Nonlinear model predictive control method based on support vector machine for groove type reactor

Abstract

The invention discloses a nonlinear model predictive control method based on support vector machine for groove type reactor, which consists of support vector machine open loop identification circuit and closed-loop control circuit, the vector machine comprises support vector machine and its black box identifier, a controlled member groove type reactor, an internal prediction model, a feedback calibration and closed-loop output, a non-linear controller design, and a reference track, wherein the support vector machine identifies the non-parameter internal forecast model of the groove type reactor, obtains the closed-loop output through model output error for feedback calibration, and calculates the single step and multi step forecasting and analyzing control rule exerted to the system.

Description

technical field [0001] The invention relates to the field of industrial automatic control, in particular to a non-linear model predictive control method based on a support vector machine for a trough reactor. Background technique [0002] The trough reactor (CSTR) is a typical chemical process. Due to its inherent nonlinear characteristics, it is often used as a typical severe nonlinear object to test various control methods designed. For a schematic diagram of the principle of CSTR, see figure 1 . [0003] A single-stage irreversible exothermic reaction A→B (A represents the chemical species entering the reactor, B represents the product after the reaction) is carried out in the reactor, through the heat transfer fluid flowing through the cooling jacket (C represents the heat transfer fluid In, D represents the outflow of the heat transfer fluid) to control the characteristics of the entire chemical reaction. The whole process can be described by the following set of non...

AI Technical Summary

Problems solved by technology

The trough reactor (CSTR) process is inherently nonlinear, and the traditional model predictive control algorithms are all based on linear predictive models. The predictive model has large errors and the control effect is not very good. The severe nonlinearity makes these Predictive control technology can not achieve the desired effect. In addition, theoretically speaking, the study of nonlinear model predictive control technology has important practical significance. Complex chemical engineering equipment such as CSTR must use nonlinear model predictive control technology to achieve better control effect

However, the development of nonlinear model predictive control is far from satisfactory, mainly because of several difficulties in nonlinear predictive control, that is, the current urgent problem of nonlinear predictive control is: Difficult to obtain, models usually obtained through transfer function or state-space methods are difficult to use for control purposes

(2) The solution of nonlinear rolling optimization is difficult to obtain analytically. Generally, it can only be obtained through numerical optimization, and it cannot be guaranteed to be the global optimum.

Although the neural network can approach nonlinear objects infinitely, the geometric topology is difficult to determine, the learning speed is slow, it is easy to fall into local minimum and over-learning phenomenon, and the generalization ability is poor.

In addition, using numerical optimization methods such as gradient descent to obtain control laws is not only slow, but also not optimal.

Images