Enhancing property prediction and process optimization in building materials through machine learning: A review

Στεργίου, Κωνσταντίνος Ι.; Ntakolia, Charis; Varytis, Paris; Koumoulos, Elias P.; Karlsson, Patrik; Moustakidis, Serafeim

doi:10.1016/j.commatsci.2023.112031

Cited by 60 publications

(19 citation statements)

References 106 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of fly ash as a raw material in the manufacture of lowperformance inputs in construction not only brings environmental benefits, such as the reduction of CO 2 emissions in the cement manufacturing processes and the impacts associated with the inappropriate disposal of the ashes, but also financial benefits. 92,93 Similarly, the use of glass as an added material for the manufacture of mortars also achieves economic and environmental benefits. Calculating these economic advantages is important because the construction industry is a changing economic sector that is always looking for better quality and more adequate prices.…”

Section: Economic Valuationmentioning

confidence: 99%

Circular economy strategy for the valorization of fly ash as a substitute for cement in monoliths (resistance and reactivity evaluation)

Morales,

Herrera,

López

et al. 2023

Env Prog and Sustain Energy

View full text Add to dashboard Cite

Fly ash is currently a problem in different companies, mainly in thermoelectric plants, which must follow a production and consumption model that involves reusing, renewing, and recycling, thus contributing to the circular economy. This work aims to evaluate the reactivity and compressive strength of different types of ashes in concrete monoliths. For this purpose, sugarcane bagasse (SCBA), bituminous coal (BC), and untreated hazardous waste (RUD) were evaluated as replacements for cement. Monoliths and mortars have been manufactured in different mixtures, taken to a curing room, and their compressive strength and reactivity have been determined at different times (up to 28 days for the monoliths and up to 90 for the mortars), mainly in order to check the formation of calcium silicate hydrate (CSH) gels. In the monolith tests, the best performances have been with SCBA and BC, which have been used for the manufacture of the mortars. On day 56, the behavior of the replacement of 30% fly ash (15% BC:15% SCBA) presents a type H mortar behavior, with better results than the control. By day 90, all replacements had the same resistance as M mortars and even higher resistances than the control. This demonstrates the feasibility of its use in the production of Portland cement for the manufacture of low‐performance inputs. This implies the possible reduction of impacts, both in waste disposal sites and in emissions caused by the construction industry, thus contributing to the circular economy.

show abstract

Section: Economic Valuationmentioning

confidence: 99%

Circular economy strategy for the valorization of fly ash as a substitute for cement in monoliths (resistance and reactivity evaluation)

Morales,

Herrera,

López

et al. 2023

Env Prog and Sustain Energy

View full text Add to dashboard Cite

show abstract

“…Within this landscape, the application of advanced machine learning techniques has emerged as a transformative approach to materials research [4,5,6,7]. As materials continue to play a pivotal role in various industries, the accurate prediction of their mechanical behavior, such as the bulk modulus, becomes important [8]. This research aims to contribute to this evolving paradigm by focusing on the prediction of the bulk modulus.…”

Section: Introductionmentioning

confidence: 99%

Optimizing Neural Networks for Enhanced Material Property Predictions: Insights from Bulk Modulus Analysis

Syamsul,

Pradipto,

Soehianie

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This research presents a deep learning model designed to accurately compute material properties, with a specific focus on the bulk modulus. This study places significant emphasis on hyperparameter optimization, involving adjustments to batch size, learning rate, hidden layer, and neuron count. The dataset, comprising 7107 diverse materials, undergoes thorough preprocessing, which includes outlier removal and the extraction of elemental property descriptors using the matminer library and the Magpie dataset. The core model utilized in this research is an Artificial Neural Network (ANN), with the descriptors serving as crucial input features. Model performance assessment is conducted by using the Mean Absolute Error (MAE) as a quantitative metric, providing insights into predictive accuracy. This research also employs sensitivity analysis to scrutinize the significance of 132 features in predicting the bulk modulus property, contributing to an understanding of material behavior dynamics and facilitating model optimization. The results highlight the impact of neuron count, layer depth, learning rate, and batch size on prediction accuracy. Furthermore, feature importance analysis underscores the critical role of specific material properties, with mean covalent radius emerging as the most influential factor in predicting the bulk modulus. These discoveries provide guidelines for optimizing neural network configurations and material property descriptors for predicting material elasticity.

show abstract

“…In recent decades, the application of data science and machine learning (ML) to material science has evolved from a relatively niche field to an integral part of the natural sciences [1]. The growing body of research in this domain covers all stages of the materials development cycle including discovery, characterisation, property prediction [2][3][4], screening [5,6], retrosynthesis [7,8], analysis of simulation trajectories [9], and optimising synthesis conditions [10,11]. In all cases, appropriately representing the relevant material (whether in terms of structure, chemistry, properties, or functionalities) is a crucial consideration when choosing or designing ML methods to assist materials development.…”

Section: Introductionmentioning

confidence: 99%

Graph representation of multi-dimensional materials

Cai,

Parker,

Barnard

2024

J. Phys. Mater.

View full text Add to dashboard Cite

The integration of graph-based representations with machine learning methodologies is transforming the landscape of material discovery, offering a flexible approach for modelling a variety of materials, from molecules and nanomaterials to expansive 3D bulk materials. Nonetheless, the literature often lacks a systematic exploration from the perspective of material dimensionality. While it is important to design representations and algorithms that are universally applicable across species, it is intuitive for material scientists to align the underlying patterns between dimensionality and the characteristics of the employed graph descriptors. In this review, we provide an overview of the graph representations as inputs to machine learning models and navigate the recent applications, spanning the diverse range of material dimensions. This review highlights both persistent gaps and innovative solutions to these challenges, emphasising the pressing need for larger benchmark datasets and leveraging graphical patterns. As graph-based machine learning techniques evolve, they present a promising frontier for accurate, scalable, and interpretable material applications.

show abstract

Enhancing property prediction and process optimization in building materials through machine learning: A review

Cited by 60 publications

References 106 publications

Circular economy strategy for the valorization of fly ash as a substitute for cement in monoliths (resistance and reactivity evaluation)

Circular economy strategy for the valorization of fly ash as a substitute for cement in monoliths (resistance and reactivity evaluation)

Optimizing Neural Networks for Enhanced Material Property Predictions: Insights from Bulk Modulus Analysis

Graph representation of multi-dimensional materials

Contact Info

Product

Resources

About