Next Article in Journal
Carbon Quantum Dot-Based Sensors: Photochemical Principles and Multimodal Applications
Previous Article in Journal
A Review on Ultra-High-Strength Aluminum Alloys for Aerospace Applications: Forming, Microstructure, and Mechanical Properties
Previous Article in Special Issue
Study on the Noise Reduction Characteristics of Porous Elastic Road Surface Based on Finite Element Analysis and Noise Field Tests
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Materials
Volume 19
Issue 9
10.3390/ma19091808
materials-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Editorial

Artificial Intelligence in Materials Science and Engineering

by
Piotr Lacki
1,*,
Janina Adamus
1,
Anna Derlatka
1,
Wojciech Więckowski
2 and
Krzysztof Cpałka
3
1
Department of Civil Engineering, Czestochowa University of Technology, Dabrowskiego 69, 42-201 Czestochowa, Poland
2
Department of Mechanical Engineering, Czestochowa University of Technology, Dabrowskiego 69, 42-201 Czestochowa, Poland
3
Department of Artificial Intelligence, Czestochowa University of Technology, Dabrowskiego 69, 42-201 Czestochowa, Poland
*
Author to whom correspondence should be addressed.
Materials 2026, 19(9), 1808; https://doi.org/10.3390/ma19091808
Submission received: 27 March 2026 / Accepted: 22 April 2026 / Published: 29 April 2026
(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)
Versions Notes
The collection of 20 scientific articles published within the Special Issue titled “Artificial Intelligence in Materials Science and Engineering” provides a comprehensive overview of contemporary materials engineering, where traditional research methods are increasingly bolstered by advanced digital tools. These publications, featured in the ‘Materials Simulation and Design’ section, demonstrate how integrating Artificial Intelligence (AI) and numerical methods within Materials Science and Engineering accelerates the development of innovative technologies. This Special Issue serves as an interdisciplinary bridge connecting two often separate worlds: computer science theorists and materials engineering practitioners. AI researchers (computer scientists, mathematicians) frequently seek real-world, complex datasets to validate their models. Conversely, materials engineers possess unique experimental data but may lack the specialized expertise to implement techniques such as various metaheuristic optimization techniques exemplified by the Sparrow Search Algorithm [1,2] or Multi-Task Learning models [3,4]. Publishing these works in a single venue demonstrates to engineers which AI tools have reached the maturity required for laboratory implementation.
The analysis of this collection supports the thesis that integrating AI with materials science is not merely an incremental improvement, but a fundamental paradigm shift. The traditional approach, based on empirical testing of thousands of samples, is being replaced by intentional, digital property design. The application of AI represents a breakthrough in structural design and parameter optimization. Based on the presented works, several dominant research directions can be identified.
Implementation of Machine Learning (ML) and Artificial Intelligence (AI). Artificial Intelligence is employed to optimize manufacturing processes, including the fabrication of functionally graded materials (FGMs) [5] and rotary friction welding [6]. Publication [5] highlights the role of AI in managing the complexity of materials with variable property gradients, which is a critical factor in additive manufacturing (3D printing). ML models such as artificial neural networks, Support Vector Machines (SVMs), and Multi-Task Learning (MTL) algorithms are utilized to predict mechanical properties [3,7,8] and material durability under extreme conditions, such as the frost resistance of concrete [1,9].
The integration of ML facilitates the precise customization of the elastic modulus in lattice materials [7]. Furthermore, the application of Multi-Task Learning in the design of concrete-filled double steel tubes (CFDST) demonstrates AI’s capability to identify nonlinear correlations between structural parameters that traditional design codes cannot directly determine [3,10]. Finally, genetic algorithms (GAs) are implemented to navigate complex design spaces to achieve materials with optimized configurations and target densities [7,11,12].
