Real-time global optimization intelligent control system and method for fuel cell bus

Abstract

The invention discloses a real-time global optimization intelligent control system and method for a fuel cell bus, and the method comprises the steps that a vehicle driving communication unit downloads prediction model parameters to a fuel cell vehicle controller when the fuel cell bus is at a driving starting point; a battery management system and a driving motor real-time power calculation module respectively obtain the real-time SOC and the real-time power of the battery pack; an optimal SOC prediction model module obtains an optimal SOC reference trajectory prediction value of a next working condition segment, the MPC prediction control module obtains a power reference value, and all the parameters are input into the fuel cell control unit to judge the working state of the fuel cell. In the driving process, the bus continuously uploads fragmented working condition information through the bus driving communication unit, and after each travel is completed, the cloud analysis workstation performs incremental learning training through the working condition information uploaded in real time to update the optimal SOC prediction model. According to the invention, the fuel cell bus canbe accurately and flexibly controlled in real time, and the fuel consumption is reduced.

Description

technical field [0001] The invention belongs to the technical field of energy management of new energy vehicles, and in particular relates to a real-time global optimization intelligent control system and method for a fuel cell bus. Background technique [0002] As the number of automobiles in my country continues to increase, the energy and environmental pressures on the automobile industry are also increasing. Due to the increasing dependence on non-renewable energy sources such as oil year by year, the implementation of energy substitution is imminent, so hydrogen energy has entered the public eye because of its high calorific value, abundant reserves, and excellent environmental friendliness; from the perspective of hydrogen energy application, fuel Battery vehicles have become one of the key research directions. According to statistics, more than 40 car companies in the Chinese market have participated in the production of hydrogen fuel cell vehicles. On the other hand...

AI Technical Summary

Problems solved by technology

[0004] The prior art involves a method for energy management of plug-in hybrid electric vehicles based on deep reinforcement learning. The invention has the following disadvantages: 1) It does not involve modifying the rules involved due to data changes, and deep reinforcement learning is only the case of using massive data Dimensionality reduction and fusion processing are performed, and a system needs to be retrained when new data is added; 2) The dynamic step-by-step update algorithm is not involved, and the data in the database is dynamically changing. When faced with new data, the learning method should be able to cope with The trained system makes some changes to learn the knowledge contained in the new data

The prior art also relates to an energy management method for plug-in hybrid electric vehicles based on intelligent prediction. The invention has the following disadvantages: 1) The use of deep learning for model prediction has a great impact on the timeliness and accuracy of database search , so the prediction range can only reach short-term; 2) When there is a large difference from the target driving route, the model needs to be rebuilt

Images