Bus Driving Cycle Construct Based on Principal Component Analysis for Lanzhou City

Abstract

The construction of city bus driving cycle is the key to improve traffic efficiency and transportation capacity. In this paper, the data acquisition parameter model is established by taking the Lanzhou city as an example. The data collected from the vehicle recorder are divided into several kinematics sequences. The eigenvalues of these sequences are investigated by principal component analysis and cluster analysis with SPSS tool. Based on the correlation coefficient of collected data from five typical bus lines for more than one month, three representative kinematic sequences are selected to construct the bus driving cycle for Lanzhou city. Experiments show that: 1) The bus driving cycle for Lanzhou city has the characteristics of less uniform time, low average speed and frequent acceleration and deceleration; 2) There exist large differences in bus driving characteristics between the European ECE15 driving cycle, commonly used in the China's urban roads and that of Lanzhou city.

A Neural Network and Principal Component Analysis Approach to Develop a Real-Time Driving Cycle in an Urban Environment: The Case of Addis Ababa, Ethiopia

“…In this approach, a machine classification learner was applied to classify trips, and the NN clustering method was found to provide better performance accuracy than the other approaches. However, [6,7,10,13] applied the k-means clustering algorithm to the principal component score to classify the driving sequences into different clusters. The DC duration was not determined on the basis of previous studies; rather, the methodology proposed in this study provided the DC duration that best matched the data collected in real time.…”

“…During DC development, the classification method is applied to kinematic segments to cluster them into heterogonous classes based on statistical properties. Several researchers have applied principal component analysis (PCA) using the k-means clustering method [5,6,[9][10][11]. The authors of [12] applied PCA to reduce fifteen characteristic parameters to three factor scores, Liu et al (2018) applied PCA to reduce fifteen kinematic characteristics values to four principal components based on the eigenvalue [10], and Zhou et al (2017) reduced eight driving parameters to three principal components using PCA [13].…”

“…Several researchers have applied principal component analysis (PCA) using the k-means clustering method [5,6,[9][10][11]. The authors of [12] applied PCA to reduce fifteen characteristic parameters to three factor scores, Liu et al (2018) applied PCA to reduce fifteen kinematic characteristics values to four principal components based on the eigenvalue [10], and Zhou et al (2017) reduced eight driving parameters to three principal components using PCA [13]. However, there has been no evaluation of which clustering method offers the best performance with PCA.…”