Utilization of Digital Twins. Current research underscores the increasing significance of AI-augmented Digital Twin systems for real-time process parameter optimization [6,13,14,15] and advanced structural health assessment of storage tanks [16]. Remote equipment monitoring can be facilitated through Internet of Things (IoT) [17,18] frameworks. By integrating these applications with AI-driven algorithms, predictive maintenance strategies can be implemented to extend asset service life and minimize operational downtime. Specifically, IoT sensors enable the real-time acquisition and transmission of critical parameters, such as corrosion rates and structural strain, which are essential for effective storage tank diagnostics. The Digital Twin concept serves as a cornerstone for faultless production and reliable operation. Industry 4.0 frameworks rely on these digital reflections of physical processes to facilitate continuous monitoring and instantaneous optimization. By integrating artificial neural networks (ANNs) with the Finite Element Method (FEM), it is possible to develop a Digital Twin for the rotary friction welding process capable of optimizing parameters in less than 0.1 s [6]. Such solutions enable highly effective adaptive process control. Similarly, numerical simulations of the lost-foam casting process are utilized to eliminate structural defects in critical components for electric vehicles [19]. Modern maintenance systems, particularly for large-scale storage infrastructure, are evolving toward autonomous ecosystems. The integration of robotics (drones), 3D scanning, and AI-driven processing of non-destructive testing (NDT) data enables the creation of digitized equipment models. These systems facilitate predictive maintenance by autonomously estimating the remaining useful life of the assets [16].
Advanced Numerical Simulations (FEM/FEA). The Finite Element Method (FEM) remains the cornerstone for analyzing stress distributions, heat transfer, and structural deformations. It is extensively employed in pavement engineering and design [20,21,22,23,24,25], the thermal insulation analysis of building envelopes [26,27], and the optimization of casting processes for the automotive industry [19]. Specifically, these numerical frameworks allow for the evaluation of complex material behaviors, such as temperature-dependent moduli in asphalt mixtures and heat flow through multi-layered masonry walls, ensuring structural integrity and energy efficiency. In the context of aerospace engineering, publication [28] demonstrates the efficacy of high-fidelity simulations in optimizing stiffened grid panels [29,30], where numerical modeling is essential for balancing weight reduction with structural integrity.
Modeling of Mechanical Properties and Durability. A significant number of studies focus on damage prediction and structural integrity. Numerical models facilitate a deeper understanding of crack initiation mechanisms in compacted graphite iron (CGI) [31,32], as well as the effects of non-uniform longitudinal crack width distribution on the degradation of the rebar–concrete bond in corrosion-affected structures [33,34]. Furthermore, in the aerospace sector, the Hartman–Schijve crack growth equations are employed to support the durability analysis and airworthiness certification of repairs performed using the cold spray deposition method [35,36,37]. These approaches allow for a more precise estimation of service life by accounting for microstructural variability and environmental degradation.
Sustainability and Environmental Engineering. Research in this field encompasses the utilization of industrial waste for the production of eco-friendly self-compacting concrete [38,39] and the evaluation of storage conditions’ impact on the thermal properties of insulation materials, a factor directly influencing energy efficiency and greenhouse gas emission reduction [11,27]. Studies on thermal insulation (including aerogels, resol boards, and expanded polystyrene) combine laboratory measurements of the thermal conductivity coefficient l with numerical heat flow simulations. This integrated approach helps mitigate design errors that lead to interstitial condensation and excessive energy loss [26,27,40,41]. A significant contribution of this Special Issue is the application of AI and statistical tools to address environmental challenges and assess material durability in changing climatic conditions.
−
Statistically Assisted Recycling. The application of experimental–statistical modeling [42] enabled the development of self-compacting concrete incorporating brick powder and recycled sand [38]. These models allow for the prediction of the mixture’s workability and compressive strength, significantly reducing the necessity for extensive laboratory trial batches.
−
Thermal Retrofitting and Building Physics. Comprehensive analyses of insulation materials, ranging from traditional mineral wool to advanced aerogel blankets [26], are supported by TRISCO and WUFI simulation software. This research demonstrates that even minor storage errors—resulting in a degradation of thermal parameters by up to 19%—can be accurately modeled. Such precision enables enhanced energy management throughout the building’s life cycle [27].
Durability Under Extreme Conditions. Artificial Intelligence demonstrates superior performance in scenarios where classical mathematical models fail due to the excessive complexity of environmental variables.
−
Frost Damage Prediction. The implementation of the Sparrow Search Algorithm-optimized Extreme Learning Machine (SSA-ELM) to predict concrete durability in permafrost regions [1] represents a significant advancement in cold-region civil engineering. This model exhibits higher predictive accuracy compared to standard Long Short-Term Memory (LSTM) networks or Support Vector Machines (SVMs).
