In order to comprehensively analyze the risk factors and accurately find the high risk factors related to accidents, an analysis model of risk factors of urban bus operation is proposed, in which the advantages of the structural analysis of the Fault Tree Analysis (FTA) and the correlation analysis of the Cumulative Logistic Regression (CLR) are combined. Firstly, based on the accident data in Northeast China, FTA is used to compile the urban bus operation fault tree. In the fault tree, 16 bus operation risk factors are classified, while the risk factors are sorted and compared from three aspects: structural importance, probability importance, and critical importance. And then, the 11 higher risk factors are selected according to the discriminant principle. Secondly, bus operation accidents are divided into fatal accidents, injury accidents, and major economic loss accidents. The CLR model is used to fit the much higher risk factors that lead to urban bus operation accidents from above 11 higher risk factors. Finally, the scientific rationality and applicability of the model are verified, through the goodness of fit test and the comparison test with the actual probability of occurrence.

Taking truck drivers’ braking patterns as the research objects, this study used a large amount of truck running data. A recognition method of truck drivers’ braking patterns was proposed to determine the distribution of braking patterns during the operation of trucks. First, the segmented data of braking behaviors were collected in order to extract 25 characteristic parameters. Additionally, seven main correlation factors were obtained by dimensionality reduction. The FCM clustering algorithm and CH scores were used to identify nine categories of truck drivers’ braking behaviors. Then the LDA2vec model was used to identify the distribution of different braking behavior words in braking patterns, and three categories of truck drivers’ braking patterns were identified. The test results showed that the accuracy of the truck drivers’ braking pattern recognition model based on LDA2vec was higher than 85%, and braking patterns of drivers in the daily operation process could be mined from vehicle operation data. Furthermore, through the monitoring and pre-warning of the braking patterns and targeted training of drivers, traffic accidents could be avoided. At the same time, this paper’s results can be used to protect human life and health and reduce environmental pollution caused by traffic congestion or traffic accidents.

No abstract