A new classification algorithm for low concentration slurry based on machine vision
Abstract Machine vision was utilized in this study to accurately classify the low concentration slurry. Orthogonal experiment L9(34) indicated that the optimal coal slurry collection images were achieved with exposure value of 10, slurry layer thickness of 7 cm, and light intensity of 5 × 104 lux. S...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83765-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559511860510720 |
|---|---|
| author | Chuanzhen Wang Xinyi Wang Andile Khumalo Fengcheng Jiang Jintao Lv |
| author_facet | Chuanzhen Wang Xinyi Wang Andile Khumalo Fengcheng Jiang Jintao Lv |
| author_sort | Chuanzhen Wang |
| collection | DOAJ |
| description | Abstract Machine vision was utilized in this study to accurately classify the low concentration slurry. Orthogonal experiment L9(34) indicated that the optimal coal slurry collection images were achieved with exposure value of 10, slurry layer thickness of 7 cm, and light intensity of 5 × 104 lux. Subsequently, a new low concentration classification model was systematically developed, encompassing aspects such as original image acquisition, data augmentation, dataset partitioning, classification algorithm design, and model evaluation. DCGAN was employed for image generation, achieving favorable outcomes with generator learning rate set at 5 × 10− 5, discriminator at 1 × 10− 6, and iteration number at 2000. At the point, the maximum SSIM similarity reached 0.9381, and the pHash similarity was 0.9375. Results from subsequent CNN model training, with 200 iterations, the accuracy on training and validation sets was demonstrated over 95% for coal slurry concentration prediction. Further evaluation using recall, precision, and F1-score revealed CNN network model metrics: maximum recall 1.000, minimum 0.800; maximum precision 1.000, minimum 0.700; and highest F1 score 1.000, lowest 0.778. Additionally, the accuracy of this model on the test set reached as high as 94%. The findings indicated the excellent performance in low concentration detection of coal slurry throughout this study. |
| format | Article |
| id | doaj-art-a97d8203702048ac8697fcdba9392e37 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a97d8203702048ac8697fcdba9392e372025-01-05T12:27:05ZengNature PortfolioScientific Reports2045-23222024-12-0114112910.1038/s41598-024-83765-xA new classification algorithm for low concentration slurry based on machine visionChuanzhen Wang0Xinyi Wang1Andile Khumalo2Fengcheng Jiang3Jintao Lv4Anhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and TechnologyAnhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and TechnologyAnhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and TechnologyAnhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and TechnologyAnhui Engineering Research Center for Coal Clean Processing and Carbon Reduction, College of Material Science and Engineering, Anhui University of Science and TechnologyAbstract Machine vision was utilized in this study to accurately classify the low concentration slurry. Orthogonal experiment L9(34) indicated that the optimal coal slurry collection images were achieved with exposure value of 10, slurry layer thickness of 7 cm, and light intensity of 5 × 104 lux. Subsequently, a new low concentration classification model was systematically developed, encompassing aspects such as original image acquisition, data augmentation, dataset partitioning, classification algorithm design, and model evaluation. DCGAN was employed for image generation, achieving favorable outcomes with generator learning rate set at 5 × 10− 5, discriminator at 1 × 10− 6, and iteration number at 2000. At the point, the maximum SSIM similarity reached 0.9381, and the pHash similarity was 0.9375. Results from subsequent CNN model training, with 200 iterations, the accuracy on training and validation sets was demonstrated over 95% for coal slurry concentration prediction. Further evaluation using recall, precision, and F1-score revealed CNN network model metrics: maximum recall 1.000, minimum 0.800; maximum precision 1.000, minimum 0.700; and highest F1 score 1.000, lowest 0.778. Additionally, the accuracy of this model on the test set reached as high as 94%. The findings indicated the excellent performance in low concentration detection of coal slurry throughout this study.https://doi.org/10.1038/s41598-024-83765-xLow concentration classificationMachine visionConvolutional neural networksGenerative adversarial networksMineral processingCoal slurry |
| spellingShingle | Chuanzhen Wang Xinyi Wang Andile Khumalo Fengcheng Jiang Jintao Lv A new classification algorithm for low concentration slurry based on machine vision Scientific Reports Low concentration classification Machine vision Convolutional neural networks Generative adversarial networks Mineral processing Coal slurry |
| title | A new classification algorithm for low concentration slurry based on machine vision |
| title_full | A new classification algorithm for low concentration slurry based on machine vision |
| title_fullStr | A new classification algorithm for low concentration slurry based on machine vision |
| title_full_unstemmed | A new classification algorithm for low concentration slurry based on machine vision |
| title_short | A new classification algorithm for low concentration slurry based on machine vision |
| title_sort | new classification algorithm for low concentration slurry based on machine vision |
| topic | Low concentration classification Machine vision Convolutional neural networks Generative adversarial networks Mineral processing Coal slurry |
| url | https://doi.org/10.1038/s41598-024-83765-x |
| work_keys_str_mv | AT chuanzhenwang anewclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT xinyiwang anewclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT andilekhumalo anewclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT fengchengjiang anewclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT jintaolv anewclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT chuanzhenwang newclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT xinyiwang newclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT andilekhumalo newclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT fengchengjiang newclassificationalgorithmforlowconcentrationslurrybasedonmachinevision AT jintaolv newclassificationalgorithmforlowconcentrationslurrybasedonmachinevision |