Abdelwahhab Khatir
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Abdelwahhab Khatir has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
Roberto Capozucca
5 shared publications- Amine Osmani
LM2SC, Civil Engineering Department, University of Science and Technology of Oran Mohamed Boudiaf (USTO-MB), 1505, El Mnaouer, Oran 31000, Algeria
4 shared publications Erica Magagnini
4 shared publicationsSamir Khatir
4 shared publicationsAbdelmoumin Oulad Brahim
3 shared publicationsThanh Cuong-Le
Center for Engineering Application and Technology Solutions, Ho Chi Minh City Open University, Ho Chi Minh, Vietnam
3 shared publications
Latest Publications
- Open Access
Influence of Natural Perlite Fineness Variation on the Physico-Mechanical Properties of Mortars
This study investigates the influence of natural perlite fineness on the physical and mechanical properties of cement mortars. Natural perlite was ground for 2, 4, and 6 h, producing Blaine fineness values of 3040, 5900, and 8030 cm2/g, respectively. Standardized mortars were prepared by replacing 15% and 25% of the cement mass with perlite. The effects of perlite fineness were evaluated through superplasticizer dosage, semi-adiabatic calorimetry, and compressive strength at curing ages from 1 to 180 days, and water-accessible porosity at 180 days. The results showed that perlite fineness influenced the fresh and hardened properties of the mortars. Increasing fineness generally reduced the superplasticizer dosage required to achieve the target consistency. Perlite-containing mortars exhibited lower early heat release than the reference mortar, and increasing perlite fineness partially enhanced heat evolution. The finest perlite improved compressive-strength development and produced the lowest water-accessible porosity at both replacement levels, particularly at later ages. These findings demonstrate that natural perlite fineness is an important parameter influencing the physical and mechanical properties of mortars.
Open AccessInfluence of Natural Perlite Fineness Variation on the Physico-Mechanical Properties of Mortars
This study investigates the influence of natural perlite fineness on the physical and mechanical properties of cement mortars. Natural perlite was ground for 2, 4, and 6 h, producing Blaine fineness values of 3040, 5900, and 8030 cm2/g, respectively. Standardized mortars were prepared by replacing 15% and 25% of the cement mass with perlite. The effects of perlite fineness were evaluated through superplasticizer dosage, semi-adiabatic calorimetry, and compressive strength at curing ages from 1 to 180 days, and water-accessible porosity at 180 days. The results showed that perlite fineness influenced the fresh and hardened properties of the mortars. Increasing fineness generally reduced the superplasticizer dosage required to achieve the target consistency. Perlite-containing mortars exhibited lower early heat release than the reference mortar, and increasing perlite fineness partially enhanced heat evolution. The finest perlite improved compressive-strength development and produced the lowest water-accessible porosity at both replacement levels, particularly at later ages. These findings demonstrate that natural perlite fineness is an important parameter influencing the physical and mechanical properties of mortars.
- Open Access
Damage Detection in FGM Plates Using Modal Strain Energy and Gaussian Process Regression
The extensive use of composite materials, particularly Functionally Graded Materials (FGMs), across a wide range of industrial applications has generated a critical demand for robust and reliable structural health monitoring (SHM) and damage detection systems to ensure operational safety and long-term structural integrity. In this paper, a numerically validated comprehensive SHM framework is proposed for FGM plates through finite element investigations, based on modal strain energy analysis and employing isogeometric analysis (IGA) for accurate dynamic response evaluation. The proposed damage detection methodology exploits variations in modal strain energy characteristics induced by structural degradation. In the first stage, a damage detection index derived from modal strain energy distributions is used to efficiently and accurately identify the location of damage within the structure. In the second stage, the identified damage indices are employed as input features within a Gaussian-Process-Regression (GPR)-based framework, while the corresponding damage-severity levels are treated as outputs, enabling reliable damage quantification for FGM components. A series of numerical damage scenarios are systematically investigated to assess the performance of the proposed approach. The numerical results demonstrate the high predictive accuracy and effectiveness of the proposed methodology under the investigated damage scenarios and simulation conditions, highlighting its potential for vibration-based damage assessment of FGM plates.
