An aggregate gradation detection method based on multi-view information fusion

Fan, Weijun; Chen, Zeqi; Zhang, Luo; Guo, Bin

doi:10.1016/j.powtec.2021.04.019

Cited by 16 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hamzeloo 11 estimated the particle size distribution of ores on the industrial conveyor belt by using a neural network, and found that the maximum inner circle was the most suitable method to characterize the particle size. Fan 12 extracted information from five perspectives for aggregate in the process of particle falling, proposed an equivalent volume characterization method of aggregate, and converted aggregate volume into mass through the least square method, thus realizing aggregate gradation more efficiently. Wang 13 proposed a deep learning based concrete aggregate segmentation method and added a compression and excitation module in ResNeXt50 to improve feature extraction efficiency.…”

Section: Introductionmentioning

confidence: 99%

Research on aggregate grading based on deep learning

Wu¹,

Lu²,

Su³

et al. 2022

Third International Conference on Computer Science and Communication Technology (ICCSCT 2022)

View full text Add to dashboard Cite

Aggregate grading is an important link in aggregate production. Aiming at solving the problems of low efficiency of traditional artificial quality detection method and the detection accuracy affected by the subjective consciousness of the tester, combined with the method of deep learning, the intelligent grading of aggregates is realized in this paper. According to the aggregate provided by the local gravel company, 200 digital images of aggregate were taken and marked. Using FCN, DeepLabv3+, Attention-UNet, DANet, PSPNet to achieve the segmentation of aggregates. The particle size of the aggregate is calculated by drawing the minimum circumscribed circle of the aggregate, and then the aggregate is classified. The experimental results show that the method combined with deep learning has an accuracy rate of more than 95% in aggregate detection, and can accurately measure the particle size of aggregates, which is of great significance to the intelligent development of the industry.

show abstract

Section: Introductionmentioning

confidence: 99%