IGBO-based two-stage pendulum two-dimensional bridge crane RBF neural network modeling method

Abstract

The invention discloses an IGBO-based two-stage pendulum two-dimensional bridge crane RBF neural network modeling method. The method comprises the following steps: 1) obtaining input and output data of a two-stage pendulum two-dimensional bridge crane system through an experiment or field acquisition; 2) providing a gradient-based optimization algorithm for improving global search and local search strategies, and providing a two-stage pendulum two-dimensional bridge crane RBF neural network modeling method based on the algorithm; 3) setting operation parameters of an algorithm, and taking the sum of root-mean-square errors of output and actual output of the RBF neural network model as an objective function of the IGBO; and 4) operating the IGBO to obtain an optimal parameter estimation value of the RBF neural network, and inputting the optimal value into the RBF neural network model to obtain a simulation model of the bridge crane. According to the RBF neural network modeling method, multiple output models of the bipolar pendulum two-dimensional bridge crane can be established at the same time, and the method is also suitable for modeling of other complex systems.

Description

technical field [0001] The invention relates to an intelligent optimization modeling method, in particular to an IGBO-based double-stage pendulum two-dimensional bridge crane RBF neural network modeling method. Background technique [0002] Overhead cranes usually have X, Y, and Z degrees of freedom and directions of hook movement. On the one hand, the trolley carrying goods can move left and right on the slide rail; while the slide rail can move back and forth on the bridge rail orthogonal to it; the hook hanging on the trolley can realize the up and down movement of the goods, and can happen 180 degrees or 360 degree rotation. Since the number of available controllers of the overhead crane system is smaller than its degrees of freedom, the overhead crane system is a typical nonlinear underactuated system. The key problem in the study of bridge crane system is how to quickly move the goods from the initial position to the target position, and at the same time limit the sw...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of the traditional bipolar pendulum two-dimensional bridge crane mechanism modeling method with complex and low precision, the present invention proposes a two-stage pendulum two-dimensional bridge crane RBF neural network modeling method based on IGBO. In order to adjust the parameters of the RBF neural network, the position output model, the first-level swing angle output model and the second-level swing angle output model of the bipolar pendulum bridge crane are established. The model built by this method can well reflect the bridge crane The nonlinear characteristics of the system

Images