Geomechanics and Engineering

  • 재33권6호
  • /
  • Pages.567-581
  • /
  • 2023
  • /
  • 2005-307X(pISSN)
  • /
  • 2092-6219(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Predicting the rock fragmentation in surface mines using optimized radial basis function and cascaded forward neural network models

  • Xiaohua Ding (School of Mines, China University of Mining and Technology) ;
  • Moein Bahadori (Faculty of Engineering, University of Gonabad) ;
  • Mahdi Hasanipanah (Department of Geotechnics and Transportation, Faculty of Civil Engineering, Universiti Teknologi Malaysia) ;
  • Rini Asnida Abdullah (Department of Geotechnics and Transportation, Faculty of Civil Engineering, Universiti Teknologi Malaysia)
  • 투고 : 2022.07.15
  • 심사 : 2023.05.02
  • 발행 : 2023.06.25
⟨ 이전 논문 다음 논문 ⟩

초록

The prediction and achievement of a proper rock fragmentation size is the main challenge of blasting operations in surface mines. This is because an optimum size distribution can optimize the overall mine/plant economics. To this end, this study attempts to develop four improved artificial intelligence models to predict rock fragmentation through cascaded forward neural network (CFNN) and radial basis function neural network (RBFNN) models. In this regards, the CFNN was trained by the Levenberg-Marquardt algorithm (LMA) and Conjugate gradient backpropagation (CGP). Further, the RBFNN was optimized by the Dragonfly Algorithm (DA) and teaching-learning-based optimization (TLBO). For developing the models, the database required was collected from the Midouk copper mine, Iran. After modeling, the statistical functions were computed to check the accuracy of the models, and the root mean square errors (RMSEs) of CFNN-LMA, CFNN-CGP, RBFNN-DA, and RBFNN-TLBO were obtained as 1.0656, 1.9698, 2.2235, and 1.6216, respectively. Accordingly, CFNN-LMA, with the lowest RMSE, was determined as the model with the best prediction results among the four examined in this study.

키워드

과제정보

This paper is supported by the National Natural Science Foundation of China (Grant No. 52174131).

참고문헌

  1. Abujazar, M.S.S., Fatihah, S., Ibrahim, I.A., Kabeel, A. and Sharil, S. (2018), "Productivity modelling of a developed inclined stepped solar still system based on actual performance and using a cascaded forward neural network model", J. Cleaner Product.. 170, 147-159. https://doi.org/10.1016/j.jclepro.2017.09.092.
  2. Apostolopoulou, M., Armaghani, D.J., Bakolas, A., Douvika, M.G., Moropoulou, A. and Asteris, P.G. (2019), "Compressive strength of natural hydraulic lime mortars using soft computing techniques", Procedia Struct. Integrity, 17, 914-923. https://doi.org/10.1016/j.prostr.2019.08.122.
  3. Armaghani, D.J., Asteris, P.G., Fatemi, S.A., Hasanipanah, M., Tarinejad, R., Rashid, A.S.A. and Huynh, V.V. (2020a), "On the use of neuro-swarm system to forecast the pile settlement", Appl. Sci.. 10(6), https://doi.org/10.3390/app10061904.
  4. Armaghani, D.J., Hatzigeorgiou, G.D., Karamani, C., Skentou, A., Zoumpoulaki, I. and Asteris, P.G. (2019), "Soft computing-based techniques for concrete beams shear strength", Procedia Struct. Integrity, 17, 924-933. https://doi.org/10.1016/j.prostr.2019.08.123.
  5. Armaghani, D.J., Mirzaei, F., Toghroli, A. and Shariati, A. (2020b), "Indirect measure of shear strength parameters of fiber-reinforced sandy soil using laboratory tests and intelligent systems", Geomech. Eng., 22(5), 397-414. https://doi.org/10.12989/gae.2020.22.5.397.
  6. Asl, P.F., Monjezi, M., Hamidi, J.K. and Armaghani, D.J. (2018), "Optimization of flyrock and rock fragmentation in the tajareh limestone mine using metaheuristics method of firefly algorithm", Eng. with Comput., 34(2), 241-251. https://doi.org/10.1007/s00366-017-0535-9.
