An evaluation method for the traffic connection plan of intercity railway stations based on passenger flow impact

Abstract

The present invention provides an evaluation method for the traffic connection plan of intercity railway stations based on passenger flow influence, and the specific steps are as follows: S1: Establish an index model for the influencing factors of passenger flow at intercity railway stations; S2: Conduct principal component analysis on continuous variables; S21: Construct a sample data matrix and standardize it; S22: Calculate the sample covariance matrix; S23: Calculate the eigenvalues and eigenvectors of the covariance matrix; S24: Calculate the principal component contribution rate and the cumulative contribution rate; S25: Write out the principal components; S3: Establish a multiple linear regression model for the influencing factors of passenger flow at stations; S4: Calculate the scores of traffic connection plans; The present invention can be used as a basis for evaluating the traffic connection plan before and after adjustment and comparing multiple plans from the perspective of passenger flow. The present invention selects influencing factors from three perspectives: line, station, and traffic connection, which is more comprehensive than existing research in the study of passenger flow at intercity railway stations.

Description

Technical Field

[0001] The present invention belongs to the technical field of public transportation facility planning, and particularly relates to an evaluation method for the traffic connection plan of an intercity railway station based on the influence of passenger flow. Background Art

[0002] With the rapid advancement of China's urbanization process, the urban space has gradually expanded, the distance between cities has gradually shortened, and the interconnection has been continuously strengthened. A number of urban agglomerations at different development stages and of different scales have been formed nationwide. The efficient linkage between different cities within the urban agglomeration has realized the orderly flow of elements such as technology, information, and talents on a wider scale, and improved the efficiency and effectiveness of resource combination and allocation.

[0003] An intercity railway is a dedicated high-speed, convenient, and high-density passenger dedicated line railway that serves between adjacent cities or urban agglomerations and has a designed speed of 200 km / h or less for passenger trains. It is one of the main bodies of the intercity rapid transportation network within the urban agglomeration. The service object of the intercity railway generally focuses on cross-city passenger flow. Compared with the urban rail transit system, its station spacing is generally larger, the station service area is wider, and sufficient traffic connection facilities and services need to be provided to attract passengers from a farther range. Compared with private transportation methods such as cars, the intercity railway has advantages in economy, speed, punctuality, and safety within its service corridor. However, it cannot achieve door-to-door transportation, and the convenience and comfort during the connection process are significantly lower than those of cars. The service level of the traffic connection process is an important factor determining the passenger flow attraction of the intercity railway. From the actual operation situation of the intercity railways in various urban agglomerations in China, except for the lines in several channels with large passenger flow demands, other intercity railways all have problems of poor passenger flow benefits.

[0004] The existing research on the traffic connection of intercity railway stations focuses on comprehensive passenger transport hub stations, and conducts comprehensive evaluation and optimization of traffic connection from the perspectives of the convenience of passenger traffic connection, the matching of facility capacity and demand, and the pros and cons of flow line design. It does not consider the entire connection process of passengers, study the influence of the traffic connection plan on passenger flow, and does not propose an evaluation method for the traffic connection of intercity stations from the perspective of passenger flow. Intercity railway stations with low passenger flow are generally located in the peripheral areas of the city or the boundary areas of adjacent cities. These stations often have problems such as few connecting bus lines, large bus departure intervals, and poor road traffic accessibility, resulting in low traffic connection efficiency and large room for optimization.

[0005] In summary, to evaluate the traffic connection plan of intercity railway stations from the perspective of passenger flow impact and improve the passenger flow volume of stations and the passenger flow benefits of intercity railways at the traffic connection level, it is necessary to study an evaluation method for the traffic connection plan of intercity railway stations based on passenger flow impact, establish a comprehensive evaluation system for the traffic connection plan of intercity railway stations from the perspective of passenger flow, and study the calculation method of the weights of various indicators to realize the evaluation and comparison between different intercity railway stations and between different connection plans of the same station. Summary of the Invention

[0006] In view of the above problems, the present invention proposes an evaluation method for the traffic connection plan of intercity railway stations based on passenger flow impact. Based on the existing operation data of intercity railways and the traffic connection conditions of intercity railway stations, a linear regression model between the passenger flow volume of intercity railway stations and various influencing factor variables is established by using the method of principal component analysis + multiple regression analysis. The scores of the traffic connection plan are calculated by weighted summation of the traffic connection indicators of the stations with the regression coefficients as the weights, which serves as the basis for the evaluation and comparison of the traffic connection plans of intercity railway stations.

