Search

In this paper, firstly, we study the reinforcement learning algorithm, which is a related technology of knowledge graph, and use reinforcement learning to structure the application framework of health care knowledge graph and construct the domain dictionary. And based on the BitLab21 dataset, entity relationship annotation is performed on the named entity recognition result set to realize entity relationship extraction of clinical electronic medical records. Then, the HacRED dataset is used to evaluate the deep learning model, and comparison tests and ablation experiments are conducted to verify the effectiveness of reinforcement learning for constructing knowledge graphs, respectively. Finally, a deviation monitoring method and a data feature extraction method for the case dataset are proposed, and a comparative study of different feature extraction methods is conducted to illustrate the advantages of feature fusion in distinguishing abnormal deviation patterns. All three features have relatively good recognition accuracy for normal patterns, which can reach 100%. The error curves perform well, and their training and testing errors converge very quickly to below 0.01 with less than 5 iterations and achieve nearly 100% recognition accuracy. Reinforcement learning-based knowledge mapping of case datasets and feature fusion-based data machine bias detection can improve the efficiency of medical detection.

The roughness of the joint surface plays a significant role in evaluating the shear strength of rock. The waviness (first-order) and unevenness (second-order) of natural joints have different effects on the characterization of joint surface roughness. To accurately quantify the influence of the two-order asperity on the joint roughness coefficient (JRC) prediction of joint surface profile curve, the optimal sampling interval of the asperity was determined through the change of the Rp{R}_{{\rm{p}}} value of the joint surface profile curve. The separation of the two-order asperity of 48 joint surface profile curves was completed at the optimal sampling interval, and morphological parameters of the asperity such as iave{i}_{{\rm{ave}}}, Rmax{R}_{{\rm{\max }}}, and Rp{R}_{{\rm{p}}} were counted from three aspects: asperity angle of the profile curve, asperity degree, and the trace length. Based on the statistical results of the morphological parameters considering the two-order asperity, the new nonlinear prediction models were proposed. The results showed that the curve slope mutation point SI = 2 mm is the optimal separation distance of the two-order asperity of the joint surface profile curve. The refined separation method that considers the waviness and unevenness of morphological parameters can characterize the detailed morphological features of the joint surface in more dimensions. The support vector regression (SVR) and random forest (RF) models that take into account a two-order asperity separated results have higher accuracy than traditional models. The prediction accuracy has improved by 7–8% in SVR model compared with SVR(SO) and RF(SO). The SVR nonlinear model that considering separation of two-orders of joint surface roughness is more suitable for the prediction of JRC.

Designing bifunctional catalysts to reduce the oxygen evolution reaction (OER) and oxygen reduction reaction (ORR) reaction barriers while accelerating the reaction kinetics is perceived to be a promising strategy to improve the performance of Zinc–air batteries. Unsymmetric configuration in single‐atom catalysts has attracted attention due to its unique advantages in regulating electron orbitals. In this work, a seesaw effect in unsymmetric Fe–Co bimetallic monoatomic configurations is proposed, which can effectively improve the OER/ORR bifunctional activity of the catalyst. Compared with the symmetrical model of Fe–Co, a strong charge polarization between Co and Fe atoms in the unsymmetric model is detected, in whom the spin‐down electrons around Co atoms are much higher than those spin‐up electrons. The seesaw effect occurred between Co atoms and Fe atoms, resulting in a negative shift of the d‐band center, which means that the adsorption of oxygen intermediates is weakened and more conducive to their dissociation. The optimized reaction kinetics of the catalyst leads to excellent performance in ZABs, with a peak power density of 215 mW cm−2 and stable cycling for >1300 h and >4000 cycles. Flexible Zinc–air batteries have also gained excellent performance to demonstrate their potential in the field of flexible wearables. [ABSTRACT FROM AUTHOR]

To realize the overall optimization of electric arc furnace (EAF) steelmaking system, a multi‐objective optimization model including smelting cost, energy consumption per ton of steel, and carbon emission per ton of steel is established. The model is optimized by multi‐objective genetic algorithm to improve the charging structure. At the same time, the data in the optimal solution set are used to analyze the influence of the change of scrap ratio on smelting cost, carbon emission per ton of steel, and smelting cycle. According to the actual working conditions and the demand of steel plant, the optimized results are selected. Compared with the actual production data, the proportion of scrap steel increases to 50.9%, the ratio of molten iron decreases to 38.8%, the smelting cost per ton of steel decreases by 12 Yuan, the energy consumption per ton of steel decreases by 4%, the carbon emission per ton of steel significantly decreases by 13%, and the smelting cycle is shortened by 2 min, but at the cost of increasing the power consumption per ton of steel. The optimized results and the analysis of the change of scrap ratio provide reference for the optimization of EAF steelmaking system. [ABSTRACT FROM AUTHOR]

Fe single‐atom catalysts (SACs) are a promising catalyst for oxygen reduction reaction (ORR) in both Zn–air batteries (ZABs) but have a certain distance to compete with Pt‐based catalysts. Rational modulation of the coordination environment in the second coordination shell of SACs offers an opportunity to improve the intrinsic ORR activity, yet a challenge. Here, a novel strategy is reported to construct a dual‐metal catalyst by introducing a single Co atom in the second coordination shell of the Fe center. The dual‐metal N3─Fe─N─Co site with a certain Fe─Co distance of 0.312 nm is constructed. It allows for manipulation of the positive shift of the Fe center charge state, driving the d‐band center up‐shift by 0.63 eV, thereby offering the optimal adsorption of intermediates. Benefiting from this structure, the as‐prepared Fe(Co2nd)‐NC enables an excellent ORR activity with a half‐wave potential of 0.948 V in 0.1 M KOH. As a cathode in ZABs, it delivered an outstanding peak power density of 218 mW cm−2 and a specific capacity of 915 mAh gZn−1 at 5 mA cm−2, respectively, with superior long‐term durability over 680 h. The second shell layer alignment regulation strategy shows great potential for energy storage applications. [ABSTRACT FROM AUTHOR]

This paper investigates the deterioration of, and the abnormal temperature rise in, the GFRP core rod material of compact V-string composite insulators subjected to prolonged alternating flexural loading under wind-induced stresses. The axial stress on the GFRP (Glass Fiber Reinforced Plastic) core rod, resulting from transverse wind loads, is a focal point of examination. By establishing a stress model and damage model, the paper simulates and computes the evolution of damage in the outer arc material of composite insulator core rods subjected to alternating flexural loads. Additionally, a multi-factor coupled aging platform is set up, integrating humidity, heat, and mechanical stress, to simulate the crazing deterioration process of composite insulators under alternating flexural loads. Experimental results reveal that during 400,000 alternating load cycles, the core rod underwent stages of surface damage, damage increasing, fatigue embrittlement, matrix hydrolysis, and fiber fracture. Simultaneously, the silicone rubber sheath on the outer side of the composite insulator's bending arc develops cracks over aging time, creating pathways for moisture ingress into the interface and core rod. The dielectric constant and dielectric loss factor of the aging region of the core rod increase to varying degrees compared to the non-aging part. Moreover, the degree of abnormal heating of the samples intensifies with the duration of aging experiments. These findings underscore the significance of understanding the aging and decay-like fracture process of compact line V-string composite insulators. They provide crucial insights for future research aimed at enhancing the material properties of composite insulator core rods. [ABSTRACT FROM AUTHOR]