Skip to main content
SpringerLink
Log in

A Deep Variational Autoencoder Based Inverse Method for Active Energy Consumption of Mining Plants and Ball Grinding Circuit Investigation

  • Regular Paper
  • Published:
International Journal of Precision Engineering and Manufacturing-Green Technology Aims and scope Submit manuscript

Abstract

The natural ore distribution is unique, and the mining process entirely depends on it. Thus, every mining has its way of dressing ore due to the plan of industry. Therefore, in optimal and control energy systems, the relation between ore distribution, parameters of stages, and the final output are vital to understanding the entire dressing plant. In this way, the paper purpose of developing a learning-based inverse method to understand the relationship between the ore (gathered from a few different open pits) and the final recovery rate of minerals. The variational autoencoder’s exceptional property is suitable for the learning-based inverse method, and the low dimensional space in the encoding and decoding process connects to the first input ore and the final outputs regarding the daily plan. When the first input ore is determined corresponding to the planned recovery, we use the low dimensional space to express the stages’ appropriate parameters. The milling stage is the most crucial stage of the plant, and for the validation propose of the method, the real experiment that investigated the learning result of the selected ball milling stage. Finally, the predictive-based control system was considered based on generating a variational autoencoder-based learning feature.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Abbreviations

fi :

ith stage of dressing process

κ :

The number of sampled best recovery

\(\mu\) :

Mean value of encoder

\(\sigma\) :

Standard variation of encoder

\({\varvec{\epsilon }}\) :

Normally distributed random sampling

h :

low dimensional space variable

\(D_{KL}\) :

Kullback–Leibler divergence

\({\mathbf{t}} _{f_{i}}\) :

Parameters of ith stage

\({\mathbf{y}} _{f_{i}}\) :

Outcome of ith stage

References

  1. Ma, S., Jiang, Z., & Liu, W. (2019). Modeling drying-energy consumption in automotive painting line based on ANN and MLR for real-time prediction. International Journal of Precision Engineering and Manufacturing-Green Technology, 6, 241. https://doi.org/10.1007/s40684-019-00064-x.

    Article  Google Scholar 

  2. Cao, C. T., Do, V. P., & Lee, B. R. (2019). Tube defect detection algorithm under noisy environment using feature vector and neural networks. International Journal of Precision Engineering and Manufacturing, 20, 559. https://doi.org/10.1007/s12541-019-00023-1.

    Article  Google Scholar 

  3. Park, J. K., An, W. H., & Kang, D. J. (2019). Convolutional neural network based surface inspection system for non-patterned welding defects. International Journal of Precision Engineering and Manufacturing, 20, 363. https://doi.org/10.1007/s12541-019-00074-4.

    Article  Google Scholar 

  4. Santos, T., & Kern, R. (2018). Understanding wafer patterns in semiconductor production with variational auto-encoders. ESANN.

  5. Di Palma, F., De Nicolao, G., Miraglia, G., Pasquinetti, E., & Piccinini, F. (2005). Unsupervised spatial pattern classification of electrical-wafer-sorting maps in semiconductor manufacturing. Pattern Recognition Letters, 26(12), 1857–1865.

    Article  Google Scholar 

  6. Jang, D., Jung, J., & Seok, J. (2016). Modeling and parameter optimization for cutting energy reduction in MQL milling process. International Journal of Precision Engineering and Manufacturing-Green Technology, 3, 5–12. https://doi.org/10.1007/s40684-016-0001-y.

    Article  Google Scholar 

  7. Hou, L., Yue, X., Xiao, X., & Xu, W. (2019). Fabric texture removal with deep convolutional neural networks. In W. Wong (Ed.), Artificial intelligence on fashion and textiles. AITA 2018. Advances in intelligent systems and computing (Vol. 849). Springer. https://doi.org/10.1007/978-3-319-99695-0_34.

    Chapter  Google Scholar 

  8. Kestur, R., Meduri, A., & Narasipura, O. (2019). MangoNet: A deep semantic segmentation architecture for a method to detect and count mangoes in an open orchard. Engineering Applications of Artificial Intelligence, 77, 59–69. https://doi.org/10.1016/j.engappai.2018.09.011.

    Article  Google Scholar 

  9. Kim, D. H., Kim, T. J. Y., Wang, X., et al. (2018). Smart machining process using machine learning: A review and perspective on machining industry. International Journal of Precision Engineering and Manufacturing-Green Technology, 5, 555. https://doi.org/10.1007/s40684-018-0057-y.

