Metal-Metal Bonding Process Research Based on Xgboost Machine Learning Algorithm.

Conventionally, the optimization of bonding process parameters requires multi-parameter repetitive experiments, the processing of data, and the characterization of complex relationships between process parameters, and performance must be achieved with the help of new technologies. This work focused on improving metal-metal bonding performance by applying SLJ experiments, finite element models (FEMs), and the Xgboost machine learning (ML) algorithm. The importance ranking of process parameters on tensile-shear strength (TSS) was evaluated with the interpretation toolkit SHAP (Shapley additive explanations) and it optimized reasonable bonding process parameters. The validity of the FEM was verified using SLJ experiments. The Xgboost models with 70 runs can achieve better prediction results. According to the degree of influence, the process parameters affecting the TSS ranked from high to low are roughness, adhesive layer thickness, and lap length, and the corresponding optimized values were 0.89 µm, 0.1 mm, and 27 mm, respectively. The experimentally measured TSS values increased by 14% from the optimized process parameters via the Xgboost model. ML methods provide a more accurate and intuitive understanding of process parameters on TSS.

Optimization of Vibration Pretreatment Microwave Curing in Composite Laminate Molding Process.

Vibration pretreatment microwave curing is a high-quality and efficient composite out-of-autoclave molding process. Focusing on interlaminar shear strength, the effects of pretreatment temperature, pretreatment time and vibration acceleration on the molding performance of composite components were analyzed sequentially using the orthogonal test design method; a scanning electron microscope (SEM) and optical digital microscope (ODM) were used to analyze the void content and fiber-resin bonding state of the specimens under different curing and molding processes. The results show that the influence order of the different vibration process parameters on the molding quality of the components was: vibration acceleration > pretreatment temperature > pretreatment time. Within the parameters analyzed in this study, the optimal vibration pretreatment process parameters were: pretreatment temperature of 90 °C, pretreatment time of 30 min, and vibration acceleration of 10 g. Using these parameters, the interlaminar shear strength of the component was 82.12 MPa and the void content was 0.37%. Compared with the microwave curing process, the void content decreased by 71.8%, and the interlaminar shear strength increased by 31.6%. The microscopic morphology and mechanical properties basically reached the same level as the standard autoclave process, which achieved a high-quality out-of-autoclave curing and molding manufacturing of aerospace composite components.

Comparative Failure Study of Different Bonded Basalt Fiber-Reinforced Polymer (BFRP)-AL Joints in a Humid and Hot Environment.

Fiber-reinforced polymer (FRP) materials are increasingly used in automotive industrial fields to achieve lightweight. In order to study the influence of high temperature and high humidity on the bonding structure between different materials, this paper selects basalt fiber-reinforced resin composite materials (BFRP) and aluminum alloy (Al), and uses Araldite® 2012 and Araldite® 2014, two adhesives, to make single lap joints (SLJs). The aging test was carried out for 0 (unaged), 10, 20, and 30 days under the environment of 80 °C/95% relative humidity (RH) and 80 °C/pure water. In this work, simple Fickian law was used to simulate the hygroscopic change law of dumbbell specimens of two adhesives and BFRP in a pure water environment. It was discovered that Araldite® 2012 is most affected by moisture, but the time to reach the maximum water absorption in Araldite® 2014 was shorter than in Araldite® 2012. The failure strength of the joint was obtained through a quasi-static tensile experiment, and it was found that the Araldite® 2014 adhesive joint first increased and then decreased in a high temperature environment. The strength increased by 11.63% after 20 days of aging under an 80 °C/95%RH environment, and increased by 16.66% after 10 days of aging under an 80 °C/pure water environment, which indicates that post-curing reaction occurred. The strength of Araldite® 2012 joints showed a downward trend. After 30 days of aging, it reduced by 40.38% under an 80 °C/95%RH environment and 41.11% under an 80 °C/pure water environment. By observing the load-displacement curve, it was found that, as time increased, the slope of the curve decreased, indicating that the stiffness of the bonded joint decreased with time. The failure modes of the joints were analyzed by macroscopic images and microscopic SEM methods, and the results showed that the surface failure transitions from a mixed failure to a complete tear failure over time. The failure of the basalt fiber/resin interface was because the interaction between the epoxy resin in the adhesive and the epoxy resin in BFRP was greater than the force between the basalt fiber layer and the epoxy resin layer in the BFRP sheet.