Mixed gas deviation self-learning method and system and readable storage medium

Abstract

The invention provides a mixed gas deviation self-learning method and system and a readable storage medium. The method comprises the steps that firstly, a domain controller obtains model deviation of a pre-control model in an engine controller and working condition data corresponding to the model deviation; then, the domain controller conducts alternative region division according to the model deviation and the working condition data, alternative regions are generated, and self-learning parameters corresponding to the alternative regions are obtained; the domain controller sends the self-learning parameters to the engine controller; and the engine controller updates a corresponding self-learning algorithm in the engine controller by using the self-learning parameters and conducts mixed gas deviation self-learning based on the self-learning algorithm. Therefore, the newly divided alternative region can be used as the self-learning region, so that updating of the self-learning region can be realized, the mixed gas deviation self-learning dispersion difference can be updated, and improvement of the air-fuel ratio control precision of the mixed gas is facilitated.

Description

technical field [0001] The invention relates to the technical field of automobiles, in particular to a method, system and readable storage medium for self-learning of mixture gas deviation. Background technique [0002] With the continuous tightening of emission and fuel consumption regulations, the requirements for vehicle emissions are becoming more and more stringent. For a vehicle's engine, the pre-control deviation of the air-fuel ratio (that is, the mass ratio between air and fuel in the mixture) has a significant impact on the accuracy of the engine's air-fuel ratio control, and then affects the emission characteristics of the vehicle's entire life cycle. In the powertrain control, the local linear model tree (lolimot) algorithm can usually be used for self-learning of the mixture deviation to improve the emission characteristics of the vehicle and improve the emission consistency. [0003] However, the lolimot algorithm currently set in the engine controller (Electr...

AI Technical Summary

Problems solved by technology

[0003] However, the lolimot algorithm currently installed in the engine controller (Electronic Control Unit, ECU) of the vehicle is based on the self-learning area demarcated offline. The self-learning area is only obtained by measuring and calculating a few experimental vehicles, and It cannot completely replace the characteristics of individual vehicles on the market; moreover, traditional engine controllers are limited by storage resources and computing resources, so they can only self-learn the self-learning parameters in the self-learning interval after dividing the self-learning interval. The self-learning of the self-learning interval division cannot be carried out, which affects the control accuracy of the air-fuel ratio of the vehicle mixture

Images