[0007] The technical solution of the present invention is as follows: An evaluation method for the traffic connection plan of intercity railway stations based on passenger flow impact, and the specific steps are as follows:

[0008] S1: Establish an index system C for the influencing factors of the passenger flow of intercity railway stations, and propose evaluation indicators for the traffic connection plan of intercity railway stations;

[0009] Establish an index system C for the influencing factors of the passenger flow of intercity railway stations C = {C1, C2, C3}; C1 is a set of line attribute indicators, C1 = {x 1_1 , x 1_2 , x 1_3 , …, x 1_m+1}, where x 1_1 is the number of full-day train departure schedules of this station, and x 1_2 ~x 1_m+1 are respectively 0-1 variables representing the m lines to which the station belongs; C2 is a set of indicators of the station attributes, C2 = {x 2_1 , x 2_2 , x 2_3 , x 2_4 , …, x 2_13}, where x 2_1 is the population covered within 1500 meters of the station, x 2_2 is the number of employment positions covered within 1500 meters of the station, x 2_3 and x 2_4 are respectively 0-1 variables indicating whether the station is located in the central urban area or other areas, x 2_5 , x 2_6 and x 2_7are 0-1 variables representing whether the traffic function level of the station belongs to comprehensive hub, hub and general station, respectively, and x 2_8 ~x 2_13 are 0-1 variables representing whether the land use types around the site are industrial, transportation, residential, special, comprehensive and others, respectively; C3 is the index set representing traffic connection, C3 = {x 3_1 , x 3_2 , x 3_3 , x 3_4 , …, x 3_9}, where x 3_1 and x 3_2 are the population and number of employment positions covered within a 30-minute reach by public transportation centered on the station, respectively, and x 3_3 and x 3_4 are the population and number of employment positions covered within a 30-minute reach by car centered on the station, respectively, x 3_5 is the road network density within a 1500-meter range of the site, x 3_6 is the connection distance of bus stops, x 3_7 is the number of conventional bus connection lines, x 3_8 is the number of subway connection lines, x 3_9 is the walkability of connection.

[0010] S2: Select continuous variables for principal component analysis;

[0011] S21: Construct a sample data matrix and standardize it;

[0012] S22: Calculate the sample covariance matrix;

[0013] S23: Calculate the eigenvalues and eigenvectors of the covariance matrix;

[0014] S24: Calculate the principal component contribution rate and cumulative contribution rate;

[0015] S25: Write out the principal components;

[0016] S3: Use the principal components and other variables not participating in the principal component analysis as explanatory variables to establish a multiple linear regression model for the influencing factors of passenger flow at the station, write out the linear expression of the passenger flow at the station with respect to each index in the index system C, and extract the coefficients ω 3_1 , ω 3_2 , …, ω 3_9 ;

[0017] S4: Use the coefficients ω 3_1 , ω 3_2 , …, ω 3_9As the weight coefficient, it is multiplied by each traffic connection index of the station and then summed to calculate the score Score of the station traffic connection plan, that is:

[0018] Score = ω 3_1 x 3_1 + ω 3_2 x 3_2 + ω 3_3 x 3_3 + … + ω 3_9 x 3_9

[0019] Preferably, step S2 is specifically as follows:

[0020] S21: Construct a sample data matrix and perform standardization processing on it

[0021] Select x 2_1 、x 2_2 、x 3_1 、x 3_2 、x 3_3 、x 3_4 、x 3_5 、x 3_6 、x 3_7 、x 3_8 、x 3_9 A total of 11 variables, namely, as the objects of principal component analysis, for a sample composed of n stations, construct a sample data matrix X a as:

[0022]

[0023] In the above formula, represents the value of the variable x 2_1 of the first station in the sample, and so on; calculate the mean a of the j-th column of the matrix X and the standard deviation S j :

[0024]

[0025] Perform standardization processing on the above 11 variables by column to obtain variables X1 to X 11 :

[0026]

[0027] X a The standardized matrix X b is:

[0028]

[0029] S22: Calculate the sample covariance matrix

[0030] Matrix X b The covariance matrix of

[0031]

[0032] where

[0033]

[0034] In the formula, are respectively the average values of the b ith column and jth column of matrix X;

