ABSTRACT Coal and biomass are important solid fuels, and the viscosity and fusion temperature of their ash have a significant impact on the stable operation of entrained‐flow gasifiers with liquid slag discharge. In this study, separate machine learning (ML) models were developed to predict the viscosity and fusion temperature of coal ash and biomass ash using six regression models: LightGBM, SVR, RF, XGBoost, DNN, and CatBoost. Model performance was evaluated using MAE, RMSE, and R 2 , whereas Bayesian optimization combined with 5‐fold cross‐validation was employed to validate ML models. CatBoost performed best in predicting coal ash fusion temperature and viscosity, with MAE ≤ 25.37°C, R 2 ≥ 0.91 for temperature, and MAE ≤ 0.20, R 2 ≥ 0.97 for viscosity. For biomass ash, LightGBM provided the performance in predicting fusion temperature, achieving an MAE ≤ 18.62°C and R 2 ≥ 0.86. Feature analyzing uncovered that temperature is the dominant factor governing coal ash viscosity. Furthermore, symbolic regression distillation yielded optimal empirical formulas for accurate and efficient prediction of the ash viscosity and temperature. This work provides a practical data‐driven framework for optimizing entrained‐flow gasifier operation and slagging control.
ABSTRACT Lithium‐ion batteries have attracted sustained attention because of their wide applications in energy storage systems. In laboratory research and development, the electrochemical performance of electrode materials is commonly evaluated using half‐cell configurations. However, half‐cell cycling tests are time‐consuming and involve certain safety risks, which may constrain the rapid iterative development of electrode materials. Therefore, an efficient early warning method for half‐cell failure is of practical interest. In this work, a dataset was constructed from electrochemical cycling data of half‐cells based on lithium‐rich cathode materials, and a grid‐search‐optimized gradient boosting decision tree model (GBDT) was developed for early failure prediction. Statistical features, including the mean, standard deviation, and decay rate, were extracted from the first 50 cycles to convert high‐dimensional time‐series data into structured descriptors, thereby achieving effective dimensionality reduction. Using only the mean and standard deviation of specific discharge capacity from the first 50 cycles, the GBDT model achieved the best performance, with accuracies of 0.98 and 0.96 on the training and test sets, respectively. At a current density of 1C, failure identification was also achieved using the mean specific discharge energy as a single feature, with an accuracy of 0.90. These results demonstrate the feasibility of early failure prediction based on limited early‐cycle data and may provide a certain reference value for half‐cell evaluation in laboratory scenarios and for the lightweight development of emerging electrode materials.
ABSTRACT To overcome the strength‐conductivity trade‐off in Cu–Ni–Sn alloys, this study integrates machine learning, thermodynamic calculations, and experiments to design alloys from a phase‐selectivity perspective. SHAP analysis reveals that the coexistence of Ni3Sn and Ni3Sn2 precipitates yields synergistic strengthening superior to single‐phase precipitation. Feature screening identifies the variance of covalent radius and mean Allred–Rochow electronegativity as key physical parameters coupling mechanical and electrical properties. By combining a support vector regression model with thermodynamic phase‐equilibrium calculations, an optimal 350°C aging design window, corresponding to a Sn/(Ni + Sn) mass ratio of approximately 40%–56%, was identified for dual‐phase coexistence. Experimental validation of the predicted Cu–9Ni–9Sn alloy demonstrates a favorable property balance, achieving a tensile strength of 1351 MPa, hardness of 415 HV, and electrical conductivity of 12.43% IACS. Microstructural analysis confirms that the excellent performance originates from the multi‐scale dislocation obstruction by γ‐DO22/γ‐L12 ordered phases and Ni3Sn2 precipitates, coupled with reduced electron scattering due to solute depletion. This closed‐loop paradigm offers a transferable route for multiphase regulation in precipitation‐strengthened alloys.
ABSTRACT As a high‐performance polymeric material, the thermal stability, mechanical strength, and processability of copolyamides (co‐PAs) are determined by the structural design of diamines, diacids, and their stoichiometric ratios. Labor‐intensive experimental design approaches struggle to efficiently explore the vast structural space of the co‐PAs. Here, we develop the sequence‐sensitive multifidelity (SSMF) hybrid modeling methods to predict the properties of copolyamide chains, and modify the genetic algorithm as a teacher–student dual‐model strategy to achieve the inverse design of copolyamide structures. Based on the long SMILES representations of the copolyamide chain sequences, an SSMF hybrid model is constructed by combining two complementary models, that is, a high‐sequence sensitivity model and a high‐efficiency model, enhancing its accuracy through knowledge distillation. Within the modified genetic algorithm framework, the student model enables a massive population iteration, whereas the teacher model conducts the final optimization of inverse design results. Such a teacher‐student dual‐model strategy effectively identifies candidate structures that simultaneously satisfy the targeted glass transition temperature, melting point, and tensile modulus from over 2 billion virtual structures. The developed SSMF modeling method and the teacher‐student cooperative inverse design approach can promote the design of other copolymer structures, especially their chain sequences, advancing the AI‐assisted design of polymeric materials.
ABSTRACT Biomaterials science literature contains rich experimental data scattered across unstructured text, tables, and figures, making manual extraction unscalable. Existing regex‐based and multi‐agent methods are limited by insufficient semantic understanding and poor multitask consistency. We developed MatInform, a two‐stage multi‐agent information extraction framework integrating preprocessing and paragraph awareness where a Main Agent unifies global variables (e.g., material names and methods) and Sub‐Agents perform six constrained fine‐grained extraction tasks in parallel, following a biomaterial‐domain six‐task unified schema covering composition, processing, characterization, antibacterial activity, biocompatibility, and ion release. Evaluated on 20 annotated Ti‐based papers, MatInform achieves a four‐model average System F1 of 0.826. Ablation studies identify the two‐stage architecture as the primary contributor to performance, whereas preprocessing and paragraph awareness contribute marginal improvements. Applied to 1469 titanium‐based antibacterial material papers, MatInform extracts structured data for 8127 samples. Downstream machine learning and SHAP analysis guide the development of a Ca–AgZn modified Ti material with excellent antibacterial performance and enhanced cell proliferation. With minor code adaptation, the framework yields an F1 of 0.764 on 20 ceramic fiber papers. Overall, the framework enables reusable automated extraction with consistent and interpretable multitask coordination.