−
Soil and Pavement Dynamics. Research in this area includes the analysis of temperature-dependent viscosity and elastic moduli of asphalt binders [20,43], the load-transfer efficiency of dowel bars in concrete pavements [22,44], and the 3D modeling of permeable pavements [21]. A novel approach based on Network Analysis facilitates a comprehensive understanding of how seasonal moisture fluctuations impact the geotechnical parameters of subgrade soils [45,46]. This insight is critical for designing asphalt pavements with enhanced resistance to reflective and fatigue cracking, particularly when subjected to variable climatic loading [20,21,47].
Interdisciplinary Applications. The research spectrum presented is remarkably broad, spanning from medical radiotherapy [48] and aerospace engineering (stiffened panels, wind tunnels) [28,49] to geotechnics and the impact of seasonality on soil properties in road construction [45,50,51].
Digital tools. Modern materials engineering relies on the integration of Artificial Intelligence (ML, SSA-ELM, MTL) with advanced numerical simulations (FEM, Monte Carlo [52,53]), enabling the precise design of structural properties and the prediction of durability under extreme conditions [1,3,7,54,55]. Table 1 summarizes the application of digital tools in selected publications.
A pivotal trend is the implementation of Digital Twin systems which, powered by genetic algorithms and neural networks, facilitate real-time manufacturing process optimization and infrastructure diagnostics [6,13,14,15,16]. These tools drastically reduce Research and Development (R&D) cycles, minimize technological defects [19,28], and promote sustainable development through the precise modeling of energy efficiency and material recycling [27,38].
Efficiency of Research Methodologies. The efficiency of the research methodologies presented in the analyzed publications is based on complementarity: traditional numerical simulations (FEM, Monte Carlo) provide high physical fidelity and deep insight into microstructures [31,48]; however, they are time-consuming and computationally intensive. In contrast, Machine Learning (ML/AI) algorithms, once trained, offer near-instantaneous property predictions with an average error rate of less than 10%. This enables the rapid screening of thousands of design variants [3,7]. A comparison of the efficiency of these research methods is summarized in Table 2. The highest efficiency is achieved by hybrid systems and Digital Twins. By integrating the computational speed of AI with the accuracy of numerical models, these systems enable real-time optimization of technological processes (with response times below 0.1 s), a feat unattainable by classical experimental or purely numerical methods [1,6,16].
Synergy Between AI and Materials Engineering. The synergy between Artificial Intelligence (AI) and materials engineering is manifested in the transition from traditional “trial-and-error” methodologies to intelligent inverse design. In this approach, algorithms precisely determine structural parameters based on predefined target properties [3,7]. The integration of Machine Learning with physical models facilitates the development of Digital Twin systems capable of adjusting manufacturing processes in milliseconds and detecting anomalies invisible to conventional inspection methods [5,6]. This interaction is summarized in Table 3.
This constructive interaction not only drastically accelerates the discovery of novel materials but also revolutionizes infrastructure diagnostics by enabling a shift from reactive repairs to predictive life-cycle management [1,16].
The Future of AI-Assisted Engineering. The synthesis of these twenty research papers leads to the conclusion that Artificial Intelligence does not replace the engineer but drastically extends their analytical and design capabilities. The convergence of AI and materials science has transitioned from a theoretical concept to a practical engineering instrument. Contemporary engineering is shifting away from traditional trial-and-error methodologies toward intelligent inverse design. The studies included in this Special Issue demonstrate that integrating experimental data with AI models facilitates the following:
−
Enhanced Efficiency. AI enables navigation through vast design spaces where the number of chemical compositions or geometric parameters exceeds human cognitive limits. Processes such as casting [19,56,57,58] and pavement engineering [21] gain a new dimension of quality through high-precision predictive modeling.
−
Cost Reduction. The integration of Finite Element Method (FEM) simulations with Machine Learning (ML), as demonstrated in [7,19], allows for virtual prototyping. This drastically reduces material and energy consumption during the Research and Development (R&D) phase.
−
Improved Safety and Durability. Utilizing advanced fracture models [31,59] and bond degradation analysis [33,60] enables the design of safer infrastructure supported by Digital Twin systems. Advanced analytics of cracking and corrosion [31,33,35,61] facilitate the construction of more resilient machinery and structures.
−
Environmental Sustainability. AI-driven optimization of building insulation [27,62] and the implementation of recycled materials [38,63] directly support sustainable development goals.
