Research on decoupling method of force sensor based on PSO-ELM

Abstract

In minimally invasive surgical robot system, the implementation of the force feedback function can increase the flexibility of the surgeon during surgery and reduce the risk of damage to the tissues and organs of the patient. In order to achieve the force detection during surgical process, this paper designs a 3- axis force sensor based on fiber Bragg grating (FBG). When decoupling the sensor, a decoupling result superior to least square (LS) is achieved by combining extreme learning machine (ELM) and particle swarm optimization (PSO). By using PSO-ELM for decoupling, the average error rates in three mutually perpendicular directions are 1.35%, 1.07%, 5.70%, respectively.