Ultrasound computed tomography for material inspection: Principles, design and applications

Khairi, Mohd; Ibrahim, Suhaimi; Yunus, Mohd Amri Md; Faramarzi, Mahdi; Sean, Goh Pei; Pusppanathan, Jaysuman; Abid, Azwad

doi:10.1016/j.measurement.2019.06.053

Cited by 46 publications

(22 citation statements)

References 171 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other areas of CNN application include image classification [25], video analysis, natural language processing, city monitoring, industrial cameras and all kinds of devices providing images made with ordinary photographic techniques [44]. Creating images obtained by resolving the inverse problem, such as tomographic images, is a relatively new area of application for CNN and is therefore difficult [18,11].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Maintenance of industrial reactors supported by deep learning driven ultrasound tomography

Kłosowski

Rymarczyk

Kania

et al. 2020

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

Maintenance of industrial reactors supported by deep learning driven ultrasound toMography eksploatacja reaktorów przeMysłowych ze wspoMaganieM toMografii ultradźwiękowej i algorytMów głębokiego uczeniaMonitoring of industrial processes is an important element ensuring the proper maintenance of equipment and high level of processes reliability. The presented research concerns the application of the deep learning method in the field of ultrasound tomography (UST). A novel algorithm that uses simultaneously multiple classification convolutional neural networks (CNNs) to generate monochrome 2D images was developed. In order to meet a compromise between the number of the networks and the number of all possible outcomes of a single network, it was proposed to divide the output image into 4-pixel clusters. Therefore, the number of required CNNs has been reduced fourfold and there are 16 distinct outcomes from single network. The new algorithm was first verified using simulation data and then tested on real data. The accuracy of image reconstruction exceeded 95%. The results obtained by using the new CNN clustered algorithm were compared with five popular machine learning algorithms: shallow Artificial Neural Network, Linear Support Vector Machine, Classification Tree, Medium k-Nearest Neighbor classification and Naive Bayes. Based on this comparison, it was found that the newly developed method of multiple convolutional neural networks (MCNN) generates the highest quality images.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

Maintenance of industrial reactors supported by deep learning driven ultrasound tomography

Kłosowski

Rymarczyk

Kania

et al. 2020

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

show abstract

“…In recent years, much effort has been expended on generating material property maps non-destructively using tomographic inversion, where material properties such as wave speed, or microstructural descriptors such as grain orientation, are estimated from the scattered wave field data recorded at the surface of an object. A wide range of advanced tomographic algorithms are used across geophysics [1,2,12,40,58,67,69], bio-medicine [19] and NDE [14,37,55,56]. A common approach is to use iterative methods to improve the fit of the measured data to forward modelled data which depend on an estimate of the material map.…”

Section: Introductionmentioning

confidence: 99%

Real-time super-resolution mapping of locally anisotropic grain orientations for ultrasonic non-destructive evaluation of crystalline material

Singh

Tant

Curtis

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

Estimating the spatially varying microstructures of heterogeneous and locally anisotropic media non-destructively is necessary for the accurate detection of flaws and reliable monitoring of manufacturing processes. Conventional algorithms used for solving this inverse problem come with significant computational cost, particularly in the case of high-dimensional, nonlinear tomographic problems, and are thus not suitable for near-real-time applications. In this paper, for the first time, we propose a framework which uses deep neural networks (DNNs) with full aperture, pitch-catch and pulse-echo transducer configurations, to reconstruct material maps of crystallographic orientation. We also present the first application of generative adversarial networks (GANs) to achieve super-resolution of ultrasonic tomographic images, providing a factor-four increase in image resolution and up to a 50% increase in structural similarity. The importance of including appropriate prior knowledge in the GAN training data set to increase inversion accuracy is demonstrated: known information about the material’s structure should be represented in the training data. We show that after a computationally expensive training process, the DNNs and GANs can be used in less than 1 second (0.9 s on a standard desktop computer) to provide a high-resolution map of the material’s grain orientations, addressing the challenge of significant computational cost faced by conventional tomography algorithms.

show abstract

“…In order to inspect the internal structures of manufactured components, industrial computed tomography (ICT), ultrasonic scattering computed tomography (USCT), and laser ultrasonic testing are conventionally used in industry. [ 19–26 ] However, the resolution of ICT and USCT is about 20–300 µm such that they are typically used for defect analysis in industries such as automobiles, electronic parts, or surface welding. As a noninvasive optical inspection method, optical coherence tomography (OCT) provides micrometer resolution and penetration depth of several millimeters and has been applied in various biomedical fields.…”

Section: Introductionmentioning

confidence: 99%

High‐Sensitivity Profilometry for Measurement of Multilayer Structure with Low‐Coherence Composite Interferometer

Lin

Cheng

Hsu

2021

Adv Materials Technologies

View full text Add to dashboard Cite

High‐sensitivity profilometry provides valuable tools for measurement of the surface structure of a device. On the other hand, tomographic techniques such as ultrasound imaging or optical coherence tomography can be used to measure the inner structure of a device with micrometer resolution. However, the multilayer structure of a device such as a display panel cannot be measured with nanometer sensitivity using conventional profilometry and tomographic techniques. For this purpose, a new type of profilometry based on the technique of low‐coherence composite interferometer is proposed and demonstrated. With the phase compensation mechanism of the technique, phase fluctuation resulted from the instability of scanning component and environment can be significantly reduced and a high axial sensitivity can be achieved. The technique is demonstrated by measuring nine interfaces of a display panel with a displacement sensitivity of 11.73 nm without requiring any preknowledge on the structure and has the potential to become a new technique for inspecting the multilayer structure of a packaged device in industry.

show abstract

Ultrasound computed tomography for material inspection: Principles, design and applications

Cited by 46 publications

References 171 publications

Maintenance of industrial reactors supported by deep learning driven ultrasound tomography

Maintenance of industrial reactors supported by deep learning driven ultrasound tomography

Real-time super-resolution mapping of locally anisotropic grain orientations for ultrasonic non-destructive evaluation of crystalline material

High‐Sensitivity Profilometry for Measurement of Multilayer Structure with Low‐Coherence Composite Interferometer

Contact Info

Product

Resources

About