Search Advanced

Journal of Industrial and Management Optimization

2026, Volume 22, Issue 1: 256-281. doi: 10.3934/jimo.2026010
Previous Article Next Article
Research article

A multi-objective framework based on estimation of distribution algorithms for data-driven fuel experimental design

  • 1.
    Universidad Politécnica de Madrid, Madrid, Spain
  • 2.
    Repsol Technology Lab., Madrid, Spain
  • Published: 21 November 2025

  • 90C29, 62K05

  • Fuel design is a critical field of energy production, demanding precision, efficiency, and safety. Hence, laboratory experimentation is a fundamental step for finding the best formula that can tackle further constraints. Given that laboratory experimentation is costly and time-consuming, there is a compelling need for an efficient approach to undertake it This challenge has led to the development of intelligent methods, instead of using the traditional alternatives in sampling methods over the cost function. In this article, we propose a pioneering approach based on multi-objective optimization using estimation of distribution algorithms to find the optimal fuel formula. This approach suggests the set of experiments that should be carried out in the laboratory. We went one step further allowing experts to set those ingredients that should take a fixed value in the formulation and also controlling the exploration/exploitation trade-off of the optimizer. The resulting output for the experts is a diverse set of experiments to carry out. Our findings unveiled a spectrum of results across varying levels of exploration. When compared with some state-of-the-art optimizers, our estimation of distribution algorithm approach outperforms them. Moreover, we identified several ingredients, traditionally not considered by the experts, whose presence in the total mixture has a major impact on the fuel performance. This enriches the overall interpretability of both our methodology and the underlying fuel design challenge.

    Citation: Vicente P. Soloviev, Pedro Larrañaga, Marco Bernabei, Marina A. Chirita, Jose M. Seoane, Pedro Fontán, Concha Bielza. A multi-objective framework based on estimation of distribution algorithms for data-driven fuel experimental design[J]. Journal of Industrial and Management Optimization, 2026, 22(1): 256-281. doi: 10.3934/jimo.2026010

    Related Papers:

  • Fuel design is a critical field of energy production, demanding precision, efficiency, and safety. Hence, laboratory experimentation is a fundamental step for finding the best formula that can tackle further constraints. Given that laboratory experimentation is costly and time-consuming, there is a compelling need for an efficient approach to undertake it This challenge has led to the development of intelligent methods, instead of using the traditional alternatives in sampling methods over the cost function. In this article, we propose a pioneering approach based on multi-objective optimization using estimation of distribution algorithms to find the optimal fuel formula. This approach suggests the set of experiments that should be carried out in the laboratory. We went one step further allowing experts to set those ingredients that should take a fixed value in the formulation and also controlling the exploration/exploitation trade-off of the optimizer. The resulting output for the experts is a diverse set of experiments to carry out. Our findings unveiled a spectrum of results across varying levels of exploration. When compared with some state-of-the-art optimizers, our estimation of distribution algorithm approach outperforms them. Moreover, we identified several ingredients, traditionally not considered by the experts, whose presence in the total mixture has a major impact on the fuel performance. This enriches the overall interpretability of both our methodology and the underlying fuel design challenge.



