Parameter self-tuning method of MISO (Multiple Input and Single Output) partial format model-free controller based on partial derivative information

Abstract

The invention discloses a parameter self-tuning method of an MISO (Multiple Input and Single Output) partial format model-free controller based on partial derivative information, which comprises the steps that a partial derivative information set is used to serve as input of a BP neural network, the BP neural network performs forward calculation and outputs parameters to be tuned such as a penaltyfactor and a step factor of the MISO partial format model-free controller through an output layer, a control input vector in allusion to a controlled object is calculated by adopting a control algorithm of the MISO partial format model-free controller, the minimization of the value of a system error function is taken as an objective, a gradient descent method is adopted to perform system error back propagation calculation respectively in allusion to a gradient information set of each parameter to be tuned by combining the control input, a hidden layer weight coefficient and an output layer weight coefficient of the BP neural network are updated in real time online, and parameter self-tuning of the controller based on the partial derivative information is realized. The parameter self-tuning method provided by the invention of the MISO partial format model-free controller based on the partial derivative information can effectively overcome a problem of online tuning for controller parameters and has a good control effect for the MISO system.

Description

technical field [0001] The invention belongs to the field of automatic control, in particular to a parameter self-tuning method of a MISO partial format model-free controller based on partial derivative information. Background technique [0002] The control problem of MISO (Multiple Input and Single Output) system has always been one of the major challenges in the field of automation control. [0003] Existing implementations of MISO controllers include MISO partial scheme model-free controllers. MISO partial format model-free controller is a new type of data-driven control method, which does not rely on any mathematical model information of the controlled object, but only relies on the input and output data measured by the MISO controlled object in real time for controller analysis and design, and The realization is simple, the calculation burden is small and the robustness is strong, and the unknown nonlinear time-varying MISO system can also be well controlled, and has a...

AI Technical Summary

Problems solved by technology

[0006] However, the MISO partial scheme model-free controller needs to rely on empirical knowledge to pre-set the penalty factor λ and the step size factor ρ before it is actually put into use. 1 ,…,ρ L and other parameters, the penalty factor λ and step size factor ρ have not yet been realized in the actual commissioning process 1 ,…,ρ L Online self-tuning of other parameters

The lack of effective parameter tuning means not only makes the debugging process of the MISO partial format model-free controller time-consuming and laborious, but also sometimes seriously affects the control effect of the MISO partial format model-free controller, restricting the performance of the MISO partial format model-free controller. Promote application

Images