Using artificial neural networks for real-time observation of the endurance state of a steel specimen under loading

Selek, Murat; Şahi̇n, Ömer Sinan; Kahramanli, Sirzat

doi:10.1016/j.eswa.2008.09.059

Cited by 10 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, none of the aforementioned techniques, including Selek et al (2009), reported the computational speed of their developed algorithms, which might be an obstacle in applying those methodologies in high volume production environments. Furthermore, it is clear that the linear subspace algorithms developed for face detection have not been fully utilized in fault detection techniques in manufacturing environments despite its success in face detection (Er et al 2005) and crack detection in bridges (Abdel-Qader et al 2006).…”

Section: Related Fault Detection Backgroundmentioning

confidence: 96%

“…One constraint in this approach is the use of magnetic particles to increase the accuracy of their algorithm, and thus, it cannot be easily generalized. Now most of the quality assurance/fault detection techniques, applied to products focus on utilizing neural networks/expert systems see Chang et al (2009), Chen et al (2009), Selek et al (2009.…”

Section: Related Fault Detection Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Real-time fault detection in manufacturing environments using face recognition techniques

Megahed

Camelio

2010

J Intell Manuf

View full text Add to dashboard Cite

New image processing techniques as well digital image capture equipment provide an opportunity for fast detection and diagnosis of quality problems in manufacturing environments compared with traditional dimensional measurement techniques. This paper proposes a new use of image processing to detect in real-time quality faults using images traditionally obtained to guide manufacturing processes. The proposed method utilizes face recognition tools to eliminate the need of specific feature detection on determining out-of-specification parts. The focus of the proposed methodology is on computational efficiency to ensure that the algorithm runs in real time in high volume manufacturing environments. The algorithm is trained with previously classified images. New images are then classified into two groups, healthy and unhealthy. This paper proposes a method that combines Discrete Cosine Transform with Fisher's Linear Discriminant Analysis to detect faults, such as cracks, directly from aluminum stamped parts.

show abstract

Section: Related Fault Detection Backgroundmentioning

confidence: 96%

Section: Related Fault Detection Backgroundmentioning

confidence: 99%

Real-time fault detection in manufacturing environments using face recognition techniques

Megahed

Camelio

2010

J Intell Manuf

View full text Add to dashboard Cite

show abstract

“…They are made up of simple processing units which are linked by weighted connections to form structures that are able to learn relationships between sets of variables. Recently ANN is the most commonly used in different aspect of science (Behzad, Asghari, Eazi, & Palhang, 2009;Bildirici & Ersin, 2009;Chauhan, Ravi, & Chandra, 2009;Das, Turkoglu, & Sengur, 2009;Duran, Rodriguez, & Consalter, 2009;Gençoglu & Cebeci, 2009;Mostafa, 2009;Paliwal & Kumar, 2009;Selek, S ßahin, & Kahramanli, 2009;Sun, Liu, Tsai, & Hsieh, 2009;Wu & Chan, 2009;Yudong & Lenan, 2009).…”

Section: Ann and Efficiencymentioning

confidence: 98%

An integrated artificial neural network algorithm for performance assessment and optimization of decision making units

Azadeh

Saberi

Anvari

2010

Expert Systems with Applications

View full text Add to dashboard Cite

“…This technique enables also the user to get recorded data for in-situ and instant damage detection. Nowadays, the developments of IRT have also enabled the scientists to investigate the fatigue of metals by using this technique [12][13][14]. Active IRT was utilized for impact damage in carbon fiber composites [15][16][17] and glass-fiber composites [18].…”

Section: Introductionmentioning

confidence: 99%

Detection of Delaminations of Laminar Composites by Infrared Thermography

Şahi̇n¹,

Selek²

2016

CBU J of Sci

Self Cite

View full text Add to dashboard Cite

The laminar composite materials may lost their bending stiffness and strength by formation of the delamination during production and service. However, these delaminations can be barely visible by the naked eye and thus the damage detection of composites materials is inspected generally in laboratory. In this study, the in situ detection of the delamination in laminar composite materials was investigated by using infrared thermography approach. First the composite materials were subjected to low velocity impacts to create arbitrary delamination. Then, these composites materials were exposed to cyclic bending loading and observed by using a thermal camera. The temperature variations caused by the friction within delaminated field have been investigated. It is shown that the delamination damages under cyclic loads cause to a serious internal friction and the delamination can be detected by infrared thermography.

show abstract

Using artificial neural networks for real-time observation of the endurance state of a steel specimen under loading

Cited by 10 publications

References 22 publications

Real-time fault detection in manufacturing environments using face recognition techniques

Real-time fault detection in manufacturing environments using face recognition techniques

An integrated artificial neural network algorithm for performance assessment and optimization of decision making units

Detection of Delaminations of Laminar Composites by Infrared Thermography

Contact Info

Product

Resources

About