Ensemble learning-based parameter self-setting method of SISO tight format model-free controller

Abstract

The invention discloses an ensemble learning-based parameter self-setting method of an SISO tight format model-free controller. An ensemble learning algorithm comprises three individual algorithms, namely, a PSO algorithm, a BP neural network and a recurrent neural network. The system error is used as the input of the ensemble learning algorithm; online setting is carried out on the parameters ofthe SISO tight format model-free controller by the three individual algorithms, and three groups of temporary setting parameters are output; the results are input into the controller to calculate thecontrol input of a controlled object; and calculation is performed to obtain three groups of temporary system errors, the weight ratios of the individual algorithms are calculated by using a softmax function; and weighted summation is performed on the weight ratios and the temporary setting parameters, so that final to-be-set parameters of the SISO tight format model-free controller can be obtained, and parameter self-setting is realized. According to the ensemble learning-based parameter self-setting method of an SISO tight format model-free controller, the advantages of the different individual algorithms are combined, the algorithm generalization is enhanced, the online setting problem of controller parameters is solved, and a good control effect is achieved on an SISO system.

Description

technical field [0001] The invention belongs to the field of automatic control, and in particular relates to a parameter self-tuning method of an SISO compact format model-free controller based on integrated learning. Background technique [0002] SISO (Single Input and Single Output) systems are widely used in reactors, precision Distillation towers, machines, equipment, devices, production lines, workshops, factories and other controlled objects. With the continuous improvement of the level of science and technology, industrial devices are becoming larger and more complex, making the production process more and more strongly nonlinear and time-varying. It is often difficult to achieve the ideal control effect for complex controlled objects with linear and time-varying characteristics. Model-free controller is a new type of data-driven control model, which has a good control effect on unknown nonlinear time-varying systems, so it has a good application prospect. [0003]...

AI Technical Summary

Problems solved by technology

[0008] The object of the present invention is to provide a parameter self-tuning method based on ensemble learning for a SISO compact format model-free controller, so as to solve the parameter online self-tuning problem of the SISO compact format model-free controller

Images