The growing use of composites in automotive and aerospace fields highlights the need for effective joining of dissimilar materials. Adhesive bonding offers significant advantages over traditional methods. Therefore, comprehensively exploring the relationship between multiple design variables and joint strength, and subsequently achieving accurate prediction of joint strength based on this understanding, is essential for enhancing the effectiveness and efficiency of adhesive joint structural optimization. However, the joint—the critical yet weakest part—has strength governed by complex structural variables that are not fully understood, limiting optimization potential. Based on the effectiveness of finite element simulation in tensile fracture mechanics, this study developed a deep neural network (DNN). Combining the DNN model with a genetic algorithm (GA), both single-objective and multi-objective optimization were conducted. The single-objective optimization focused solely on maximizing joint strength, while the multi-objective GA further quantified the Pareto optimal trade-offs between joint strength and bond area, identifying compromise solutions. The effectiveness of the optimized parameters was validated, demonstrating higher efficiency and accuracy compared to traditional optimization methods such as response surface methodology (RSM). This integrated approach provides a robust framework for predicting joint strength and achieving effective optimization of bonded structures.

Helical structures are widely used in various engineering disciplines due to their energy storage and vibration damping characteristics. Existing studies have investigated the dynamic responses of various helical structures under static, low-speed dynamic and high-speed dynamic loadings. However, systematic understandings on the relationship between the complicated multi-parameters of helical structures and significant spike forces remain challenging. The present work develops a transient finite element model for a beehive helical structure sample, of which results are validated by a real engine test at 7800 rpm engine speed. The simulation results are in excellent agreement with the testing results and reveal that the dynamic spike forces are caused by collision effects between narrow coils. Next, 2 types of machine learning models, namely a deep neural networks (DNN) model and a genetic programming (GP) model, are developed and compared using simulation results. It is noted that the deep neural networks model has better prediction accuracy with the R² value of the testing set reaches 0.939. Finally, the relationships between multiple geometric parameters of the helical structure and the peak dynamic forces are plotted based on the developed machine learning model. In addition, design spaces that balance lower peak forces and vibration damping performance are proposed. These findings would be beneficial for systematic multi-parameter analysis and better designs of helical structures with superior mechanical performance.