This Special Issue serves as evidence that we have reached a pivotal turning point where materials engineering is evolving into a digital discipline. This transformation enables the development of technologies that were considered impossible to optimize only a decade ago. The presented research provides a robust knowledge platform that stimulates further innovation in materials science, addressing the challenges of modern industry and environmental protection.
Perspective on Interdisciplinary Collaboration. This Special Issue serves as a unique platform bridging the gap between Artificial Intelligence theorists and materials science practitioners. For AI researchers, it provides a rich repository of complex physical problems and unique datasets essential for validating cutting-edge algorithms. Conversely, for materials scientists, these publications offer an inspiring roadmap for transitioning from traditional, empirical methodologies to the active integration of digital tools within standard laboratory workflows. This constructive interaction facilitates the dismantling of disciplinary silos and promotes the advancement of Explainable Artificial Intelligence (XAI). By aligning mathematical model precision with physical interpretability, XAI ensures that data-driven insights remain consistent with fundamental material phenomena.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Zhao, Y.; Yang, B.; Zhang, K.; Guo, A.; Yu, Y.; Chen, L. Machine Learning Models for Predicting Freeze-Thaw Damage of Concrete Under Subzero Temperature Curing Conditions. Materials 2025, 18, 2856. [Google Scholar] [CrossRef] [PubMed]
  2. Li, J.; Wu, Y. Improved Sparrow Search Algorithm with the Extreme Learning Machine and Its Application for Prediction. Neural Process. Lett. 2022, 54, 4189–4209. [Google Scholar] [CrossRef]
  3. Wang, Z.; Zhou, J.; Peng, K. The Potential of Multi-Task Learning in CFDST Design: Load-Bearing Capacity Design with Three MTL Models. Materials 2024, 17, 1994. [Google Scholar] [CrossRef]
  4. Wang, H.; Wang, J. Short-term wind speed prediction based on feature extraction with Multi-task Lasso and Multilayer Perceptron. Energy Rep. 2022, 8, 191–199. [Google Scholar] [CrossRef]
  5. Karimzadeh, M.; Basvoju, D.; Vakanski, A.; Charit, I.; Xu, F.; Zhang, X. Machine Learning for Additive Manufacturing of Functionally Graded Materials. Materials 2024, 17, 3673. [Google Scholar] [CrossRef]
  6. Lacki, P.; Adamus, J.; Lachs, K.; Lacki, W. Optimization of Rotary Friction Welding Parameters Through AI-Augmented Digital Twin Systems. Materials 2025, 18, 1923. [Google Scholar] [CrossRef]
  7. Liu, F.; Wu, H.; Wu, X.; Xiang, Z.; Huang, S.; Chen, M. Data-Driven Bi-Directional Lattice Property Customization and Optimization. Materials 2024, 17, 5599. [Google Scholar] [CrossRef] [PubMed]
  8. Sparks, T.D.; Kauwe, S.K.; Parry, M.E.; Tehrani, A.M.; Brgoch, J. Machine Learning for Structural Materials. Annu. Rev. Mater. Res. 2020, 50, 27–48. [Google Scholar] [CrossRef]
  9. Miao, H.; Guo, C.; Lu, Z.; Chen, Z. 3D mesoscale analysis of concrete containing defect damages during different freeze-thaw cycles. Constr. Build. Mater. 2022, 358, 129449. [Google Scholar] [CrossRef]
  10. de Mattos Neto, P.S.; de Oliveira, J.F.; Júnior, D.S.D.O.S.; Siqueira, H.V.; Marinho, M.H.; Madeiro, F. An adaptive hybrid system using deep learning for wind speed forecasting. Inf. Sci. 2021, 581, 495–514. [Google Scholar] [CrossRef]
  11. Ascione, F.; Bianco, N.; Maria Mauro, G.; Napolitano, D.F. Building envelope design: Multi-objective optimization to minimize energy consumption, global cost and thermal discomfort. Application to different Italian climatic zones. Energy 2019, 174, 359–374. [Google Scholar] [CrossRef]