  7. Asteris, P.G., Koopialipoor, M., Armaghani, D.J., Kotsonis, E.A. and Lourenco, P.B. (2021a), "Prediction of cement-based mortars compressive strength using machine learning techniques", Neural Comput. Appl., 33(19), 13089-13121. https://doi.org/10.1007/s00521-021-06004-8.
  8. Asteris, P.G., Lourenco, P.B., Hajihassani, M., Adami, C.E.N., Lemonis, M.E., Skentou, A.D., Marques, R., Nguyen, H., Rodrigues, H. and Varum, H. (2021b), "Soft computing-based models for the prediction of masonry compressive strength", Eng. Struct., 248, 113276. https://doi.org/10.1016/j.engstruct.2021.113276.
  9. Asteris, P.G., Mamou, A., Hajihassani, M., Hasanipanah, M., Koopialipoor, M., Le, T.T., Kardani, N. and Armaghani, D.J. (2021c), "Soft computing-based closed form equations correlating l and n-type schmidt hammer rebound numbers of rocks", Transport. Geotech., 29, 100588. https://doi.org/10.1016/j.trgeo.2021.100588.
  10. Asteris, P.G., Nozhati, S., Nikoo, M., Cavaleri, L. and Nikoo, M. (2019), "Krill herd algorithm-based neural network in structural seismic reliability evaluation", Mech. Adv. Mater. Struct., 26(13), 1146-1153. https://doi.org/10.1080/15376494.2018.1430874..
  11. Asteris, P.G., Skentou, A.D., Bardhan, A., Samui, P. and Lourenco, P.B. (2021d), "Soft computing techniques for the prediction of concrete compressive strength using non-destructive tests", Constr. Build. Mater., 303, 124450. https://doi.org/10.1016/j.conbuildmat.2021.124450.
  12. Baghbani, A., Choudhury, T., Samui, P. and Costa, S. (2023), "Prediction of secant shear modulus and damping ratio for an extremely dilative silica sand-based on machine learning techniques", Soil Dyn. Earthq. Eng., 165, 107708. https://doi.org/10.1016/j.soildyn.2022.107708.
  13. Bahadori, M. and Bakhshandeh Amnieh, H. (2018), "Implementation of hyperbolic tangent function to estimate size distribution of rock fragmentation by blasting in open pit mines", Int. J. Min. Geo-Eng., 52(2), 187-197. https://doi.org/10.22059/ijmge.2018.221013.594642.
  14. Bahadori, M., Bakhshandeh Amnieh, H. and Khajezadeh, A. (2016), "A new geometrical-statistical algorithm for predicting two-dimensional distribution of rock fragments caused by blasting", Int. J. Rock Mech. Min. Sci., 86, 55-64. https://doi.org/10.1016/j.ijrmms.2016.04.002.
  15. Bai, X.D., Cheng, W.C., Ong, D.E. and Li, G. (2021), "Evaluation of geological conditions and clogging of tunneling using machine learning", Geomech. Eng., 25(1), 59-73. https://doi.org/10.12989/gae.2021.25.1.059.
  16. Bardhan, A., Gokceoglu, C., Burman, A., Samui, P. and Asteris, P.G. (2021), "Efficient computational techniques for predicting the california bearing ratio of soil in soaked conditions", Eng. Geol., 291, 106239. https://doi.org/10.1016/j.enggeo.2021.106239.
  17. Bardhan, A. and Samui, P. (2022), "Probabilistic slope stability analysis of heavy-haul freight corridor using a hybrid machine learning paradigm", Transport. Geotech., 37, 100815, https://doi.org/10.1016/j.trgeo.2022.100815.
  18. Benamara, C., Gharbi, K., Nait Amar, M. and Hamada, B. (2020), "Prediction of wax appearance temperature using artificial intelligent techniques", Arabian J. Sci. Eng., 45, 1319-1330. https://doi.org/10.1007/s13369-019-04290-y.
  19. Bhandari, S. (1997), Engineering Rock Blasting Operations, A. A. Balkema, Rotterdam, Netherlands.
  20. Cavaleri, L., Asteris, P.G., Psyllaki, P.P., Douvika, M.G., Skentou, A.D. and Vaxevanidis, N.M. (2019), "Prediction of surface treatment effects on the tribological performance of tool steels using artificial neural networks", Appl. Sci., 9(14). https://doi.org/10.3390/app9142788.
