The invention relates to the technical field of engines, in particular to a dynamic adjusting method for engine
exhaust gas recirculation control, which comprises the following steps: S1, collecting multi-
source data in real time; s2, data preprocessing and
feature extraction; s3, constructing an EGR dynamic model; s4, performing
intelligent decision making and hierarchical regulation and control; s5, evaluating and feeding back the regulation and
control effect in real time; through multi-
source data fusion and an intelligent
algorithm,
millisecond response and dynamic self-adaptive adjustment of the EGR rate are achieved, the problem of
lag of a traditional control strategy is solved, and the response speed and the control precision of the
system are improved; according to the hierarchical regulation and control strategy based on
reinforcement learning,
NOx emission reduction,
power performance maintenance and fuel economy improvement are considered, and performance imbalance caused by single target optimization is avoided;
environmental factor data is introduced to participate in model calculation, so that the EGR
system can keep the optimal working state under the conditions of different temperatures, altitudes and the like, and the technical application range is widened.