[0035] S23: Calculate the eigenvalues and eigenvectors of the covariance matrix

[0036] The eigenvalues of matrix R are obtained as λ1, λ2, …, λ 11 , and satisfy λ1 ≥ λ2 ≥ … ≥ λ 11 ≥ 0;

[0037] The corresponding unit eigenvectors are respectively:

[0038]

[0039] S24: Calculate the main component contribution rate and the cumulative contribution rate

[0040]

[0041] S25: Write out the main components

[0042] Take the first, second, …, wth (w < 11) main components corresponding to the cumulative contribution rate greater than a certain percentage or the eigenvalue greater than 1. The ith main component is:

[0043]

[0044] Preferably, step S3 is specifically as follows:

[0045] Taking the daily inbound and outbound volume Y of the intercity railway station as the explained variable, and taking the main components F1, F2, …, F w and the variables x 1_1 , x 1_2 , …, x 1_m+1 , x 2_3 , x 2_4 , …, x 2_13 that do not participate in the principal component analysis as the explained variables, and establish a multiple regression linear model;

[0046] The expression of the multiple linear regression model is In the formula is the column vector of predicted values of the regression equation, X is the matrix constructed from the sample data of each variable, and ω is the column vector of coefficients of each variable including the constant term; in the sample consisting of n stations:

[0047]

[0048] ω = (ω1, ω2, ω3, …, ω w+m+12 , b) T

[0049] In the above formula, ω1, ω2, ω3, …, ω w+m+12 are the regression coefficients of each explained variable in the regression equation, and b is the constant term of the regression equation;

[0050] Use the least squares method to estimate the parameters of the regression model and solve for the coefficient column vector ω that minimizes the sum of squares h(ω) of the difference between the predicted value and the actual value * , where

[0051] h(ω) = (y - Xω) T (y - Xω)

[0052] In the formula, y is the column vector of sample actual values;

[0053] By taking the derivative of h(ω) and setting it equal to zero, we can solve for:

[0054] ω * = (X T X) - 1X T y

[0055] Substitute the expressions of F1, F2, …, F w with respect to each original variable participating in the principal component analysis into the regression equation to obtain the final regression model expression:

[0056] Y = ω 1_1 x 1_1 + ω 1_2 x 1_2 + … + ω 3_9 x 3_9 + b′

[0057] In the formula, ω 1_1 , ω 1_2 , …, ω 3_9 are the regression coefficients of each original variable, where ω 3_1 , ω 3_2 , …, ω 3_9 are the coefficients of each traffic connection variable, used to calculate the score of the station traffic connection plan, and b′ is the constant term of the final regression formula;

[0058] In the process of establishing the multiple linear regression model above, the stepwise regression method is adopted to identify and add significant variables one by one, and only the variables passing the significance test are retained in the regression equation.

[0059] The present invention is applicable to the situation where there are two or more intercity railway lines and at least more than ten stations in operation within an urban agglomeration to meet the sample quantity requirements for each variable to participate in the regression analysis. For emerging urban agglomerations with fewer operating intercity railway lines and stations, the operating data of intercity railways in other mature urban agglomerations can be used for calculation, and the obtained results can be applied to the evaluation of the traffic connection plan for intercity railway stations within this urban agglomeration.

[0060] Compared with the prior art, the present invention has the following advantages:

[0061] (1) An evaluation method for the traffic connection plan of intercity railway stations is proposed from the perspective of passenger flow impact. Existing evaluations of the traffic connection services of intercity railway stations often consider aspects such as connection convenience, matching of facility capacity and demand, and quality of flow line design, focusing on the layout optimization of connection facilities at the station level, and do not evaluate factors such as the layout of bus lines around the station, road traffic supply, and convenience of slow traffic from the perspective of passenger flow impact. There are some intercity railway stations with poor passenger flow benefits, and the improvement of their traffic connection services should first focus on increasing the number of passengers served by the station and improving the surrounding travel conditions. This method can be used as a basis for judging before and after the adjustment of the traffic connection plan and comparing multiple plans from the perspective of passenger flow.