  21. Chen, G., Fu, K., Liang, Z., Sema, T., Li, C., Tontiwachwuthikul, P. and Idem, R. (2014), "The genetic algorithm based back propagation neural network for MMP prediction in CO2-EOR process", Fuel., 126, 202-212. https://doi.org/10.1016/j.fuel.2014.02.034.
  22. Chen, H., Asteris, P.G., Jahed Armaghani, D., Gordan, B. and Pham, B.T. (2019), "Assessing dynamic conditions of the retaining wall: developing two hybrid intelligent models", Appl. Sci., 9(6), https://doi.org/10.3390/app9061042.
  23. Cheng, M.Y. and Prayogo, D. (2017), "A novel fuzzy adaptive teaching-learning-based optimization (FATLBO) for solving structural optimization problems", Eng. with Comput., 33, 55-69. https://doi.org/10.1007/s00366-016-0456-z.
  24. Chu, H., Yang, X., Li, S. and Liang, W. (2019), "Experimental study on the blasting-vibration safety standard for young concrete based on the damage accumulation effect", Constr. Build. Mater., 217, 20-27. https://doi.org/10.1016/j.conbuildmat.2019.05.070.
  25. Dare-Bryan, P., Mansfield, S. and Schoeman, J. (2013). "Blast optimisation through computer modelling of fragmentation, heave and damage", Proceedings of the Rock Fragmentation by Blasting: The 10th International Symposium on Rock Fragmentation by Blasting, 2012 , Fragblast 10.
  26. Dimitraki, L., Christaras, B., Marinos, V., Vlahavas, I. and Arampelos, N. (2019), "Predicting the average size of blasted rocks in aggregate quarries using artificial neural networks", Bull. Eng. Geol. Environ., 78, 2717-2729. https://doi.org/10.1007/s10064-018-1270-1.
  27. Djordjevic, N. (1999). "A two-component model of blast fragmentation", AusIMM Proceedings, 304(2), 9-13.
  28. Ebrahimi, E., Monjezi, M., Khalesi, M.R. and Armaghani, D.J. (2016), "Prediction and optimization of back-break and rock fragmentation using an artificial neural network and a bee colony algorithm", Bull. Eng Geol. Environ., 75, 27-36. https://doi.org/10.1007/s10064-015-0720-2.
  29. Elsharkawy, A.M. (1998). "Modeling the properties of crude oil and gas systems using RBF network", SPE Asia Pacific oil and gas conference and exhibition, https://doi.org/10.2118/49961-MS.
  30. Esmaeili, M., Salimi, A., Drebenstedt, C., Abbaszadeh, M. and Aghajani Bazzazi, A. (2015), "Application of PCA, SVR, and ANFIS for modeling of rock fragmentation", Arabian J. Geosci., 8, 6881-6893. https://doi.org/10.1007/s12517-014-1677-3.
  31. Fang, Q., Nguyen, H., Bui, X.N., Nguyen-Thoi, T. and Zhou, J. (2021), "Modeling of rock fragmentation by firefly optimization algorithm and boosted generalized additive model", Neural Comput. Appl., 33(8), 3503-3519. https://doi.org/10.1007/s00521-020-05197-8.
  32. Gao, W., Karbasi, M., Hasanipanah, M., Zhang, X. and Guo, J. (2018), "Developing GPR model for forecasting the rock fragmentation in surface mines", Eng. with Comput., 34(2), 339-345. http://doi.org/10.1007/s00366-017-0544-8.
  33. Gupta, V.K., Khani, H., Ahmadi-Roudi, B., Mirakhorli, S., Fereyduni, E. and Agarwal, S. (2011), "Prediction of capillary gas chromatographic retention times of fatty acid methyl esters in human blood using MLR, PLS and back-propagation artificial neural networks", Talanta, 83(3), 1014-1022. https://doi.org/10.1016/j.talanta.2010.11.017.
  34. Hasanipanah, M., Amnieh, H.B., Arab, H. and Zamzam, M.S. (2018), "Feasibility of PSO-ANFIS model to estimate rock fragmentation produced by mine blasting", Neural Comput. Appl., 30(4), 1015-1024. http://doi.org/10.1007/s00521-016-2746-1.
