Multi-model control method based on self learning

Abstract

The invention discloses a multi-model control method based on self learning. The multi-model control method comprises the steps that (1) a model base is built, and the model base consists of a group of local models of a non-linear model; (2) a group of controllers are built, and a group of local controllers are designed according to the local model in the model base; (3) the performance evaluation is executed: output errors and differences between system output y and model output yi are observed, and a performance feedback or value function is calculated or sent to an API (application program interface) module on the basis of signals; and (4) a similar policy iteration algorithm is executed: performance feedback signals are observed, error signals between reference output and system output are received, the signals are used as the Markov decision process states, and meanwhile, the states are fed back to become return signals for enhancing the leaning. The multi-model control method has the advantages that the principle is simple, the application range is wide, the reliability is high, the general performance and the convergence of the control can be ensured, and the like.

Description

technical field [0001] The present invention mainly relates to the field of control of complex nonlinear systems, in particular a multi-model control method based on self-learning, which uses reinforcement learning and approximate dynamic programming ideas to realize the optimal conversion between multiple controllers, so The invention belongs to a multi-model self-learning conversion control method. Background technique [0002] With the development of modern industry and technology, the complexity of engineering system devices is showing a steady upward trend. More importantly, this trend largely emphasizes the need for a method: practical methods that can help engineers better understand and interpret complex models and complete control tasks. [0003] For decades, although there have been many studies on solving complex nonlinear models, the advanced models and advanced control methods proposed in these studies have not been widely used to solve practical problems. The...

AI Technical Summary

Problems solved by technology

Although this method can improve the transient performance of the system to a certain extent, when there are unknown disturbances, the system feedback lacks robustness. Of course, this is also a common problem of the adaptive method.

Images