[0062] (2) All influencing factors of the passenger flow volume of intercity railway stations are comprehensively considered, and the influence of other factors except traffic connection factors on the passenger flow of the station is eliminated. Existing analyses of the influencing factors of the passenger flow of rail transit stations mainly focus on urban rail transit stations, and there is little research on intercity railway stations. The travel characteristics of intercity railway passenger flow are different from those of subway passenger flow. The passenger flow attraction range of intercity railway stations is wider, and it is not only affected by the surrounding land use and development, but also more easily affected by the convenience of traffic connection. At the same time, the inherent attributes and competitiveness of intercity lines also have a significant impact on the passenger flow of stations. The present invention selects influencing factors from three perspectives: lines, stations, and traffic connection, which is more comprehensive than existing research in the study of the passenger flow of intercity railway stations.

[0063] The present invention can serve the design of traffic connection facilities and services around newly built intercity railway stations and the improvement of existing intercity railway stations. Based on the influence of passenger flow, it evaluates and optimizes the comprehensive plan for the configuration of traffic connection services in different modes, and can ensure that intercity railway stations achieve the maximum passenger flow attraction under limited facility equipment and labor costs. Description of the Drawings

[0064] Figure 1 It is a schematic diagram of the score ranking of the traffic connection plans of each intercity railway station. Detailed implementation manners

[0065] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0066] To solve the defects and deficiencies in the above technologies, the present invention provides an evaluation method for the traffic connection plan of intercity railway stations based on passenger flow impact, which is used to evaluate and compare different intercity railway connection plans from the perspective of passenger flow.

[0067] Based on the existing operation data of intercity railways and the traffic connection situation, this method selects the influencing factors of station passenger flow from three perspectives: station attributes, line attributes, and traffic connection. By using the method of principal component analysis + multiple regression analysis, a linear regression model is established between the passenger flow volume of intercity railway stations and the variable of each influencing factor, to study the influence degree of each factor on passenger flow. Then, relevant variables related to traffic connection are selected from them to establish a comprehensive evaluation system for traffic connection plans. Finally, based on the regression coefficients, the weights of each evaluation index are determined, and the score of the traffic connection plan is calculated as the basis for evaluating the traffic connection plan.

[0068] An evaluation method for the traffic connection plan of intercity railway stations based on passenger flow impact provided by the present invention specifically includes the following steps:

[0069] Step 1: Establish an index system for influencing factors of passenger flow at intercity railway stations

[0070] The passenger flow at intercity railway stations is mainly affected by three aspects: line attributes, station attributes, and traffic connection. Based on this, an index system for influencing factors C = {C1, C2, C3} is established.

[0071] C1 is the index set representing line attributes, C1 = {x 1_1 , x 1_2 , x 1_3 , …, x 1_m+1}, where x 1_1 is the number of full-day train departure trips at this station, and x 1_2 ~x 1_m+1 are 0-1 variables representing the m lines to which the station belongs respectively. In addition to being affected by the station's own attributes and the surrounding land development, the passenger flow at intercity railway stations is also related to factors such as the cross-city demand size of the line corridor, the line network structure, the line operation service level, and the competition of other modes within the corridor. The 0-1 variables of each line are introduced to eliminate the influence of line factors on the station passenger flow.

[0072] C2 is the index set representing station attributes, C2 = {x 2_1 , x 2_2 , x 2_3 , x 2_4 , …, x 2_13}, where x2_1 Population (in ten thousands) covered within a 1500-meter radius of the station, x 2_2 Employment (in ten thousands) covered within a 1500-meter radius of the station, x 2_3 and x 2_4 are 0-1 variables indicating whether the station is located in the central urban area or other areas, x 2_5 、x 2_6 and x 2_7 are 0-1 variables indicating whether the traffic function level of the station belongs to comprehensive hub, hub, and general station respectively, x 2_8 ~x 2_13 are 0-1 variables indicating whether the land use type around the station is industrial, transportation, residential, special, comprehensive, and other respectively. The classification of the traffic function level of the station and the surrounding land use type can be determined with reference to relevant specification standards.

[0073] C3 represents the index set for traffic connection, C3 = {x 3_1 ,x 3_2 ,x 3_3 ,x 3_4 ,…,x 3_9}, where x 3_1 、x 3_2 are the population and number of employment positions (in ten thousands) covered within a 30-minute reach by public transportation centered on the station respectively, x 3_3 、x 3_4 are the population and number of employment positions (in ten thousands) covered within a 30-minute reach by car centered on the station respectively, x 3_5 is the road network density within a 1500-meter radius of the station (km / km 2 ), x 3_6 is the connection distance of the bus stop (m), x 3_7 is the number of conventional bus connection lines, x 3_8 is the number of subway connection lines, x 3_9 is the walkability of connection.