    Article  Google Scholar 

  10. Park, C. W., Kwon, K. S., Kim, W. B., Min, B. K., Park, S. J., et al. (2009). Energy consumption reduction technology in manufacturing: A selective review of policies, standards, and research. International Journal of Precision Engineering and Manufacturing, 10(5), 151–173. https://doi.org/10.1007/s12541-009-0107-z.

    Article  Google Scholar 

  11. Widrow, B., & Lehr, M. A. (1990). 30 years of adaptive neural networks: Perceptron, madaline, and backpropagation. Proceedings of the IEEE, 78(9), 1415–1442. https://doi.org/10.1109/5.58323.

    Article  Google Scholar 

  12. Stange, W. (1993). Using artificial neural networks for the control of grinding circuits. Minerals Engineering, 6(5), 479–489. https://doi.org/10.3182/20131218-3-IN-2045.00103

    Article  Google Scholar 

  13. Veerendra, S., Banerjee, P. K., Tripathy, S. K., Saxena, V. K., & Venugopal, R. (2013). Artificial neural network modeling of ball mill grinding process. Journal of Powder Metallurgy and Mining, 2, 106. https://doi.org/10.4172/2168-9806.1000106.

    Article  Google Scholar 

  14. Ding, H., Guo, D., Cheng, K., & Cui, Q. (2014). An investigation on quantitative analysis of energy consumption and carbon footprint in the grinding process. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 228(6), 950–956.

    Article  Google Scholar 

  15. Umucu, Y., Deniz, V., Bozkurt, V., & Caglar, M. F. (2016). The evaluation of grinding process using artificial neural network. International Journal of Mineral Processing, 146, 46–53. https://doi.org/10.1016/j.minpro.2015.11.013.

    Article  Google Scholar 

  16. Ge, Z., Song, Z., Ding, S. X., & Huang, B. (2017). Data mining and analytics in the process industry: The role of machine learning. IEEE Access, 5, 20590–20616. https://doi.org/10.1109/ACCESS.2017.2756872.

    Article  Google Scholar 

  17. Eliya, N., Elad, M., Loren, L., Warren, J., David, B., & Yair, B. (2017). Deep learning methods for improved decoding of linear codes. IEEE Journal of Selected Topics in Signal Processing, 12, 131–199.

    Google Scholar 

  18. Kingma, D., & Ba, J. (2015). A method for stochastic optimization. International Conference on Learning Representations

  19. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, S., Davis, A., Dean, J., Devin, M. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467

  20. Chen, X., Yang, J., Li, S., & Li, Q. (2010). An improved control strategy for ball mill grinding circuits. In K. Li, M. Fei, L. Jia, & G. W. Irwin (Eds.), Life system modeling and intelligent computing. ICSEE 2010, LSMS 2010. Lecture notes in computer science (Vol. 6328). Springer. https://doi.org/10.1007/978-3-642-15621-2_45.

    Chapter  Google Scholar 

  21. (1980). House Documents, Otherwise Publ. as Executive Documents: 13th Congress, 2d session-49th congress, vol. 30, pp 375

  22. Radhakrishnan, V. R. (1999). Model based supervisory control of a ball mill grinding circuit. Journal of Process Control, 9, 195–211.

    Article  Google Scholar 

  23. Chen, X., Li, Q., & Fei, S. (2008). Constrained model predictive control in ball mill grinding process. Powder Technology, 186, 31–39.

    Article  Google Scholar 

  24. Zhao, D., & Chai, T. (2013). Intelligent optimal control system for ball mill grinding process. Journal of Control Theory and Applications, 11, 454. https://doi.org/10.1007/s11768-013-1210-3.

    Article  Google Scholar 

  25. Duarte-Mermoud, M. A., Sepulveda, F., Castillo, A., Contreras, A., Lazcano, V., Giménez, P., & Castelli, L. (1999). A comparative experimental study of five multivariable control strategies applied to a grinding plant. Powder Technology, 104, 1–28. https://doi.org/10.1016/S0032-5910(98)00210-1.

    Article  Google Scholar 

  26. ten Berge, J. M. F., & Kiers, H. A. L. (1999). Retrieving the correlation matrix from a truncated PCA solution: The inverse principal component problem. Psychometrika, 64, 317–324. https://doi.org/10.1007/BF02294298

    Article  MATH  Google Scholar 

  27. Poole, B., Lahiri, S., Raghu, M., Sohl-Dickstein, J., & Ganguli, S. (2016). Exponential expressivity in deep neural networks through transient chaos. Advances in Neural Information Processing Systems, 29, 3360–3368.

