A bus operation state division method based on a natural break method

Abstract

The application discloses a bus operation state classification method based on a natural break point method, and steps of the method comprise the following steps: S1, collecting bus travel speed data; S2, setting a bus operation state classification number k; S3, using the natural break point method to divide bus travel speed order statistics into k subsets; and S4, outputting critical speed between bus operation states. The application adopts a natural break point classification method to accurately classify bus operation states, and the output critical speed between bus operation states has strong stability for different natural days, so that the problem that bus operation states are difficult to be stably identified due to time heterogeneity of bus operation environments can be effectively solved.

Description

Technical Field

[0001] This invention relates to the field of urban public transportation systems, and specifically to a method for classifying bus operation states based on the natural discontinuity method. Background Technology

[0002] With the construction and development of urban public transport, improving the quality of public transport services has become a major issue facing the public transport system. Accurately evaluating the operational status of public transport and identifying weaknesses in the operation process are fundamental to improving the speed of public transport services, and effectively classifying the operational status of public transport is an important part of evaluating the operational status.

[0003] In the field of urban transportation, research on the classification of road traffic flow operation states is relatively more complete than that of public transportation systems, and current methods for classifying public transportation operation states mainly follow those for road traffic flow operation states. However, there are significant differences between bus traffic and road traffic flow: for example, buses need to stop at designated stops to serve passengers, some roads have dedicated bus lanes, and the technical performance (especially power performance) of buses differs considerably from that of cars, which constitute the main body of road traffic flow. Therefore, directly applying the conclusions of existing road traffic flow operation state classification research to the public transportation system will result in insufficient accuracy, thus necessitating further research on the classification of public transportation operation states. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method for classifying bus operation states based on the natural discontinuity method, which can overcome the influence of the time heterogeneity of the bus operation environment on the critical speed between bus operation states and accurately classify bus operation states.

[0005] The technical solution adopted by this invention to solve its technical problem is: to construct a method for classifying bus operation states based on the natural discontinuity method, including the following steps:

[0006] S1. Collect bus travel speed data;

[0007] S2. Set the number of bus operation status categories, k;

[0008] S3. Use the natural discontinuity method to divide the bus trip speed sequence statistics into k subsets;

[0009] S4 outputs the critical speed between bus operating states.

[0010] According to the above scheme, in step S1, the collected bus travel speed data is the ratio of the bus travel distance to the travel time within a fixed time interval, and the fixed time interval is set to 5 minutes or 10 minutes.

[0011] According to the above scheme, in step S2, the number of bus operation status categories k is set to 4. Each category corresponds to one bus operation status. The four bus operation statuses are defined as congested, slow-moving, smooth-moving, and ideal. In congested status, the bus speed is low and fluctuates greatly; in slow-moving status, the bus speed is relatively low and increases approximately steadily as traffic density decreases; in smooth-moving status, the bus speed is relatively high and increases rapidly as traffic density decreases; and in ideal status, the bus speed is high and increases sharply as traffic density decreases.

[0012] According to the above scheme, in step S3, the bus trip speed sequence statistics are a dataset composed of bus trip speed data arranged in ascending order.

[0013] According to the above scheme, in step S3, the natural discontinuity method is used to classify the sequential statistics of bus travel speed. The natural discontinuity method is based on the inherent natural grouping of the data, maximizing the similarity within each group and maximizing the dissimilarity between external groups, while identifying the classification interval, thus achieving the most appropriate grouping based on similarity values. This grouping method divides an ordered dataset into multiple classes, and for these classes, boundaries are set at locations where the differences in data values ​​are relatively large. The significance of the natural discontinuity method lies in the fact that for any sequential statistic, there are natural (not artificially set) turning points. These turning points are statistically significant and can divide the research objects into groups with similar properties, serving as good boundaries for classification. Classifying bus operating states requires finding the critical points between states, i.e., the boundary points of travel speed classification, which perfectly aligns with the principle of the natural discontinuity method. Using the natural discontinuity method to analyze bus travel speed data can find the natural boundaries of travel speed classification and define the critical thresholds of bus operating states.

[0014] Includes the following steps:

[0015] S301. Input the number of categories k = 4;

[0016] S302. Divide the bus trip speed sequence statistics into k subsets. For a dataset with N samples, we have: One approach is to divide it into k subsets;

[0017] S303. Calculate the sum of squared deviations of the mean of each subset, abbreviated as SDAM. j is a velocity subset from the k subsets, n is the sample size of that velocity subset, and v i For a velocity sample in this velocity subset, This is the mean of the subset of velocities;

[0018] S304. Calculate the sum of squared deviations from the class mean for all subsets, abbreviated as SDCM. m is One of the classification schemes;

[0019] S305. Find the minimum value of SDCM among all classification schemes. The classification result corresponding to this scheme is the same as the classification result output by the natural discontinuity method.

