Nonlinear autoregressive-moving average-L2 (NARMA-L2) controller for multivariable ball mill plant
-
Rodrigo de A. Bustamante
,
Beatriz S. M. Bastos
Abstract
Mineral processing facilities concern an enormous amount of dynamically complex unit operations (due to nonlinearities), for instance ball mill system. Normally, these processes need multivariable controllers to smooth actions by designing for plant constraints such as deadtimes and dynamics interactions. The present work presents a comparison between a classical PI and nonlinear moving average autoregressive-linearization level 2 (NARMA-L2) controllers based on artificial neural network (ANN) for a ball mill system. The manipulated variables of this plant are the rotation velocity (Vr) and the feeding weight (Wf), while the controlled parameters are the hold up (HU) and the mass fraction under 45 μm (P45). The simulation was built in the MATLAB software (Simulink), comparing the actions of PI and NARMA-L2 controllers in the face of operational changes in specific regions (constraints). The performance of proposed controllers was verified by the integral of absolute error (IAE), integral of squared error (ISE), or the integral of time-weighted absolute error (ITAE). The results of simulation showed the validity of the model obtained and the control technique proposed in this paper, which contributes to studies of multivariate controller designs for ball mills with significant applications. Additionally, this paper brings a first hybrid approach (PI/NARMA-L2) with successful implementation described in the literature.
Funding source: CNPq/MCT
Funding source: CAPES
Funding source: FAPERJ
Funding source: FINEP
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: The authors would like to thank the CNPq/MCT, CAPES, FAPERJ and FINEP for the financial support to the Department of Chemical and Material Engineering (DEQM) at the Pontifical Catholic University of Rio de Janeiro (PUC-Rio).
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
1. Gorrasi, G, Sorrentino, A. Mechanical milling as a technology to produce structural and functional bio-nanocomposites. Green Chem 2015;17:2610–25. https://doi.org/10.1039/c5gc00029g.Search in Google Scholar
2. Nkwanyana, S, Loveday, B. Addition of pebbles to a ball-mill to improve grinding efficiency. Miner Eng 2017;103–104:72–7. https://doi.org/10.1016/j.mineng.2016.09.004.Search in Google Scholar
3. de Oliveira, ALR, Tavares, LM. Modeling and simulation of continuous open circuit dry grinding in a pilot-scale ball mill using Austin’s and Nomura’s models. Powder Technol 2018;340:77–87. https://doi.org/10.1016/j.powtec.2018.09.016.Search in Google Scholar
4. Kato, T, Granata, G, Tsunazawa, Y, Takagi, T, Tokoro, C. Mechanism and kinetics of enhancement of cerium dissolution from weathered residual rare earth ore by planetary ball milling. Miner Eng 2019;134:365–71. https://doi.org/10.1016/j.mineng.2019.02.017.Search in Google Scholar
5. Tukarambai, M, Hemanth Varma, MS, Raju, CAI. Batch grinding studies by a ball mill for hematite ore. Mater Today Proc 2019;26:825–32.10.1016/j.matpr.2019.12.425Search in Google Scholar
6. Xing Peng, Y, Ni, X, Zhu, ZC, Yu, ZF, Yin, ZX, Li, TQ, et al.. Friction and wear of liner and grinding ball in iron ore ball mill. Tribol Int 2017;115:506–17. https://doi.org/10.1016/j.triboint.2017.06.017.Search in Google Scholar
7. Matos, AM, Nunes, S, Costa, C, Barroso-Aguiar, JL. Spent equilibrium catalyst as internal curing agent in UHPFRC. Cement Concr Compos 2019;104:103362. https://doi.org/10.1016/j.cemconcomp.2019.103362.Search in Google Scholar
