A Convolutional Neural Network-Based Driving Cycle Prediction Method for Plug-in Hybrid Electric Vehicles With Bus Route

Driving cycle prediction plays a key role in energy management strategy (EMS) for hybrid electric vehicles (HEVs). This paper studies a driving cycle prediction method based on convolutional neural network (CNN). Firstly, the k-shape clustering method is used to group the driving cycle data into six different types. Moreover, this method is compared with the k-means algorithm which is often used for clustering driving cycles. Secondly, CNN is adopted to predict the different types of the driving cycles based on the results of k-Shape clustering. Some basic features are selected to construct the input of the networks with no assistance of human experience. In the process of training neural networks, some high-level features which can describe the information of a driving cycle more accurately are extracted, and the deep neural networks are built, which are different from traditional experience-based driving cycle prediction methods. And then, the better performance of the proposed method is illustrated by making a comparison with the traditional machine learning method. Finally, an adaptive energy management strategy for plug-in hybrid electric buses (PHEB) based on deep learning is given, and simulation results prove the effectiveness of the proposed method.

[1]  Fengchun Sun,et al.  Investigating adaptive-ECMS with velocity forecast ability for hybrid electric vehicles , 2017 .

[2]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[3]  Abbas Fotouhi,et al.  Tehran driving cycle development using the k-means clustering method , 2013 .

[4]  Petru Palcu,et al.  Whole-Day Driving Prediction Control Strategy: Analysis on Real-World Drive Cycles , 2018, IEEE Transactions on Transportation Electrification.

[5]  Ying Yang,et al.  Driving Cycle Development for Electric Vehicle Application using Principal Component Analysis and K-means Cluster: With the Case of Shenyang, China , 2017 .

[6]  Xin Wang,et al.  Improving failures prediction by exploring weighted shape‐based time‐series clustering , 2018, Qual. Reliab. Eng. Int..

[7]  Luis Gravano,et al.  k-Shape: Efficient and Accurate Clustering of Time Series , 2015, SIGMOD Conference.

[8]  Chengliang Yin,et al.  Design of an energy management strategy for parallel hybrid electric vehicles using a logic threshold and instantaneous optimization method , 2009 .

[9]  G. Glatting,et al.  Comparison of five cluster validity indices performance in brain [18F]FET‐PET image segmentation using k‐means , 2017, Medical physics.

[10]  Datong Qin,et al.  A Dynamic Control Strategy for Hybrid Electric Vehicles Based on Parameter Optimization for Multiple Driving Cycles and Driving Pattern Recognition , 2017 .

[11]  I Schifter,et al.  A Driving Cycle for Vehicle Emissions Estimation in the Metropolitan Area of Mexico City , 2005, Environmental technology.

[12]  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.

[13]  Chun Wang,et al.  An on-line predictive energy management strategy for plug-in hybrid electric vehicles to counter the uncertain prediction of the driving cycle , 2017 .

[14]  Simon Fong,et al.  Forecasting Energy Consumption from Smart Home Sensor Network by Deep Learning , 2017 .

[15]  Jianqiu Li,et al.  The influence of driving cycle characteristics on the integrated optimization of hybrid energy storage system for electric city buses , 2017 .

[16]  Richard Millham,et al.  Elephant search algorithm applied to data clustering , 2018, Soft Comput..

[17]  Nilanjan Dey,et al.  Predicting unusual energy consumption events from smart home sensor network by data stream mining with misclassified recall , 2018, J. Ambient Intell. Humaniz. Comput..

[18]  Edwin Tazelaar,et al.  Driving cycle characterization and generation, for design and control of fuel cell buses , 2009 .

[19]  Gianfranco Chicco,et al.  Automated load pattern learning and anomaly detection for enhancing energy management in smart buildings , 2018, Energy.

[20]  Chao Yang,et al.  Multimode Energy Management for Plug-In Hybrid Electric Buses Based on Driving Cycles Prediction , 2016, IEEE Transactions on Intelligent Transportation Systems.

[21]  Guolin Wang,et al.  Building Tianjin driving cycle based on linear discriminant analysis , 2017 .

[22]  Zheng Chen,et al.  Multi-objective parameter optimization for a single-shaft series-parallel plug-in hybrid electric bus using genetic algorithm , 2016, Science China Technological Sciences.

[23]  Eamonn J. Keogh,et al.  Clustering Time Series Using Unsupervised-Shapelets , 2012, 2012 IEEE 12th International Conference on Data Mining.

[24]  Thorsten Benter,et al.  Impact of driving style and road grade on gaseous exhaust emissions of passenger vehicles measured by a Portable Emission Measurement System (PEMS) , 2017 .

[25]  Eva Ericsson,et al.  Independent driving pattern factors and their influence on fuel-use and exhaust emission factors , 2001 .

[26]  Yahui Zhang,et al.  A hybrid dynamic programming-rule based algorithm for real-time energy optimization of plug-in hybrid electric bus , 2014 .

[27]  Guillermo R. Bossio,et al.  Optimization of power management in an hybrid electric vehicle using dynamic programming , 2006, Math. Comput. Simul..

[28]  Seung-Ki Sul,et al.  Fuzzy-logic-based torque control strategy for parallel-type hybrid electric vehicle , 1998, IEEE Trans. Ind. Electron..

[29]  Geeta Sikka,et al.  Recent Techniques of Clustering of Time Series Data: A Survey , 2012 .

[30]  Bo Gao,et al.  Energy Management in Plug-in Hybrid Electric Vehicles: Recent Progress and a Connected Vehicles Perspective , 2017, IEEE Transactions on Vehicular Technology.

[31]  Hong Wang,et al.  A novel energy management for hybrid off-road vehicles without future driving cycles as a priori , 2017 .

[32]  Swarnajyoti Patra,et al.  A fast automatic optimal threshold selection technique for image segmentation , 2017, Signal Image Video Process..

[33]  Chandra Sekhar,et al.  k-Shape clustering algorithm for building energy usage patterns analysis and forecasting model accuracy improvement , 2017 .