    加载中


    [1] J. Deutch, Is net zero carbon 2050 possible?, Joule 4 (2020), 2237–2240. https://doi.org/10.1016/j.joule.2020.09.002 doi: 10.1016/j.joule.2020.09.002
    [2] K. C. Seto, G. Churkina, A. Hsu, M. Keller, P. W. G. Newman, B. Qin, et al., From low-to net-zero carbon cities: The next global agenda, Annu. Rev. Environ. Resour., 46 (2021), 377–415. https://doi.org/10.1146/annurev-environ-050120-113117 doi: 10.1146/annurev-environ-050120-113117
    [3] A. Jankovic, G. Chaudhary, F. Goia, Designing the design of experiments (doe)–an investigation on the influence of different factorial designs on the characterization of complex systems, Energy Build., 250 (2021), 111298. https://doi.org/10.1016/j.enbuild.2021.111298 doi: 10.1016/j.enbuild.2021.111298
    [4] F. A. C. Viana, Things you wanted to know about the latin hypercube design and were afraid to ask, 10th World Congr. Struct. Multidiscip. Optim. vol., 19 (2013), 1–9.
    [5] H. Vieira, S. M. Sanchez, K. H. Kienitz, M. C. N. Belderrain, Efficient, nearly orthogonal-and-balanced, mixed designs: An effective way to conduct trade-off analyses via simulation, J. Simul., 7 (2013), 264–275. https://doi.org/10.1057/jos.2013.14 doi: 10.1057/jos.2013.14
    [6] R. H. Myers, D. C. Montgomery, C. M. Anderson-Cook, Response surface methodology: Process and product optimization using designed experiments, John Wiley Sons, 2016. https://doi.org/10.1080/00224065.2017.11917988 doi: 10.1080/00224065.2017.11917988
    [7] V. P. Soloviev, P. Larrañaga, C. Bielza, Estimation of distribution algorithms using gaussian bayesian networks to solve industrial optimization problems constrained by environment variables, J. Combin. Optim., 44 (2022), 1077–1098. https://doi.org/10.1007/s10878-022-00879-6 doi: 10.1007/s10878-022-00879-6
    [8] H. Liu, Y. S. Ong, J. Cai, A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design, Struct. Multidiscip. Optim., 57 (2018), 393–416. https://doi.org/10.1007/s00158-017-1739-8 doi: 10.1007/s00158-017-1739-8
    [9] S. Greenhill, S. Rana, S. Gupta, P. Vellanki, S. Venkatesh, Bayesian optimization for adaptive experimental design: A review, IEEE Access, 8 (2020), 13937–13948. https://doi.org/10.1109/ACCESS.2020.2966228 doi: 10.1109/ACCESS.2020.2966228
    [10] K. Hanaoka, Comparison of conceptually different multi-objective bayesian optimization methods for material design problems, Mater. Today Commun., 31 (2022), 103440. https://doi.org/10.1016/j.mtcomm.2022.103440 doi: 10.1016/j.mtcomm.2022.103440
    [11] K. Hanaoka, Bayesian optimization for goal-oriented multi-objective inverse material design, iScience, 24 (2021), 102781. https://doi.org/10.1016/j.isci.2021.102781 doi: 10.1016/j.isci.2021.102781
    [12] X. Sun, Z. Shi, G. Lei, Y. Guo, J. Zhu, Multi-objective design optimization of an ipmsm based on multilevel strategy, IEEE Trans. Ind. Electron., 68 (2020), 139–148. https://doi.org/10.1109/TIE.2020.2965463 doi: 10.1109/TIE.2020.2965463
    [13] Z. Pan, D. Lei, L. Wang, A knowledge-based two-population optimization algorithm for distributed energy-efficient parallel machines scheduling, IEEE Trans. Cybern., 52 (2020), 5051–5063. https://doi.org/10.1109/TCYB.2020.3026571 doi: 10.1109/TCYB.2020.3026571
    [14] H. Wang, B. R. Sarker, J. Li, J. Li, Adaptive scheduling for assembly job shop with uncertain assembly times based on dual q-learning, Int. J. Prod. Res., 59 (2021), 5867–5883. https://doi.org/10.1080/00207543.2020.1794075 doi: 10.1080/00207543.2020.1794075