8. Nunes, S, Costa, C. Numerical optimization of self-compacting mortar mixture containing spent equilibrium catalyst from oil refinery. J Clean Prod 2017;158:109–21. https://doi.org/10.1016/j.jclepro.2017.04.161.Search in Google Scholar
9. Wang, H, Meng, T, Zhang, H, Cheng, S, Zhang, L, Liu, Z. The mechanism on decreasing the microbiological contamination of superfine green tea powder by ball milling. LWT Food Sci Technol 2020;134:109966. https://doi.org/10.1016/j.lwt.2020.109966.Search in Google Scholar
10. Jiang, G, Ramachandraiah, K, Wu, Z, Li, S, Eun, JB. Impact of ball-milling time on the physical properties, bioactive compounds, and structural characteristics of onion peel powder. Food Biosci 2020;36:100630. https://doi.org/10.1016/j.fbio.2020.100630.Search in Google Scholar
11. Chen, PC, Lin, C, Chen, MH, Chiang, PY. The micronization process for improving the dietary value of okara (soybean residue) by planetary ball milling. LWT 2020;132:109848.10.1016/j.lwt.2020.109848Search in Google Scholar
12. Broseghini, M, Gelisio, L, D’Incau, M, Azanza Ricardo, CL, Pugno, NM, Scardi, P. Modeling of the planetary ball-milling process: the case study of ceramic powders. J Eur Ceram Soc 2016;36:2205–12. https://doi.org/10.1016/j.jeurceramsoc.2015.09.032.Search in Google Scholar
13. Ahsanzadeh-Vadeqani, M, Razavi, RS, Barekat, M, Borhani, GH, Mishra, AK. Preparation of yttria nanopowders for use in transparent ceramics by dry ball-milling technique. J Eur Ceram Soc 2017;37:2169–77. https://doi.org/10.1016/j.jeurceramsoc.2016.12.006.Search in Google Scholar
14. Wei, D, Craig, IK. Grinding mill circuits – a survey of control and economic concerns. Int J Miner Process 2009;90:56–66. https://doi.org/10.1016/j.minpro.2008.10.009.Search in Google Scholar
15. Song Chen, X, Yong Zhai, J, Hua Li, S, Li, Q. Application of model predictive control in ball mill grinding circuit. Miner Eng 2007;20:1099–108. https://doi.org/10.1016/j.mineng.2007.04.007.Search in Google Scholar
16. Monov, V, Sokolov, B, Stoenchev, S. Grinding in ball mills: modeling and process control. Cybern Inf Technol 2012;12:51–68. https://doi.org/10.2478/cait-2012-0012.Search in Google Scholar
17. Feng, L, Yang, F, Zhang, W, Tian, H. Model predictive control of duplex inlet and outlet ball mill system based on parameter adaptive particle swarm optimization. Math Probl Eng 2019:2019. https://doi.org/10.1155/2019/6812754.Search in Google Scholar
18. Craig, IK, McLeod, IM. Run-of-mine ore milling circuit. Contr Eng Pract 1996;4:1–12. https://doi.org/10.1016/0967-0661(95)00200-0.Search in Google Scholar
19. Shekar Besta, C, Chidambaram, M. Tuning of multivariable PI controllers by BLT method for TITO systems tuning of multivariable PI controllers by BLT method for TITO systems. Chem Eng Commun 2016;203:527–38. https://doi.org/10.1080/00986445.2015.1039121.Search in Google Scholar
20. Aguila-Camacho, N, Le Roux, JD, Duarte-Mermoud, MA, Orchard, ME. Control of a grinding mill circuit using fractional order controllers. J Process Contr 2017;53:80–94. https://doi.org/10.1016/j.jprocont.2017.02.012.Search in Google Scholar
21. Hägglund, T. The one-third rule for PI controller tuning. Comput Chem Eng 2019;127:25–30. https://doi.org/10.1016/j.compchemeng.2019.03.027.Search in Google Scholar
22. Dash, S. Load frequency control of solar PV and solar thermal integrated micro grid using Narma-L2 controller. CoRR 2020;arXiv:2004.05776v1.Search in Google Scholar
