Submit to Special Issue Submit Abstract to Special Issue Review for Materials Propose a Special Issue

Journal Menu

Journal Browser

Artificial Intelligence in Materials Science and Engineering

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Related Special Issues
Published Papers

A special issue of Materials (ISSN 1996-1944). This special issue belongs to the section "Materials Simulation and Design".

Deadline for manuscript submissions: 30 October 2025 | Viewed by 16049

Share This Special Issue

Special Issue Editors

Prof. Dr. Piotr Lacki

E-Mail Website
Guest Editor

Department of Civil Engineering, Faculty of Civil Engineering, Czestochowa University of Technology, 69 Dąbrowskiego St., 42-201 Częstochowa, Poland
Interests: materials sciences; metal forming; refill friction stir spot welding; numerical simulation; civil engineering; composite beams; genetic algorithms; neural networks
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Janina Adamus

E-Mail Website
Guest Editor

Department of Civil Engineering, Faculty of Civil Engineering, Czestochowa University of Technology, 69 Dąbrowskiego St., 42-201 Częstochowa, Poland
Interests: metal forming; tribology; heat transfer through building partitions; artificial intelligence in technical solutions
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Anna Derlatka

E-Mail Website
Guest Editor

Department of Civil Engineering, Faculty of Civil Engineering, Czestochowa University of Technology, 69 Dąbrowskiego St., 42-201 Częstochowa, Poland
Interests: artificial neural network; thin-walled structures; composite beams; steel-concrete composite structures; refill friction stir spot welding; numerical simulation

Prof. Dr. Wojciech Więckowski

E-Mail Website
Guest Editor

Department of Technology and Automation, Faculty of Mechanical Engineering and Computer Science, Czestochowa University of Technology, 69 Dąbrowskiego St., 42-201 Częstochowa, Poland
Interests: metal forming; sheet metal stamping; tribology; bioengineering; biomaterials; numerical simulation; friction stir welding; artificial neural network

Prof. Dr. Krzysztof Cpałka

E-Mail Website
Guest Editor

Institute of Computational Intelligence, Czestochowa University of Technology, Dabrowskiego 69, 42-201 Czestochowa, Poland
Interests: artificial intelligence; fuzzy systems; population-based algorithms; neural networks; interpretability

Special Issue Information

Dear Colleagues,

The combination of Artificial Intelligence (AI) and Materials Science and Engineering gives rise to innovative approaches that accelerate the discovery, development and optimization of materials and technologies with improved properties. This constructive interaction holds immense promise for revolutionizing industries ranging from civil engineering to metal forming, ushering in a new era of material innovation.

AI plays a crucial role in predictive modeling, enabling researchers to simulate and understand the behavior of materials under various conditions. Machine learning algorithms analyze complex datasets to predict material responses to different external factors, such as temperature, pressure, or chemical exposure. This capability enhances our ability to design materials with tailored properties for specific applications. As we delve deeper into this interdisciplinary collaboration, the synergies between AI and Materials Science are expected to yield breakthroughs with far-reaching implications for diverse industries and technological advancements.

The objective of this Special Issue is to establish a knowledge platform that encourages researchers and engineers to advance research in the field of Materials Science and Engineering, employing the diverse applications of artificial intelligence.

This Special Issue invites the submission of manuscripts that explore the utilization of AI in Materials Science and Engineering, particularly concerning through classical and state-of-the-art manufacturing techniques. We encourage the submission of full papers on this subject.

