Adaptive Network Based Fyzzy inference System (ANFIS) for an Active Transfemoral Prosthetic Leg by Using In-Socket Sensory System

摘要

Prosthetic leg is known as one of the solutions to help the amputee to regain back their ambulation ability. However, most of the current existing knee components still lacks in the ability to provide active body propulsion, which in turn. Thus, higher metabolic energy consumption is required by the amputee in doing locomotion movement. Hence, this study proposed the idea of developing both the mechanical structure as well as an ANFIS knowledge-based control system of the active actuated knee joint for transfemoral (TF) prosthetic leg. ANFIS was adopted using Matlab software to analyze human gait phase recognition necessary for cadence and torque control required by the knee joint mechanism while the actuated knee joint was developed using Inventor CAD software. Physical simulation of the controller presented a realistic simulation of the actuated of the knee joint in terms of knee mechanism. The fuzzy system could replicate human gait cycle by categorizing the cycle into seven gait phases.