  35. Hasanipanah, M., Jahed Armaghani, D., Bakhshandeh Amnieh, H., Majid, M.Z.A. and Tahir, M.M.D. (2017), "Application of PSO to develop a powerful equation for prediction of flyrock due to blasting", Neural Comput. Appl., 28(1), 1043-1050. https://doi.org/10.1007/s00521-016-2434-1.
  36. Hasanipanah, M., Jahed Armaghani, D., Khamesi, H., Bakhshandeh Amnieh, H. and Ghoraba, S. (2016), "Several non-linear models in estimating air-overpressure resulting from mine blasting", Eng. with Comput., 32(3), 441-455. https://doi.org/10.1007/s00366-015-0425-y.
  37. Haykin, S. (1999), Neural Networks A Comprehensive Foundation, BeiJing: Tsinghua University Press&Pren 一 6ce HaJ1.
  38. Haykin, S. (2009), Neural Networks and Learning Machines, Pearson Education India.
  39. Hino, K. (1956), "Fragmentation of rock through blasting and shock wave theory of blasting", Proceedings of the 1st US Symposium on Rock Mechanics (USRMS).
  40. Huang, J., Asteris, P.G., Manafi Khajeh Pasha, S., Mohammed, A.S. and Hasanipanah, M. (2022), "A new auto-tuning model for predicting the rock fragmentation: a cat swarm optimization algorithm", Eng. with Comput., 38(3), 2209-2220. https://doi.org/10.1007/s00366-020-01207-4.
  41. Hustrulid, W. and Johnson, J. (2008). "A gas pressure-based drift round blast design methodology", Proceedings of the 5th International Conference & Exhibition on Mass Mining, Sweden, Lulea.
  42. Hustrulid, W.A. (1999), Blasting Principles for Open Pit Mining: General Design Concepts, Balkema.
  43. Iverson, S., Hustrulid, W., Johnson, J., Tesarik, D. and Akbarzadeh, Y. (2009). "The extent of blast damage from a fully coupled explosive charge", Proceedings of the 9th International Symposium on Rock Fragmentation by Blasting, (Fragblast-9).
  44. Jimeno, C.L., Jimeno, E.L., Carcedo, F.J.A. and De Ramiro, Y.V. (1995), Drilling and Blasting of Rocks, CRC Press.
  45. Johnson, J.C. (2010), The Hustrulid Bar-A Dynamic Strength Test and its Application to the Cautious Blasting of Rock, The University of Utah.
  46. Kaloop, M.R., Bardhan, A., Samui, P., Hu, J.W. and Zarzoura, F. (2022), "Computational intelligence approaches for estimating the unconfined compressive strength of rocks", Arabian J. Geosci., 16(1), 37. https://doi.org/10.1007/s12517-022-11085-3.
  47. Kanchibotla, S.S., Valery, W. and Morrell, S. (1999). "Modelling fines in blast fragmentation and its impact on crushing and grinding", Proceedings of the Explo '99-A Conference on Rock Breaking, The Australasian Institute of Mining and Metallurgy, Kalgoorlie, Australia.
  48. Konya, C.J. and Walter, E.J. (1991), Rock Blasting and Overbreak Control, United States. Federal Highway Administration.
  49. Lansivaara, T.T., Farhadi, M.S. and Samui, P. (2023), "Performance of traditional and machine learning-based transformation models for undrained shear strength", Arabian J. Geosci., 16(3), 183. https://doi.org/10.1007/s12517-022-11173-4.
  50. Le, T.T., Skentou, A.D., Mamou, A. and Asteris, P.G. (2022), "Correlating the unconfined compressive strength of rock with the compressional wave velocity effective porosity and schmidt hammer rebound number using artificial neural networks", Rock Mech. Rock Eng., 55(11), 6805-6840. https://doi.org/10.1007/s00603-022-02992-8.
  51. Li, C., Zhou, J., Khandelwal, M., Zhang, X., Monjezi, M. and Qiu, Y. (2022), "Six novel hybrid extreme learning machine-swarm intelligence optimization (ELM-SIO) models for predicting backbreak in open-pit blasting", Natural Resour. Res., 31(5), 3017-3039. https://doi.org/10.1007/s11053-022-10082-3.
  52. Liu, L.L. and Wang, X.M. (2021), "Landslide susceptibility assessment using feature selection-based machine learning models", Geomech. Eng., 25(1), 1-16. https://doi.org/10.12989/gae.2021.25.1.001.
