Remote self-learning of driving cycle for electric vehicle demonstrating area

The analysis of statistic data collected from real-time driving cycle of electric vehicle in demonstrating area is providing evident that some driving cycle conditions have significant influence on vehicle performance. In addition, vehicle performance results derived from driving cycles data show relationships that help to optimize control strategy. Statistical acceleration and deceleration distributions are developed as a function of speed and road type [1].This paper presents a remote driving cycle self-learning system based on data stream collected from in-vehicle device using general packer radio service (GPRS). The remote driving cycle self-learning system adopts an in-vehicle device to acquire driving cycle data of electric vehicle through CAN bus and communicate wirelessly with data server by GPRS network and INTERNET. All this data can be stored in data server and be analyzed to classify as different driving cycle using SOM network. According to analyzed result, corresponding driving control strategy [2] is switched to optimize electric vehicle performance. The study shows that the remote driving cycle self-learning system is effective method to define and characterize driving cycle in electric vehicle in demonstrating area. In the sample application, the remote driving cycle self-learning system plays an importance role in optimizing the control and energy management strategy of electric vehicle.