23. Kheioon, IA, Munahi, BS, Abdulaali, AH. A new fuzzy-NARMA L2 controller design for active suspension system; 2017. Basrah J Eng Sci 2017;17:43–50. https://doi.org/10.33971/bjes.17.2.6.Search in Google Scholar
24. Narendra, KS, Mukhopadhyay, S. Adaptive control using neural networks and approximate models. IEEE Trans Neural Netw 1997;8:475–85. https://doi.org/10.1109/72.572089.Search in Google Scholar PubMed
25. Pukrittayakamee, A, De Jesús, O, Hagan, MT. Smoothing the control action for NARMA-L2 controllers. Midwest Symp Circuits Syst 2002;3:37–40.10.1109/MWSCAS.2002.1186964Search in Google Scholar
26. Al-Dunainawi, Y, Abbod, MF, Jizany, A. A new MIMO ANFIS-PSO based NARMA-L2 controller for nonlinear dynamic systems. Eng Appl Artif Intell 2017;62:265–75. https://doi.org/10.1016/j.engappai.2017.04.016.Search in Google Scholar
27. Soltani, H, Karimi, A, Falahatpisheh, S. The optimization of biodiesel production from transesterification of sesame oil via applying ultrasound-assisted techniques: comparison of RSM and ANN-PSO hybrid model. Chem Prod Process Model 2022;17:55–67. https://doi.org/10.1515/cppm-2020-0076.Search in Google Scholar
28. Sivapathasekaran, C, Sen, R. Performance evaluation of an ANN-GA aided experimental modeling and optimization procedure for enhanced synthesis of marine biosurfactant in a stirred tank reactor. J Chem Technol Biotechnol 2013;88:794–9. https://doi.org/10.1002/jctb.3900.Search in Google Scholar
29. Mahmoodi-Babolan, N, Heydari, A, Nematollahzadeh, A. Removal of methylene blue via bioinspired catecholamine/starch super adsorbent and the efficiency prediction by response surface methodology and artificial neural network-particle swarm optimization. Bioresour Technol 2019;294:122084. https://doi.org/10.1016/j.biortech.2019.122084.Search in Google Scholar PubMed
30. Jeyachandran, C, Rajaram, M. Comparative performance analysis of various training algorithms for control of CSTR process using NARMA-L2 control. In: TISC 2011 – Proc. 3rd Int. Conf. Trendz Inf. Sci. Comput. 2011:5–10 pp.10.1109/TISC.2011.6169075Search in Google Scholar
31. Paul, R, Chokkadi, S. Implementation of NARMA-L2 controller for shell and tube heat exchanger temperature process. Ind Eng Chem Res 2016;55:5644–53. https://doi.org/10.1021/acs.iecr.5b03791.Search in Google Scholar
32. Reddy, GP, Krishna, PR, Swetha, C. NARMA-L2 control of a bioreactor with input multiplicities. In: Proceedings of the World Congress on Engineering and Computer Science; 2013, vol II:23–5 pp.Search in Google Scholar
33. Diaz, S, Perez-Correa, JR, Cipriano, A, Fernandez-Fernandez, M. Intelligent control applications on a binary distillation column. In: 2016 IEEE Int. Conf. Autom. ICA-ACCA, 2016; 2016. https://doi.org/10.1109/ica-acca.2016.7778496.Search in Google Scholar
34. Kallemback, GM. Optimization and nonlinear predictive control for dry grinding circuit [Master dissertation]. Federal University of Rio de Janeiro (UFRJ); 2012.Search in Google Scholar
35. Abiodun, OI, Jantan, A, Omolara, AE, Dada, KV, Mohamed, NAE, Arshad, H. State-of-the-art in artificial neural network applications: a survey. Heliyon 2018;4:1–41. https://doi.org/10.1016/j.heliyon.2018.e00938.Search in Google Scholar PubMed PubMed Central
36. Fadhil Ahmed, D, Khalaf, AH. Artificial neural networks controller for crude oil distillation column of baiji refinery. J Chem Eng Process Technol 2015;07:1–9. https://doi.org/10.4172/2157-7048.1000272.Search in Google Scholar
37. Venkanna, VJ, Reddy, GP, Kumar, R. Comparative analysis of PID and NARMA L2 controllers for shell and tube heat exchanger. Int J Adv Eng Manag Sci 2016;2:1202–7.Search in Google Scholar