[0074] The definitions of each variable are specifically shown in Table 1.

[0075] Table 1 Definitions of Each Index Variable

[0076]

[0077]

[0078] Step 2: Select continuous variables for principal component analysis

[0079] Among the variables defined in Step 1, there is an obvious correlation between some variables of station attributes and transportation connections. Therefore, it is necessary to perform dimensionality reduction on the variables first. The principal component analysis method uses the idea of dimensionality reduction to transform a set of highly correlated independent variables into a set of independent variables without linear relationships.

[0080] For this problem, the specific calculation process of the principal component analysis is as follows:

[0081] The first step: Construct a sample data matrix and standardize it.

[0082] Select x 2_1 、x 2_2 、x 3_1 、x 3_2 、x 3_3 、x 3_4 、x 3_5 、x 3_6 、x 3_7 、x 3_8 、x 3_9 A total of 11 variables are used as the objects of principal component analysis. For a sample composed of n stations, construct a matrix X a as:

[0083]

[0084] In the above formula, represents the value of the variable x 2_1 of the first station in the sample, and so on. Calculate the mean a of the j-th column of the matrix X and the standard deviation S j :

[0085]

[0086] Standardize the above 11 variables by column to obtain variables X1 to X 11 :

[0087]

[0088] X a The standardized matrix X b is:

[0089]

[0090] The second step: Calculate the sample covariance matrix.

[0091] The covariance matrix of the matrix X b is:

[0092]

[0093] Among them,

[0094]

[0095] In the formula, are respectively the average values of the b ith column and jth column of the matrix X.

[0096] Step 3: Calculate the eigenvalues and eigenvectors of the covariance matrix

[0097] The eigenvalues of the matrix R are obtained as λ1, λ2, …, λ 11 , and satisfy λ1 ≥ λ2 ≥ … ≥ λ 11 ≥ 0.

[0098] The corresponding unit eigenvectors are respectively:

[0099]

[0100] Step 4: Calculate the contribution rate and cumulative contribution rate of the principal components

[0101]

[0102]

[0103] Step 5: Write out the principal components

[0104] Take the first, second, …, wth principal components (w < 11) corresponding to the cumulative contribution rate greater than a certain percentage or the eigenvalue greater than 1. The ith principal component is:

[0105]

[0106] Step 3: Establish a multiple linear regression model for the influencing factors of passenger flow at the station

[0107] Taking the daily inbound and outbound volume Y of the intercity railway station as the explained variable, and taking the principal components F1, F2, …, F w and the variables x 1_1 , x 1_2 , …, x 1_m+1 , x 2_3 , x 2_4 , …, x 2_13 that did not participate in the principal component analysis as the explanatory variables, establish a multiple regression linear model.

[0108] The general expression of the multiple linear regression model is In the formula is the predicted value column vector of the regression equation, X is the matrix constructed by the sample data of each variable, and ω is the variable coefficient column vector containing the constant term. In the sample composed of n stations in this example:

[0109]

[0110] ω = (ω1, ω2, ω3, …, ω w+m+12 , b) T

[0111] In the above formula, ω1, ω2, ω3, …, ω w+m+12 are the regression coefficients of the explained variables in the regression equation, and b is the constant term of the regression equation.

[0112] Using the least squares method for parameter estimation of the regression model, solve the coefficient column vector ω that minimizes the sum of squares h(ω) of the difference between the predicted value and the actual value * , where

[0113] h(ω) = (y - Xω) T (y - Xω)

[0114] In the formula, y is the column vector of the actual values of the samples.

[0115] By taking the derivative of h(ω) and setting it equal to zero, we can solve:

[0116] ω * = (X T X) -1 X T y

[0117] Substitute the expressions of F1, F2, …, F w with respect to the original variables participating in the principal component analysis into the regression equation to obtain the final regression model expression:

[0118] Y = ω 1_1 x 1_1 + ω 1_2 x 1_2 + … + ω 3_9 x 3_9 + b′

[0119] In the formula, ω 1_1 , ω 1_2 , …, ω 3_9 are the coefficients corresponding to the variables in Table 1, where ω 3_1 , ω 3_2 , …, ω 3_9 are the coefficients of each traffic connection variable, used to calculate the score of the station traffic connection plan, and b′ is the constant term of the final regression formula.