Prof. Dr. Piotr Lacki
Prof. Dr. Janina Adamus
Prof. Dr. Anna Derlatka
Prof. Dr. Wojciech Więckowski
Prof. Dr. Krzysztof Cpałka
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Materials is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

artificial intelligence
artificial neural network
fuzzy system
population-based algorithm
genetic algorithms
bioengineering
metal forming
civil engineering
composite structures
friction stir welding
numerical simulation

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Related Special Issues

Memristors for Neuromorphic Circuits and Artificial Intelligence Applications in Materials (14 articles)
Importance of Machine Intelligence for Construction Material and Structural Engineering Applications in Materials (8 articles)

Published Papers (14 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

26 pages, 5352 KiB

Open AccessArticle

Optimization of Rotary Friction Welding Parameters Through AI-Augmented Digital Twin Systems

by Piotr Lacki, Janina Adamus, Kuba Lachs and Wiktor Lacki

Materials 2025, 18(9), 1923; https://doi.org/10.3390/ma18091923 - 24 Apr 2025

Viewed by 150

Abstract

In this study, Artificial Neural Networks (ANN) were employed to develop a Digital Twin (DT) of the Rotary Friction Welding (RFW) process. The neural network models were trained to predict the peak temperature generated during the welding process of dissimilar Ti Grade 2/AA 5005 joints over a temperature range of 20–640 °C. This prediction was based on a parametric numerical model of the RFW process constructed using the Finite Element Method (FEM) within the ADINA System software. Numerical simulations enabled a detailed analysis of the temperature distribution within the weldment. Accurate temperature predictions are essential for assessing the mechanical properties and microstructural integrity of the welded materials. Artificial Intelligence (AI) models, trained on historical data and real-time inputs, dynamically adjust critical process parameters—such as rotational speed, axial force, and friction time—to maintain optimal weld quality. A key advantage of employing AI-augmented DT systems in the RFW process is the ability to conduct real-time (less than 0.1 s) optimization and adaptive control. By integrating a Genetic Algorithm (GA) with the DT algorithm of the RFW process, the authors developed an effective tool for analyzing parameters such as axial force and rotational speed, in order to determine the optimal welding conditions, which translates into improved joint quality, minimized defects, and maximized process efficiency. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

37 pages, 13496 KiB

Open AccessArticle

Seasonal Dynamics in Soil Properties Along a Roadway Corridor: A Network Analysis Approach

by Ibrahim Haruna Umar, Ahmad Muhammad, Hang Lin, Jubril Izge Hassan and Rihong Cao

Materials 2025, 18(8), 1708; https://doi.org/10.3390/ma18081708 - 9 Apr 2025

Viewed by 310

Abstract

Understanding soil properties’ spatial and temporal variability is essential for optimizing road construction and maintenance practices. This study investigates the seasonal variability of soil properties along a 4.8 km roadway in Maiduguri, Nigeria. Using a novel integration of network analysis and geotechnical testing, we analyzed nine soil parameters (e.g., particle size distribution (PSD), Atterberg limits, California bearing ratio) across wet (September 2024) and dry (January 2021) seasons from 25 test stations. Average Atterberg limits (LL: 22.8% wet vs. 17.5% dry; PL: 18.7% wet vs. 14.7% dry; PI: 4.2% wet vs. 2.8% dry; LS: 1.8% wet vs. 2.3% dry), average compaction characteristics (MDD: 1.8 Mg/m³ wet vs. 2.1 Mg/m³ dry; OMC: 12.3% wet vs. 10% dry), and average CBR (18.9% wet vs. 27.5% dry) were obtained. Network construction employed z-score standardization and similarity metrics, with multi-threshold analysis (θ = 0.05, 0.10, 0.15) revealing critical structural differences. During the wet season, soil networks exhibited a 5.0% reduction in edges (321 to 305) and density decline (1.07 to 1.02) as thresholds tightened, contrasting with dry-season networks retaining 99.38% connectivity (324 to 322 edges) and stable density (0.99). Seasonal shifts in soil classification (A-4(1)/ML wet vs. A-2(1)/SM dry) underscored moisture-driven plasticity changes. The findings highlight critical implications for adaptive road design, emphasizing moisture-resistant materials in wet seasons and optimized compaction in dry periods. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

