Development of a Bayesian Network-Based Parallel Mechanism for Lower Limb Gait Rehabilitation.

This study aims to address the clinical needs of hemiplegic and stroke patients with lower limb motor impairments, including gait abnormalities, muscle weakness, and loss of motor coordination during rehabilitation. To achieve this, it proposes an innovative design method for a lower limb rehabilitation training system based on Bayesian networks and parallel mechanisms. A Bayesian network model is constructed based on expert knowledge and structural mechanics analysis, considering key factors such as rehabilitation scenarios, motion trajectory deviations, and rehabilitation goals. By utilizing the motion characteristics of parallel mechanisms, we designed a rehabilitation training device that supports multidimensional gait correction. A three-dimensional digital model is developed, and multi-posture ergonomic simulations are conducted. The study focuses on quantitatively assessing the kinematic characteristics of the hip, knee, and ankle joints while wearing the device, establishing a comprehensive evaluation system that includes range of motion (ROM), dynamic load, and optimization matching of motion trajectories. Kinematic analysis verifies that the structural design of the device is reasonable, aiding in improving patients' gait, enhancing strength, and restoring flexibility. The Bayesian network model achieves personalized rehabilitation goal optimization through dynamic probability updates. The design of parallel mechanisms significantly expands the range of joint motion, such as enhancing hip sagittal plane mobility and reducing dynamic load, thereby validating the notable optimization effect of parallel mechanisms on gait rehabilitation.