Research shows that treadmill shock-absorbing devices can reduce the impact of ground reaction forces on the knee and ankle joints during running. Most existing treadmills use fixed or passive shock absorption, meaning their shock-absorbing systems do not actively adjust to changes in ground reaction forces (GRFs). Methods: This study establishes a mathematical model integrating human motion biomechanics and treadmill running surfaces, analyzing the relationships between various parameters affecting the system. Ultimately, an optimal shock-absorbing treadmill control system is designed, utilizing a microcontroller as the main control unit, airbags for shock absorption, and a widely used foot pressure testing system. Objective: The goal is to more effectively prevent running injuries caused by excessive foot pressure. Compared to conventional shock absorption systems, this design features an active multilevel adjustment function with higher precision in regulation. Results: The experimental results demonstrate that the ground reaction force (GRF) generated by the optimal shock-absorbing treadmill control system is reduced by up to 10% compared to that of a conventional shock-absorbing treadmill. Conclusions: This leads to a smaller impact force on the knees due to foot pressure, resulting in better injury prevention outcomes.

Visual inspection detects manual assembly actions to improve quality. Existing methods mainly analyze behaviors in single assembly scenarios using action recognition algorithms, but they cannot adapt to dynamic product switching and varying station environments in manual assembly lines. This paper proposes an adaptive assembly inspection method based on hand motion trajectories. By constructing an assembly inspection model based on the "Component-Tool-Product" triplet, the YOLOv9 model is employed to capture the spatiotemporal hand trajectory data stream. The assembly process is divided into a sequence of transitions between different assembly regions based on the hand's trajectory. The system analyzes the real-time hand trajectories using Dynamic Time Warping (DTW) and dwell time algorithms to obtain real-time assembly flow, allowing for the detection of missed and misassembled components. Additionally, the frame difference method is introduced to extract hand motion features, and an Attention Feature Fusion (AFF) module is used to integrate multi-scale features with motion texture information, enhancing the performance of the object detection model. Experimental results show that the proposed algorithm effectively reduces the false detection rate, with an average detection accuracy of 96% for missed and misassembled behaviors. The improved YOLOv9 model achieves an mAP@0.5 of 93.94%.