17 pages, 2738 KiB

Open AccessArticle

Assessing the Effectiveness of Dowel Bars in Jointed Plain Concrete Pavements Using Finite Element Modelling

by Saima Yaqoob and Johan Silfwerbrand

Materials 2025, 18(3), 588; https://doi.org/10.3390/ma18030588 - 28 Jan 2025

Viewed by 764

Abstract

Aggregate interlocking and dowel bar systems are the two primary mechanisms in a jointed plain concrete pavement for transferring the wheel loads from the loaded slab to the adjacent unloaded slab, avoiding critical stresses and excessive deformations across the joint. Aggregate interlocking is suitable for small joint openings, while the dowel bar provides effective load transmission for both smaller and wider joint openings. In this study, a three-dimensional finite element model was developed to investigate the structural performance of dowelled jointed plain concrete pavements. The developed model was compared with an analytical solution, i.e., Westergaard’s method. The current study investigated the effectiveness of the dowel bars in jointed plain concrete pavements considering the modulus of elasticity and the thickness of the base layer, as well as dowel bar diameter and length. Furthermore, the load transfer efficiency (LTE) of a rounded dowel bar was compared with that of plate dowel bars (i.e., rectangular and diamond-shaped dowel bars) of a similar cross-sectional area and length. This study showed that the LTE was enhanced by 4% when the base layer’s modulus of elasticity increased from 450 MPa to 6000 MPa, while the increase in stress was 23%. A 1.2% improvement in the LTE and a 2.1% reduction in flexural stress were observed as the base layer’s thickness increased from 100 to 250 mm. Moreover, increasing the dowel bar’s diameter from 20 mm to 38 mm enhanced the LTE by 4.3% and 3.8% for base layer moduli of 450 MPa and 4000 MPa, respectively. The corresponding rise in stresses was 10% and 5%. The diamond-shaped dowel bar of a 50 × 32 mm size showed a 0.48% increase in the LTE, while sizes of 100 × 16 mm and 200 × 8 mm reduced the stress 6.7% and 23.1%, respectively, compared to that in the rounded dowel bar. With rectangular dowel bars, a 4% rise in the stress was noted compared to that with the rounded dowel bar. Increasing the length of the diamond-shaped dowel bar slightly improved the LTE but had no impact on the stress in the concrete slab. The findings from this study can help highway engineers improve pavements’ durability, make cost-effective decisions, contribute to resource savings in large-scale concrete pavement projects, and enhance the overall quality of infrastructure. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

23 pages, 15546 KiB

Open AccessArticle

Sustainable Alkali-Activated Self-Compacting Concrete for Precast Textile-Reinforced Concrete: Experimental–Statistical Modeling Approach

by Vitalii Kryzhanovskyi and Jeanette Orlowsky

Materials 2024, 17(24), 6280; https://doi.org/10.3390/ma17246280 - 22 Dec 2024

Viewed by 981

Abstract

Industrial and construction wastes make up about half of all world wastes. In order to reduce their negative impact on the environment, it is possible to use part of them for concrete production. Using experimental–statistical modeling techniques, the combined effect of brick powder, recycling sand, and alkaline activator on fresh and hardened properties of self-compacting concrete for the production of textile-reinforced concrete was investigated. Experimental data on flowability, passing ability, spreading speed, segregation resistance, air content, and density of fresh mixtures were obtained. The standard passing ability tests were modified using a textile mesh to maximize the approximation to the real conditions of textile concrete production. To determine the dynamics of concrete strength development, compression and flexural tests at the ages of 1, 3, 7, and 28 days and splitting tensile strength tests of 28 days were conducted. The preparation technology of the investigated modified mixtures depending on the composition is presented. The resulting mathematical models allow for the optimization of concrete compositions for partial replacement of slag cement with brick powder (up to 30%), and natural sand with recycled sand (up to 100%) with the addition of an alkaline activator in the range of 0.5–1% of the cement content. This allows us to obtain sustainable, alkali-activated high-strength self-compacting recycling concrete, which significantly reduces the negative impact on the environment and promotes the development of a circular economy in the construction industry. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

