Drive Cycle Identification and Energy Demand Estimation for Refuse-Collecting Vehicles

Drive cycle identification and future energy demand prediction are advantageous when developing hybrid propulsion systems. They are applicable to vehicles that are driven along the same route every day, such as busses, refuse-collecting vehicles (RCVs), or delivery vehicles. Drive cycle identification can be used to identify what power transients can be expected to prepare the power train to operate under these conditions. If the energy management algorithm of a hybrid vehicle can account for future energy demand, then it can be arranged in such a way that the non-fossil-fuel energy sources are fully depleted at the end of the drive cycle. Given that RCVs always drive in similar drive cycles, a drive cycle has been modeled and its main characteristics parameterized. The model is separated into different drive cycles that are related to different power consumption modes. In this paper, a new method to identify drive cycles and the energy left to finish a route is proposed. The drive cycle identification is based on artificial intelligence algorithms, which have been trained and tested with real data with an average efficiency in drive cycle identification of over 90%. The energy necessary to finish the route is based on vehicle energy models and statistical analysis. This method can be used in the daily management of fleet vehicles to replace fossil fuel by electric energy, as is demonstrated in the proposed examples.

[1]  Jihong Wang,et al.  Development of a Novel Sensorless Longitudinal Road Gradient Estimation Method Based on Vehicle CAN Bus Data , 2007, IEEE/ASME Transactions on Mechatronics.

[2]  Manuel Moreno-Eguilaz,et al.  Experimentally Compared Fuel Consumption Modelling of Refuse Collecting Vehicles for Energy Optimization Purposes , 2014 .

[3]  Bo Egardt,et al.  Assessing the potential of predictive control for hybrid vehicle powertrains using stochastic dynamic programming , 2005 .

[4]  Oliver Sawodny,et al.  Drive Cycle Prediction and Energy Management Optimization for Hybrid Hydraulic Vehicles , 2013, IEEE Transactions on Vehicular Technology.

[5]  Reza Langari,et al.  Intelligent energy management agent for a parallel hybrid vehicle-part I: system architecture and design of the driving situation identification process , 2005, IEEE Transactions on Vehicular Technology.

[6]  Judith Gurney BP Statistical Review of World Energy , 1985 .

[7]  Yi Lu Murphey,et al.  Intelligent Vehicle Power Control Based on Machine Learning of Optimal Control Parameters and Prediction of Road Type and Traffic Congestion , 2009, IEEE Transactions on Vehicular Technology.

[8]  Daniela Chrenko,et al.  Predictive Energy Management for Hybrid Vehicles Based on Driving Cycle Recognition , 2017, 2017 IEEE Vehicle Power and Propulsion Conference (VPPC).

[9]  D. J. Purdy,et al.  Road vehicle state estimation using low-cost GPS/INS , 2011 .

[10]  Reza Langari,et al.  Intelligent energy management agent for a parallel hybrid vehicle-part II: torque distribution, charge sustenance strategies, and performance results , 2005, IEEE Transactions on Vehicular Technology.

[11]  John Krumm,et al.  Route Prediction from Trip Observations , 2008 .