  12. Patra, T.K.; Meenakshisundaram, V.; Hung, J.-H.; Simmons, D.S. Neural-Network-Biased Genetic Algorithms for Materials Design: Evolutionary Algorithms That Learn. ACS Comb. Sci. 2017, 19, 96–107. [Google Scholar] [CrossRef] [PubMed]
  13. Attaran, M.; Celik, B.G. Digital Twin: Benefits, use cases, challenges, and opportunities. Decis. Anal. J. 2023, 6, 100165. [Google Scholar] [CrossRef]
  14. Sharma, A.; Kosasih, E.; Zhang, J.; Brintrup, A.; Calinescu, A. Digital Twins: State of the art theory and practice, challenges, and open research questions. J. Ind. Inf. Integr. 2022, 30, 100383. [Google Scholar] [CrossRef]
  15. Boje, C.; Guerriero, A.; Kubicki, S.; Rezgui, Y. Towards a semantic Construction Digital Twin: Directions for future research. Autom. Constr. 2020, 114, 103179. [Google Scholar] [CrossRef]
  16. Stoicescu, A.-A.; Ripeanu, R.G.; Tănase, M.; Toader, L. Current Methods and Technologies for Storage Tank Condition Assessment: A Comprehensive Review. Materials 2025, 18, 1074. [Google Scholar] [CrossRef]
  17. Odili, P.O.; Daudu, C.D.; Adefemi, A.; Ekemezie, I.O.; Usiagu, G.S. Integrating advanced technologies in corrosion and inspection management for oil and gas operations. Eng. Sci. Technol. J. 2024, 5, 597–611. [Google Scholar] [CrossRef]
  18. Zulkifli, C.Z.; Garfan, S.; Talal, M.; Alamoodi, A.H.; Alamleh, A.; Ahmaro, I.Y.Y.; Sulaiman, S.; Ibrahim, A.B.; Zaidan, B.B.; Ismail, A.R.; et al. IoT-Based Water Monitoring Systems: A Systematic Review. Water 2022, 14, 3621. [Google Scholar] [CrossRef]
  19. Sun, C.; Cao, Z.; Jin, Y.; Cui, H.; Wang, C.; Qiu, F.; Shu, S. Numerical Simulation of Lost-Foam Casting for Key Components of A356 Aluminum Alloy in New Energy Vehicles. Materials 2024, 17, 2363. [Google Scholar] [CrossRef]
  20. Jiang, Y.; Xu, J.; Zhang, H.; Liang, Y.; Du, J.; Wu, D. Study on the Temperature-Dependence of the Modulus of LSAM-50 Pavement Materials. Materials 2025, 18, 2606. [Google Scholar] [CrossRef]
  21. Siao, J.-H.; Chang, T.-C.; Wang, Y.-M. A Finite Element Model for Simulating Stress Responses of Permeable Road Pavement. Materials 2024, 17, 3012. [Google Scholar] [CrossRef]
  22. Yaqoob, S.; Silfwerbrand, J. Assessing the Effectiveness of Dowel Bars in Jointed Plain Concrete Pavements Using Finite Element Modelling. Materials 2025, 18, 588. [Google Scholar] [CrossRef]
  23. Al-Humeidawi, B.H.; Mandal, P. Numerical evaluation of the combined effect of dowel misalignment and wheel load on dowel bars performance in JPCP. Eng. Struct. 2022, 252, 113655. [Google Scholar] [CrossRef]
  24. Yoo, P.J.; Al-Qadi, I.L. Effect of Transient Dynamic Loading on Flexible Pavements. Transp. Res. Rec. J. Transp. Res. Board 2007, 1990, 129–140. [Google Scholar] [CrossRef]
  25. Lu, G.; Liu, P.; Törzs, T.; Wang, D.; Oeser, M.; Grabe, J. Numerical analysis for the influence of saturation on the base course of permeable pavement with a novel polyurethane binder. Constr. Build. Mater. 2020, 240, 117930. [Google Scholar] [CrossRef]
  26. Pomada, M.; Adamus, J. Analysis of Material Solutions for Internal Insulation of Masonry Walls-A Case Study. Materials 2025, 18, 4330. [Google Scholar] [CrossRef] [PubMed]
  27. Pomada, M.; Kieruzel, K.; Ujma, A.; Palutkiewicz, P.; Walasek, T.; Adamus, J. Analysis of Thermal Properties of Materials Used to Insulate External Walls. Materials 2024, 17, 4718. [Google Scholar] [CrossRef]
  28. Nan, S.; Zhang, X. Optimization of the Elastic Modulus of the Filler in High-Rib Thin-Web Grid-Stiffened Panels with Bending Forming Process. Materials 2025, 18, 3782. [Google Scholar] [CrossRef]
  29. Zhou, W.; Li, Y.; Shi, Z.; Lin, J. An analytical solution for elastic buckling analysis of stiffened panel subjected to pure bending. Int. J. Mech. Sci. 2019, 161–162, 105024. [Google Scholar] [CrossRef]
  30. Zhou, W.; Shi, Z.; Li, Y.; Rong, Q.; Zeng, Y.; Lin, J. Elastic-plastic buckling analysis of stiffened panel subjected to global bending in forming process. Aerosp. Sci. Technol. 2021, 115, 106781. [Google Scholar] [CrossRef]