23 pages, 14182 KiB

Open AccessArticle

Data-Driven Bi-Directional Lattice Property Customization and Optimization

by Fuyuan Liu, Huizhong Wu, Xiaoteng Wu, Zhouyi Xiang, Songhua Huang and Min Chen

Materials 2024, 17(22), 5599; https://doi.org/10.3390/ma17225599 - 15 Nov 2024

Viewed by 801

Abstract

Customizing and optimizing lattice materials poses a challenge to designers. This study proposed a data-driven generative method to customize and optimize lattice material. The method utilizes subdivision modeling to parametrically describe lattice morphologies and skeletons. Next, the homogenization method is employed to analyze elastic moduli for collecting a dataset. Then, a two-tiered machine learning (ML) framework is proposed to predict the elastic modulus for a forward design. The first-tier model employs polynomial regression to estimate relative density, which serves as an additional input feature for the second-tier model. The prediction accuracy of the second-tier model is improved through the additional inputs. The forward and reverse design strategies offer a flexible and accurate means of tailoring lattice properties to meet specific performance requirements. Two case studies demonstrate the practical value of the framework: customizing a lattice material to achieve a desired elastic modulus and optimizing the mechanical performance of lattice materials under relative density constraints. The results show that the prediction accuracy of the elastic modulus using the two-tiered ML model achieved an error of less than 10% compared to finite element analysis, demonstrating the reliability of the proposed approach. Furthermore, the optimization design achieved up to a 25% improvement in mechanical performance compared to conventional lattice configurations under the same relative density constraints. These findings underscore the advantages of combining generative design, machine learning, and genetic algorithms to navigate complex design spaces and achieve enhanced material performance. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

20 pages, 1981 KiB

Open AccessArticle

Analysis of Thermal Properties of Materials Used to Insulate External Walls

by Marta Pomada, Klaudia Kieruzel, Adam Ujma, Paweł Palutkiewicz, Tomasz Walasek and Janina Adamus

Materials 2024, 17(19), 4718; https://doi.org/10.3390/ma17194718 - 26 Sep 2024

Cited by 2 | Viewed by 1826

Abstract

This article emphasizes the significance of understanding the actual thermal properties of thermal insulation materials, which are crucial for avoiding errors in building design and estimating heat losses within the energy balance. The aim of this study was to analyse the thermal parameters of selected thermal insulation materials, particularly in the context of their stability after a period of storage under specific conditions. The materials chosen for this study include commonly used construction insulations such as polystyrene and mineral wool, as well as modern options like rigid foam composites. Experimental studies were conducted, including the determination of the thermal conductivity coefficient λ, as well as numerical analyses and analytical calculations of heat flow through a double-layer external wall with a window. The numerical analyses were performed using the TRISCO software version 12.0w, based on the finite element method (FEM). A macrostructural analysis of the investigated materials was also performed. The findings indicated that improper storage conditions adversely affect the thermal properties of insulation materials. Specifically, storing materials outdoors led to a deterioration in insulating properties, with an average reduction of about 4% for the standard materials and as much as 19% for the tested composite material. Insufficient understanding of the true thermal properties of insulation materials can result in incorrect insulation layer thickness, degrading the fundamental thermal parameters of external walls. This, in turn, increases heat loss through major building surfaces, raises heating costs, and indirectly contributes to greenhouse gas emissions. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Graphical abstract

