On-line detection research on manufactured sand grading based on deep learning

被引：0

作者：

Huang F. ^{[1
]}

Fang H. ^{[1
]}

Yang J. ^{[1
]}

Pan W. ^{[1
]}

机构：

[1] College of Mechanical Engineering and Automation, Huaqiao University, Xiamen

来源：

Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2022年 / 43卷 / 10期

关键词：

Deep learning; Fineness modulus; Gradation; Instance segmentation; Manufactured sand;

D O I：

10.19650/j.cnki.cjsi.J2210095

中图分类号：

学科分类号：

摘要：

The gradation and fineness modulus of manufactured sand are important quality indicators in industrial sand production. To solve the problem that the traditional method of grading detection of manufactured sand cannot be implemented online under the actual working condition. This article combines experimental research to propose an online detection method for manufactured sand grading based on deep learning. Firstly, the images of the stacked manufactured sand on the conveyor belt are collected. Then, the manufactured sand images are segmented by the convolution neural network (CNN). Finally, the gradation and fineness modulus of manufactured sand is computerized online by the image processing technology. Comparative experimental results show that the mask R-CNN instance segmentation model can effectively segment intact particles in the manufactured sand stacking scenario. The equivalent elliptical Feret short diameter is used as the equivalent particle size parameter and the area gradation is used as the gradation characterization parameter. The maximum repeatability error values of online detection of two groups of fineness modulus manufactured sand are 0.03 and 0.05. The maximum repeatability error values of particle size interval are 2.97% and 3.43%. Compared with traditional detection methods, this method is feasible and can meet the requirements of online detection in industrial sand production. © 2022, Science Press. All right reserved.

引用

页码：165 / 176

页数：11

共 26 条

[1]

CAI B, WANG R Q, YE SH Y., Comparison of dynamic image analysis, laser diffraction and sieve analysis, Charcoal Element, 1, pp. 27-34, (2018)

[2]

BAGHERI G H, BONADONNA C, MANZELLA I, Et al., On the characterization of size and shape of irregular particles, Powder Technology, 270, pp. 141-153, (2014)

[3]

HUANG Y M, WANG L H., Effect of particle shape of limestone manufactured sand and natural sand on concrete, Procedia Engineering, 210, pp. 87-92, (2017)

[4]

YANG J H, FANG H Y, CHEN S J., Development of particle size and shape measuring system for machine-made sand, Particulate Science and Technology, 37, 8, pp. 974-980, (2018)

[5]

MAITRE J, BOUCHARD K, BEDARD L P., Mineral grains recognition using computer vision and machine learning, Computers & Geosciences, 130, pp. 84-93, (2019)

[6]

CAI Y Y, FANG H Y, YU W, Et al., Digital image processing based particle size grading measurement method for machine-made sand, Journal of Huaqiao University, 40, 5, pp. 567-573, (2019)

[7]

HUANG X Y., Study on gradation measurement and compensation algorithm of manufactured sand based on dynamic image method, (2020)

[8]

LAN J H, WANG D, SHEN X P., Research progress on visual image detection based on convolutional neural network, Chinese Journal of Scientific Instrument, 41, 4, pp. 167-182, (2020)

[9]

HAMZELOO E, MASSINAEI M, MEHRSHAD N., Estimation of particle size distribution on an industrial conveyor belt using image analysis and neural networks, Powder Technology, 261, pp. 185-190, (2014)

[10]

YU N B, LIU J N, GAO L, Et al., Auto-segmentation method based on deep learning for the knee joint in MR images, Chinese Journal of Scientific Instrument, 41, 6, pp. 140-149, (2020)

← 1 2 3 →