[0120] In the process of establishing the above multiple linear regression model, the stepwise regression method can be adopted to identify and add significant variables one by one, and only the variables passing the significance test are retained in the regression equation.

[0121] Step 4: Write the formula for calculating the score of the transportation connection plan

[0122] Take the coefficients ω 3_1 , ω 3_2 , …, ω 3_9 as the weight coefficients, multiply them by each transportation connection index of the station and sum them up to calculate the score Score of the station transportation connection plan, that is:

[0123] Score = ω 3_1 x 3_1 + ω 3_2 x 3_2 + ω 3_3 x 3_3 + … + ω 3_9 x 3_9 Specific embodiments

[0125] Taking 6 operating intercity railways in a certain urban agglomeration as the research object for example analysis, there are a total of 78 intercity railway stations on each line. At present, some stations have the problem of low passenger flow efficiency. To study the strategy for improving the passenger flow of stations from the perspective of enhancing transportation connection services, this evaluation method can be applied as a reference for optimizing and comparing transportation connection plans.

[0126] Collect and calculate the relevant data of each station according to the definitions of each variable in Table 1 above, and construct a data set containing 78 samples × 29 indicators (each sample contains 7 line attribute indicators, 13 station attribute indicators, and 9 transportation connection indicators).

[0127] Select x 2_1 , x 2_2 , x 3_1 , x 3_2 , x 3_3 , x 3_4 , x 3_5 , x 3_6 , x 3_7 , x 3_8 , x 3_9 A total of 11 variables as the object of principal component analysis. After the data set is standardized, calculate the covariance matrix, and calculate the principal component contribution rate according to its eigenvalues and eigenvectors. Extract three principal components for subsequent analysis with the eigenvalue greater than 1 as the standard:

[0128] F1 = 0.124X1 + 0.133X2 + 0.132X3 + 0.133X4 + 0.126X5 + 0.128X6 + 0.106X7 + 0.017X8 + 0.126X9 + 0.114X 10 + 0.017X 11

[0129] F2 = -0.194X1 - 0.120X2 + 0.023X3 + 0.033X4 + 0.041X5 + 0.044X6 - 0.209X7 + 0.748X8 - 0.063X9 + 0.36X 10 -0.117X 11

[0130] F3 = 0.059X1 + 0.053X2 - 0.071X3 - 0.066X4 - 0.050X5 - 0.051X6 - 0.026X7 + 0.130X8 - 0.074X9 + 0.090X 10 +0.971X 11

[0131] Wherein, F1, F2 and F3 are three principal components extracted, and X1, X2, … X 11 are variables corresponding to 11 variables participating in the principal component analysis after standardization.

[0132] Taking the daily in-out volume Y of the station as the explained variable, and taking F1, F2, F3 and the remaining variables not participating in the principal component analysis as the explanatory variables, a multiple linear regression model is constructed by the stepwise regression method. F1, x 1_2 , x 1_5 and x 1_7 are selected into the model through significance tests. The determination coefficient R 2 of the regression equation is 0.789, and its expression is:

[0133] Y = 3538.024F1 + 3504.802x 1_2 -27141.712x 1_5 +204.237x 1_7 -3624.472

[0134] After restoring F1 to the original variable, the expression of the final regression equation is obtained:

[0135] Y = 3504.802x 1_2 -27141.712x 1_5 +204.237x 1_7 +92.674x 2_1 +122.538x 2_2 +14.117x 3_1 +18.742x 3_2 +6.304x 3_3 +10.237x 3_4 +122.371x 3_5 +0.167x 3_6 +40.270x 3_7 +692.700x3_8 +395.647x 3_9 -7299.947

[0136] The calculation formula for the score of the traffic connection plan is as follows:

[0137] Score=14.117x 3_1 +18.742x 3_2 +6.304x 3_3 +10.237x 3_4 +122.371x 3_5 +0.167x 3_6 +40.270x 3_7 +692.700x 3_8 +395.647x 3_9

[0138] Based on the above formula, the score ranking of the traffic connection plans for each intercity railway station is as Figure 1 shown.