    [15] F. Zhao, F. Yin, L. Wang, Y. Yu, A co-evolution algorithm with dueling reinforcement learning mechanism for the energy-aware distributed heterogeneous flexible flow-shop scheduling problem, IEEE Trans. Syst. Man. Cybern. Syst., 55 (2024), 1794–1809. https://doi.org/10.1109/TSMC.2024.3510384 doi: 10.1109/TSMC.2024.3510384
    [16] M. Khishe, N. Orouji, M. R. Mosavi, Multi-objective chimp optimizer: an innovative algorithm for multi-objective problems, Expert Syst. Appl., 211 (2023), 118734. https://doi.org/10.1016/j.eswa.2022.118734 doi: 10.1016/j.eswa.2022.118734
    [17] Q. Wang, G. Chen, M. Khishe, B. F. Ibrahim, S. Rashidi, Multi-objective optimization of iot-based green building energy system using binary metaheuristic algorithms, J. Build. Eng., 68 (2023), 106031. https://doi.org/10.1016/j.jobe.2023.106031 doi: 10.1016/j.jobe.2023.106031
    [18] N. Mashru, G. G. Tejani, P. Patel, M. Khishe, Optimal truss design with moho: A multi-objective optimization perspective, PLoS One, 19 (2024), e0308474. https://doi.org/10.1371/journal.pone.0308474 doi: 10.1371/journal.pone.0308474
    [19] S. Liu, J. Li, H. Aghajanirefah, Reinforced concrete structures with damped seismic buckling-restrained bracing optimization using multi-objective evolutionary niching choa, Steel Compos. Struct., 47 (2023), 147. https://doi.org/10.1017/ssh.2022.38 doi: 10.1017/ssh.2022.38
    [20] M. Aljaidi, N. Mashru, P. Patel, D. Adalja, P. Jangir, Arpita, et al., Morime: A multi-objective rime optimization framework for efficient truss design, Results Eng., 25 (2025), 103933. https://doi.org/10.1016/j.rineng.2025.103933 doi: 10.1016/j.rineng.2025.103933
    [21] P. Patel, D. Adalja, N. Mashru, Multi objective elk herd optimization for efficient structural design, Sci. Rep. 15 (2025), 11767. https://doi.org/10.1038/s41598-025-96263-5 doi: 10.1038/s41598-025-96263-5
    [22] X. Liu, W. Zuo, Q. Li, K. Zhou, Y. H. Huang, Y. W. Li, et al., Multi-objective optimization of an ammonia-fueled micro planar combustor with a secondary oxygen injection for thermophotovoltaic applications, Energy, 385 (2025), 138044. https://doi.org/10.1016/j.energy.2025.138044 doi: 10.1016/j.energy.2025.138044
    [23] W. Zuo, F. Li, Q. Li, Z. J. Chen, Y. H. Huang, H. Q. Chu, Multi-objective optimization of micro planar combustor with tube outlet by rsm and nsga-ii for thermophotovoltaic applications, Energy, 291 (2024), 130396. https://doi.org/10.1016/j.energy.2024.130396 doi: 10.1016/j.energy.2024.130396
    [24] Z. Fu, W. Zuo, Q. Li, K. Zhou, Y. H. Huang, Y. W. Li, Multi-objective optimization of liquid cooling plate partially filled with porous medium for thermal management of lithium-ion battery pack by rsm, nsga-ii and topsis, Energy 318 (2025), 134853. https://doi.org/10.1016/j.energy.2025.134853 doi: 10.1016/j.energy.2025.134853
    [25] W. Zuo, D. Li, Q. Li, Q. J. Cheng, K. Zhou, J. Qiang, Multi-objective optimization of multi-channel cold plate under intermittent pulsating flow by rsm and nsga-ii for thermal management of electric vehicle lithium-ion battery pack, Energy, 283 (2023), 129085. https://doi.org/10.1016/j.energy.2023.129085 doi: 10.1016/j.energy.2023.129085
    [26] J. Li, W. Zuo, Y. Zhang, Q. Q. Li, K. Sun, K. Zhou, et al., Multi-objective optimization of miniu-channel cold plate with sio2 nanofluid by rsm and nsga-ii, Energy, 242 (2022), 123039. https://doi.org/10.1016/j.energy.2021.123039 doi: 10.1016/j.energy.2021.123039