  53. Menad, N.A. and Noureddine, Z. (2019), "An efficient methodology for multi-objective optimization of water alternating CO2 EOR process", J. Taiwan Inst. Chem. Engineers, 99, 154-165. https://doi.org/10.1016/j.jtice.2019.03.016.
  54. Mirjalili, S. (2016), "Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems", Neural Comput. Appl., 27(4), 1053-1073. https://doi.org/10.1007/s00521-015-1920-1.
  55. Mirjalili, S., Song Dong, J., Sadiq, A.S. and Faris, H. (2020), Genetic Algorithm: Theory, Literature Review, and Application in Image Reconstruction, Springer International Publishing, Cham. https://doi.org/10.1007/978-3-030-12127-3_5.
  56. Moayedi, H., Abdullahi, M.a.M., Nguyen, H. and Rashid, A.S.A. (2021), "Comparison of dragonfly algorithm and Harris hawks optimization evolutionary data mining techniques for the assessment of bearing capacity of footings over two-layer foundation soils", Eng. with Comput., 37(1), 437-447. http://doi.org/10.1007/s00366-019-00834-w.
  57. Morrell, S. (2004), "Predicting the specific energy of autogenous and semi-autogenous mills from small diameter drill core samples", Minerals Eng., 17(3), 447-451. http://doi.org/10.1016/j.mineng.2003.10.019.
  58. Nait Amar, M. (2020), "Modeling solubility of sulfur in pure hydrogen sulfide and sour gas mixtures using rigorous machine learning methods", Int. J. Hydrogen Energ., 45(58), 33274-33287. https://doi.org/10.1016/j.ijhydene.2020.09.145.
  59. Nait Amar, M., Jahanbani Ghahfarokhi, A., Ng, C.S.W. and Zeraibi, N. (2021a), "Optimization of WAG in real geological field using rigorous soft computing techniques and nature-inspired algorithms", J. Petroleum Sci. Eng., 206, 109038. https://doi.org/10.1016/j.petrol.2021.109038.
  60. Nait Amar, M. and Zeraibi, N. (2019), "An efficient methodology for multi-objective optimization of water alternating CO2 EOR process", J. Taiwan Inst. Chem. Engineers, 99, 154-165. https://doi.org/10.1016/j.jtice.2019.03.016.
  61. Nait Amar, M., Ghriga, M.A., Ben Seghier, M.E.A. and Ouaer H. (2021b), "Predicting solubility of nitrous oxide in ionic liquids using machine learning techniques and gene expression programming", J. Taiwan Inst. Chem. Engineers, 128, 156-168. https://doi.org/10.1016/j.jtice.2021.08.042
  62. Nait Amar, M., Ghriga, M.A. and Ouaer, H. (2021c), "On the evaluation of solubility of hydrogen sulfide in ionic liquids using advanced committee machine intelligent systems", J. Taiwan Inst. Chem. Engineers, 118, 159-168. https://doi.org/10.1016/j.jtice.2021.01.007.
  63. Napier-Munn, T.J., Morrell, S., Morrison, R.D. and Kojovic, T. (1996), Mineral Comminution Circuits: Their Operation And Optimisation, Julius Kruttschnitt Mineral Research Centre, University of Queensland, Indooroopilly, Qld Australia.
  64. Ouchterlony, F. (2005), "The Swebrec© function: linking fragmentation by blasting and crushing", Min. Tech., 114(1), 29-44. https://doi.org/10.1179/037178405X44539.
  65. Pan, C.J., Tsai, M.C., Su, W.N., Rick, J., Akalework, N.G., Agegnehu, A.K., Cheng, S.-Y. and Hwang, B.-J. (2017), "Tuning/exploiting Strong Metal-Support Interaction (SMSI) in Heterogeneous Catalysis", J. Taiwan Inst. Chem. Engineers, 74, 154-186. https://doi.org/10.1016/j.jtice.2017.02.012.
  66. Rahimi, R. and Abdollahzade, A. (2020), "Study the process of self dilution in thickeners by computational fluid dynamics", J. Anal. Numer. Method. Min. Eng., 9(21), 33-42. https://doi.org/10.29252/anm.2019.8929.1311.
