Latest open access articles published in Journal of Hybrid Modelling and Intelligent Engineering Systems at https://www.acadlore.com/journals/JHMIES https://www.acadlore.com/journals/JHMIES Acadlore en Creative Commons Attribution(CC - BY) JHMIES support@acadlore.com https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010105 High-entropy alloys (HEAs) exhibit high mechanical strength, phase stability, and damage tolerance, making them promising materials for advanced structural applications. However, reliable prediction of their mechanical response and microstructural failure remains challenging because alloy composition, phase constitution, grain characteristics, thermodynamic descriptors, and deformation behaviour are strongly coupled. This study investigates a physics-guided hybrid modelling framework that integrates physically meaningful alloy descriptors with Transformer-based representation learning for failure and mechanical response prediction in HEAs. Mixing entropy, atomic size mismatch, valence electron concentration, phase stability parameters, and microstructural and mechanical descriptors were incorporated into the data-driven modelling architecture to establish physically informed relationships between material characteristics and failure behaviour. The developed framework was used to predict ultimate tensile strength (UTS), failure strain, stress–strain response, and microstructural failure probability. The results showed close agreement between the predicted and measured UTS and failure strain and demonstrated higher $R^2$ values than random forest, extreme gradient boosting (XGBoost), convolutional neural network (CNN), long short-term memory (LSTM), and standard Transformer models. The predicted stress–strain curves also reproduced the principal deformation behaviour observed in the experimental data. Failure-probability mapping and attention analysis identified the material and microstructural features associated with failure, while the ablation study showed that incorporating physics-guided information improved predictive accuracy, reliability, and interpretability. These findings demonstrate that the structured integration of physics-based descriptors and Transformer learning provides an effective hybrid modelling strategy for relating material constitution to mechanical response and failure. The proposed framework provides a physically informed and interpretable approach to failure prediction and data-assisted design of HEAs and offers a transferable modelling strategy for intelligent engineering analysis of complex material systems. 03-15-2026 <![CDATA[ High-entropy alloys (HEAs) exhibit high mechanical strength, phase stability, and damage tolerance, making them promising materials for advanced structural applications. However, reliable prediction of their mechanical response and microstructural failure remains challenging because alloy composition, phase constitution, grain characteristics, thermodynamic descriptors, and deformation behaviour are strongly coupled. This study investigates a physics-guided hybrid modelling framework that integrates physically meaningful alloy descriptors with Transformer-based representation learning for failure and mechanical response prediction in HEAs. Mixing entropy, atomic size mismatch, valence electron concentration, phase stability parameters, and microstructural and mechanical descriptors were incorporated into the data-driven modelling architecture to establish physically informed relationships between material characteristics and failure behaviour. The developed framework was used to predict ultimate tensile strength (UTS), failure strain, stress–strain response, and microstructural failure probability. The results showed close agreement between the predicted and measured UTS and failure strain and demonstrated higher $R^2$ values than random forest, extreme gradient boosting (XGBoost), convolutional neural network (CNN), long short-term memory (LSTM), and standard Transformer models. The predicted stress–strain curves also reproduced the principal deformation behaviour observed in the experimental data. Failure-probability mapping and attention analysis identified the material and microstructural features associated with failure, while the ablation study showed that incorporating physics-guided information improved predictive accuracy, reliability, and interpretability. These findings demonstrate that the structured integration of physics-based descriptors and Transformer learning provides an effective hybrid modelling strategy for relating material constitution to mechanical response and failure. The proposed framework provides a physically informed and interpretable approach to failure prediction and data-assisted design of HEAs and offers a transferable modelling strategy for intelligent engineering analysis of complex material systems. ]]> Physics-Guided Hybrid Transformer Modelling for Microstructural Failure and Mechanical Response Prediction in High-Entropy Alloys elangovan muniyandy doi: 10.56578/jhmies010105 Journal of Hybrid Modelling and Intelligent Engineering Systems 03-15-2026 Journal of Hybrid Modelling and Intelligent Engineering Systems 03-15-2026 2026 1 1 Article 49 10.56578/jhmies010105 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010105 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010104 Reliable monitoring of chip formation and tool degradation is essential for machining quality, process stability, and condition-based maintenance in intelligent