Mathematical morphology approach to internal defect analysis of A356 aluminum alloy wheel hubs

Zhang, Jun‐Sheng; Hao, Lihua; Jiao, Tengyun; Que, Lusong; Wang, Mingquan

doi:10.3934/math.2020209

Cited by 5 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, researchers have done some work, such as Li [1], in order to improve the accuracy of automobile wheel hub defect image detection and recognition, an improved peak algorithm-the trend peak algorithm-was proposed to extract the wheel hub defect area and combined with the BP neural network to recognize the wheel hub defects. Zhang [2] aimed at the internal defects such as air hole and shrinkage cavity in the process of low-pressure casting of the wheel hub, a method of defect extraction based on mathematical morphology was employed, all of which belongs to the traditional recognition method's artificial design feature, so in the face of complex samples, the robustness is poor. While deep learning technology has advantages: automatic feature extraction, weight sharing, and needless image preprocessing.…”

Section: Instructionmentioning

confidence: 99%

“…In order to illustrate the structural matching between the semantic space and the feature space, we tried to minimize the pairing relationships between classes in these two spaces. Therefore, we constructed relational matrices D a for semantic descriptors and image features, and each of these elements was derived from 2 2 , where a u and a v represent semantic descriptors of seen class defects u and v respectively. The image feature relationship matrix D ϕ was built, and each element was calculated by the formula…”

Section: Structure Matching Strategymentioning

confidence: 99%

See 1 more Smart Citation

Wheel Hub Defects Image Recognition Base on Zero-Shot Learning

Sun

Wang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

In the wheel hub industry, the quality control of the product surface determines the subsequent processing, which can be realized through the hub defect image recognition based on deep learning. Although the existing methods based on deep learning have reached the level of human beings, they rely on large-scale training sets, however, these models are completely unable to cope with the situation without samples. Therefore, in this paper, a generalized zero-shot learning framework for hub defect image recognition was built. First, a reverse mapping strategy was adopted to reduce the hubness problem, then a domain adaptation measure was employed to alleviate the projection domain shift problem, and finally, a scaling calibration strategy was used to avoid the recognition preference of seen defects. The proposed model was validated using two data sets, VOC2007 and the self-built hub defect data set, and the results showed that the method performed better than the current popular methods.

show abstract

Section: Instructionmentioning

confidence: 99%

Section: Structure Matching Strategymentioning

confidence: 99%

Wheel Hub Defects Image Recognition Base on Zero-Shot Learning

Sun

Wang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The automated inspection of tire rims is generally performed using X-ray analysis or conventional image processing [ 1 , 2 , 3 ]. In the current study, we constructed an automated system to detect defects on the forged aluminum rims of electric vehicles, using deep learning and convolutional neural networks [ 4 , 5 , 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

Integration of Deep Learning Network and Robot Arm System for Rim Defect Inspection Application

Mao

Chiu

Lin

et al. 2022

Sensors

View full text Add to dashboard Cite

Automated inspection has proven to be the most effective approach to maintaining quality in industrial-scale manufacturing. This study employed the eye-in-hand architecture in conjunction with deep learning and convolutional neural networks to automate the detection of defects in forged aluminum rims for electric vehicles. RobotStudio software was used to simulate the environment and path trajectory for a camera installed on an ABB robot arm to capture 3D images of the rims. Four types of surface defects were examined: (1) dirt spots, (2) paint stains, (3) scratches, and (4) dents. Generative adversarial network (GAN) and deep convolutional generative adversarial networks (DCGAN) were used to generate additional images to expand the depth of the training dataset. We also developed a graphical user interface and software system to mark patterns associated with defects in the images. The defect detection algorithm based on YOLO algorithms made it possible to obtain results more quickly and with higher mean average precision (mAP) than that of existing methods. Experiment results demonstrated the accuracy and efficiency of the proposed system. Our developed system has been shown to be a helpful rim defective detection system for industrial applications.

show abstract

Uneven distribution of cooling rate, microstructure and mechanical properties for A356-T6 wheels fabricated by low pressure die casting

Han,

Dong,

et al. 2024

Journal of Manufacturing Processes

View full text Add to dashboard Cite

Mathematical morphology approach to internal defect analysis of A356 aluminum alloy wheel hubs

Cited by 5 publications

References 21 publications

Wheel Hub Defects Image Recognition Base on Zero-Shot Learning

Wheel Hub Defects Image Recognition Base on Zero-Shot Learning

Integration of Deep Learning Network and Robot Arm System for Rim Defect Inspection Application

Uneven distribution of cooling rate, microstructure and mechanical properties for A356-T6 wheels fabricated by low pressure die casting

Contact Info

Product

Resources

About