[0020] According to the above scheme, in step S4, the output critical speed of the bus operation state is the speed of the dividing point between bus operation states divided by the natural discontinuity method under a set number of categories.

[0021] According to the above scheme, in step S4, the number of critical speeds for the output bus operation status is equal to the number of status categories k minus 1. When the bus operation status is divided into 4 categories, there are 3 critical speeds.

[0022] According to the above scheme, the physical meaning of the critical speed of the bus operation status output in step S4 is as follows: the three critical speeds from smallest to largest represent the congestion speed, smooth traffic speed, and ideal speed, respectively.

[0023] The method for classifying bus operation states based on the natural discontinuity method of the present invention has the following beneficial effects:

[0024] 1. This invention uses the natural discontinuity method to classify ordered travel speed statistics. The classified speed intervals have monotonicity and a one-to-one mapping with each operating state, ensuring that each speed corresponds to only one operating state and that the same speed does not correspond to multiple states. Furthermore, the critical speed value is consistent with the speed distribution range of the perceived speed of public transportation in daily life.

[0025] 2. This invention overcomes the problem that the time heterogeneity of the bus operating environment makes it difficult to stably identify its operating state, and obtains a stable critical speed value for the bus operating state. Attached Figure Description

[0026] Figure 1 This is a flowchart of the bus operation state division method based on the natural discontinuity method of the present invention.

[0027] Figure 2 The present invention relates to a distribution map of bus travel speed based on 30 natural days in November 2019 in a certain city, using the natural discontinuity method to divide the travel speed of the city's operating status. Detailed Implementation

[0028] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0029] like Figure 1-2 As shown, the bus operation state division method based on the natural discontinuity method of the present invention includes the following steps:

[0030] S1. Collect bus travel speed data; the collected bus travel speed data is the ratio of bus travel distance to travel time within a fixed time interval, which is set to 5 minutes or 10 minutes.

[0031] S2. Set the number of bus operation status categories k; the number of categories k is set to 4, with each category corresponding to one bus operation status. The four bus operation statuses correspond to the following real-world meanings: congested state, slow-moving state, smooth-moving state, and ideal state. In a congested state, the bus speed is low and fluctuates greatly; in a slow-moving state, the bus speed is relatively low, and the speed increases approximately steadily as the traffic density decreases; in a smooth-moving state, the bus speed is relatively high, and the speed increases rapidly as the traffic density decreases; in an ideal state, the bus speed is high, and the speed increases sharply as the traffic density decreases.

[0032] S3. Use the natural discontinuity method to divide the ordinal statistics of bus travel speed into k subsets; classify the ordinal statistics of bus travel speed data using the natural discontinuity method. The natural discontinuity method is based on the inherent natural grouping in the data, maximizing the similarity within each group and maximizing the dissimilarity between external groups, and identifying the classification interval to achieve the most appropriate grouping based on similarity values. This grouping method divides an ordered dataset into multiple classes, and for these classes, sets their boundaries at locations where the differences in data values ​​are relatively large. The significance of the natural discontinuity method is that for any ordinal statistic, there are natural (not artificially set) turning points. These turning points are statistically significant and can divide the research objects into groups with similar properties, serving as good boundaries for classification. The classification of bus operation states requires finding the critical points between states, i.e., the boundary points of travel speed classification, which perfectly matches the principle of the natural discontinuity method. Using the natural discontinuity method to analyze bus travel speed data, the natural boundaries of travel speed classification can be found, and the critical thresholds of bus operation states can be determined.

[0033] The calculation steps are as follows:

[0034] S301. Input the number of categories k = 4;

[0035] S302. Divide the bus trip speed data, i.e., the dataset consisting of bus trip speed data arranged in ascending order, into k subsets. For a dataset with N samples, we have: One approach is to divide it into k subsets;

[0036] S303. Calculate the sum of squared deviations from the array mean (SDAM) for each subset. j is a velocity subset from the k subsets, n is the sample size of that velocity subset, and v i For a velocity sample in this velocity subset, This is the mean of the subset of velocities;

[0037] S304. Calculate the sum of deviations from the class mean (SDCM) for all subsets. m represents one of the classification schemes;

[0038] S305. Find the minimum value of SDCM among all classification schemes. The classification result corresponding to this scheme is the same as the classification result output by the natural discontinuity method.