[0139] The present invention is applicable to the situation where there are two or more intercity railway lines and at least more than ten stations in operation within the urban agglomeration to meet the sample quantity requirements for each variable to participate in the regression analysis. For emerging urban agglomerations with fewer intercity railway operation lines and stations, the intercity railway operation data within other mature urban agglomerations can be used for calculation, and the solution results can be applied to the evaluation of the traffic connection plans for intercity railway stations within this urban agglomeration.

[0140] Compared with the prior art, the present invention has the following advantages:

[0141] (1) A method for evaluating the traffic connection plan for intercity railway stations is proposed from the perspective of passenger flow impact. The existing evaluations of the traffic connection services for intercity railway stations often consider aspects such as connection convenience, the matching of facility capacity and demand, and the quality of flow line design, focusing on the layout optimization of the connection facilities at the station level, and do not evaluate factors such as the layout of bus lines around the station, road traffic supply, and slow traffic convenience from the perspective of passenger flow impact. There are some intercity railway stations with poor passenger flow benefits, and the improvement of their traffic connection services should first focus on increasing the number of passengers served by the station and improving the surrounding travel conditions. This method can be used as a basis for judging before and after the adjustment of the traffic connection plan and for comparing multiple plans from the perspective of passenger flow.

[0142] (2)Comprehensively consider the influencing factors of the passenger flow of intercity railway stations, and eliminate the influence of other factors on the station passenger flow except for the traffic connection factors. The existing analysis objects of the influencing factors of rail transit station passenger flow are mainly urban rail transit stations, and there is less research on intercity railway stations. The travel characteristics of intercity railway passenger flow are different from those of subway passenger flow. The passenger flow attraction range of intercity railway stations is wider. It is not only affected by the surrounding land use and development, but also more easily affected by the convenience of traffic connection. At the same time, the own attributes and competitiveness of intercity lines also have a significant impact on the station passenger flow. The present invention selects influencing factors from three perspectives: line, station and traffic connection, which is more comprehensive than the existing research in the study of intercity railway station passenger flow.

[0143] The present invention can serve the design of the traffic connection facilities and services around newly built intercity railway stations and the improvement of existing intercity railway stations. Based on the influence of passenger flow, evaluate and optimize the comprehensive scheme of traffic connection service configuration in different modes, and can ensure that intercity railway stations achieve the maximum passenger flow attraction under the limited facilities, equipment and labor costs.

[0144] For those of ordinary skill in the art, without departing from the creative concept of this application, several variations and improvements can also be made to the embodiments of the present invention, and these all belong to the protection scope of this application.

