap of non-destructive testing & evaluation (NDT&E) and structural health monitoring (SHM). In practical situation, the temperature variation will be unknown in a priori and hence will give rise to uncertainty and unreliability in the defect detection. This paper demonstrates the potential use of low frequency (LF) RFID tag antenna based wireless sensors to characterise corrosion and crack progression in high-temperature conditions for potential structural monitoring. Consideration of the parasitic parameters which depend on the temperature variation is presented. The key factors that influences the sensing accuracy with regards to different materials due to inhomogeneity are presented. A cost-effective self-compensation method is proposed by means of a self-swept frequency measurement through selection and fusion of temperature dependent feature near the tag's resonance region. The experimental work validates the effectiveness of the method in temperature compensation and some initial results demonstrate the efficiency of the technique to overcome the inhomogeneity.

show abstract

Implementing an ultrasonic inspection system to find surface and internal defects in hot, moving steel using EMATs

Cited by 25 publications

References 4 publications

Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

The effect of EMAT coil geometry on the Rayleigh wave frequency behaviour

Temperature Independent Defect Monitoring Using Passive Wireless RFID Sensing System

Contact Info

Product

Resources

About