38. Guijo-Rubio, D, Durán-Rosal, AM, Gutiérrez, PA, Gómez-Orellanaa, AM, Casanova-Mateo, C, Sanz-Justo, J, et al.. Evolutionary artificial neural networks for accurate solar radiation prediction. Energy 2020;210:1–11. https://doi.org/10.1016/j.energy.2020.118374.Search in Google Scholar
39. Hafeez, A, Taqvi, SA, Fazal, T, Khan, Z, Amjad, US, Bokhari, A, et al.. Optimization on cleaner intensification of ozone production using artificial neural network and response surface methodology: parametric and comparative study. J Clean Prod 2020;252:119833. https://doi.org/10.1016/j.jclepro.2019.119833.Search in Google Scholar
40. Sarkar, T, Salauddin, M, Hazra, SK, Chakraborty, R. Comparative study of predictability of response surface methodology (RSM) and artificial neural network-particle swarm optimization (ANN-PSO) for total colour difference of pineapple fortified rasgulla processing. Int J Intell Netw 2020;1:17–31. https://doi.org/10.1016/j.ijin.2020.06.001.Search in Google Scholar
41. Bensingh, RJ, Machavaram, R, Boopathy, SR, Jebaraj, C. Injection molding process optimization of a bi-aspheric lens using hybrid artificial neural networks (ANNs) and particle swarm optimization (PSO). Meas J Int Meas Confed 2019;134:359–74. https://doi.org/10.1016/j.measurement.2018.10.066.Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Nonlinear autoregressive-moving average-L2 (NARMA-L2) controller for multivariable ball mill plant
- An enhanced feedback-feedforward control scheme for process industries
- Appling the computational fluid dynamics studies of the thermogravitational column for N2-CO2 and He-Ar gas mixtures separation
- An enhancement in series cascade control for non-minimum phase system
- Modelling and simulation of industrial multistage flash desalination process with exergetic and thermodynamic analysis. A case study of Azzour seawater desalination plant
- Development of a CFD-based simulation model and optimization of thermal diffusion column: application on noble gas separation
- A machine-learning reduced kinetic model for H2S thermal conversion process
- Design strategies for oxy-combustion power plant captured CO2 purification
- Energy-saving investigation of vacuum reactive distillation for the production of ethyl acetate
- Reducing total annual cost and CO2 emissions in batch distillation for separating ternary wide boiling mixtures using vapor recompression heat pump
Articles in the same Issue
- Frontmatter
- Research Articles
- Nonlinear autoregressive-moving average-L2 (NARMA-L2) controller for multivariable ball mill plant
- An enhanced feedback-feedforward control scheme for process industries
- Appling the computational fluid dynamics studies of the thermogravitational column for N2-CO2 and He-Ar gas mixtures separation
- An enhancement in series cascade control for non-minimum phase system
- Modelling and simulation of industrial multistage flash desalination process with exergetic and thermodynamic analysis. A case study of Azzour seawater desalination plant
- Development of a CFD-based simulation model and optimization of thermal diffusion column: application on noble gas separation
- A machine-learning reduced kinetic model for H2S thermal conversion process
- Design strategies for oxy-combustion power plant captured CO2 purification
- Energy-saving investigation of vacuum reactive distillation for the production of ethyl acetate
- Reducing total annual cost and CO2 emissions in batch distillation for separating ternary wide boiling mixtures using vapor recompression heat pump