manufacturing systems. However, individual sensing modalities and isolated learning models provide incomplete representations of the heterogeneous and time-dependent interactions that characterize computer numerical control (CNC) milling. This study investigates a hybrid multimodal modelling framework that integrates heterogeneous sensing, complementary feature-learning mechanisms, and joint classification–regression tasks for chip morphology and progressive flank-wear monitoring. Vibration, acoustic emission (AE), cutting force, spindle current, and temperature signals were synchronized and fused within a unified modelling architecture. A convolutional neural network (CNN) was used to extract local signal characteristics, a bidirectional long short-term memory (BiLSTM) network modelled temporal dependencies, and Transformer-based self-attention captured long-range interactions within the fused representation. The resulting features were used jointly to classify continuous, segmented, discontinuous, and serrated chip morphologies and to estimate progressive flank wear. The framework was evaluated under variations in spindle speed, feed rate, and wet and dry machining conditions, together with sensor-fusion comparisons and architectural ablation experiments. The full multimodal configuration achieved approximately 97.2% chip-classification accuracy, while the complete hybrid architecture reached approximately 98% in the ablation analysis and maintained prediction accuracy above 94% across the investigated cutting conditions. Tool-wear estimates also showed close agreement with the experimentally measured values. These results indicate that coordinated integration of heterogeneous sensing with complementary local, sequential, and attention-based modelling mechanisms improves predictive stability and robustness under variable machining conditions. The proposed framework provides a structured hybrid-modelling approach for intelligent machining-process monitoring and offers a basis for predictive maintenance and adaptive CNC manufacturing systems. 03-12-2026 <![CDATA[ <p>Reliable monitoring of chip formation and tool degradation is essential for machining quality, process stability, and condition-based maintenance in intelligent manufacturing systems. However, individual sensing modalities and isolated learning models provide incomplete representations of the heterogeneous and time-dependent interactions that characterize computer numerical control (CNC) milling. This study investigates a hybrid multimodal modelling framework that integrates heterogeneous sensing, complementary feature-learning mechanisms, and joint classification–regression tasks for chip morphology and progressive flank-wear monitoring. Vibration, acoustic emission (AE), cutting force, spindle current, and temperature signals were synchronized and fused within a unified modelling architecture. A convolutional neural network (CNN) was used to extract local signal characteristics, a bidirectional long short-term memory (BiLSTM) network modelled temporal dependencies, and Transformer-based self-attention captured long-range interactions within the fused representation. The resulting features were used jointly to classify continuous, segmented, discontinuous, and serrated chip morphologies and to estimate progressive flank wear. The framework was evaluated under variations in spindle speed, feed rate, and wet and dry machining conditions, together with sensor-fusion comparisons and architectural ablation experiments. The full multimodal configuration achieved approximately 97.2% chip-classification accuracy, while the complete hybrid architecture reached approximately 98% in the ablation analysis and maintained prediction accuracy above 94% across the investigated cutting conditions. Tool-wear estimates also showed close agreement with the experimentally measured values. These results indicate that coordinated integration of heterogeneous sensing with complementary local, sequential, and attention-based modelling mechanisms improves predictive stability and robustness under variable machining conditions. The proposed framework provides a structured hybrid-modelling approach for intelligent machining-process monitoring and offers a basis for predictive maintenance and adaptive CNC manufacturing systems.</p> ]]> Hybrid Multimodal Modelling for Joint Chip Morphology Classification and Tool Wear Prediction in Computer Numerical Control Milling g. shanmugasundar doi: 10.56578/jhmies010104 Journal of Hybrid Modelling and Intelligent Engineering Systems 03-12-2026 Journal of Hybrid Modelling and Intelligent Engineering Systems 03-12-2026 2026 1 1 Article 35 10.56578/jhmies010104 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010104 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010103 Accurate buckling prediction of functionally graded porous (FGP) nanobeams requires the simultaneous consideration of material gradation, porosity distribution, transverse shear deformation, and small-scale effects. Conventional analytical models provide a sound mechanical basis; however, they become less convenient when repeated evaluations and multi-objective design decisions are required. This study develops a hybrid analytical-machine-learning framework for predicting and interpreting the buckling behavior of FGP nanobeams. An analytical model was formulated using exponential shear deformation theory and Eringen’s nonlocal elasticity theory. The governing equations were derived from the minimum total potential energy principle and solved by Navier’s method for simply supported boundary conditions. The formulation was verified against published benchmark results and was subsequently used to generate 540 configurations covering different slenderness ratios, nonlocal parameters, porosity coefficients, and porosity distributions. A residual-learning surrogate was then constructed by combining a regularized Ridge baseline with nonlinear machine learning (ML) models. Nested cross-validation (CV) showed that the hybrid support vector regression model with a radial basis function produced the lowest prediction errors, with a root mean square error (RMSE) of 0.00729, a mean absolute error (MAE) of 0.00309, and an $R^2$ of 0.999900. The analytical and surrogate results showed that the buckling load decreases with increasing slenderness ratio, nonlocal parameter, and porosity coefficient, while the functionally graded X-pattern (FGX) distribution retains the highest buckling resistance. The conformal prediction intervals achieved 97.04% empirical coverage. SHapley Additive exPlanations (SHAP) analysis identified the slenderness ratio as the dominant input, and Nondominated Sorting Genetic Algorithm II (NSGA-II) yielded a Pareto-based compromise between porosity and buckling resistance. The proposed framework demonstrates how analytical mechanics, residual learning, uncertainty quantification, model interpretation, and multi-objective optimization can be coordinated within a unified engineering design procedure. 03-05-2026 <![CDATA[ <p>Accurate buckling prediction of functionally graded porous (FGP) nanobeams requires the simultaneous consideration of material gradation, porosity distribution, transverse shear deformation, and small-scale effects. Conventional analytical models provide a sound mechanical basis; however, they become less convenient when repeated evaluations and multi-objective design decisions are required. This study develops a hybrid analytical-machine-learning framework for predicting and interpreting the buckling behavior of FGP nanobeams. An analytical model was formulated using exponential shear deformation theory and Eringen’s nonlocal elasticity theory. The governing equations were derived from the minimum total potential energy principle and solved by Navier’s method for simply supported boundary conditions. The formulation was verified against published benchmark results and was subsequently used to generate 540 configurations covering different slenderness ratios, nonlocal parameters, porosity coefficients, and porosity distributions. A residual-learning surrogate was then constructed by combining a regularized Ridge baseline with nonlinear machine learning (ML) models. Nested cross-validation (CV) showed that the hybrid support vector regression model with a radial basis function produced the lowest prediction errors, with a root mean square error (RMSE) of 0.00729, a mean absolute error (MAE) of 0.00309, and an $R^2$ of 0.999900. The analytical and surrogate results showed that the buckling load decreases with increasing slenderness ratio, nonlocal parameter, and porosity coefficient, while the functionally graded X-pattern (FGX) distribution retains the highest buckling resistance. The conformal prediction intervals achieved 97.04% empirical coverage. SHapley Additive exPlanations (SHAP) analysis identified the slenderness ratio as the dominant input, and Nondominated Sorting Genetic Algorithm II (NSGA-II) yielded a Pareto-based compromise between porosity and buckling resistance. The proposed framework demonstrates how analytical mechanics, residual learning, uncertainty quantification, model interpretation, and multi-objective optimization can be coordinated within a unified engineering design procedure.</p> ]]> Hybrid Analytical-Machine-Learning Surrogate Modeling for Buckling Prediction and Design of Functionally Graded Porous Nanobeams burak i̇kinci mehmet avcar doi: 10.56578/jhmies010103 Journal of Hybrid Modelling and Intelligent Engineering Systems 03-05-2026 Journal of Hybrid Modelling and Intelligent Engineering Systems 03-05-2026 2026 1 1 Article 16 10.56578/jhmies010103 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010103 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010102 In this study, an adaptive linear neuron (ADALINE) network is employed to adjust the parameters of a conventional proportional-integral (PI) controller. The proposed adaptive neuron controller (NEURON-PI) has been used here instead of the conventional power system stabilizer (PSS) to control the rotor speed deviation of the single-machine infinite-bus (SMIB) system. The rotor speed deviation is used as a control error fed to the neural network in order to adjust the PI controller gains. This strategy achieves an optimal response of the power system against a wide range of operational conditions. The linearized Heffron-Phillips model of the SMIB system with the proposed NEURON-PI controller is simulated using MATLAB R2025a/Simulink software. The simulation results have shown that the power system using the proposed control technique becomes more reliable for a wide range of operating conditions as the speed deviation and power angle deviation become less oscillatory compared to the conventional PSS controller tuned by the equilibrium optimizer algorithm (EOA) reported in a previous study. 02-19-2026 <![CDATA[ <p>In this study, an adaptive linear neuron (ADALINE) network is employed to adjust the parameters of a conventional proportional-integral (PI) controller. The proposed adaptive neuron controller (NEURON-PI) has been used here instead of the conventional power system stabilizer (PSS) to control the rotor speed deviation of the single-machine infinite-bus (SMIB) system. The rotor speed deviation is used as a control error fed to the neural network in order to adjust the PI controller gains. This strategy achieves an optimal response of the power system against a wide range of operational conditions. The linearized Heffron-Phillips model of the SMIB system with the proposed NEURON-PI controller is simulated using MATLAB R2025a/Simulink software. The simulation results have shown that the power system using the proposed control technique becomes more reliable for a wide range of operating conditions as the speed deviation and power angle deviation become less oscillatory compared to the conventional PSS controller tuned by the equilibrium optimizer algorithm (EOA) reported in a previous study.</p> ]]> An Adaptive Neuron-Proportional-Integral Controller Type Power System Stabilizer for Single-Machine Infinite-Bus System alyaseh askir issa ali doi: 10.56578/jhmies010102 Journal of Hybrid Modelling and Intelligent Engineering Systems 02-19-2026 Journal of Hybrid Modelling and Intelligent Engineering Systems 02-19-2026 2026 1 1 Article 8 10.56578/jhmies010102 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010102 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010101 The intrinsic variability associated with waste-derived bitumen modifiers poses persistent limitations for conventional deterministic pavement design approaches. This study establishes a hybrid modelling architecture that integrates physics-informed boundary constraints with stochastic simulation components to predict the rheological performance of asphalt binders modified with waste frying oil. Literature-derived parameter ranges are embedded within a Gaussian copula-based dependency structure and expanded through large-scale Monte Carlo simulation to generate a statistically convergent dataset comprising 1,000,000 realizations. The integrated modelling structure preserves the nonlinear relationships among key rheological indicators, including penetration, softening point, and modifier dosage, while maintaining physical consistency. The predictive capability of the proposed architecture is validated using standard statistical metrics, achieving coefficients of determination exceeding 0.98 for penetration and 0.93 for softening point. A mode-based master curve is further constructed to provide a stable and computationally efficient representation of binder behaviour across varying modifier contents. The results demonstrate that the proposed hybrid modelling structure offers a reliable alternative to extensive laboratory testing, reducing experimental effort while retaining predictive fidelity. From a system perspective, the framework provides a structured basis for incorporating material variability into pavement performance evaluation and can be interpreted as a simplified digital twin component for asphalt material systems. The study thereby contributes to the integration of stochastic modelling within engineering-oriented predictive structures for sustainable pavement design. 02-16-2026 <![CDATA[ The intrinsic variability associated with waste-derived bitumen modifiers poses persistent limitations for conventional deterministic pavement design approaches. This study establishes a hybrid modelling architecture that integrates physics-informed boundary constraints with stochastic simulation components to predict the rheological performance of asphalt binders modified with waste frying oil. Literature-derived parameter ranges are embedded within a Gaussian copula-based dependency structure and expanded through large-scale Monte Carlo simulation to generate a statistically convergent dataset comprising 1,000,000 realizations. The integrated modelling structure preserves the nonlinear relationships among key rheological indicators, including penetration, softening point, and modifier dosage, while maintaining physical consistency. The predictive capability of the proposed architecture is validated using standard statistical metrics, achieving coefficients of determination exceeding 0.98 for penetration and 0.93 for softening point. A mode-based master curve is further constructed to provide a stable and computationally efficient representation of binder behaviour across varying modifier contents. The results demonstrate that the proposed hybrid modelling structure offers a reliable alternative to extensive laboratory testing, reducing experimental effort while retaining predictive fidelity. From a system perspective, the framework provides a structured basis for incorporating material variability into pavement performance evaluation and can be interpreted as a simplified digital twin component for asphalt material systems. The study thereby contributes to the integration of stochastic modelling within engineering-oriented predictive structures for sustainable pavement design. ]]> A Hybrid Modelling Architecture for Predicting Rheological Performance of Waste Frying Oil–Modified Asphalt Binders via Stochastic–Physical Integration serdal terzi ekinhan eriskin doi: 10.56578/jhmies010101 Journal of Hybrid Modelling and Intelligent Engineering Systems 02-16-2026 Journal of Hybrid Modelling and Intelligent Engineering Systems 02-16-2026 2026 1 1 Article 1 10.56578/jhmies010101 https://www.acadlore.com/article/JHMIES/2026_1_1/jhmies010101