An Adaptive Algorithm for Hybrid Electric Vehicle Energy Management Based on Driving Pattern Recognition

Abstract

In this paper we present a novel adaptation method for the Adaptive Equivalent fuel Consumption Minimization Strategy (A-ECMS). The approach is based on Driving Pattern Recognition (DPR). The Equivalent (fuel) Consumption Minimization Strategy (ECMS) method provides real-time suboptimal energy management decisions by minimizing the "equivalent" fuel consumption of a hybrid-electric vehicle. The equivalent fuel consumption is a combination of the actual fuel consumption and electrical energy use, and an equivalence factor is used to convert electrical power used into an equivalent chemical fuel quantity. In this research, a driving pattern recognition method is used to obtain better estimation of the equivalence factor under different driving conditions. A time window of past driving conditions is analyzed periodically and recognized as one of the Representative Driving Patterns (RDPs). Periodically updating the control parameter according to the driving conditions yields more precise estimation of the equivalent fuel consumption cost, thus providing better fuel economy. Besides minimizing the instantaneous equivalent fuel consumption, the battery State of Charge (SOC) management is also maintained by using a PI controller to keep the SOC around a nominal value. The primary improvement of the proposed A-ECMS over other algorithms with similar objectives is that it does not require the knowledge of future driving cycles and has a low computational burden. Results obtained in this research show that the driving conditions can be successfully recognized and good performance can be achieved in various driving conditions while sustaining battery SOC within desired limits.