Mechanical arm flexible joint control method based on fuzzy neural network

Abstract

The invention provides a mechanical arm flexible joint control method based on a fuzzy neural network. The method comprises the following steps that a fuzzy neural network model is established, a neural network parameter learning algorithm is developed; the learning algorithm determines a connection weight parameter of a consequent network and a subordinating degree function center value and a width parameter of an antecedent network; and a fuzzy neural network controller is established according to an identification model to overcome the influence of many nonlinear characteristics of a flexible joint. According to the provided technical scheme, two kinds of control methods of fuzzy logic and the neural network are combined, and the fuzzy neural network controller base on an X model is adopted, so that the neural network is provided with a structure of a fuzzy system, each layer and each node of the neural network correspond to a part of the fuzzy system, the network is different fromblack box operation of a general neural network, all parameters are of definite physical significances, and the network can adapt to the characteristics such as time varying of rigidity and nonlinearfriction of the flexible mechanical arm joint.

Description

Technical field: [0001] The invention relates to the field of robot dynamics control, in particular to a method for controlling flexible joints of a manipulator based on a fuzzy neural network. Background technique: [0002] The mechanical arm joint as the movable part of the mechanical arm is very important for the precise control of the positioning of the mechanical arm. In this year, due to the advantages of large reduction ratio and compact structure, more and more flexible transmission components such as harmonic reducers are used in mechanical Arm joint transmission. However, at this stage, in-depth research on the joints of the manipulator, especially the flexible joints containing the coercive reducer and other flexible transmission mechanisms, such as the in-depth research on the modeling of nonlinear phenomena such as flexibility and friction inside the joints of the manipulator, is needed. Precise control over flexible joints. The working conditions of the manip...

AI Technical Summary

Problems solved by technology

The working conditions of the manipulator are complex and changeable, and there are factors such as geometric nonlinearity. The dynamic parameters of the manipulator will change under different working conditions. It is difficult to obtain a good control effect by using traditional methods.

Images