Tehnički vjesnik, Vol. 31 No. 2, 2024.
Izvorni znanstveni članak
https://doi.org/10.17559/TV-20231011001015
Advanced Optical Coherence Tomography for Real-Time Detection of Defects in Aluminum Alloy Laser Welding
Zhengying Jiang
; College of computer science and technology, Changchun university of science and technology, Changchun ,130022, China; College of Physics, Changchun Normal University, Changchun,130032, China
Zhengang Jiang
; College of computer science and technology, Changchun university of science and technology, Changchun ,130022, China
*
* Dopisni autor.
Sažetak
In order to measure the quality of aluminum alloy laser welding workpiece online, an optical coherence tomography on-line detection system was established. Porosity is one of the most common defects in laser welding of aluminum alloy. The porosity produced during welding will seriously affect the welding quality. Firstly, a test device of laser welding quality detection system is built based on optical coherence tomography algorithm. Then, the theoretical model of the optical coherence tomography detection system is built, and the key parameters affecting the detection device are qualitatively analyzed. Then, deep convolutional neural network algorithm is used to process the image. Finally, the testing equipment is used to test the sample, and the testing results are analyzed. The experimental results show that this method can detect the weld quality of laser welding, and the detection accuracy is 20 μm.
Ključne riječi
deep convolutional neural network; laser welding; optical coherence tomography
Hrčak ID:
314821
URI
Datum izdavanja:
29.2.2024.
Posjeta: 1.340 *