    [27] Z. Chen, W. Zuo, K. Zhou, Q. Q. Li, Y. H. Huang, J. Qiang, Multi-objective optimization of proton exchange membrane fuel cells by rsm and nsga-ii, Energy Convers. Manage., 277 (2023), 116691. https://doi.org/10.1016/j.enconman.2023.116691 doi: 10.1016/j.enconman.2023.116691
    [28] P. Larrañaga, J. A. Lozano, Estimation of distribution algorithms: A new tool for evolutionary computation, Kluwer Academic Publishers, 2001.
    [29] C. A. Coello, Evolutionary algorithms for solving multi-objective problems, Springer, 2007.
    [30] D. Koller, N. Friedman, Probabilistic graphical models: Principles and techniques, The MIT. Press, 2009.
    [31] J. Ceberio, A. Mendiburu, J. A. Lozano, A roadmap for solving optimization problems with estimation of distribution algorithms, Nat. Comput., 23 (2022), 1–15. https://doi.org/10.1007/s11047-022-09913-2 doi: 10.1007/s11047-022-09913-2
    [32] R. Armañanzas, I. Inza, R. Santana, Y. Saeys, J. L. Flores, J. A. Lozano, et al., A review of estimation of distribution algorithms in bioinformatics, BioData Mining, 1 (2008), 1–12. https://doi.org/10.1186/1756-0381-1-6 doi: 10.1186/1756-0381-1-6
    [33] V. P. Soloviev, P. Larrañaga, C. Bielza, Quantum parametric circuit optimization with estimation of distribution algorithms, Proc. Genet. Evol. Comput. Congr. Companion, 4 (2022), 2247–2250. https://doi.org/10.1145/3520304.3533963 doi: 10.1145/3520304.3533963
    [34] H. Karshenas, R. Santana, C. Bielza, P. Larrañaga, Multiobjective estimation of distribution algorithm based on joint modeling of objectives and variables, IEEE Trans. Evol. Comput., 18 (2013), 519–542. https://doi.org/10.1109/TEVC.2013.2281524 doi: 10.1109/TEVC.2013.2281524
    [35] K. Metaxiotis, K. Liagkouras, Multiobjective evolutionary algorithms for portfolio management: A comprehensive literature review, Expert Syst. Appl., 39 (2012), 11685–11698. https://doi.org/10.1016/j.eswa.2012.04.053 doi: 10.1016/j.eswa.2012.04.053
    [36] A. Mukhopadhyay, U. Maulik, S. Bandyopadhyay, C. A. Coello, A survey of multiobjective evolutionary algorithms for data mining: Part i, IEEE Trans. Evol. Comput., 18 (2013), 4–19. https://doi.org/10.1109/TEVC.2013.2290086 doi: 10.1109/TEVC.2013.2290086
    [37] Z. Wang, M. Li, J. Li, A multi-objective evolutionary algorithm for feature selection based on mutual information with a new redundancy measure, Inf. Sci., 307 (2015), 73–88. https://doi.org/10.1016/j.ins.2015.02.031 doi: 10.1016/j.ins.2015.02.031
    [38] H. Mühlenbein, J. Bendisch, H. M. Voigt, From recombination of genes to the estimation of distributions ii. continuous parameters, Int. Conf. Parallel Problem Solving from Nature, 1996,188–197. https://doi.org/10.1007/3-540-61723-X_983 doi: 10.1007/3-540-61723-X_983
    [39] P. Larrañaga, R. Etxeberria, J. A. Lozano, J. M. Peña, Optimization in continuous domains by learning and simulation of gaussian networks, Proc. Genet. Evol. Comput. Congr., 2000,201–204. https://doi.org/10.1007/11903697_69 doi: 10.1007/11903697_69
    [40] V. P. Soloviev, C. Bielza, P. Larrañaga, Semiparametric estimation of distribution algorithms for continuous optimization, IEEE Trans. Evol. Comput., 4 (2023), 1069–1083. https://doi.org/10.1109/TEVC.2023.3290670 doi: 10.1109/TEVC.2023.3290670
    [41] N. Khan, D. E. Goldberg, M. Pelikan, Multi-objective bayesian optimization algorithm, Proc. 4th Annu. Conf. Genet. Evol. Comput., 8 (2022), 684–684. https://doi.org/10.1016/j.softx.2020.100520 doi: 10.1016/j.softx.2020.100520