Open AccessDamage Detection in FGM Plates Using Modal Strain Energy and Gaussian Process Regression
The extensive use of composite materials, particularly Functionally Graded Materials (FGMs), across a wide range of industrial applications has generated a critical demand for robust and reliable structural health monitoring (SHM) and damage detection systems to ensure operational safety and long-term structural integrity. In this paper, a numerically validated comprehensive SHM framework is proposed for FGM plates through finite element investigations, based on modal strain energy analysis and employing isogeometric analysis (IGA) for accurate dynamic response evaluation. The proposed damage detection methodology exploits variations in modal strain energy characteristics induced by structural degradation. In the first stage, a damage detection index derived from modal strain energy distributions is used to efficiently and accurately identify the location of damage within the structure. In the second stage, the identified damage indices are employed as input features within a Gaussian-Process-Regression (GPR)-based framework, while the corresponding damage-severity levels are treated as outputs, enabling reliable damage quantification for FGM components. A series of numerical damage scenarios are systematically investigated to assess the performance of the proposed approach. The numerical results demonstrate the high predictive accuracy and effectiveness of the proposed methodology under the investigated damage scenarios and simulation conditions, highlighting its potential for vibration-based damage assessment of FGM plates.
- 24 August 2026
- Published by Springer Nature in Mechanics of Time-Dependent Materials
- Vol. 30 (3) , 63
Experimental investigation of the flexural performance of concrete slabs reinforced with recycled metallic fibers and polypropylene grids
- 24 August 2026
- Published by Springer Nature in Mechanics of Time-Dependent Materials
- Vol. 30 (3) , 63
Experimental investigation of the flexural performance of concrete slabs reinforced with recycled metallic fibers and polypropylene grids
- Open Access
- 28 July 2026
- Published by Ho Chi Minh City Open University Journal of Science in HCMCOU Journal of Science - Advances in Computational Structures
- Vol. 16 (2) , 7-50
Artificial, convolutional, and deep neural networks for structural health monitoring: A review
The reliability and durability of civil engineering structures rely heavily on advanced Structural Health Monitoring (SHM) systems based on in-depth knowledge. Conventional approaches, often based on manual inspections suffer from high costs, long inspection times, and subjective judgment. Neural Network-based methods have recently emerged as powerful tools, enabling not only the automation of monitoring processes but also the structuring and formalization of engineering knowledge and decision-making mechanisms.This review provides three main contributions: (a) a systematic comparison of Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), and Deep Neural Networks (DNNs) in SHM, including accuracy, computational cost, data requirements, and interpretability; (b) a synthesis of hybrid models that combine neural networks with optimisation algorithms such as, GA, PSO, AOA, and others, as an emerging trend; and (c) a critical discussion of knowledge formalisation and explainable AI in SHM, an aspect often overlooked in previous reviews. Furthermore, different learning strategies supervised, unsupervised, and reinforcement learning summarizing their strengths and limitations. Challenges related to data availability, model complexity, interpretability, and the integration of domain knowledge are also discussed. By synthesizing recent advances and identifying future research directions, this review provides researchers and practitioners with a comprehensive reference for selecting and developing neural network-based SHM systems.