12 pages, 2490 KiB

Open AccessArticle

Impact of Scattering Foil Composition on Electron Energy Distribution in a Clinical Linear Accelerator Modified for FLASH Radiotherapy: A Monte Carlo Study

by James C. L. Chow and Harry E. Ruda

Materials 2024, 17(13), 3355; https://doi.org/10.3390/ma17133355 - 7 Jul 2024

Cited by 4 | Viewed by 1567

Abstract

This study investigates how scattering foil materials and sampling holder placement affect electron energy distribution in electron beams from a modified medical linear accelerator for FLASH radiotherapy. We analyze electron energy spectra at various positions—ionization chamber, mirror, and jaw—to evaluate the impact of Cu, Pb-Cu, Pb, and Ta foils. Our findings show that close proximity to the source intensifies the dependence of electron energy distribution on foil material, enabling precise beam control through material selection. Monte Carlo simulations are effective for designing foils to achieve desired energy distributions. Moving the sampling holder farther from the source reduces foil material influence, promoting more uniform energy spreads, particularly in the 0.5–10 MeV range for 12 MeV electron beams. These insights emphasize the critical role of tailored material selection and sampling holder positioning in optimizing electron energy distribution and fluence intensity for FLASH radiotherapy research, benefiting both experimental design and clinical applications. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

15 pages, 6097 KiB

Open AccessEditor’s ChoiceArticle

Crack Initiation in Compacted Graphite Iron with Random Microstructure: Effect of Volume Fraction and Distribution of Particles

by Xingling Luo, Konstantinos P. Baxevanakis and Vadim V. Silberschmidt

Materials 2024, 17(13), 3346; https://doi.org/10.3390/ma17133346 - 6 Jul 2024

Cited by 4 | Viewed by 1407

Abstract

Thanks to the distinctive morphology of graphite particles in its microstructure, compacted graphite iron (CGI) exhibits excellent thermal conductivity together with high strength and durability. CGI is extensively used in many applications, e.g., engine cylinder heads and brakes. The structural integrity of such metal-matrix materials is controlled by the generation and growth of microcracks. Although the effects of the volume fraction and morphology of graphite inclusions on the tensile response of CGI were investigated in recent years, their influence on crack initiation is still unknown. Experimental studies of crack initiation require a considerable amount of time and resources due to the highly complicated geometries of graphite inclusions scattered throughout the metallic matrix. Therefore, developing a 2D computational framework for CGI with a random microstructure capable of predicting the crack initiation and path is desirable. In this work, an integrated numerical model is developed for the analysis of the effects of volume fraction and nodularity on the mechanical properties of CGI as well as its damage and failure behaviours. Finite-element models of random microstructure are generated using an in-house Python script. The determination of spacings between a graphite inclusion and its four adjacent particles is performed with a plugin, written in Java and implemented in ImageJ. To analyse the orientation effect of inclusions, a statistical analysis is implemented for representative elements in this research. Further, Johnson–Cook damage criteria are used to predict crack initiation in the developed models. The numerical simulations are validated with conventional tensile-test data. The created models can support the understanding of the fracture behaviour of CGI under mechanical load, and the proposed approach can be utilised to design metal-matrix composites with optimised mechanical properties and performance. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

15 pages, 4736 KiB

Open AccessArticle

A Finite Element Model for Simulating Stress Responses of Permeable Road Pavement

by Jhu-Han Siao, Tung-Chiung Chang and Yu-Min Wang

Materials 2024, 17(12), 3012; https://doi.org/10.3390/ma17123012 - 19 Jun 2024

Viewed by 1393

Abstract

Permeable road pavements, due to their open-graded design, suffer from low structural strength, restricting their use in areas with light traffic volume and low bearing capacity. To expand application of permeable road pavements, accurate simulation of stress parameters used in pavement design is essential. A 3D finite element (3D FE) model was developed using ABAQUS/CAE 2021 to simulate pavement stress responses. Utilizing a 53 cm thick permeable road pavement and a 315/80 R22.5 wheel as prototypes, the model was calibrated and validated, with its accuracy confirmed through t-test statistical analysis. Simulations of wheel speeds at 11, 15, and 22 m/s revealed significant impact on pavement depths of 3 cm and 8 cm, while minimal effects were observed at depths of 13 cm and 33 cm. Notably, stress values at a depth of 3 cm with 15 m/s speed in the open-graded asphalt concrete (OGFC) surface layer exceeded those at the speed of 11 m/s, while at a depth of 8 cm in the porous asphalt concrete (PAC) base layer, an opposite performance was observed. This may be attributed to the higher elastic modulus of the OGFC surface layer, which results in different response trends to velocity changes. Overall, lower speeds increase stress responses and prolong action times for both layers, negatively affecting pavement performance. Increasing the moduli of layers is recommended for new permeable road pavements for low-speed traffic. Furthermore, considering the effects of heavy loads and changes in wheel speed, the recommended design depth for permeable road pavement is 30 cm. These conclusions provide a reference for the design of permeable road pavements to address climate change and improve performance. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

30 pages, 22061 KiB

Open AccessArticle

Durability Analysis of Cold Spray Repairs: Phase I—Effect of Surface Grit Blasting

by Daren Peng, Caixian Tang, Jarrod Watts, Andrew Ang, R. K. Singh Raman, Michael Nicholas, Nam Phan and Rhys Jones

Materials 2024, 17(11), 2656; https://doi.org/10.3390/ma17112656 - 31 May 2024

Cited by 2 | Viewed by 877

Abstract

This paper presents the results of an extensive investigation into the durability of cold spray repairs to corrosion damage in AA7075-T7351 aluminium alloy specimens where, prior to powder deposition, the surface preparation involved grit blasting. In this context, it is shown that the growth of small naturally occurring cracks in cold spray repairs to simulated corrosion damage can be accurately computed using the Hartman–Schijve crack growth equation in a fashion that is consistent with the requirements delineated in USAF Structures Bulletin EZ-SB-19-01, MIL-STD-1530D, and the US Joint Services Structural Guidelines JSSG2006. The relatively large variation in the da/dN versus ΔK curves associated with low values of da/dN highlights the fact that, before any durability assessment of a cold spray repair to an operational airframe is attempted, it is first necessary to perform a sufficient number of tests so that the worst-case small crack growth curve needed to perform the mandated airworthiness certification analysis can be determined. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

16 pages, 2367 KiB

Open AccessArticle

Numerical Simulation of Lost-Foam Casting for Key Components of A356 Aluminum Alloy in New Energy Vehicles

by Chi Sun, Zhanyi Cao, Yanzhu Jin, Hongyu Cui, Chenggang Wang, Feng Qiu and Shili Shu

Materials 2024, 17(10), 2363; https://doi.org/10.3390/ma17102363 - 15 May 2024

Cited by 2 | Viewed by 1314

Abstract

The intricate geometry and thin walls of the motor housing in new energy vehicles render it susceptible to casting defects during conventional casting processes. However, the lost-foam casting process holds a unique advantage in eliminating casting defects and ensuring the strength and air-tightness of thin-walled castings. In this paper, the lost-foam casting process of thin-walled A356 alloy motor housing was simulated using ProCAST software (2016.0). The results indicate that the filling process is stable and exhibits characteristics of diffusive filling. Solidification occurs gradually from thin to thick. Defect positions are accurately predicted. Through analysis of the defect volume range, the optimal process parameter combination is determined to be a pouring temperature of 700 °C, an interfacial heat transfer coefficient of 50, and a sand thermal conductivity coefficient of 0.5. Microscopic analysis of the motor housing fabricated using the process optimized through numerical simulations reveals the absence of defects such as shrinkage at critical locations. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

21 pages, 15097 KiB

Open AccessArticle

The Potential of Multi-Task Learning in CFDST Design: Load-Bearing Capacity Design with Three MTL Models