  67. Rao, R.V., Savsani, V.J. and Vakharia, D.P. (2011), "Teaching-learning-based optimization: A novel method for constrained mechanical design optimization problems", Comput.-Aided Design. 43(3), 303-315, http://doi.org/10.1016/j.cad.2010.12.015.
  68. Shadab Far, M., Wang, Y. and Dallo, Y.A.H. (2019), "Reliability analysis of the induced damage for single-hole rock blasting", Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards. 13(1), 82-98, https://doi.org/10.1080/17499518.2018.1508728.
  69. Skentou, A.D., Bardhan, A., Mamou, A., Lemonis, M.E., Kumar, G., Samui, P., Armaghani, D.J. and Asteris, P.G. (2023), "Closed-form equation for estimating unconfined compressive strength of granite from three non-destructive tests using soft computing models", Rock Mech. Rock Eng., 56(1), 487-514. https://doi.org/10.1007/s00603-022-03046-9.
  70. Soltani-Mohammadi, S., Amnieh, H.B. and Bahadori, M. (2011), "Predicting ground vibration caused by blasting operations in Sarcheshmeh copper mine considering the charge type by adaptive neuro-fuzzy inference system (ANFIS)", Archiv. Min. Sci., 56(4), 701-710.
  71. Sui Kim, I.T., Sethu, V., Arumugasamy, S.K. and Selvarajoo, A. (2020), "Fenugreek seeds and okra for the treatment of palm oil mill effluent (POME) - Characterization studies and modeling with backpropagation feedforward neural network (BFNN)", J. Water Process Eng., 37, 101500. https://doi.org/10.1016/j.jwpe.2020.101500.
  72. Taylor, K.E. (2001), "Summarizing multiple aspects of model performance in a single diagram", J. Geophys. Res.: Atmos., 106(7), 7183-7192. http://doi.org/10.1029/2000JD900719.
  73. Wyllie, D.C. and Mah, C. (2004), Rock Slope Engineering, CRC Press.
  74. Xie, C., Nguyen, H., Bui, X.-N., Choi, Y., Zhou, J. and Nguyen-Trang, T. (2021), "Predicting rock size distribution in mine blasting using various novel soft computing models based on meta-heuristics and machine learning algorithms", Geosci. Front., 12(3). https://doi.org/101108, 10.1016/j.gsf.2020.11.005.
  75. Zeng, J., Asteris, P.G., Mamou, A.P., Mohammed, A.S., Golias, E.A., Armaghani, D.J., Faizi, K. and Hasanipanah, M. (2021), "The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand", Appl. Sci., 11(3). https://doi.org/10.3390/app11030908.
  76. Zhou, J., Dai, Y., Khandelwal, M., Monjezi, M., Yu, Z. and Qiu, Y. (2021a), "Performance of hybrid SCA-RF and HHO-RF models for predicting backbreak in open-pit mine blasting operations", Natural Resour. Res., 30(6), 4753-4771. https://doi.org/10.1007/s11053-021-09929-y.
  77. Zhou, J., Li, C., Arslan, C.A., Hasanipanah, M. and Bakhshandeh Amnieh, H. (2021b), "Performance evaluation of hybrid FFA-ANFIS and GA-ANFIS models to predict particle size distribution of a muck-pile after blasting", Eng. with Comput., 37(1), 265-274. https://doi.org/10.1007/s00366-019-00822-0.
  78. Zhou, J., Qiu, Y., Khandelwal, M., Zhu, S. and Zhang, X. (2021c), "Developing a hybrid model of Jaya algorithm-based extreme gradient boosting machine to estimate blast-induced ground vibrations", Int. J. Rock Mech. Min. Sci., 145, 104856. https://doi.org/10.1016/j.ijrmms.2021.104856.
  79. Zhou, J., Shen, X., Qiu, Y., Shi, X. and Khandelwal, M. (2022), "Cross-correlation stacking-based microseismic source location using three metaheuristic optimization algorithms", Tunn. Undergr. Sp. Tech., 126, 104570. https://doi.org/10.1016/j.tust.2022.104570.
  80. Zimmermann, A.S. and Mattedi, S. (2020), "Density and speed of sound prediction for binary mixtures of water and ammonium-based ionic liquids using feedforward and cascade forward neural networks", J. Molecular Liquids, 311, 113212. https: //doi.org/10.1016/j.molliq.2020.113212.