  31. Luo, X.; Baxevanakis, K.P.; Silberschmidt, V.V. Crack Initiation in Compacted Graphite Iron with Random Microstructure: Effect of Volume Fraction and Distribution of Particles. Materials 2024, 17, 3346. [Google Scholar] [CrossRef] [PubMed]
  32. Luo, X.; Baxevanakis, K.P.; Silberschmidt, V.V. Microstructure-Based CZE Model for Crack Initiation and Growth in CGI: Effects of Graphite-Particle Morphology and Spacing. Solids 2024, 5, 123–139. [Google Scholar] [CrossRef]
  33. Kurihara, T.; Mitani, R.; Kanakubo, T. Effect of Longitudinal Crack Width Variation on Bond Behavior Degradation Due to Rebar Corrosion in Reinforced Concrete. Materials 2025, 18, 4335. [Google Scholar] [CrossRef] [PubMed]
  34. Lin, H.; Zhao, Y.; Feng, P.; Ye, H.; Ozbolt, J.; Jiang, C.; Yang, J.-Q. State-of-the-art review on the bond properties of corroded reinforcing steel bar. Constr. Build. Mater. 2019, 213, 216–233. [Google Scholar] [CrossRef]
  35. Peng, D.; Tang, C.; Watts, J.; Ang, A.; Raman, R.K.S.; Nicholas, M.; Phan, N.; Jones, R. Durability Analysis of Cold Spray Repairs: Phase I-Effect of Surface Grit Blasting. Materials 2024, 17, 2656. [Google Scholar] [CrossRef]
  36. Yin, S.; Cavaliere, P.; Aldwell, B.; Jenkins, R.; Liao, H.; Li, W.; Lupoi, R. Cold spray additive manufacturing and repair: Fundamentals and applications. Addit. Manuf. 2018, 21, 628–650. [Google Scholar] [CrossRef]
  37. Pathak, S.; Saha, G. Development of Sustainable Cold Spray Coatings and 3D Additive Manufacturing Components for Repair/Manufacturing Applications: A Critical Review. Coatings 2017, 7, 122. [Google Scholar] [CrossRef]
  38. Kryzhanovskyi, V.; Orlowsky, J. Sustainable Alkali-Activated Self-Compacting Concrete for Precast Textile-Reinforced Concrete: Experimental-Statistical Modeling Approach. Materials 2024, 17, 6280. [Google Scholar] [CrossRef]
  39. Onyelowe, K.C.; Ebid, A.M.; Ghadikolaee, M.R. GRG-optimized response surface powered prediction of concrete mix design chart for the optimization of concrete compressive strength based on industrial waste precursor effect. Asian J. Civ. Eng. 2024, 25, 997–1006. [Google Scholar] [CrossRef]
  40. Bjarløv, S.P.; Finken, G.R.; Odgaard, T. Retrofit with Interior Insulation on Solid Masonry Walls in Cool Temperate Climates—An Evaluation of the influence of Interior Insulation Materials on Moisture Condition in the Building Envelope. Energy Procedia 2015, 78, 1461–1466. [Google Scholar] [CrossRef]
  41. Odgaard, T.; Bjarløv, S.P.; Rode, C. Interior insulation—Characterisation of the historic, solid masonry building segment and analysis of the heat saving potential by 1d, 2d, and 3d simulation. Energy Build. 2018, 162, 1–11. [Google Scholar] [CrossRef]
  42. Bolla, S.; Matla, Y.; Wani, F.M.; Vemuri, J. Predictive Modeling for Compressive Strength in Sustainable Concrete Using Machine Learning Techniques. In Advances in Environmental Sustainability, Energy and Earth Science; Pathak, P., Ilyas, S., Srivastava, R.R., Dar, J., Kothandaraman, S., Eds.; Springer Nature: Cham, Switzerland, 2024; pp. 175–186. [Google Scholar]
  43. Acharjee, P.K.; Souliman, M.I.; Khalifah, R.; Elwardany, M. Frequency- and temperature-dependent dynamic shear modulus and phase angle prediction models based on existing asphalt binder viscosity data using Artificial Neural Network (ANN). Constr. Build. Mater. 2024, 414, 134772. [Google Scholar] [CrossRef]
  44. Peng, P.; Tian, B.; Niu, K. A Study on the Working Performance of Dowel Bars with Horizontal Installation Errors. J. Highw. Transp. Res. Dev. (Engl. Ed.) 2012, 6, 33–38. [Google Scholar] [CrossRef]
  45. Umar, I.H.; Muhammad, A.; Lin, H.; Hassan, J.I.; Cao, R. Seasonal Dynamics in Soil Properties Along a Roadway Corridor: A Network Analysis Approach. Materials 2025, 18, 1708. [Google Scholar] [CrossRef]
