Abstract
In an iron ore pelletization plant, pellets are produced inside a rotating disc pelletizer. Online pellet size distribution is an important performance indicator of the pelletization process. Image processing-based system is an effective solution for online size analysis of iron ore pellets. This paper proposes a machine learning algorithm for estimating the size class of the pellets during their production by imaging from an area inside the disc pelletizer. Instead of computing the size of each individual pellets in the acquired image, this method proposes a qualitative approach to get the overall size estimate of the pellets in production. The key idea of this paper is to find out whether the disc is producing VERY SMALL, SMALL, MEDIUM, or BIG-sized pellets. A weighted average ensemble of different convolutional neural networks such as VGG16, Mobilenet, and Resnet50 is used to achieve this objective. Furthermore, batch normalization is applied to improve the estimation performance of the proposed model. A novel data augmentation method is applied to the in situ captured images to create the data set used to train and evaluate the proposed ensemble of CNN models. Results of experiments indicate that it is possible to detect the operating state of the pelletization disc by acquiring images from the inside area of the disc with sufficient accuracy.
Similar content being viewed by others
Code availability
The image dataset used for training and evaluation of the proposed model and the source codes are available at https://bit.ly/3b4eTQ4.
References
Kawatra SK, Claremboux V (2021) Iron Ore Pelletization: Part I. fundamentals. Miner Process Extr Metall Rev. https://doi.org/10.1080/08827508.2021.1897586
de Moraes SL, de Lima JRB, Ribeiro TR (2018) Iron ore pelletizing process: an overview. In: Shatokha V (ed) Iron ores and iron oxide materials. IntechOpen, London, pp 41–59. https://doi.org/10.5772/intechopen.73164
Shirmohammadi S, Ferrero A (2014) Camera as the instrument: the rising trend of vision based measurement. IEEE Instrum Meas Mag 17(3):41–47. https://doi.org/10.1109/MIM.2014.6825388
Wu X, Liu XY, Yuan F (2021) Experimental analysis of image dehazing algorithms for pelletization process images. ISIJ Int 61(1):269–279. https://doi.org/10.2355/isijinternational.ISIJINT-2020-295
Wu X, Liu XY, Yuan F (2021) Fast dehazing method for improving the image quality in pellet size measurement. Comput Ind 128:10348. https://doi.org/10.1016/J.COMPIND.2021.103438
Wu X, Liu XY, Sun W, Mao C-G, Yu C (2019) An image-based method for online measurement of the size distribution of iron green pellets using dual morphological reconstruction and circle-scan. Powder Technol 347:186–198. https://doi.org/10.1016/j.powtec.2019.03.007
Heydari M, Amirfattahi R, Nazari B, Rahimi P (2016) An industrial image processing-based approach for estimation of iron ore green pellet size distribution. Powder Technol 303:260–268. https://doi.org/10.1016/J.POWTEC.2016.09.020
Heydari M, Amirfattahi R, Nazari B, Bastani A (2013) Iron ore green pellet diameter measurement by using of image processing techniques. In: Proceedings of 21st Iranian Conference on Electrical Engineering (ICEE), pp 1–6. https://doi.org/10.1109/IranianCEE.2013.6599563
Thurley MJ, Andersson T (2008) An industrial 3D vision system for size measurement of iron ore green pellets using morphological image segmentation. Miner Eng 21(5):405–415. https://doi.org/10.1016/J.MINENG.2007.10.020
Liu XY, Mao C, Sun W, Wu X (2018) Image-based method for measuring pellet size distribution in the stable area of disc pelletizer. ISIJ Int 58(11):2088–2094. https://doi.org/10.2355/isijinternational.ISIJINT-2018-384
Khanafer M, Shirmohammadi S (2020) Applied AI in instrumentation and measurement: the deep learning revolution. IEEE Instrum Meas Mag 23(6):10–17. https://doi.org/10.1109/MIM.2020.9200875
Nayak DK, Das DP, Behera SK, Das SP (2020) Monitoring the fill level of a ball mill using vibration sensing and artificial neural network. Neural Comput Appl 32(5):1501–1511. https://doi.org/10.1007/s00521-019-04555-5
Das S, Das DP, Sarangi CK, Bhoi B (2020) Estimation of hydrogen flow rate in atmospheric Ar:H2 plasma by using artificial neural network. Neural Comput Appl 32(5):1357–1365. https://doi.org/10.1007/s00521-018-3674-z
Gonzalez RC (2018) Deep convolutional neural networks [Lecture Notes]. IEEE Signal Process Mag 35(6):79–87. https://doi.org/10.1109/MSP.2018.2842646
Si Z, Yu Y, Yang M, Li P (2021) Hybrid solar forecasting method using satellite visible images and modified convolutional neural networks. IEEE Trans Ind Appl 57(1):5–16. https://doi.org/10.1109/TIA.2020.3028558
Liu J, Gao Q, Tang Z, Xie Y, Gui W, Ma T, Niyoyita JP (2020) Online monitoring of flotation froth bubble-size distributions via multiscale deblurring and multistage jumping feature-fused full convolutional networks. IEEE Trans Instrum Meas 69(12):9618–9633. https://doi.org/10.1109/TIM.2020.3006629
Karimpouli S, Tahmasebi P (2019) Image-based velocity estimation of rock using convolutional neural networks. Neural Netw 111:89–97. https://doi.org/10.1016/j.neunet.2018.12.006
Duan J, X. yan Liu, X. Wu, C. Mao, (2020) Detection and segmentation of iron ore green pellets in images using lightweight U-net deep learning network. Neural Comput Appl 32(10):5775–5790. https://doi.org/10.1007/s00521-019-04045-8
Duan J, Liu XY (2021) Online monitoring of green pellet size distribution in haze-degraded images based on VGG16-LU-Net and haze judgment. IEEE Trans Instrum Meas 70:1–16. https://doi.org/10.1109/TIM.2021.3052018
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition [Online]. https://arxiv.org/abs/1409.1556. Accessed 29 January 2022
Wu X, Liu XY, Duan J (2021) Online size distribution measurement of dense iron green pellets using an efficient and multiscale nested U-net method. Powder Technol 387:584–600. https://doi.org/10.1016/j.powtec.2021.04.045
Deo AJ, Behera SK, Das DP (2021) Detection of material build-up during online size distribution analysis of iron ore green pellets using MobilenetV2. In: Proceedings of 2021 International Symposium of Asian Control Association on Intelligent Robotics and Industrial Automation (IRIA). pp 1–6. https://doi.org/10.1109/IRIA53009.2021.9588756
Deo AJ, Sahoo A, Behera SK, Das DP (2021) Machine learning based image processing for iron ore pellet size analysis. In: Proceedings of 4th Biennial International Conference on Nascent Technologies in Engineering (ICNTE), pp 1–5. https://doi.org/10.1109/ICNTE51185.2021.9487768
Feng Y, Chen Z, Wang D, Chen J, Feng Z (2020) DeepWelding: a deep learning enhanced approach to GTAW using multisource sensing images. IEEE Trans Ind Inf 16(1):465–474. https://doi.org/10.1109/TII.2019.2937563
Wang S, Dehghanian P, Li L (2020) Power grid online surveillance through PMU-embedded convolutional neural networks. IEEE Trans Ind Appl 56(2):1146–1155. https://doi.org/10.1109/TIA.2019.2958786
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) MobileNets: Efficient convolutional neural networks for mobile vision applications [Online]. http://arxiv.org/abs/1704.04861. Accessed 29 January 2022
Maschler B, Weyrich M (2021) Deep transfer learning for industrial automation: a review and discussion of new techniques for data-driven machine learning. IEEE Ind Electron Mag 15(2):65–75. https://doi.org/10.1109/MIE.2020.3034884
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet: A large-scale hierarchical image database. In: Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp 248–255. https://doi.org/10.1109/CVPR.2009.5206848
Polikar R (2006) Ensemble based systems in decision making. IEEE Circuits Syst Mag 6(3):21–45. https://doi.org/10.1109/MCAS.2006.1688199
Kuncheva LI, Bezdek JC, Duin RPW (2001) Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recognit 34(2):299–314. https://doi.org/10.1016/S0031-3203(99)00223-X
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift [Online]. https://arxiv.org/abs/1502.03167. Accessed 29 January 2022
Kingma DP, Lei Ba J (2014) ADAM: A method for stochastic optimization [Online]. https://arxiv.org/1412.6980v9. Accessed 29 January 2022
Choudhary T, Mishra V, Goswami A, Sarangapani J (2021) A transfer learning with structured filter pruning approach for improved breast cancer classification on point-of-care devices. Comput Biol Med 134:104432. https://doi.org/10.1016/j.compbiomed.2021.104432
Transfer learning for training deep learning models. In Mathworks, https://in.mathworks.com/discovery/transfer-learning.html. Accessed 03 May 2022
Acknowledgements
Arya Jyoti Deo acknowledges the Council of Scientific and Industrial Research (CSIR), India, for providing financial support under the Senior Research Fellowship scheme (File No. 31/9(0141)/2018-EMR-I). Animesh Sahoo would like to thank CSIR-IMMT for providing the required facilities and support during his internship. Santosh Kumar Behera and Debi Prasad Das acknowledge Ministry of Steel, Govt. of India for financial support under Sanction No. 44(i) dated 07/03/2022 and CSIR-IMMT-project GAP-363 for a part of this work.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflict of interest to declare to the best of their knowledge.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Deo, A.J., Sahoo, A., Behera, S.K. et al. Vision-based size classification of iron ore pellets using ensembled convolutional neural network. Neural Comput & Applic 34, 18629–18641 (2022). https://doi.org/10.1007/s00521-022-07473-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07473-1