Adaptive Neuro-Fuzzy Friction Compensation Mechanism to Robotic Actuators

Abstract

This paper presents a non-linear friction compensation mechanism using a combination of neural network (NN) with fuzzy system (neuro-fuzzy compensator), applied to harmonic-drive robotic actuators. The friction compensation torque is constituted by NN output, which is trained off-line. Since the friction changes significantly over time, temperature and equipment operational conditions, the NN loses its performance. To recover this performance, a fuzzy algorithm is proposed to deal with the variation friction parameters. The output of the fuzzy algorithm is a gain that multiplied by the NN output will adjust the friction compensation torque. Experimental results have shown the efficiency of the proposed mechanism.

Dead Zone Compensation in Direct Current Motors: A Review

“…Among the papers that were found, some use the control strategies discussed in this article, but with one of the controls with a different function from compensating for the dead zone. This is the case in the article Machado et al (2007), that an artificial neural network is used to compensate, in torque, the dead zone and a fuzzy logic to make adjustments to the neural network. The output of the ANN, which obtains an estimated torque that compensates for the torque lost by the dead zone, is multiplied by a gain from the fuzzy logic, in order to compensate for changes in the dead zone due to the time and operating conditions.…”