Shu Wang

This paper develops a methodology for constructing a representative electric vehicle (EV) urban driving cycle as a basis for studying the differences in estimated energy consumption, taking Xi’an as an example. The test route is designed in accordance with the overall topological structure of the urban roads in the study region and the results of a traffic flow survey. Wavelet decomposition and reconstruction are utilized to preprocess the original data. Principal component analysis (PCA) is used to reduce the number of the kinetic parameters. The fuzzy C-means (FCM) clustering algorithm is used to cluster the driving segments. A representative EV urban driving cycle is constructed in accordance with the time proportions of three classes of driving segments and the correlation coefficients of the characteristic parameters. Finally, the differences in energy consumption estimates obtained using the constructed Xi’an EV urban driving cycle (XA-EV-UDC) and the international driving cycles are studied. The comparison shows that when international driving cycles are used to estimate the energy consumption and driving range of EVs, large relative errors will result, with energy consumption errors of 9.65 to 21.17% and driving range errors of 20.10 to 38.14%. Therefore, to accurately estimate energy consumption and driving range of EVs under real-world driving conditions, representative EV driving cycles for each typical city and region should be constructed.

The accuracy and real time are crucial in turning intention recognition. Therefore, a hybrid model of Gaussian mixture hidden Markov and generalized growing and pruning algorithm for radial basis function neural network is constructed to recognize driver turning intention real timely. The feature parameters of the driving intention identification are determined using principal component analysis. The turning initial stage is selected for identifying turning intention, thus improving the real time of hybrid model. Using support vector machine model and Gaussian mixture hidden Markov model and Gaussian mixture hidden Markov model/generalized growing and pruning algorithm for radial basis function hybrid model, driver turning intention is identified in normal turning and sharp turning. The results show that Gaussian mixture hidden Markov model/generalized growing and pruning algorithm for radial basis function hybrid model identifies turning intention accurately and more efficiently. The accuracy is as high as 96.88% in the normal turning, which is 24.53% higher than that obtained using the Gaussian mixture hidden Markov model and 25.88% higher than that obtained using the support vector machine. The recognition in the turning initial stage is 1.8 s quicker than that in the turning keeping stage. The identification accuracy and real time of hybrid model are substantially better than those of the Gaussian mixture hidden Markov model and support vector machine, especially in the normal turning. When applied in control systems, this method can improve the safety and comfort of vehicle operation and reduce the burden of drivers.