- 28 July 2026
- Published by Ho Chi Minh City Open University Journal of Science in HCMCOU Journal of Science - Advances in Computational Structures
- Vol. 16 (2) , 7-50
Open AccessArtificial, convolutional, and deep neural networks for structural health monitoring: A review
The reliability and durability of civil engineering structures rely heavily on advanced Structural Health Monitoring (SHM) systems based on in-depth knowledge. Conventional approaches, often based on manual inspections suffer from high costs, long inspection times, and subjective judgment. Neural Network-based methods have recently emerged as powerful tools, enabling not only the automation of monitoring processes but also the structuring and formalization of engineering knowledge and decision-making mechanisms.This review provides three main contributions: (a) a systematic comparison of Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), and Deep Neural Networks (DNNs) in SHM, including accuracy, computational cost, data requirements, and interpretability; (b) a synthesis of hybrid models that combine neural networks with optimisation algorithms such as, GA, PSO, AOA, and others, as an emerging trend; and (c) a critical discussion of knowledge formalisation and explainable AI in SHM, an aspect often overlooked in previous reviews. Furthermore, different learning strategies supervised, unsupervised, and reinforcement learning summarizing their strengths and limitations. Challenges related to data availability, model complexity, interpretability, and the integration of domain knowledge are also discussed. By synthesizing recent advances and identifying future research directions, this review provides researchers and practitioners with a comprehensive reference for selecting and developing neural network-based SHM systems.
- Open Access
Analytical and Numerical Evaluation of Additional Deflection in Tapered Steel Beams with Variable Diameter Web Openings
This study presents an analytical formulation for predicting the additional elastic deflection of tapered steel beams with variable-diameter circular web openings, a configuration that is not addressed by existing analytical models or current design codes. The proposed formulation accounts for the coupled effects of cross-section tapering, progressive variation in opening diameter along the span, and shear–bending interaction within perforated regions. To the best of the authors’ knowledge, this is the first analytical model addressing such complex non-prismatic cellular beam configurations. The formulation is implemented in MATLAB R2019a, enabling fast and automated deflection calculations over a wide parametric range, including various loading cases, tapering ratios, beam spans, web-post widths, and opening dimensions. For prismatic configurations, the analytical predictions are benchmarked against Eurocode 3 and the SCI P355 design guide, both originally developed for beams with constant cross-sections and regular openings. The results demonstrate the improved accuracy and broader applicability of the proposed approach. For tapered configurations with variable-diameter openings, the formulation is assessed against finite element simulations performed in Abaqus/CAE 2017, with the numerical model previously validated against experimental results available in the literature. The proposed method provides a reliable and practical analytical tool for the serviceability assessment of tapered perforated steel beams in structural engineering applications.
Open AccessAnalytical and Numerical Evaluation of Additional Deflection in Tapered Steel Beams with Variable Diameter Web Openings
This study presents an analytical formulation for predicting the additional elastic deflection of tapered steel beams with variable-diameter circular web openings, a configuration that is not addressed by existing analytical models or current design codes. The proposed formulation accounts for the coupled effects of cross-section tapering, progressive variation in opening diameter along the span, and shear–bending interaction within perforated regions. To the best of the authors’ knowledge, this is the first analytical model addressing such complex non-prismatic cellular beam configurations. The formulation is implemented in MATLAB R2019a, enabling fast and automated deflection calculations over a wide parametric range, including various loading cases, tapering ratios, beam spans, web-post widths, and opening dimensions. For prismatic configurations, the analytical predictions are benchmarked against Eurocode 3 and the SCI P355 design guide, both originally developed for beams with constant cross-sections and regular openings. The results demonstrate the improved accuracy and broader applicability of the proposed approach. For tapered configurations with variable-diameter openings, the formulation is assessed against finite element simulations performed in Abaqus/CAE 2017, with the numerical model previously validated against experimental results available in the literature. The proposed method provides a reliable and practical analytical tool for the serviceability assessment of tapered perforated steel beams in structural engineering applications.