    [42] M. Pelikan, D. E. Goldberg, E. Cantú-Paz, Boa: The bayesian optimization algorithm, Proc. Genet. Evol. Comput. Congr., 1999,525–532.
    [43] K. Deb, A. Pratap, S. Agarwal, T. A. Meyarivan, A fast and elitist multiobjective genetic algorithm: Nsga-ii, IEEE Trans. Evol. Comput., 6 (2002), 182–197. https://doi.org/10.1109/4235.996017 doi: 10.1109/4235.996017
    [44] M. Pelikan, K. Sastry, D. E. Goldberg, Multiobjective hboa, clustering, and scalability, Proc. 7th Annu. Conf. Genet. Evol. Comput., 8 (2005), 663–670. https://doi.org/10.1145/1068009.1068122 doi: 10.1145/1068009.1068122
    [45] K. P. Murphy, Machine learning: A probabilistic perspective, The MIT. Press, 2012.
    [46] C. Bielza, P. Larrañaga, Bayesian networks in neuroscience: A survey, Front. Comput. Neurosci., 8 (2014), 131. https://doi.org/10.7209/tanso.2014.131 doi: 10.7209/tanso.2014.131
    [47] C. Puerto-Santana, P. Larrañaga, C. Bielza, Autoregressive asymmetric linear gaussian hidden markov models, IEEE Trans. Pattern Anal. Mach. Intell., 9 (2021), 4642–4658. https://doi.org/10.1109/TPAMI.2021.3068799 doi: 10.1109/TPAMI.2021.3068799
    [48] B. Mihaljević, C. Bielza, P. Larrañaga, Bayesian networks for interpretable machine learning and optimization, Neurocomputing, 456 (2021), 648–665. https://doi.org/10.1016/j.neucom.2021.01.138 doi: 10.1016/j.neucom.2021.01.138
    [49] I. Tsamardinos, C. F. Aliferis, Towards principled feature selection: Relevancy, filters and wrappers, Int. Workshop Artif. Intell. Stat., 2003,300–307.
    [50] M. Li, X. Yao, Quality evaluation of solution sets in multiobjective optimisation: A survey, ACM Comput. Surv., 52 (2019), 1–38. https://doi.org/10.1145/3300148 doi: 10.1145/3300148
    [51] E. Zitzler, L. Thiele, M. Laumanns, C. M. Fonseca, V. G. Da Fonseca, Performance assessment of multiobjective optimizers: An analysis and review, IEEE Trans. Evol. Comput., 7 (2003), 117–132. https://doi.org/10.1109/TEVC.2003.810758 doi: 10.1109/TEVC.2003.810758
    [52] F. Pedregosa, G. Varoquaux, A. Gramfort, Scikit-learn: Machine learning in python, J. Mach. Learn. Res., 12 (2011), 2825–2830.
    [53] J. Bergstra, D. Yamins, D. Cox, Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures, Int. Conf. Mach. Learn., 2013,115–123.
    [54] K. T. Fang, R. Li, A. Sudjianto, Design and modeling for computer experiments, CRC Press, 2005. https://doi.org/10.1201/9781420034899
    [55] S. Lloyd, Least squares quantization in pcm, IEEE Trans. Inf. Theory, 28 (1982), 129–137. https://doi.org/10.1109/TIT.1982.1056489 doi: 10.1109/TIT.1982.1056489
    [56] Q. Zhang, H. Li, Moea/d: A multiobjective evolutionary algorithm based on decomposition, IEEE Trans. Evol. Comput., 11 (2007), 712–731. https://doi.org/10.1109/TEVC.2007.892759 doi: 10.1109/TEVC.2007.892759
    [57] J. Kaufmann, A. Schering, Analysis of variance anova, Wiley Encycl. Clin. Trials, 2007. https://doi.org/10.1002/9781118445112.stat06938 doi: 10.1002/9781118445112.stat06938
  • jimo-22-01-010-s001.pdf
  • Reader Comments
  • © 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索
Journal of Industrial and Management Optimization
1.6 3.3

Metrics

Article views(400) PDF downloads(19) Cited by(0)

Preview PDF
Download XML
Export Citation
Article outline

Figures and Tables

Figures(13)  /  Tables(3)

Other Articles By Authors

Related pages

Tools

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog