Numerical and Data-Driven Optimization of Counterflow Classifier Support Structures Considering Deflection, Stress, Weight, and Manufacturing Cost
DOI:
https://doi.org/10.23960/jemit.535Keywords:
counterflow classifier, finite element analysis, machine learning, surrogate modeling, multi-objective optimization, structural optimization, manufacturing costAbstract
Counterflow classifier machines are widely used in industrial separation processes, including tobacco primary processing, where structural stability is essential to maintain operational reliability and production continuity. Excessive deflection of support structures may reduce component alignment, increase vibration transmission, accelerate wear, and increase maintenance costs. This study proposes a numerical and data-driven optimization framework for redesigning counterflow classifier support structures by considering maximum deflection, von Mises stress, structural weight, safety factor, and manufacturing cost. A baseline support structure was reconstructed using computer-aided design, followed by finite element analysis under fixed–fixed boundary conditions and operational loading. Parametric design variables included hollow section thickness, section height, section width, number of supports, support position, cross-support angle, and material type. A synthetic design dataset was generated from finite element simulations and used to train machine learning surrogate models, including random forest, gradient boosting, Gaussian process regression, and artificial neural network models. The best surrogate model was subsequently integrated with a multi-objective optimization procedure to identify Pareto-optimal design candidates. The representative results showed that the optimized hollow reinforced structure (Opt-5) reduced maximum deflection by approximately 49.2% compared with the baseline design, while achieving 40.5% lower manufacturing cost and 54.3% lower weight compared with the solid candidate design (D06), all while maintaining a safety factor greater than 2.0. The proposed framework demonstrates that the integration of finite element analysis, machine learning surrogate modeling, and multi-objective optimization can provide an efficient approach for industrial machinery redesign and structural decision-making.
Downloads
References
Blakey-Milner, B., Gradl, P., Snedden, G., Brooks, M., Pitot, J., Lopez, E., Leary, M., Berto, F., & du Plessis, A. (2021). Metal additive manufacturing in aerospace: A review. Materials & Design, 209, Article 110008. https://doi.org/10.1016/j.matdes.2021.110008
Cuomo, S., Schiano, V., Cola, D., Giampaolo, F., Rozza, G., Raissi, M., & Piccialli, F. (2022). Scientific machine learning through physics-informed neural networks: Where we are and what's next. Journal of Scientific Computing, 92(3), Article 88. https://doi.org/10.1007/s10915-022-01939-z
Gad, A. G. (2022). Particle swarm optimization algorithm and its applications: A systematic review. Archives of Computational Methods in Engineering, 29, 2531-2561. https://doi.org/10.1007/s11831-021-09694-4
Ghafariasl, P., Mahmoudan, A., Mohammadi, M., Nazarparvar, A., Hoseinzadeh, S., Fathali, M., Chang, S., Zeinalnezhad, M., & Astiaso Garcia, D. (2024). Neural network-based surrogate modeling and optimization of a multigeneration system. Applied Energy, 364, Article 123130. https://doi.org/10.1016/j.apenergy.2024.123130
Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A. (2024). Interpreting black-box models: A review on explainable artificial intelligence. Cognitive Computation, 16, 45-74. https://doi.org/10.1007/s12559-023-10179-8
Hosamo, H. H., Tingstveit, M. S., Nielsen, H. K., Svennevig, P. R., & Svidt, K. (2022). Multiobjective optimization of building energy consumption and thermal comfort based on integrated BIM framework with machine learning-NSGA II. Energy and Buildings, 277, Article 112479. https://doi.org/10.1016/j.enbuild.2022.112479
Kannangara, K. K. P. M., Zhou, W., Ding, Z., & Hong, Z. (2022). Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method. Journal of Rock Mechanics and Geotechnical Engineering, 14(4), 1052-1063. https://doi.org/10.1016/j.jrmge.2022.01.002
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3, 422-440. https://doi.org/10.1038/s42254-021-00314-5
Kristombu Baduge, S., Thilakarathna, S., Perera, J. S., Arashpour, M., Sharafi, P., Teodosio, B., Shringi, A., & Mendis, P. (2022). Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications. Automation in Construction, 141, Article 104440. https://doi.org/10.1016/j.autcon.2022.104440
Kudela, J., & Matousek, R. (2022). Recent advances and applications of surrogate models for finite element method computations: A review. Soft Computing, 26(24), 13709-13733. https://doi.org/10.1007/s00500-022-07362-8
Liu, G., Zhang, X., Chen, X., He, Y., Cheng, L., Huo, M., Yin, J., Hao, F., Chen, S., Wang, P., Yi, S., Wan, L., Mao, Z., Chen, Z., Wang, X., Cao, Z., & Lu, J. (2021). Additive manufacturing of structural materials. Materials Science and Engineering: R: Reports, 145, Article 100596. https://doi.org/10.1016/j.mser.2020.100596
Maharani, N. F. R., Pratama, N. R., & Dachyar, M. (2024). E-commerce promotional products selection using SWARA and TOPSIS. International Journal of Innovative Science and Research Technology, 9(4), 2925-2932. https://doi.org/10.38124/ijisrt/ijisrt24apr2676
Picard, M., Scott-Boyer, M.-P., Bodein, A., Périn, O., & Droit, A. (2021). Integration strategies of multi-omics data for machine learning analysis. Computational and Structural Biotechnology Journal, 19, 3735-3746. https://doi.org/10.1016/j.csbj.2021.06.030
Sahoo, S. K., & Goswami, S. S. (2023). A comprehensive review of multiple criteria decision-making (MCDM) methods: Advancements, applications, and future directions. Decision Making Advances, 1(1), 25-48. https://doi.org/10.31181/dma1120237
Samadian, D., Muhit, I. B., & Dawood, N. (2025). Application of data-driven surrogate models in structural engineering: A literature review. Archives of Computational Methods in Engineering, 32(2). https://doi.org/10.1007/s11831-024-10152-0
Sotoudeh-Anvari, A. (2022). The applications of MCDM methods in COVID-19 pandemic: A state of the art review. Applied Soft Computing, 126, Article 109238. https://doi.org/10.1016/j.asoc.2022.109238
Thompson, A. P., Aktulga, H. M., Berger, R., Bolintineanu, D. S., Brown, W. M., Crozier, P. S., in 't Veld, P. J., Kohlmeyer, A., Moore, S. G., Nguyen, T. D., Shan, R., Stevens, M. J., Tranchida, J., Trott, C., & Plimpton, S. J. (2022). LAMMPS: A flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Computer Physics Communications, 271, Article 108171. https://doi.org/10.1016/j.cpc.2021.108171
Wang, L., Pan, Z., & Wang, J. (2021). A review of reinforcement learning based intelligent optimization for manufacturing scheduling. Complex System Modeling and Simulation, 1(4), 257-270. https://doi.org/10.23919/CSMS.2021.0027
Wu, J., Sigmund, O., & Groen, J. P. (2021). Topology optimization of multi-scale structures: A review. Structural and Multidisciplinary Optimization, 63, 1455-1480. https://doi.org/10.1007/s00158-021-02881-8
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026

This work is licensed under a Creative Commons Attribution 4.0 International License.







