Mechatronic Prosthesis for Transfemoral Amputation with Intelligent Control Based on Neural Networks

This article presents the design of a low-cost prototype mechatronic prosthesis for a leg with transfemoral amputation. The development for construction of this mechanical prosthesis is detailed in "Low Cost Mechatronics Prototype Prosthesis for Transfermoral Amputation Controlled by Myoelectric Signals" [1]. This prototype was designed and implemented with a mechanical brake of the knee and foot to help people walk. This article expands the development of this prosthesis with the implementation of the electronic part. The prosthesis is activated by signals obtained by inertial sensors (IMU), which capture the angles generated when walking (in thigh, knee and foot) allowing to reproduce the human gait cycle through a controller, based on neural networks, which permits to replicate the movement by the activation of servomotors. In addition, the prosthesis has a constant monitoring system of physiological parameters such as temperature and humidity inside the stump, which can be visualized through an application for smart devices to protect and alert about the patient's wellness.