Claims

1. An evaluation method for the traffic connection plan of intercity railway stations based on the influence of passenger flow, characterized in that The specific steps are as follows: S1: Establish an index system C for the influencing factors of passenger flow at intercity railway stations, and propose evaluation indicators for the traffic connection plan of intercity railway stations; Establish an index system for influencing factors of passenger flow at intercity railway stations ; is the set of line attribute indicators, , where is the number of daily train departures from this station, ~ are 0-1 variables representing the m lines to which the representative stations belong respectively; is the set of indicators of station attributes, , where is the population covered within 1500 meters of the station, is the number of employment positions covered within 1500 meters of the station, and are 0-1 variables indicating whether the station is located in the central urban area or other areas respectively, , and are 0-1 variables indicating whether the traffic function level of the station belongs to a comprehensive hub, a hub, and a general station respectively, ~ are 0-1 variables indicating whether the land use types around the station are industrial, transportation, residential, special, comprehensive, and other respectively; is the set of indicators representing transportation connections, , where , are the population and the number of employment positions covered within a 30-minute reach by public transportation centered on the station respectively, , are the population and the number of employment positions covered within a 30-minute reach by car centered on the station respectively, is the road network density within 1500 meters of the station, is the connection distance of bus stops, is the number of conventional bus connection lines, is the number of subway connection lines, is the walkability of connections; S2: Select continuous variables for principal component analysis; S21: Construct a sample data matrix and standardize it; S22: Calculate the sample covariance matrix; S23: Calculate the eigenvalues and eigenvectors of the covariance matrix; S24: Calculate the contribution rate and cumulative contribution rate of the principal components; S25: Write out the principal components; S3: Use the principal components and other variables not involved in the principal component analysis as explanatory variables to establish a multiple linear regression model for the influencing factors of station passenger flow, write the linear expression of the station passenger flow with respect to each index in the index system C, and extract the traffic connection index set the regression coefficients corresponding to each index in , , , ; S4: Multiply the coefficients , , , as weight coefficients with each traffic connection index of the station, then sum them up to calculate the score of the station traffic connection plan , that is: 。 2. The evaluation method for the intercity railway station traffic connection plan based on passenger flow impact according to claim 1, characterized in that Step S2 is specifically as follows: S21: Construct a sample data matrix and standardize it Select , , , , , , , , , , A total of 11 variables are used as the objects of principal component analysis. For the sample composed of n stations, a sample data matrix is constructed as follows: In the above formula, represents the value of the variable of the first station in the sample, and so on; Calculation matrix Mean of the j-th column And standard deviation : , , , …, = , = , = , …, = Standardize the above 11 variables by column to obtain the variables ~ : , , , …, , The standardized matrix is as follows: S22: Calculate the sample covariance matrix Matrix The covariance matrix of is as follows: Among them, In the formula, , are respectively the averages of the th i column and the j th column of the matrix; S23: Calculate the eigenvalues and eigenvectors of the covariance matrix The eigenvalues of the matrix R are , and satisfy ; The corresponding unit eigenvectors are respectively: , , …, S24: Calculate the contribution rate and cumulative contribution rate of the principal components S25: Write out the principal components Take the first, second, ……, w-th principal components (w < 11) corresponding to the cumulative contribution rate greater than a certain percentage or the eigenvalue greater than 1. The i w-th principal component is: 。 3. The evaluation method for the intercity railway station traffic connection plan based on passenger flow impact according to claim 1, wherein Step S3 is specifically as follows: Taking the daily inbound and outbound volume Y of the intercity railway station as the explained variable, and using the principal components , , , and the variables not involved in the principal component analysis , , , , , , , as the explained variables, a multiple linear regression model is established; The expression of the multiple linear regression model is , where is the predicted value column vector of the regression equation,[[]] is the matrix constructed from the sample data of each variable,[[]] is the column vector of coefficients of each variable including the constant term; in n the sample composed of stations: In the above formula, is the regression coefficient of each explained variable in the regression equation, b is the constant term of the regression equation; Use the least squares method to estimate the parameters of the regression model and solve for the column vector of coefficients that minimizes the sum of the squares of the differences between the predicted values and the actual values of the smallest , where In the formula is the column vector of the actual sample values; By taking the derivative of and setting it equal to zero, we can solve for: Substitute , , , the expressions of the original variables involved in each principal component analysis into the regression equation, and the final regression model expression is obtained: In the formula, , , , are the regression coefficients of each original variable, where , , , are the regression coefficients of each transportation connection variable, which are used to calculate the score of the station transportation connection plan in step S4, is the constant term of the final regression formula; In the process of establishing the above-mentioned multiple linear regression model, the stepwise regression method is adopted to identify and add significant variables one by one, and only the variables passing the significance test are retained in the regression equation.

4. An evaluation device for the traffic connection plan of an intercity railway station based on the influence of passenger flow, characterized in that, This device is used to implement an evaluation method for the traffic connection plan of intercity railway stations based on passenger flow influence described in any one of claims 1-3, and includes the following modules: The module for constructing the index system of influencing factors of passenger flow at intercity railway stations is used to implement step S1: Establish an index system C for the influencing factors of passenger flow at intercity railway stations, and propose evaluation indicators for the traffic connection plan of intercity railway stations; Establish an index model for the influencing factors of passenger flow at intercity railway stations ; is the set of line attribute indicators, is the set of indicators of station attributes, is the set of indicators representing transportation connections; The principal component analysis module is used to implement step S2: Select continuous variables for principal component analysis; S21: Construct a sample data matrix and standardize it; S22: Calculate the sample covariance matrix; S23: Calculate the eigenvalues and eigenvectors of the covariance matrix; S24: Calculate the contribution rate and cumulative contribution rate of the principal components; S25: Write out the principal components; The module for establishing a multiple linear regression model of the influencing factors of passenger flow at stations is used to implement step S3: Establish a multiple linear regression model of the influencing factors of passenger flow at stations; The traffic connection plan evaluation module is used to implement step S4: Use the coefficients of the traffic connection variables in the multiple linear regression model as weight coefficients, multiply them by each traffic connection index of the station and then sum to calculate the score of the traffic connection plan of the station.

Images