Localized induction heating with one magnetizer was experimentally analyzed in order to investigate the altering effect of the magnetizer on the magnetic field. A 22MnB5 blank for tailored property was locally heated to produce the parts of a car body in white, such as the B-pillars. A lower-temperature region with a temperature in the two-phase zone and a full-austenitic high-temperature region were formed on the steel blank after 30 s. After water-quenching, the mixture microstructure (F + M) and 100% fine-grained lath martensite were obtained from the lower- and high-temperature regions, respectively. Moreover, the ultimate tensile stress (UTS) of the parts from the lower- and high-temperature regions was 977 and 1698 MPa, respectively, whereas the total elongations were 17.5% and 14.5%, respectively. Compared with the parts obtained by conventional furnace heating–water quenching (UTS: 1554 MPa, total elongation: 12%), the as-quenched phase developed a tensile strength over 100 MPa greater and a higher ductility. Thus, the new heating process can be a good foundation in subsequent experiments to arbitrarily tailor the designable low-strength zone with a higher ductility by using magnetizers.

The goal of this study is to develop an efficient machine learning framework for designing high-hardness multi-metal nitride coatings, overcoming the limitations of traditional trial-and-error methods. The development of multicomponent metal nitride hard coatings via multi-arc ion plating remains a significant challenge due to the vast compositional search space. Although theoretical studies in macroscopic, mesoscopic, and microscopic domains exist, these often focus on idealized models and lack effective coupling across scales, leading to time-consuming and labor-intensive traditional methods. With advancements in materials genomics and data mining, machine learning has become a powerful tool in material discovery. In this work, we construct a compositional search space for multicomponent nitrides based on electronic configuration, valence electron count, electronegativity, and oxidation states of metal elements in unary nitrides. The search space is further constrained by FCC crystal structure and hardness theory. By incorporating a feature library with micro-, meso-, and macro-structural characteristics and using clustering analysis with theoretical intermediate variables, the model enriches dataset information and enhances predictive accuracy by reducing experimental errors. This model is successfully applied to design multicomponent metal nitride coatings using a literature-derived database of 233 entries. Experimental validation confirms the model’s predictions, and clustering is used to minimize experimental and data errors, yielding a strong agreement between predicted optimal molar ratios of metal elements and nitrogen and measured hardness performance. Of the 100 Vickers hardness (HV) predictions made by the model using input features like molar ratios of metal elements (e.g., Ti, Al, Cr, Zr) and atomic size mismatch, 82 exceeded the dataset’s maximum hardness, with the best sample achieving a prediction accuracy of 91.6% validated against experimental measurements. This approach offers a robust strategy for designing high-performance coatings with optimized hardness.

The quality of threaded connection is an important factor affecting the service life of equipment. Extruded thread has stronger mechanical properties than traditional cutting thread. The forming of magnesium alloy AZ91D internal thread by electromagnetic induction heating assisted extrusion is a new processing method. In this work, on the basis of this process, the height and performance of internal thread are selected as the evaluation index, and the response surface method is used to analyze the influence of the process parameters on the internal thread performance. The range of process parameters (auxiliary heating temperature, hole diameter, machine tool speed) is determined by slip line and empirical method, the test data are simulated, modeled and compared with the response surface analysis method, and the best mathematical model is selected to establish the regression model, the three-dimensional response surface curve of tooth height rate and maximum tensile force is obtained. Through simulation and prediction, it is found that the hole diameter and auxiliary heating temperature have significant influence on the tooth height rate and maximum tensile force of internal thread, and the order is that the hole diameter is larger than the auxiliary heating temperature than the machine tool speed. The research results show that the measured value of tooth height rate and maximum tensile force are close to the predicted value, and the errors are 1.8% and 2.7% respectively, and the model fits well. The better forming process parameters are as follows: auxiliary heating temperature to be 220 °C, hole diameter to be 11.35 mm, machine tool speed to be200 r/min. under this parameter, the tooth height rate and maximum tensile force to be 89.056% and 38.824 KN. At the same time, it is found that with the increase of thread height, the maximum tensile force of thread is also increasing, and the thread height affects the performance of thread. Finally, the optimal process parameters are obtained by response surface method, which improves the tensile properties of extruded internal threads.

In order to reform the ability training mode, the new mode of cultivating students was put forward based on the concept of integration of production, teaching and research. A school enterprise cooperative education base was built, the interdisciplinary integration was improved and the construction of the teaching staff was strengthened. Multi-dimensional teaching was carried out, and a tutor type scientific research team was built. The purpose of the mode is that the students constantly improved their practical ability while mastering professional knowledge, so as to comprehensively improve their innovation ability.