- Top Cited Papers
- 10 February 2026
- Published by Elsevier in International Journal of Pressure Vessels and Piping
- Vol. 222
Prediction in percentage variation of frequencies on damaged pipe repaired by composite materials GFRP, CFRP, and BFRP
- 10 February 2026
- Published by Elsevier in International Journal of Pressure Vessels and Piping
- Vol. 222
Top Cited PapersPrediction in percentage variation of frequencies on damaged pipe repaired by composite materials GFRP, CFRP, and BFRP
- Top Cited Papers
- 2 January 2026
- Published by SAGE Publications in Mathematics and Mechanics of Solids
- Vol. 31 (11) , 2726-2747
Mechanics-based deep learning framework for predicting deflection of functionally graded composite plates using an enhanced whale optimization algorithm
This paper introduces a novel deep learning framework for predicting the normalized and non-dimensional deflection of functionally graded composite plates subjected to sinusoidal loading. The proposed approach integrates a deep neural network (DNN) with a novel enhanced whale optimization algorithm (EWOA) to optimize deflection predictions considering mechanical parameters as input data, including stress, strain, plate geometry, and boundary conditions. The deflection outputs are expressed in both normalized and non-dimensional forms, demonstrating a robust and generalizable prediction model applicable to various structural configurations. During the training phase, the proposed EWOA significantly enhances convergence efficiency and prediction accuracy by introducing two key improvements: chaotic initialization and an adaptive leader mechanism. The EWOA-DNN model is trained using analytically derived deflection datasets, exhibiting strong adaptability to changes in material gradation and loading scenarios. Comparative studies confirm that the suggested hybrid framework outperforms conventional optimization-based models, creating an effective and reliable artificial intelligence (AI)-driven tool for structural design, computational mechanics, and the analysis of functionally graded composite materials.
- 2 January 2026
- Published by SAGE Publications in Mathematics and Mechanics of Solids
- Vol. 31 (11) , 2726-2747
Top Cited PapersMechanics-based deep learning framework for predicting deflection of functionally graded composite plates using an enhanced whale optimization algorithm
This paper introduces a novel deep learning framework for predicting the normalized and non-dimensional deflection of functionally graded composite plates subjected to sinusoidal loading. The proposed approach integrates a deep neural network (DNN) with a novel enhanced whale optimization algorithm (EWOA) to optimize deflection predictions considering mechanical parameters as input data, including stress, strain, plate geometry, and boundary conditions. The deflection outputs are expressed in both normalized and non-dimensional forms, demonstrating a robust and generalizable prediction model applicable to various structural configurations. During the training phase, the proposed EWOA significantly enhances convergence efficiency and prediction accuracy by introducing two key improvements: chaotic initialization and an adaptive leader mechanism. The EWOA-DNN model is trained using analytically derived deflection datasets, exhibiting strong adaptability to changes in material gradation and loading scenarios. Comparative studies confirm that the suggested hybrid framework outperforms conventional optimization-based models, creating an effective and reliable artificial intelligence (AI)-driven tool for structural design, computational mechanics, and the analysis of functionally graded composite materials.
- Open Access
- 31 December 2025
- Published by Springer Nature in Research Square
Non-Destructive Characterization and AI-Based Damage Prediction in Ceresit Mortar Using Experimental Modal Analysis and Hybrid SAINT-HBA Model
In the present study, mechanical behavior of Ceresit 20 mortar is investigated through non-destructive experimental modal testing on a mortar beam. The objective was to determine the Young's modulus (E) in three principal directions longitudinal, transverse, and vertical in terms of bending frequencies. Torsion mode data was utilized in order to calculate the shear modulus (G) and to calculate Poisson's ratio (ν). A finite element model was used for validation, with very good correlation with experiment. Besides, a new Machine Learning (ML) model, Self-Attention Interpretable Neural Transformer optimized by Honey Badger Algorithm (SAINT-HBA), was introduced to predict crack depth of mortar beams. Utilizing bending and torsion frequencies of failed specimens, the model predicted single and multiple crack scenarios very well. SAINT-HBA outperformed hybrid SAINT models that used Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Artificial Ecosystem-based Optimization (AEO) and was found to be useful for structural health monitoring applications.
