Wyniki wyszukiwania - BazTech

1

Non-destructive detection of ceramic ball surface defects based on improved YOLOv8

Gu Guo-Qing, Wang Han-Lei, Miao Xu-Yi, Yan Jing-Yi, Du Jian-Zhou

Metrology and Measurement Systems

|

2025

|

Vol. 32, nr 1

1--18

EN

To address issues such as severe specular reflection, low detection accuracy, and large model parameters in ceramic ball detection, an improved YOLOv8 model, named YOLOv8-AP, is proposed for ceramic ball surface defects detection. Firstly, the coaxial light source is employed to reduce the specular reflection effect and an efficient image acquisition platform is established to obtain defect samples. Additionally, various data augmentation techniques are utilized to expand the dataset, and both the ADown module and an improved Powerful-IoU loss function are introduced to optimize the YOLOv8 network, significantly enhancing the detection efficiency for small target defects. Experimental results show that the proposed improved YOLOv8-AP model can achieve a mean average precision of 96.1% for the detection of the ceramic ball surface defects, which greatly enhances the defect detection accuracy compared to the traditional models and can hope to meet the intelligent and automatic detection requirements of ceramic ball detection online applications.

2

Crack detection of high-strength wind turbine bolts based on fiber bragg grating sensors

Chen Yu-Tao, Zhou Peng, Chen Li-Yun, Gu Guo-Qing, Dai Li-Ya, Wang Yong-Qing

Metrology and Measurement Systems

|

2024

|

Vol. 31, nr 3

511--528

EN

With the rapid development of the wind energy industry, there is an increasing concern about operation safety and reliability of high-strength wind turbine bolts. The aim of this paper is to monitor the strain change around the cracks in wind turbine bolts by means of fiber Bragg grating (FBG) sensors for crack detection. Firstly, the strain distributions of wind turbine bolts’ cracks with different locations and angles in the service condition are simulated using finite element analysis (FEA). Then, three-point grating string FBG sensors were pasted on the surface of wind turbine bolts with fatigue cracks to monitor the strain changes around the cracks in real time. By analysing the monitored strain data elaborately, the location of the crack on the bolt surface was successfully detected by identifying the location of the maximum strain detected by FBG sensors. In addition, the strain distributions in the vicinity area of the crack at different angles (0˚, 45˚ and 90˚) were also monitored and analysed in depth. The different types of crack angles could be distinguished based on of different strain distribution of the vicinity of the crack tip at different angles. The experimental results show that the FBG sensing technology has a high degree of sensitivity and accuracy in crack detection of high-strength wind turbine bolts.

3

Non-destructive detection of high-strength wind turbine bolt looseness using digital image correlation

Xie Wei-Guo, Zhou Peng, Chen Li-Yun, Gu Guo-Qing, Wang Yong-Qing, Chen Yu-Tao

Metrology and Measurement Systems

|

2023

|

Vol. 30, nr 4

839--850

EN

Looseness of high-strength wind turbine bolts is one of the main types of mechanical failure that threaten the quality and safety of wind turbines, and how to non-destructively detect bolt loosening is essential to accurate assessment of operational reliability of wind turbine structures. Therefore, to address the issue of looseness detection of high-strength wind turbine bolts, this paper proposes a non-destructive detection method based on digital image correlation (DIC). Firstly, the mathematical relationships between the in-plane displacement component of the bolt’s nut surface, the bolt’s preload force loss and the bolt loosening angle are both deduced theoretically. Then, experimental measurements are respectively conducted with DIC with different small bolt loosening angles. The results show that the bolt loosening angle detection method based on DIC has a detection accuracy of over 95%, and the bolt’s preload force loss evaluated by the deduced relationship has a good agreement with the empirical value. Therefore, the proposed DIC-based bolt loosening angle detection method can meet the requirements of engineering inspection, and can achieve quantitative assessment of preload forces loss of wind turbine bolt.

4

Flexible-elastic deformation measurement of ZnS:Cu2+ mechanoluminescent film using visual inspection and digital image correlation

Gu Guo-Qing, Xu Gui-Zhong, Shen Feng, Zhou Peng, Sun Hou-Chao, Weng Jia-Xing

Metrology and Measurement Systems

|

2023

|

Vol. 30, nr 2

353--365

EN

ZnS-based mechanoluminescent film has been widely used in the fields of stress visualization and stress sensing, due to its high brightness and repeatable stable luminescent characteristics. To evaluate the flexible-elastic deformation performance of ZnS-based mechanoluminescent film, both visual inspection and digital image correlation (DIC) are, respectively, employed for measuring the ZnS-based mechanoluminescent film. ZnS:Cu2+ mechanoluminescent powders are first mixed with polydimethylsiloxane (PDMS) matrix to produce ZnS:Cu2+-PDMS mechanoluminescent film. Then, two measurement experiments are, respectively, conducted to investigate the mechanical response and the flexible-elastic deformation performance of the prepared ZnS:Cu2+-PDMS mechanoluminescent film. On one hand, the mechanical response performance of the ZnS:Cu2+-PDMS mechanoluminescent film is validated by visual monitoring of composite concrete fracture processes. On the other hand, the prepared ZnS:Cu2+-PDMS mechanoluminescent film is also measured by DIC to obtain its full-field deformations and strains information. The flexible-elastic deformation performance of the ZnS:Cu2+-PDMS mechanoluminescent film is well demonstrated by the DIC measured results.