  46. Luleci, F.; Catbas, F.N.; Avci, O. A literature review: Generative adversarial networks for civil structural health monitoring. Front. Built Environ. 2022, 8, 1027379. [Google Scholar] [CrossRef]
  47. Acharjee, P.K.; Souliman, M.I.; Freyle, F.; Fuentes, L. Development of Dynamic Modulus Prediction Model Using Artificial Neural Networks for Colombian Mixtures. J. Transp. Eng. Part B Pavements 2024, 150, 04023038. [Google Scholar] [CrossRef]
  48. Chow, J.C.L.; Ruda, H.E. Impact of Scattering Foil Composition on Electron Energy Distribution in a Clinical Linear Accelerator Modified for FLASH Radiotherapy: A Monte Carlo Study. Materials 2024, 17, 3355. [Google Scholar] [CrossRef]
  49. Yang, X.; Ma, Y.; Wang, G.; Yang, C.; Yu, C. Three-Dimensional Deformation Calculation of Wind Tunnel Flexible Wall Using Orthogonal Beam Function. Materials 2025, 18, 3593. [Google Scholar] [CrossRef]
  50. Zhou, S.; Zhou, M.; Wang, Y.; Gao, Y.; Liu, Y.; Shi, C.; Lu, Y.; Zhou, T. Bibliometric and Social Network Analysis of Civil Engineering Sustainability Research from 2015 to 2019. Sustainability 2020, 12, 6842. [Google Scholar] [CrossRef]
  51. Hewa Welege, N.M.; Pan, W.; Kumaraswamy, M. Social network analysis applications in sustainable construction and built environment management: A review. Built Environ. Proj. Asset Manag. 2021, 11, 511–528. [Google Scholar] [CrossRef]
  52. Andreo, P. Monte Carlo simulations in radiotherapy dosimetry. Radiat. Oncol. 2018, 13, 121. [Google Scholar] [CrossRef] [PubMed]
  53. Rogers, D.W.O. Fifty years of Monte Carlo simulations for medical physics. Phys. Med. Biol. 2006, 51, R287–R301. [Google Scholar] [CrossRef]
  54. Eftekhari, S.A. A simple finite element procedure for free vibration of rectangular thin and thick plates. Appl. Math. Comput. 2021, 401, 126104. [Google Scholar] [CrossRef]
  55. Yuan, W.-H.; Wang, H.-C.; Zhang, W.; Dai, B.-B.; Liu, K.; Wang, Y. Particle finite element method implementation for large deformation analysis using Abaqus. Acta Geotech. 2021, 16, 2449–2462. [Google Scholar] [CrossRef]
  56. Wang, K.; Lv, S.; Wu, H.; Wu, G.; Wang, S.; Gao, J.; Zhu, J.; Yang, X.; Mao, X. Recent research progress on the phase-field model of microstructural evolution during metal solidification. Int. J. Miner. Met. Mater. 2023, 30, 2095–2111. [Google Scholar] [CrossRef]
  57. Mirbagheri, S.M.H.; Ashuri, H.; Varahram, N.; Davami, P. Simulation of mould filling in lost foam casting process. Int. J. Cast Met. Res. 2003, 16, 554–565. [Google Scholar] [CrossRef]
  58. Li, F.; Zhao, H.; Ren, F.; Song, S.; Shao, X.; Volinsky, A.A. Simulations and experiments of mould filling in lost foam casting. Int. J. Cast Met. Res. 2020, 33, 194–200. [Google Scholar] [CrossRef]
  59. König, M. Literature review of microstructure formation in compacted graphite Iron. Int. J. Cast Met. Res. 2010, 23, 185–192. [Google Scholar] [CrossRef]
  60. Güneyisi, E.M.; Mermerdaş, K.; Gültekin, A. Evaluation and modeling of ultimate bond strength of corroded reinforcement in reinforced concrete elements. Mater. Struct. 2016, 49, 3195–3215. [Google Scholar] [CrossRef]
  61. Dauji, S.; Bhargava, K. Neural Estimation of Bond Strength Degradation in Concrete Affected by Reinforcement Corrosion. Ina. Lett. 2018, 3, 203–215. [Google Scholar] [CrossRef]
  62. Wang, Z.; Hong, T.; Piette, M.A. Building thermal load prediction through shallow machine learning and deep learning. Appl. Energy 2020, 263, 114683. [Google Scholar] [CrossRef]
  63. Elshaarawy, M.K.; Alsaadawi, M.M.; Hamed, A.K. Machine learning and interactive GUI for concrete compressive strength prediction. Sci. Rep. 2024, 14, 16694. [Google Scholar] [CrossRef]
Table 1. Application of digital tools in selected publications.