- 31 December 2025
- Published by Springer Nature in Research Square
Open AccessNon-Destructive Characterization and AI-Based Damage Prediction in Ceresit Mortar Using Experimental Modal Analysis and Hybrid SAINT-HBA Model
In the present study, mechanical behavior of Ceresit 20 mortar is investigated through non-destructive experimental modal testing on a mortar beam. The objective was to determine the Young's modulus (E) in three principal directions longitudinal, transverse, and vertical in terms of bending frequencies. Torsion mode data was utilized in order to calculate the shear modulus (G) and to calculate Poisson's ratio (ν). A finite element model was used for validation, with very good correlation with experiment. Besides, a new Machine Learning (ML) model, Self-Attention Interpretable Neural Transformer optimized by Honey Badger Algorithm (SAINT-HBA), was introduced to predict crack depth of mortar beams. Utilizing bending and torsion frequencies of failed specimens, the model predicted single and multiple crack scenarios very well. SAINT-HBA outperformed hybrid SAINT models that used Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Artificial Ecosystem-based Optimization (AEO) and was found to be useful for structural health monitoring applications.
- Open Access
- 27 December 2025
- Published by MDPI AG in Sustainability
- Vol. 18 (1) , 294
A Novel Hybrid TOARS-Optimized Ensemble of Tree-Based Models for Predicting Soil Temperature at Shallow Depths
Accurate prediction of shallow soil temperature is essential for agriculture, geotechnical design, and ground-coupled energy systems. This study proposes a novel hybrid machine-learning framework in which four tree-based regressors (Decision Tree, Random Forest, XGBoost, and Bagging) are optimized using a newly developed Tri-phase Opposition Adaptive Random Search (TOARS) algorithm. Soil temperature measurements collected in 2024 at depths of 1.0 m and 2.0 m were combined with meteorological variables to train and evaluate the models. TOARS optimization reduced prediction errors by up to 32% for MAE and 28% for RMSE compared with default hyperparameters. At 1.0 m, the optimized Decision Tree achieved MAE = 0.29 °C, RMSE = 0.41 °C, and R2 = 0.9993, while at 2.0 m, XGBoost reached MAE = 0.35 °C, RMSE = 0.47 °C, and R2 = 0.9991. The TOARS-based hybrid ensemble provided the most stable performance across both depths. The results demonstrate that integrating TOARS with tree-based models substantially enhances predictive accuracy and offers a robust solution for soil-temperature forecasting in shallow layers.
- 27 December 2025
- Published by MDPI AG in Sustainability
- Vol. 18 (1) , 294
Open AccessA Novel Hybrid TOARS-Optimized Ensemble of Tree-Based Models for Predicting Soil Temperature at Shallow Depths
Accurate prediction of shallow soil temperature is essential for agriculture, geotechnical design, and ground-coupled energy systems. This study proposes a novel hybrid machine-learning framework in which four tree-based regressors (Decision Tree, Random Forest, XGBoost, and Bagging) are optimized using a newly developed Tri-phase Opposition Adaptive Random Search (TOARS) algorithm. Soil temperature measurements collected in 2024 at depths of 1.0 m and 2.0 m were combined with meteorological variables to train and evaluate the models. TOARS optimization reduced prediction errors by up to 32% for MAE and 28% for RMSE compared with default hyperparameters. At 1.0 m, the optimized Decision Tree achieved MAE = 0.29 °C, RMSE = 0.41 °C, and R2 = 0.9993, while at 2.0 m, XGBoost reached MAE = 0.35 °C, RMSE = 0.47 °C, and R2 = 0.9991. The TOARS-based hybrid ensemble provided the most stable performance across both depths. The results demonstrate that integrating TOARS with tree-based models substantially enhances predictive accuracy and offers a robust solution for soil-temperature forecasting in shallow layers.
- Top Cited Papers
- 27 June 2025
- Published by Springer Nature in Journal of the Brazilian Society of Mechanical Sciences and Engineering
- Vol. 47 (9) , 1-34
Advancements and emerging trends in integrating machine learning and deep learning for SHM in mechanical and civil engineering: a comprehensive review
- 27 June 2025
- Published by Springer Nature in Journal of the Brazilian Society of Mechanical Sciences and Engineering
- Vol. 47 (9) , 1-34
Top Cited PapersAdvancements and emerging trends in integrating machine learning and deep learning for SHM in mechanical and civil engineering: a comprehensive review