Intelligent automobile decoupling prediction controller based on model dynamic reconstruction and control method

Abstract

The invention discloses an intelligent automobile decoupling prediction controller based on model dynamic reconstruction and a control method. Firstly, a three-degree-of-freedom coupling nonlinear original model of an intelligent automobile is established on the basis of intelligently sensing the external environment and self parameters of the vehicle, two right inverse models of the intelligent automobile are constructed, the two right inverse models alternately learn and evolve, one right inverse model which does not execute the learning evolution function is placed on the left side of the original model, dynamic reconstruction is carried out on the intelligent automobile model so as to realize dynamic decoupling and simplified control on the model, then a model prediction controller isrespectively designed according to each sub-model in a new model obtained by reconstruction and control requirement characteristics, the decoupling prediction control of the intelligent automobile based on model dynamic reconstruction is realized, and the control performance and the intelligent level of the intelligent automobile are improved. According to the invention, the dynamic inverse modeland the model prediction control method are used in combination, the reconstructed normalized new model is used for reasonably designing the model prediction controller, and the control performance ofthe intelligent automobile is improved.

Description

technical field [0001] The invention relates to the field of smart car control, in particular to a decoupling predictive controller for smart cars based on model dynamic reconstruction and a control method thereof. Background technique [0002] Smart cars are high-tech products based on environmental perception technology, smart driving technology, wireless communication technology and computer technology. The process of transformation and upgrading of the automobile industry will be the process of gradually realizing intelligent cars. Automobiles under intelligent operation will take safety, environmental protection, energy saving, and comfort as comprehensive control goals, and jointly build an efficient and orderly transportation network. [0003] Modern society has higher and higher requirements for the quality of life, and it is hoped that smart cars can have excellent comprehensive control performance. The dynamic model of the vehicle is a strongly coupled nonlinear t...

AI Technical Summary

Problems solved by technology

The traditional control algorithm has not been well coordinated to solve the parameter change, variable coupling, control time delay and nonlinear problems in the control process for the time being. Simplified linear models are often used in simulation or testing to avoid or ignore parameter changes in the actual process. , control time lag and variable coupling characteristics, resulting in the control parameters that work well at low and medium vehicle speeds, the control effect is often not ideal at high vehicle speeds, and the control parameters that are suitable for serpentine paths may not be suitable for double shift lines. Difficult to take into account indicators such as quick response characteristics and occupant safety and comfort

Images