[0039] S4 outputs the critical speed between bus operating states.

[0040] The output critical speeds for bus operation states are the boundary speeds between bus operation states determined by the natural discontinuity method under a set number of categories. The number of output critical speeds for bus operation states is equal to the number of state categories k minus 1. When bus operation states are divided into 4 categories, there are 3 critical speeds, whose physical meanings are as follows: the three critical speeds, from smallest to largest, represent congestion speed, smooth traffic speed, and ideal speed, respectively.

[0041] In a preferred embodiment of the present invention, based on the bus travel speed data of a certain city for 30 natural days in November 2019, the speed threshold for bus operation state division is calculated according to a bus operation state division method based on the natural discontinuity method proposed in the present invention.

[0042] The specific implementation steps are as follows:

[0043] S1. Collect bus travel speed data for 30 natural days in November 2019 in a certain city, calculate the bus travel speed at fixed intervals of 10 minutes, clean and remove some abnormal data with values ​​that are too large and beyond common sense, and arrange the remaining bus travel speed data from smallest to largest to obtain the bus travel speed sequence statistics.

[0044] S2. Divide the bus operation status according to the natural discontinuity method proposed in this invention (implemented with Python software):

[0045] S201. Input the number of categories k = 4;

[0046] S202. Divide the bus trip speed sequence statistics into 4 subsets;

[0047] S203. Calculate the sum of squared deviations from the array mean (SDAM) for each subset. j is a velocity subset from the four subsets, n is the sample size of that velocity subset, and v i For a velocity sample in this velocity subset, This is the mean of the subset of velocities;

[0048] S204. Calculate the sum of deviations from the class mean (SDCM) for all subsets. m represents one of the classification schemes;

[0049] S205. Find the minimum value of SDCM among all classification schemes. The classification result corresponding to this scheme is the classification result output by the natural discontinuity method.

[0050] S3. The speeds at the boundary points between bus operating states determined by the natural discontinuity method are correlated with bus congestion speed, smooth traffic speed, and ideal speed, respectively. The bus operating state classification results for a certain city over 30 natural days in November 2019 are obtained. The speed distribution of the four operating states over 30 days is as follows: Figure 2 As shown, it exhibits extremely high stability.

[0051] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A method for classifying bus operation states based on the natural discontinuity method, characterized in that, Includes the following steps: S1. Collect bus travel speed data; S2. Set the number of bus operation status categories k ; S3. Using the natural discontinuity method, the bus travel speed sequence statistics are divided into... k A subset; The bus trip speed sequence statistics are a dataset composed of bus trip speed data arranged in ascending order; The method of natural discontinuities is used to classify and calculate the sequential statistics of bus travel speeds, including the following steps: S301, Input the number of categories k =4; S302, Divide the bus travel speed sequence statistics into k A subset, for a given set N A dataset of samples, with This scheme divides it into k A subset; S303. Calculate the sum of the squared differences of the mean of each subset, which is called the sum of deviations from the array mean. SDAM, , j for k A velocity subset within a subset of the subsets. n This represents the sample size of the velocity subset. v i For a velocity sample in this velocity subset, This is the mean of the subset of velocities; S304. Calculate the sum of the squared deviations of all subsets, which is called the sum of deviations from the class mean. SDCM, , m for One of the classification schemes; S305, Search among all classification schemes SDCM The minimum value of this scheme corresponds to the classification result output by the natural discontinuity method. S4, outputs the critical speed between bus operating states; In step S4, the output critical speed of the bus operation state is the speed at the boundary point between bus operation states divided by the natural discontinuity method under a set number of categories.

2. The method for classifying bus operation states based on the natural discontinuity method according to claim 1, characterized in that, In step S1, the collected bus travel speed data is the ratio of the bus travel distance to the travel time within a fixed time interval, which is set to 5 minutes or 10 minutes.

3. The method for classifying bus operation states based on the natural discontinuity method according to claim 1, characterized in that, In step S2, the number of categories of bus operation status k The value is set to 4, and each category corresponds to a bus operation state. The four bus operation states are defined as congested state, slow-moving state, smooth-moving state and ideal state.

4. The method for classifying bus operation states based on the natural discontinuity method according to claim 1, characterized in that, In step S4, the number of critical speeds for the output bus operation state is equal to the number of state categories. k Subtract 1.

5. The bus operation state division method based on the natural discontinuity method according to claim 4, characterized in that, In step S4, the physical meaning of the output bus operation status critical speed is as follows: the three critical speeds from smallest to largest represent congestion speed, smooth traffic speed, and ideal speed, respectively.

Images