Table 1. Application of digital tools in selected publications.
FieldTechnologies/MethodsPublications
Machine Learning/AINeural networks (ANN), MTL, SSA-ELM, SHAP interpretability[1,3,5,6,7]
Numerical MethodsFEM, FEA, Monte Carlo method, ProCAST software[16,19,21,22,26,27,31,38,48]
Process OptimizationDigital Twins, genetic algorithms (GAs)[6,7,16]
Mathematical ModelingRegression models, orthogonal functions, Hartman–Schijve equations[20,35,49]
Table 2. Comparison of research methodology efficiency.
Table 2. Comparison of research methodology efficiency.
MethodAdvantages According to Analyzed StudiesExemplary Application
Monte CarloHigh precision in modeling particle energy distribution.FLASH radiotherapy [48]
Machine Learning (ML)Ability to map nonlinear relationships and rapid prediction.CFDST design [3], Frost resistance [1]
FEM + AI HybridCombines physical interpretability with computational speed.Digital Twins in welding [6]
Statistical ModelingMulti-objective optimization of waste-based material compositions.Brick-dust-modified concrete [38]
Table 3. Synergy between AI methods and materials science and engineering.
Table 3. Synergy between AI methods and materials science and engineering.
PublicationMaterial ChallengeApplied AI Tool/ModelKey Result/Innovation
[1]Concrete frost actionSSA-ELM (Sparrow Search Algorithm)State-of-the-art precision in predicting frost damage within permafrost.
[3]CFDST structuresMulti-Task Learning (Lasso, VSTG, MLS-SVR)Identification of latent correlations between geometric parameters and strength.
[5]FGM fabricationMachine Learning (ML)Optimization of 3D printing parameters and real-time defect detection.
[6]Ti/Al dissimilar weldingDigital Twin + ANN + Genetic AlgorithmProcess optimization in <0.1 s; elimination of weld defects.
[7]Lattice customizationTwo-Tier ML (Polynomial Regression)25% improvement in mechanical performance at constant density.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Lacki, P.; Adamus, J.; Derlatka, A.; Więckowski, W.; Cpałka, K. Artificial Intelligence in Materials Science and Engineering. Materials 2026, 19, 1808. https://doi.org/10.3390/ma19091808

AMA Style

Lacki P, Adamus J, Derlatka A, Więckowski W, Cpałka K. Artificial Intelligence in Materials Science and Engineering. Materials. 2026; 19(9):1808. https://doi.org/10.3390/ma19091808

Chicago/Turabian Style

Lacki, Piotr, Janina Adamus, Anna Derlatka, Wojciech Więckowski, and Krzysztof Cpałka. 2026. "Artificial Intelligence in Materials Science and Engineering" Materials 19, no. 9: 1808. https://doi.org/10.3390/ma19091808

APA Style

Lacki, P., Adamus, J., Derlatka, A., Więckowski, W., & Cpałka, K. (2026). Artificial Intelligence in Materials Science and Engineering. Materials, 19(9), 1808. https://doi.org/10.3390/ma19091808

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop