An artificial intelligence framework that incorporates a physics-constrained inverse-design system (PHICS) built upon a directed acyclic graph (DAG) architecture for CPCMs, integrating interface, phase, and carrier engineering.
Abstract
Temperature-control materials, notably composite phase-change materials (CPCMs), show great potential for the thermal management of next-generation power electronics. However, the synergistic optimization of multiple performance metrics still relies heavily on Edisonian trial-and-error experimentation. Herein, we present an artificial intelligence framework that incorporates a physics-constrained inverse-design system (PHICS) built upon a directed acyclic graph (DAG) architecture for CPCMs, integrating interface, phase, and carrier engineering. By encoding structural hierarchies and physical causality through DAG, PHICS framework couples forward predictive modeling with a diversity-enhanced NSGA-II optimizer to efficiently map Pareto-optimal design boundaries. Guided by these predictions, we successfully fabricate a high-performance CPCM composed of an oriented graphite fiber skeleton and an n-octacosane matrix with amorphous alumina (am-Al2O3) interfacial transition layers. Benefiting from the bifunctional role of the am-Al2O3 interlayer as both an interfacial phonon bridge and electron barrier, the resulting CPCMs achieve a superior balance of thermal conduction, thermal storage, and electrical insulation. These results demonstrate the accuracy of PHICS-guided multifunctional composite design, establishing a closed-loop platform that combines physics-constrained machine learning with experimental validation to solve key thermal–electrical trade-offs.
Metal Additive Manufacturing (AM) has emerged as a crucial technology for fabricating high-performance, lightweight components for aerospace, biomedical, and energy applications. However, consistent part quality remains one of the most significant challenges because complex nonlinear interactions between material properties, process parameters, thermal histories, and defect formation mechanisms control this process. Traditional modeling approaches usually treat the scales individually, thus poorly predicting key outcomes such as porosity, melt pool morphology, and mechanical performance. In this work, a physics-aware, multi-scale Artificial Intelligence (AI)-driven optimization framework is proposed that unifies material level attributes, process settings, thermal/in-situ responses, and final mechanical properties into a single predictive pipeline. To model realistic AM behavior, a synthetic, physics-informed dataset is generated to represent the Laser Powder Bed Fusion (LPBF), Electron Beam Melting (EBM), and Directed Energy Deposition (DED) processes. Multi-level surrogate models are proposed for predictions of melt-pool width, peak temperature, porosity, and tensile properties. Defect classification models are used to predict builds with porosity exceeding a 2.5% threshold. Sensitivity analysis, feature attribution, and energy-density sweeping are conducted to identify critical cross-scale interactions and the optimal process window. The framework demonstrates the overall importance of energy density and in-situ thermal properties to defect formation and mechanical results, and it indicates that it highly predicts all tasks. The work will become part of smart digital twins in the future, providing a single, data-driven basis for stable process optimization in AM, enabling better parameter selection and improved quality assurance.
Yong He· Journal of Engineering, Proj...· 0 citations
Highlights A two-stage ML framework decouples processing and formulation optimization. The two-stage strategy allows concurrent improvement of TS and TC. The CF/SA ratio serves as a composition-derived descriptor for interfacial effects. Feature construction enhances model reliability under small-data constraints. Abstract The rational design of high-performance carbon-filled polyimide (CF/PI) composites is challenged by complex interactions among processing parameters, composition, and interfacial effects. Here, we address thermo-mechanical co-optimization in CF/PI composites through two-stage processing and formulation design. An experimental dataset was employed to construct processing and composition datasets. A CatBoost model was developed to relate hot-pressing parameters to the tensile strength (TS) of pure PI, enabling inverse optimization of processing conditions, with quantitative experimental validation of the predicted processing windows (RMSE = 3.89 MPa). Within the optimized processing window, an XGBoost-based composition-property model was further established to perform high-throughput screening and multi-objective optimization of TS and thermal conductivity (TC). To quantitatively account for interfacial effects, the mass ratio of carbon-filled to sizing agent (CF/SA) was introduced as a composition-derived feature. Model interpretation reveals that CF and graphene positively contribute to TC but negatively affect TS. Notably, formulations with CF/SA > 2 tend to achieve a more favorable TS–TC balance. Experimental validation of model-selected composite formulations confirmed the predicted trends for both TS and TC. These findings suggest that interfacial regulation is a key lever for balancing mechanical strength and thermal transport in CF/PI composites.
Yu Zhang, Wen-Ting Zhao, Luling He et al.· Materials· 0 citations
The integration of physics-based modeling and data-driven prediction is creating new opportunities for predictive design, optimization, and the deployment of digital twins in advanced manufacturing systems. In compliant mechanisms, particularly double-bridge configurations used in precision positioning and surface engineering applications, accurate prediction and optimization of amplification ratio remain challenging due to coupled geometric interactions and nonlinear design trade-offs. This study presents a Physics-Guided Digital-Twin-Ready Framework for the predictive design and multi-objective optimization of double-bridge compliant mechanisms. A physics-consistent dataset comprising 8,000 design samples was generated using Latin Hypercube Sampling, analytical compliance modeling, constraint-based filtering, and response-space stratified sampling. The resulting dataset provides balanced coverage of amplification ratios within the range of 5–50, enabling robust learning across diverse design regimes. Machine-learning models, including Random Forest and Extreme Gradient Boosting (XGBoost), were developed to predict amplification ratio from geometric and material parameters. The models achieved excellent predictive performance, with coefficients of determination (R
2
) exceeding 0.99, mean absolute errors below 0.93, and root mean square errors below 0.65. Uncertainty quantification was incorporated through ensemble variance estimation, yielding prediction intervals with less than 5% relative uncertainty in well-sampled regions. SHAP-based explainability and sensitivity analyses revealed that amplification behavior is primarily governed by geometric parameters, particularly beam lengths and flexure thickness, whereas material stiffness has comparatively lower influence. NSGA-II-based multi-objective optimization identified Pareto-optimal solutions that balance amplification ratio and equivalent stiffness, highlighting the inherent trade-off between displacement amplification and structural rigidity. The developed surrogate models enable rapid design exploration, uncertainty assessment, and optimization, while achieving computational speed-ups of approximately 10
3
–10
7
times compared with finite-element-based evaluation workflows, depending on the evaluation method. The primary contribution of this work is the integration of analytical compliance modeling, physics-consistent dataset generation, uncertainty-aware machine learning, explainable artificial intelligence, and multi-objective optimization within a unified predictive framework. The proposed methodology should be interpreted as a digital-twin-ready surrogate architecture rather than a fully implemented digital twin, as real-time sensing, and online model updating are beyond the scope of the present study. Nevertheless, the framework provides a scalable foundation for future integration with experimental measurements, multi-fidelity datasets, and digital-twin-enabled manufacturing environments.
V. Kolate, P. D. Darade, Suhas P. Deshmukh· Frontiers of Mechanical Engi...· 0 citations
This study proposed a hybrid physics-guided residual multi-task neural network framework based on a large-scale simulated J-V dataset, comprising approximately 2.47 million samples. Physics-based descriptors were constructed, and residual learning with a heuristic empirical baseline was adopted through carrier transport and interfacial contact mechanisms. The model achieved a test coefficient of determination (R2) of 0.8538 while reducing the prediction Root Mean Square Error (RMSE) by approximately 80% relative to the empirical baseline alone. For static electrical stability prediction with shunt resistance, the model obtained a test of 0.1113. However, the performance was limited by the static proxy and the lack of aging data. SHapley Additive exPlanations (SHAP) analysis indicated consistency with known device physics, especially the key role of work function difference. The proposed framework offers experimentalists a rapid and interpretable prescreening tool for device parameter optimization, and can be used to accelerate the discovery of high-efficiency and stable PSCs.
Optimizing the energy consumption(EC) of industrial robots plays a crucial role in promoting their large-scale application to support the realization of Industry 4.0. Notably, robotic grinding is particularly energy-intensive, attributed to the complex coupling between robot dynamics and the continuous contact forces required for surface finishing. Furthermore, given the intricate nature of the EC process, it is challenging to establish a precise numerical relationship between robotic process parameters and EC relying exclusively on physical mechanisms. And data-driven models require large datasets and often fail to achieve high accuracy under small-sample conditions. To address this, we propose a physics-guided data-driven EC prediction model (EC-PGDD). The heat conduction equation is employed to characterize the underlying relationship between temperature and EC, and a regularization term within the loss function of the temperature prediction model-by embedding differential operators, a smoothness prior is imposed, enhancing extrapolation in sparse data regions. Based on the physical information provided by this equation, EC-PGDD integrates predicted temperature with process parameters, encoding richer information than purely data-driven approaches. To validate the effectiveness of the proposed model and provide targeted strategies for process parameter optimization, Validation experiments on a battery end-plate robotic grinding unit., utilizing the NSGA-II algorithm for multi-objective optimization, demonstrated a 7.67% reduction in energy consumption and a 0.23% reduction in execution time.
Jihong Yan, Yan Zeng, Rui-Zhi Li· Journal of Computing and Inf...· 0 citations
Composite phase-change materials offer a scalable route for thermal energy storage, yet breaking the inherent trade-off between energy and power densities is constrained by fundamental mismatches at the skeleton-storage-medium interface. Conventional interface engineering remains trapped in empirical trial-and-error, struggling to distinguish the typically entangled variables of interfacial wettability and heat-transport behavior. Here, we present a machine learning-assisted design paradigm based on functional group deconstruction. By resolving surface functional groups into independent elemental and structural dimensions, we achieve programmable control over skeleton-molten salt interfacial behaviors. We reveal an intrinsic property decoupling: interfacial wettability is governed by bonding interactions derived from elemental composition, whereas heat transport is dictated by low-frequency phonon spectral matching rooted in geometric topology. Guided by this predictive atlas, we synthesized targeted carbon-molten salt composites. Compared to unmodified baselines, the engineered composite achieves 1.6-fold higher mass loading and 3.6-fold enhanced thermal conductivity. Crucially, after 350 thermal cycles, it retains ∼90% mass and ∼80% conductivity, decisively suppressing the degradation of pristine hosts (∼60% and ∼25% retention). Device-level finite-difference method simulations indicate this dual-property optimization effectively overcomes the inherent energy-power trade-off-sustaining triple the energy density of unmodified baselines under extreme 10C constant-power loads.
Yifei Zhu, Tiansheng Wang, Yan-Fang Zhu et al.· Advances in Materials· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