    Google Scholar 

  28. Rawlinson, N., & Sambridge, M. (2003). Seismic traveltime tomography of the crust and lithosphere. In R. Dmowska (Ed.), Advances in geophysics (Vol. 46, pp. 81–198). Elsevier.

    Google Scholar 

  29. Ilyinsky, N. B., Kacimov, A. R., & Yakimov, N. D. (1998). Analytical solutions of seepage theory problems. Inverse method, variational theorems, optimization and estimates (a review). Fluid Dynamics, 33, 157–168. https://doi.org/10.1007/BF02698697.

    Article  MathSciNet  Google Scholar 

  30. Olshausen, B. A., & Field, D. J. (1996). Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381, 607.

    Article  Google Scholar 

  31. Aharon, M., Elad, M., & Bruckstein, A. (2006). K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, 54, 4311–4322.

    Article  Google Scholar 

  32. Lucas, A., Iliadis, M., Molina, R., & Katsaggelos, A. K. (2018). Using deep neural networks for inverse problems in imaging: Beyond analytical methods. IEEE Signal Processing Magazine, 35(1), 20–36. https://doi.org/10.1109/MSP.2017.2760358.

    Article  Google Scholar 

  33. Hyun, C. M., Baek, S. H., Lee, M., Lee, S. M., Seo, J. K. (2020). Deep learning-based solvability of underdetermined inverse problems in medical imaging. arXiv:2001.01432v2 [eess.IV]

  34. Golub, G., Hansen, P., & O’Leary, D. (1999). Tikhonov regularization and total least squares. SIAM Journal on Matrix Analysis and Applications, 21(1), 185–194. https://doi.org/10.1137/S0895479897326432.

    Article  MathSciNet  MATH  Google Scholar 

  35. Seo, J. K., & Woo, E. J. (2012). Nonlinear Inverse Problems in Imaging. Wiley. https://doi.org/10.1002/9781118478141.

    Book  Google Scholar 

  36. White, T. (2016). Sampling generative network, arXiv:1609.04468v3 [cs.NE]

  37. Kim, S., Winovich, N., Chi, H., et al. (2020). Latent transformations neural network for object view synthesis. Visual Computer, 36, 1663–1677. https://doi.org/10.1007/s00371-019-01755-x.

    Article  Google Scholar 

  38. Morrison, R. D., & Morrell, S. (1998). Comparison of comminution circuit energy efficiency using simulation. Mining, Metallurgy & Exploration, 15, 22–25. https://doi.org/10.1007/BF03403153

    Article  Google Scholar 

  39. Zhou, P., Chai, T., & Wang, H. (2009). Intelligent optimal-setting control for grinding circuits of mineral processing process. IEEE Transactions on Automation Science and Engineering, 6(4), 730–743. https://doi.org/10.1109/TASE.2008.2011562.

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by Award number mfund-052018 from the Foundation for Science and Technology at Mongolian University of Science and Technology.

Author information

Authors and Affiliations

  1. School of Applied Science, Mongolian University of Science and Technology, Baga toiruu 34, Sukhbaatar district, Ulaanbaatar, 14191, Mongolia

    Munkherdene Tsagaan, Batdemberel Ganbat & Uugantuya Khurlee

  2. Tavantolgoi Shareholding Company, Tsagaan-ovoo village, Tsogttsetsii Town, Southgobi Province, Mongolia

    Seddorj Renchin

  3. Erdenet Mining Corporation, Friendship sq-1, Bayan-Undur sum, Orkhon Province, 61027, Mongolia

    Oyunjargal Ichin

Authors
  1. Munkherdene Tsagaan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Batdemberel Ganbat
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Seddorj Renchin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Uugantuya Khurlee
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Oyunjargal Ichin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Munkherdene Tsagaan.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tsagaan, M., Ganbat, B., Renchin, S. et al. A Deep Variational Autoencoder Based Inverse Method for Active Energy Consumption of Mining Plants and Ball Grinding Circuit Investigation. Int. J. of Precis. Eng. and Manuf.-Green Tech. 9, 729–744 (2022). https://doi.org/10.1007/s40684-021-00380-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40684-021-00380-1

Keywords

Search

Navigation