Research On Energy Management Strategy Based On Rule Learning For Fuel Cell Hybrid Electric Vehicles

Hydrogen is used as the main power source to drive the fuel cell hybrid electric vehicles with the advantages of zero emissions and zero noise,which makes this vehicle become one of the useful ways to tackle the problem of global warming and oil depletion.A useful energy management strategy need to be designed to reasonably distribute the output power during the driving due to the two power sources consisting of hydrogen fuel cell and lithium battery.Rule-based energy management strategies have the abilities of strong robustness and online application,but heavily depend on engineering experience,which makes they are sensitive to the driving cycle and have poor adaptability.Optimized-based energy management strategies have outstanding optimization ability and can adapt to all driving cycles,but these strategies have the disadvantages of huge calculation and requiring accurate mathematical models.Therefore,the rule learningbased strategy that combines both the advantages have become the research hot in recent years.In this paper,an energy management strategy based on rule learning method is proposed for fuel cell hybrid electric vehicles,and the main research contents are as follows:(1)The longitudinal dynamic model is built according to the analysis of fuel cell hybrid electric vehicle.The mathematical models of fuel cell and lithium-ion are established by the output power characteristics.Based on the study of the factors affecting the degradation of the power system,the power system decline models are established,which lays the foundation for solving energy management strategies.(2)The objective function of the fuel cell hybrid electric vehicle based on Pontryagin’s minimum principle is established.The hydrogen consumption conditions consisting of without constraint of power system,restricting charge and discharge rate of the lithium battery,and constraining the change rate of the output power of fuel cell are respectively analyzed according to the global optimization strategy based on Pontryagin’s minimum principle,which lays the foundation for solving offline data sets with energy management strategies based on rule learning.From the simulation results of MATLAB platform,the power system can achieve theoretical highest efficiency under the condition of without power sources constraints.Restricting the output of the fuel cell or lithium battery will reduce the power system efficiency and increase the hydrogen consumption during the trip in a certain extent.(3)According to the rule learning theory,a rule learning based energy management strategy is proposed to achieve preferable energy consumption economy for fuel cell hybrid electric vehicles.Firstly,the optimal control sequence of fuel cell power and the state of charge trajectory of lithium-ion battery pack during driving are derived offline by the Pontryagin’s minimum principle.Next,the k-means algorithm is employed to hierarchically cluster the optimal solution into the simplified data set.Then,the repeated incremental pruning to produce error reduction algorithm,as a propositional rule learning strategy,is leveraged to learn and classify the underlying rules.Finally,the multiple linear regression algorithm is applied to fit the abstracted parameters of generated rule set.Simulation results highlight that the proposed strategy can achieve the similar savings of energy consumption economy,solved by Pontryagin’s minimum principle,with less calculation intensity and without dependence on prior driving conditions,thereby manifesting the feasibility of online application.(4)Considering the inevitable decline of power systems and developing a real-time hybrid vehicle controller with practical value and improve fuel efficiency,a multiobjective optimization-oriented energy management strategy is investigated for fuel cell hybrid vehicles on the basis of rule learning.The degradation of fuel cells and lithiumion batteries are considered as the objective function and translated into the equivalent hydrogen consumption.The optimal fuel cell power sequence and state of charge trajectory,considered as the energy management input,are solved offline via the Pontryagin’s minimum principle.The k-means algorithm is employed to hierarchically cluster the optimal data set for preparation of rules extraction,and then the rules are excavated by the improved repeated incremental pruning to production error reduction algorithm.Finally,the multi-nonlinear regression algorithm is utilized to fit these rules.The simulation results highlight that the proposed rule learning-based energy management strategy can effectively save hydrogen consumption and prolong fuel cell life with real-time application potential.