by Zhenyu Wang, Jian Zhou and Kang Peng

Materials 2024, 17(9), 1994; https://doi.org/10.3390/ma17091994 - 25 Apr 2024

Cited by 3 | Viewed by 998

Abstract

Concrete-filled double steel tubes (CFDSTs) are a load-bearing structure of composite materials. By combining concrete and steel pipes in a nested structure, the performance of the column will be greatly improved. The performance of CFDSTs is closely related to their design. However, existing codes for CFDST design often focus on how to verify the reliability of a design, but specific design parameters cannot be directly provided. As a machine learning technique that can simultaneously learn multiple related tasks, multi-task learning (MTL) has great potential in the structural design of CFDSTs. Based on 227 uniaxial compression cases of CFDSTs collected from the literature, this paper utilized three multi-task models (multi-task Lasso, VSTG, and MLS-SVR) separately to provide multiple parameters for CFDST design. To evaluate the accuracy of models, four statistical indicators were adopted (R², RMSE, RRMSE, and ρ). The experimental results indicated that there was a non-linear relationship among the parameters of CFDSTs. Nevertheless, MLS-SVR was still able to provide an accurate set of design parameters. The coefficient matrices of two linear models, multi-task Lasso and VSTG, revealed the potential connection among CFDST parameters. The latent-task matrix V in VSTG divided the prediction tasks of inner tube diameter, thickness, strength, and concrete strength into three groups. In addition, the limitations of this study and future work are also summarized. This paper provides new ideas for the design of CFDSTs and the study of related codes. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

Review

Jump to: Research

21 pages, 4980 KiB

Open AccessReview

Current Methods and Technologies for Storage Tank Condition Assessment: A Comprehensive Review

by Alexandru-Adrian Stoicescu, Razvan George Ripeanu, Maria Tănase and Liviu Toader

Materials 2025, 18(5), 1074; https://doi.org/10.3390/ma18051074 - 27 Feb 2025

Viewed by 604

Abstract

This study investigates the current industry practices for storage tank assessment and the possibilities for improving inspection methods using the latest technologies on the market. This article presents the main methods and technologies for non-destructive testing (NDT), along with new methods that make them more efficient and economical. To further analyze the state of a tank and determine its lifetime expectancy, analysis methods are presented based on NDT results. The key aspects that can be improved and made more efficient are NDT procedures using robots/drones and autonomous devices; automated inspection procedures, like remote video inspection combined with local thickness measurement or 3D scanning of the tank elements for deformations; advanced analysis methods using the input from the NDT and inspection data collected using analytical calculations according to applicable standards; Finite Element Analysis (FEA); and digitalized models of equipment (Digital Twin) accompanied by artificial intelligence for data processing. The best way to make the process more efficient is to develop and use dedicated standardized software for tank condition assessment. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Figure 1

21 pages, 1925 KiB

Open AccessEditor’s ChoiceReview

Machine Learning for Additive Manufacturing of Functionally Graded Materials

by Mohammad Karimzadeh, Deekshith Basvoju, Aleksandar Vakanski, Indrajit Charit, Fei Xu and Xinchang Zhang

Materials 2024, 17(15), 3673; https://doi.org/10.3390/ma17153673 - 25 Jul 2024

Cited by 10 | Viewed by 2433

Abstract

Additive Manufacturing (AM) is a transformative manufacturing technology enabling direct fabrication of complex parts layer-by-layer from 3D modeling data. Among AM applications, the fabrication of Functionally Graded Materials (FGMs) has significant importance due to the potential to enhance component performance across several industries. FGMs are manufactured with a gradient composition transition between dissimilar materials, enabling the design of new materials with location-dependent mechanical and physical properties. This study presents a comprehensive review of published literature pertaining to the implementation of Machine Learning (ML) techniques in AM, with an emphasis on ML-based methods for optimizing FGMs fabrication processes. Through an extensive survey of the literature, this review article explores the role of ML in addressing the inherent challenges in FGMs fabrication and encompasses parameter optimization, defect detection, and real-time monitoring. The article also provides a discussion of future research directions and challenges in employing ML-based methods in the AM fabrication of FGMs. Full article

(This article belongs to the Special Issue Artificial Intelligence in Materials Science and Engineering)

► Show Figures

Journal Menu

Journal Browser

Artificial Intelligence in Materials Science and Engineering

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Related Special Issues

Published Papers (14 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI