CN113743671B - High-speed rail express special train transportation network optimization method and system - Google Patents

High-speed rail express special train transportation network optimization method and system Download PDF

Info

Publication number
CN113743671B
CN113743671B CN202111051062.1A CN202111051062A CN113743671B CN 113743671 B CN113743671 B CN 113743671B CN 202111051062 A CN202111051062 A CN 202111051062A CN 113743671 B CN113743671 B CN 113743671B
Authority
CN
China
Prior art keywords
express
economic
geographic
speed rail
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111051062.1A
Other languages
Chinese (zh)
Other versions
CN113743671A (en
Inventor
陈思
陈泽军
汤银英
梁玥
邓晓臻
钟娟
池欣忆
卜思豪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu International Railway Train Co ltd
Southwest Jiaotong University
Original Assignee
Southwest Jiaotong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southwest Jiaotong University filed Critical Southwest Jiaotong University
Priority to CN202111051062.1A priority Critical patent/CN113743671B/en
Publication of CN113743671A publication Critical patent/CN113743671A/en
Application granted granted Critical
Publication of CN113743671B publication Critical patent/CN113743671B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Artificial Intelligence (AREA)
  • Human Resources & Organizations (AREA)
  • Finance (AREA)
  • Marketing (AREA)
  • Neurology (AREA)
  • Game Theory and Decision Science (AREA)
  • Databases & Information Systems (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Remote Sensing (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a high-speed rail express special train transportation network optimization method and system, relates to the technical field of transportation, and comprises a geographical economic attribute express demand analysis module, an express demand prediction module, a high-speed rail express sharing rate operation module and a high-speed rail express network planning module. The express delivery system effectively matches express delivery requirements, effectively utilizes transportation resources according to the actual sharing effect of express delivery in high-speed rail, and solves the problems of incomplete planning and low efficiency of express delivery transportation network in high-speed rail.

Description

High-speed rail express special train transportation network optimization method and system
Technical Field
The invention relates to the technical field of transportation, in particular to a method and a system for optimizing a special high-speed rail express transportation network.
Background
In the technical field of transportation, with the development of railway engineering, high-speed rail transportation is already undertaken or is about to undertake more and more functional tasks, wherein express delivery operation is a new function and a new task undertaken by the high-speed rail transportation. Traditional express delivery operation in China mostly depends on road transportation and is limited by road engineering conditions, road conditions and climate influences, and the road transportation is increasingly difficult to effectively meet the requirements of consumers and logistics enterprises.
The medium-speed rail express delivery limited company has prospectively introduced the railway express cargo transportation business with the help of the confirmation vehicle and the existing passenger train, and has great development potential, but meanwhile, the express transportation of the high-speed rail still has a plurality of problems at present: firstly, the matching degree of infrastructure is low, the actual demand of goods transportation is not considered in the vehicle design, the network layout and the operation scheme, and the express operation capability is limited; secondly, the terminal service capacity is insufficient, and a high-speed rail express freight network based on express transportation demand space distribution is not formed; and thirdly, the passenger transport and freight transport of the high-speed rail are mixed, the linking effectiveness of the transport links is not high, the transport resources are wasted, and the transport network efficiency is to be improved.
Disclosure of Invention
Aiming at the defects in the prior art, the method and the system for optimizing the express special train transportation network of the high-speed rail provided by the invention solve the problems of low matching degree of the existing express transportation infrastructure of the high-speed rail, insufficient terminal service capacity, mixed passenger transport and freight transport, low linking efficiency of transportation links and waste of transportation resources.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
in a first aspect, a method for optimizing a special express transportation network for a high-speed rail comprises the following steps:
s1, establishing a geographical economic attribute express demand model, and identifying useful geographical economic elements according to the geographical economic attribute express demand model;
s2, collecting historical data of useful geographic economic factors and express delivery traffic, and training an express delivery demand prediction model;
s3, forecasting the potential express business volume according to the current useful geographic economic factor data through an express demand forecasting model;
s4, establishing and training a traffic express sharing rate model according to historical data of express traffic;
s5, solving the potential high-speed rail express delivery traffic through a traffic express delivery sharing rate model according to the potential express delivery traffic;
and S6, optimizing the express special train transportation network of the high-speed rail according to the useful geographical economic factors and the potential express business volume of the high-speed rail through a K-means clustering algorithm.
The beneficial effects of the invention are as follows: the method comprises the steps of analyzing the relation between express delivery business volume and economic factors on geographical space distribution through an established geographical economic attribute express delivery demand model, identifying useful geographical economic factors with high association degree, predicting potential express delivery business volume at each position on the potential geographical space through an express delivery demand prediction model, researching the sharing rate of express delivery of a high-speed rail through a traffic express delivery sharing rate model, solving the potential express delivery business volume of the high-speed rail, optimizing a special high-speed rail express transportation network in the geographical space according to the useful geographical economic factors and the potential express delivery business volume through a K mean value clustering algorithm, effectively matching express delivery demands, effectively utilizing transportation resources according to the actual sharing effect of the express delivery of the high-speed rail, and solving the problems of incomplete planning and low efficiency of the express transportation network of the high-speed rail.
Further, the step S1 includes the following sub-steps:
s11, establishing a geographical economic attribute express delivery demand model, wherein the geographical economic attribute express delivery demand model has the expression:
Figure BDA0003252768330000021
wherein q is i Express traffic for geographic unit i, (u) i ,v i ) Is the spatial coordinate of a geographic unit i, i being a closed interval [1, N ]]Positive integer of, N is the total number of geographic units, x i,j Is the geographic unit ith geographic economic element, beta 0 (u i ,v i ) For geographic unit i 0 th geographic economic element relevance degree, beta j (u i ，v i ) For the geographic unit ith geographic economic element relevance degree epsilon i I bias coefficients for geographic units, j is a closed interval [0]The positive integer inside, M is the total number of the geographic economic elements;
s12, estimating the geographic economic element association degree of the geographic economic attribute express delivery demand model by a weighted least square method, wherein the expression of the weighted least square method is as follows:
Figure BDA0003252768330000031
Figure BDA0003252768330000032
Figure BDA0003252768330000033
Figure BDA0003252768330000034
Figure BDA0003252768330000035
Figure BDA0003252768330000036
wherein,
Figure BDA0003252768330000037
estimating a vector for a degree of association of a geo-economic element of a geographical unit i, -based on the estimated degree of association>
Figure BDA0003252768330000038
For the geographic unit ith geographic economic element relevance degree beta j (u i ,v i ) W (i) is a weight matrix for geographic unit i, and->
Figure BDA0003252768330000039
Is a geographic unit i and a geographic unit i 0 Inter weight value, X is the economic element matrix, X T Is a transposed matrix of the economic factor matrix X, b is a first inverse ratio coefficient, based on the inverse transformation of the economic factor matrix X, is based on the inverse transformation of the economic factor matrix X, and is based on the inverse transformation of the economic factor matrix B>
Figure BDA00032527683300000310
From geographic cell i to geographic cell i 0 Distance of (i) 0 Is a closed interval [1, N ]]The positive integer in the express delivery system is shown as q, the express delivery traffic vector is shown as q, and e is the base number of the natural logarithm;
and S13, evaluating the geographic economic element association degree estimation result through a Chichi information criterion method, and identifying useful geographic economic elements.
The beneficial effects of the above further scheme are: in order to research the distribution of express delivery demands in geographic space, the relationship between express delivery traffic and geographic economic elements needs to be analyzed, and different economic elements have different influences on the express delivery traffic, so that the attribute association degree of each economic element on geographic information characteristics is determined, and the identification of useful geographic economic elements is particularly important. According to the scheme, a geo-economic attribute express demand model is established, the model is solved through a weighted least square method, the correlation degree of geo-economic elements is estimated, and then the model is evaluated through an Akaikeinformation criterion method (AIC), so that useful geo-economic elements are identified, and a foundation is accurately and reliably laid for subsequent engineering.
Furthermore, the express demand forecasting model comprises L express demand forecasting submodels, wherein L is a positive integer greater than 2; wherein, at least 1 express delivery demand prediction submodel is BP neural network, and it includes: an input layer, a hidden layer and an output layer; at least 1 express demand forecasting sub-model is a grey forecasting model; at least 1 express demand forecasting submodel is a cubic exponential smoothing model; the output of each express demand forecasting sub-model obtains the output of the express demand forecasting model through the following weighting types:
Figure BDA0003252768330000041
Figure BDA0003252768330000042
Se′ m ＝Se m ×η e
Figure BDA0003252768330000043
wherein y is the output of the express demand prediction model, y m For the output of the mth express demand prediction submodel, α m Is a weighting coefficient, se 'of the mth express delivery demand forecasting sub-model' m Average prediction error, se, of the mth express demand prediction submodel m An original average prediction error, eta, of the mth express delivery demand prediction submodel e C is a second inverse coefficient.
The beneficial effects of the above further scheme are: different machine learning models have different prediction effects, and the accuracy is characterized by the average prediction error; considering that the application of express delivery transportation of a high-speed rail in an actual scene has strong geographical characteristics, the scheme jointly applies various existing machine learning models and carries out weighted summation according to average prediction errors of various technologies to obtain a final prediction result; the scheme establishes an express demand prediction model which at least comprises sub-models of three different technical routes, namely a BP (feed-forward) neural network, a gray prediction model and a cubic exponential smoothing model, and integrates the advantages of the three technologies; when the current useful geographic economic factor data is input into the trained express demand forecasting model, the potential express business volume can be analyzed.
Further, the expression of the traffic express sharing rate model is as follows:
Figure BDA0003252768330000051
U n ＝(γ n,1 T n -1 +γ n,2 C n +γ n,3 E n -1 )·γ n,4 ·S n ·γ n,5 ·R n
wherein, P n Is the sharing rate of the nth mode of transportation, U n Is the effect of the nth mode of transportation, H is the sum of modes of transportation, T n Time efficiency of the nth mode of transportation, gamma n,1 Is the time-dependent weight of the nth mode of transportation, C n For convenience of the nth mode of transportation, γ n,2 Is the convenience weight of the nth mode of transportation, E n Cost of the nth mode of transportation, γ n,3 Is the cost weight of the nth mode of transportation, S n A factor of safety, gamma, for the nth mode of transportation n,4 A safety factor weight, R, of the nth mode of transportation n Is the reliability coefficient of the nth mode of transportation, gamma n,5 And the reliability coefficient weight of the nth traffic mode.
The beneficial effects of the above further scheme are: potential express business volume can only measure the integral demand of express business, however, in terms of engineering, the potential express business volume is limited by timeliness, convenience, cost, safety factor and reliability coefficient of traffic mode of geographic area, and the sharing rate of express delivery by high-speed rail is not necessarily obvious; the traffic express sharing rate model can effectively represent the sharing rate of express business by a high-speed rail, and can calculate the potential express business volume of the high-speed rail based on the sharing rate.
Further, the step S6 includes the following sub-steps:
s61, mapping each geographic unit into candidate nodes of a K-means clustering algorithm one by one, and taking useful geographic economic factors and potential high-speed rail express delivery traffic of each geographic unit as attributes of corresponding candidate nodes to obtain a candidate node set:
Z＝{z 1 ,z 2 ,z 3 ,…,z N }
Figure BDA0003252768330000061
wherein Z is a candidate node set, Z 1 To z N 1 st to Nth candidate nodes, z p,1 To z p,I+1 The attributes are respectively from 1 st to I +1 st of the p candidate nodes, wherein I is the sum of useful geographic economic factors;
s62, setting the category number of the K-means clustering algorithm, optimizing the high-speed rail express special train transportation network according to the K-means clustering constraint and the K-means clustering objective function, and solving to obtain the optimal network node geographical position and the optimal network node region of the high-speed rail express special train transportation network.
The beneficial effects of the above further scheme are: in order to not omit important information, the potential high-speed rail express delivery service volume and useful geographic economic factors are taken as the attributes of candidate nodes of a K-means clustering algorithm to form candidate nodes in a vector form, the K-means clustering algorithm is started to select the centroid and cluster the nodes according to the candidate nodes, the position of the centroid determined by iteration is the footfall of the optimal network node of the high-speed rail express delivery special train transportation network, and the clustering division result of the iteration is the respective jurisdiction division result of each optimal network node of the high-speed rail express delivery special train transportation network, so that the optimization of the high-speed rail express delivery special train transportation network is completed.
Further, the K-means clustering objective function is:
Figure BDA0003252768330000062
/>
Figure BDA0003252768330000063
where min is a function of the minimum, D R Is the comprehensive distance between samples of the K-means clustering algorithm, o k For the k-th cluster centroid,d(z p ,o k ) Is the distance, w ', of the p-th candidate node to the k-th clustered centroid' kp The weight of the distance from the p candidate node to the K clustering centroid, K is the set class number, u p Is the abscissa, v, of the p-th candidate node p Is the ordinate, u, of the p-th candidate node k Is the abscissa, v, of the kth cluster centroid k Is the ordinate of the kth cluster centroid.
Further, the K-means clustering constraint is:
w′ kp ∈(0,1)
Figure BDA0003252768330000071
Figure BDA0003252768330000072
in a second aspect, a high-speed rail express special train transportation network optimization system adopts the high-speed rail express special train transportation network optimization method, and includes: the system comprises a geographical economic attribute express demand analysis module, an express demand prediction module, a high-speed rail express share rate operation module and a high-speed rail express network planning module;
the geographic economic attribute express demand analysis module is used for establishing a geographic economic attribute express demand model and identifying useful geographic economic elements according to the geographic economic attribute express demand model;
the express delivery demand forecasting module is used for collecting useful geographic economic factors and historical data of express delivery business volume and training an express delivery demand forecasting model; predicting the potential express business volume according to the current useful geographic economic factor data through an express demand prediction model;
the express delivery sharing rate operation module for the high-speed rail is used for establishing and training a traffic express delivery sharing rate model according to historical data of express delivery service volume; solving the potential high-speed rail express business volume through a traffic express sharing rate model according to the potential express business volume;
the high-speed rail express network planning module is used for optimizing the high-speed rail express special train transportation network according to useful geographical economic factors and potential high-speed rail express business volume through a K-means clustering algorithm.
In a third aspect, a high-speed rail express special train transportation network optimization device includes:
a memory for storing a computer program;
and the processor is used for realizing the steps of the high-speed rail express special train transportation network optimization method when executing the computer program.
In a fourth aspect, a computer-readable storage medium has stored thereon a computer program, which when executed by a processor, implements the steps of the method for optimizing a high-speed rail express special transportation network described above.
Drawings
Fig. 1 is a schematic flow chart of a method for optimizing a transportation network for express trains in high-speed rails according to an embodiment of the present invention;
fig. 2 is a structural diagram of a high-speed rail express special train transportation network optimization system according to an embodiment of the present invention;
fig. 3 is a structural diagram of a high-speed rail express special train transportation network optimization device provided in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined by the appended claims, and all changes that can be made by the invention using the inventive concept are intended to be protected.
As shown in fig. 1, in an embodiment of the present invention, a method for optimizing a transportation network for express trains in high-speed railways includes the following steps:
s1, establishing a geographical economic attribute express demand model, and identifying useful geographical economic elements according to the geographical economic attribute express demand model.
Step S1 includes the following substeps:
s11, establishing a geographical economic attribute express delivery demand model, wherein the geographical economic attribute express delivery demand model has an expression as follows:
Figure BDA0003252768330000091
wherein q is i Express traffic for geographic unit i, (u) i ,v i ) Is the spatial coordinate of a geographic unit i, i being a closed interval [1, N ]]Positive integer of, N is the total number of geographic units, x i,j For the geographic unit ith geographic economic element, beta 0 (u i ,v i ) For the geographic unit i, the 0 th geographic economic element relevance, beta j (u i ,v i ) For the geographic unit ith geographic economic element relevance degree epsilon i I bias coefficients for geographic units, j is a closed interval [0]The method comprises the following steps of (1) analyzing four economic elements including GDP, CPI, disposable income and per-capita consumption expense in the embodiment, wherein M is the total number of geographic economic elements;
s12, estimating the geographic economic element association degree of the geographic economic attribute express delivery demand model by a weighted least square method, wherein the expression of the weighted least square method is as follows:
Figure BDA0003252768330000092
Figure BDA0003252768330000093
Figure BDA0003252768330000094
Figure BDA0003252768330000095
/>
Figure BDA0003252768330000101
Figure BDA0003252768330000102
wherein,
Figure BDA0003252768330000103
estimating a vector for a degree of association of a geocooconomic element of a geographic unit i>
Figure BDA0003252768330000104
For the geographic unit ith geographic economic element relevance degree beta j (u i ,v i ) W (i) is a weight matrix for geographic unit i, and->
Figure BDA0003252768330000105
Is a geographic unit i and a geographic unit i 0 Inter-weighted value, X is economic element matrix, X T Is a transposed matrix of the economic factor matrix X, b is a first inverse ratio coefficient, based on the inverse transformation of the economic factor matrix X, is based on the inverse transformation of the economic factor matrix X, and is based on the inverse transformation of the economic factor matrix B>
Figure BDA0003252768330000106
From geographic cell i to geographic cell i 0 Distance of (i) 0 Is a closed interval [1, N]The positive integer in the express delivery system is shown as q, the express delivery traffic vector is shown as q, and e is the base number of the natural logarithm;
and S13, evaluating the geographic economic element association degree estimation result through a Chichi information criterion method, and identifying useful geographic economic elements.
In order to research the distribution of express delivery demands in geographic space, the relationship between express delivery traffic and geographic economic elements needs to be analyzed, and different economic elements have different influences on the express delivery traffic, so that the attribute association degree of each economic element on geographic information characteristics is determined, and the identification of useful geographic economic elements is particularly important. According to the scheme, a geographical economic attribute express demand model is established, the model is solved through a weighted least square method, the geographical economic element association degree is estimated, the model is evaluated through an Akaikeinformation criterion method (AIC), useful geographical economic elements are identified, and a foundation is accurately and reliably laid for subsequent engineering. Since the akachi pool information criterion method is the prior art, the embodiment of the present invention is not described in detail.
S2, collecting historical data of useful geographic economic factors and express delivery traffic, and training an express delivery demand prediction model.
The express demand forecasting model comprises L express demand forecasting submodels, wherein L is a positive integer greater than 2; wherein, at least 1 express delivery demand prediction submodel is BP neural network, and it includes: an input layer, a hidden layer and an output layer; at least 1 express demand forecasting sub-model is a grey forecasting model; at least 1 express demand forecasting sub-model is a cubic exponential smoothing model; the output of each express demand forecasting sub-model obtains the output of the express demand forecasting model through the following weighting types:
Figure BDA0003252768330000111
Figure BDA0003252768330000112
Se′ m ＝Se m ×η e
Figure BDA0003252768330000113
wherein y is the output of the express demand prediction model, y m For the output of the mth express demand prediction submodel, α m Weighting coefficient, se 'for mth express demand prediction submodel' m Average prediction error, se, of the mth express demand prediction submodel m An original average prediction error, eta, of the mth express demand prediction submodel e C is a second inverse coefficient.
In the embodiment of the invention, the express demand prediction model comprises 3 express demand prediction submodels which are a BP neural network, a gray prediction model and a cubic exponential smoothing model respectively. The express demand forecasting sub-model constructed by the BP neural network is established by the following formula of the number of hidden layer neurons:
Figure BDA0003252768330000114
wherein r is 2 Number of hidden layer neurons, r 1 Is the number of neurons in the input layer, r 3 The number of neurons in the output layer, and the constant xi is a closed interval [1,10 ]]A positive integer within.
The embodiment of the invention does not describe the two prior arts of the gray prediction model and the cubic exponential smoothing model.
And S3, forecasting the potential express delivery business volume according to the current useful geographic economic factor data through an express delivery demand forecasting model.
And S4, establishing and training a traffic express sharing rate model according to historical data of express traffic.
The expression of the traffic express sharing rate model is as follows:
Figure BDA0003252768330000121
U n ＝(γ n,1 T n -1 +γ n,2 C n +γ n,3 E n -1 )·γ n,4 ·S n ·γ n,5 ·R n
wherein, P n Is the sharing rate of the nth mode of transportation, U n Is the effect of the nth mode of transportation, H is the sum of modes of transportation, T n Time efficiency of the nth mode of transportation, gamma n,1 Is a time-dependent weight of the nth mode of transportation, C n For convenience of the nth mode of transportation, gamma n,2 As a convenience weight of the nth mode of transportation, E n Cost of the nth mode of transportation, γ n,3 Cost for the nth mode of transportationWeight, S n A factor of safety, gamma, for the nth mode of transportation n,4 A safety factor weight, R, of the nth mode of transportation n Is the reliability coefficient of the nth mode of transportation, gamma n,5 And the reliability coefficient weight of the nth traffic mode.
Potential express business volume can only measure the integral demand of the express business, however, in terms of engineering, the express business is limited by timeliness, convenience, cost, safety factor and reliability coefficient of a traffic mode in a geographic area, and the sharing rate of express in a high-speed rail is not necessarily obvious; the traffic express sharing rate model can effectively represent the sharing rate of express services of high-speed rails and can calculate the potential express service volume of the high-speed rails based on the sharing rate.
In the embodiment of the invention, the traffic express sharing rate model considers three traffic modes, including: the express delivery sharing rate model can accurately calculate the sharing rate of express services of a high-speed rail.
And S5, solving the potential high-speed rail express delivery traffic through a traffic express delivery sharing rate model according to the potential express delivery traffic.
And S6, optimizing the express special train transportation network of the high-speed rail according to the useful geographical economic factors and the potential high-speed rail express business volume through a K-means clustering algorithm.
Step S6 comprises the following substeps:
s61, mapping each geographic unit into candidate nodes of a K-means clustering algorithm one by one, and taking useful geographic economic factors and potential high-speed rail express delivery traffic of each geographic unit as attributes of corresponding candidate nodes to obtain a candidate node set:
Z＝{z 1 ,z 2 ,z 3 ,…，z N }
Figure BDA0003252768330000131
wherein Z is a candidate node set, Z 1 To z N Are respectively the 1 st to Nth candidate nodes, z p,1 To z p,I+1 Respectively 1 st to I +1 st attributes of the p candidate node, wherein I is the sum of useful geographic economic elements;
s62, setting the category number of the K-means clustering algorithm, optimizing the high-speed rail express special train transportation network according to the K-means clustering constraint and the K-means clustering objective function, and solving to obtain the optimal network node geographical position and the optimal network node jurisdiction of the high-speed rail express special train transportation network.
The K-means clustering objective function is:
Figure BDA0003252768330000132
Figure BDA0003252768330000133
where min is a function of the minimum, D R Is the comprehensive distance between samples of the K-means clustering algorithm, o k Is the kth cluster centroid, d (z) p ,o k ) Is the distance, w ', of the p-th candidate node to the k-th cluster centroid' kp The weight of the distance from the p candidate node to the K clustering centroid, K is the set class number, u p Is the abscissa, v, of the p-th candidate node p Is the ordinate, u, of the p-th candidate node k Is the abscissa, v, of the k-th cluster centroid k Is the ordinate of the kth cluster centroid.
The K-means clustering constraint is:
w′ kp ∈(0,1)
Figure BDA0003252768330000141
Figure BDA0003252768330000142
in order to not omit important information, the potential high-speed rail express delivery service volume and useful geographic economic factors are taken as the attributes of candidate nodes of a K-means clustering algorithm to form candidate nodes in a vector form, the K-means clustering algorithm is started to select the centroid and cluster the nodes according to the candidate nodes, the position of the centroid determined by iteration is the footfall of the optimal network node of the high-speed rail express delivery special train transportation network, and the clustering division result of the iteration is the respective jurisdiction division result of each optimal network node of the high-speed rail express delivery special train transportation network, so that the optimization of the high-speed rail express delivery special train transportation network is completed.
In the embodiment of the present invention, the constraint conditions of the K-means clustering algorithm further include: the high-speed rail express special network (a complete set of candidate nodes) is divided into K sub-networks, all the candidate nodes cannot belong to multiple sub-networks at the same time, and the K sub-networks cannot be empty sets. The sub-network is the centroid cluster of the K-means clustering algorithm, namely the respective jurisdiction of the optimal network node. The constraint condition is needed for making the scheme more fit with natural laws and engineering.
As shown in fig. 2, the high-speed rail express train transportation network optimization system according to the embodiment of the present invention adopts the high-speed rail express train transportation network optimization method, which includes: the system comprises a geographical economic attribute express demand analysis module, an express demand prediction module, a high-speed rail express share rate operation module and a high-speed rail express network planning module;
the geographical economic attribute express demand analysis module is used for establishing a geographical economic attribute express demand model and identifying useful geographical economic elements according to the geographical economic attribute express demand model;
the express demand forecasting module is used for collecting useful geographic economic factors and historical data of express business volume and training an express demand forecasting model; predicting the potential express business volume according to the current useful geographic economic factor data through an express demand prediction model;
the high-speed rail express sharing rate operation module is used for establishing and training a traffic express sharing rate model according to historical data of express business volume; solving the potential high-speed rail express delivery traffic through a traffic express delivery sharing rate model according to the potential express delivery traffic;
the high-speed rail express network planning module is used for optimizing the high-speed rail express special train transportation network according to useful geographical economic factors and potential high-speed rail express business volume through a K-means clustering algorithm.
As shown in fig. 3, a high-speed rail express train transportation network optimization device according to an embodiment of the present invention includes:
a memory for storing a computer program;
and the processor is used for realizing the steps of the high-speed rail express special train transportation network optimization method when executing the computer program.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for optimizing the high-speed rail express special train transportation network are realized.
In conclusion, the invention analyzes the relationship between express business volume and economic factors on geographical space distribution through the established geographical economic attribute express demand model, identifies useful geographical economic factors with high relevance, predicts the potential express business volume at each position on the potential geographical space through the express demand prediction model, researches the sharing rate of high-speed rail express through the traffic express sharing rate model, solves the potential high-speed rail express business volume, optimizes a high-speed rail express special train transportation network according to the useful geographical economic factors and the potential high-speed rail express business volume in the geographical space through a K-means clustering algorithm, effectively matches express demands, effectively utilizes transportation resources according to the actual sharing effect of the high-speed rail express, and solves the problems of incomplete planning and low efficiency of the high-speed rail express transportation network.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
It will be appreciated by those of ordinary skill in the art that the embodiments described herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited embodiments and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.

Claims (4)

1. A high-speed rail express special train transportation network optimization method is characterized by comprising the following steps:
s1, establishing a geographical economic attribute express demand model, and identifying useful geographical economic elements according to the geographical economic attribute express demand model, wherein the method comprises the following steps:
s11, establishing a geographical economic attribute express delivery demand model, wherein the geographical economic attribute express delivery demand model has the expression:
Figure FDA0004054737040000011
wherein q is i Express traffic for geographic unit i, (u) i ,v i ) Is the spatial coordinate of a geographic unit i, i being a closed interval [1, N ]]Positive integer of, N is the total number of geographic units, x i,j For the geographic unit ith geographic economic element, beta 0 (u i ,v i ) For the geographic unit i, the 0 th geographic economic element relevance, beta j (u i ,v i ) For the geographic unit ith geographic economic element relevance degree epsilon i I bias coefficients for geographic units, j is a closed interval [0]The positive integer inside, M is the total number of the geographic economic elements;
s12, estimating the geographic economic element association degree of the geographic economic attribute express delivery demand model by a weighted least square method, wherein the expression of the weighted least square method is as follows:
Figure FDA0004054737040000012
Figure FDA0004054737040000013
Figure FDA0004054737040000014
Figure FDA0004054737040000015
Figure FDA0004054737040000021
Figure FDA0004054737040000022
wherein,
Figure FDA0004054737040000023
estimating a vector for a degree of association of a geo-economic element of a geographical unit i, -based on the estimated degree of association>
Figure FDA0004054737040000024
For the geographic unit ith geographic economic element relevance degree beta j (u i ,v i ) W (i) is a weight matrix for geographic unit i, and->
Figure FDA0004054737040000025
Is a geographic unit i and a geographic unit i 0 Inter weight values, X is the economic element matrix, X T Is a transposed matrix of the economic element matrix X, b is a first inverse ratio coefficient, and>
Figure FDA0004054737040000026
from geographic cell i to geographic cell i 0 Distance of (i) 0 Is a closed interval [1, N]Positive integers in the express delivery system, q is an express delivery traffic vector, and e is the base number of a natural logarithm;
s13, evaluating the geographic economic element association degree estimation result through a Chichi information criterion method, and identifying useful geographic economic elements;
s2, collecting historical data of useful geographic economic factors and express delivery traffic, and training an express delivery demand prediction model; the express demand forecasting model comprises L express demand forecasting submodels, wherein L is a positive integer greater than 2; wherein, at least 1 express delivery demand prediction submodel is BP neural network, and it includes: an input layer, a hidden layer and an output layer; at least 1 express demand forecasting sub-model is a grey forecasting model; at least 1 express demand forecasting sub-model is a cubic exponential smoothing model; the output of each express demand forecasting sub-model obtains the output of the express demand forecasting model through the following weighting types:
Figure FDA0004054737040000027
Figure FDA0004054737040000028
Se′ m ＝Se m ×η e
Figure FDA0004054737040000029
wherein y is the output of the express demand prediction model, y m For the output of the mth express demand prediction submodel, α m Weighting coefficient, se, for the mth express demand forecasting submodel ′ m Average prediction error, se, of the mth express demand prediction submodel m An original average prediction error, eta, of the mth express delivery demand prediction submodel e C is a second inverse coefficient;
s3, forecasting the potential express business volume according to the current useful geographic economic factor data through an express demand forecasting model;
s4, establishing and training a traffic express sharing rate model according to historical data of express traffic; the expression of the traffic express sharing rate model is as follows:
Figure FDA0004054737040000031
U n ＝(γ n,1 T n -1 + n,2 C n + n,3 E n -1 )· n,4 · n · n,5 · n
wherein, P n Is the sharing rate of the nth traffic mode, U n Is the effect of the nth mode of transportation, H is the sum of modes of transportation, T n Time efficiency of the nth mode of transportation, gamma n,1 Is the time-dependent weight of the nth mode of transportation, C n For convenience of the nth mode of transportation, gamma n,2 Is the convenience weight of the nth mode of transportation, E n Cost of the nth mode of transportation, γ n,3 Is the cost weight of the nth mode of transportation, S n A factor of safety, gamma, for the nth mode of transportation n,4 Is the safety factor weight, R, of the nth mode of transportation n Is the reliability coefficient of the nth mode of transportation, gamma n,5 The reliability coefficient weight of the nth traffic mode;
s5, solving the potential high-speed rail express business volume through a traffic express sharing rate model according to the potential express business volume;
s6, optimizing the express special train transportation network of the high-speed rail according to the useful geographical economic factors and the potential express business volume of the high-speed rail through a K-means clustering algorithm, and comprising the following steps:
s61, mapping each geographic unit into candidate nodes of a K-means clustering algorithm one by one, and taking useful geographic economic factors and potential high-speed rail express delivery traffic of each geographic unit as attributes of corresponding candidate nodes to obtain a candidate node set:
Z＝{z 1 ,z 2 ,z 3 ,…,z N }
Figure FDA0004054737040000041
wherein Z is a candidate node set, Z 1 To z N Are respectively the 1 st to Nth candidate nodes, z p,1 To z p,I+1 Respectively 1 st to I +1 st attributes of the p candidate node, wherein I is the sum of useful geographic economic elements;
s62, setting the category number of a K-means clustering algorithm, optimizing the high-speed rail express special train transportation network according to K-means clustering constraint and a K-means clustering objective function, and solving to obtain the optimal network node geographical position and the optimal network node jurisdiction of the high-speed rail express special train transportation network;
the K-means clustering objective function is:
Figure FDA0004054737040000042
Figure FDA0004054737040000043
where min is a function of the minimum, D R Is the comprehensive distance between samples of the K-means clustering algorithm, o k Is the kth cluster centroid, d (z) p ,o k ) Is the distance, w ', of the p-th candidate node to the k-th clustered centroid' kp The weight of the distance from the p candidate node to the K clustering centroid, K is the set class number, u p Is the abscissa, v, of the p-th candidate node p Is the ordinate, u, of the p-th candidate node k Is the abscissa, v, of the k-th cluster centroid k Is the ordinate of the kth clustering centroid;
the K-means clustering constraint is:
w′ kp ∈(0,1)
Figure FDA0004054737040000044
Figure FDA0004054737040000051
2. a high-speed rail express train transportation network optimization system is characterized in that the high-speed rail express train transportation network optimization method according to claim 1 is adopted, and the method comprises the following steps: the system comprises a geographical economic attribute express demand analysis module, an express demand prediction module, a high-speed rail express sharing rate operation module and a high-speed rail express network planning module;
the geographical economic attribute express demand analysis module is used for establishing a geographical economic attribute express demand model and identifying useful geographical economic elements according to the geographical economic attribute express demand model;
the express delivery demand forecasting module is used for collecting useful geographic economic factors and historical data of express delivery business volume and training an express delivery demand forecasting model; predicting the potential express business volume according to the current useful geographic economic factor data through an express demand prediction model;
the express delivery sharing rate operation module for the high-speed rail is used for establishing and training a traffic express delivery sharing rate model according to historical data of express delivery service volume; solving the potential high-speed rail express delivery traffic through a traffic express delivery sharing rate model according to the potential express delivery traffic;
the high-speed rail express network planning module is used for optimizing the high-speed rail express special train transportation network according to useful geographical economic factors and potential high-speed rail express business volume through a K-means clustering algorithm.
3. The utility model provides a high-speed railway express delivery special train transportation network optimization equipment which characterized in that includes:
a memory for storing a computer program;
a processor for implementing the steps of the method for optimizing a high-speed rail express train transportation network according to claim 1 when executing the computer program.
4. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the steps of the high-speed rail express train transportation network optimization method of claim 1.
CN202111051062.1A 2021-09-08 2021-09-08 High-speed rail express special train transportation network optimization method and system Active CN113743671B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111051062.1A CN113743671B (en) 2021-09-08 2021-09-08 High-speed rail express special train transportation network optimization method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111051062.1A CN113743671B (en) 2021-09-08 2021-09-08 High-speed rail express special train transportation network optimization method and system

Publications (2)

Publication Number Publication Date
CN113743671A CN113743671A (en) 2021-12-03
CN113743671B true CN113743671B (en) 2023-04-07

Family

ID=78737177

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111051062.1A Active CN113743671B (en) 2021-09-08 2021-09-08 High-speed rail express special train transportation network optimization method and system

Country Status (1)

Country Link
CN (1) CN113743671B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117395685B (en) * 2023-10-30 2024-07-09 中国铁建电气化局集团有限公司 High-speed railway wireless network optimizing system based on artificial intelligence

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5863203A (en) * 1996-01-26 1999-01-26 Dowling College Intermodal transportation simulation system
CN101593320A (en) * 2009-03-27 2009-12-02 北京交通大学 A kind of multiple transportation modes combination capacity optimization method based on the transportation demand feature
CN105740982A (en) * 2016-02-01 2016-07-06 南昌航空大学 Quantification computing method of dominant transportation distance of freight transportation mode based on sharing rate function
CN110516869A (en) * 2019-08-22 2019-11-29 西南交通大学 A kind of combined airway railway traffic hinge network plan method for shipping field

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11295622B2 (en) * 2018-04-24 2022-04-05 Joby Aero, Inc. Determining VTOL departure time in an aviation transport network for efficient resource management
US20200364630A1 (en) * 2019-05-15 2020-11-19 Target Brands, Inc. System and method for managing transportation vessels

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5863203A (en) * 1996-01-26 1999-01-26 Dowling College Intermodal transportation simulation system
CN101593320A (en) * 2009-03-27 2009-12-02 北京交通大学 A kind of multiple transportation modes combination capacity optimization method based on the transportation demand feature
CN105740982A (en) * 2016-02-01 2016-07-06 南昌航空大学 Quantification computing method of dominant transportation distance of freight transportation mode based on sharing rate function
CN110516869A (en) * 2019-08-22 2019-11-29 西南交通大学 A kind of combined airway railway traffic hinge network plan method for shipping field

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
徐玉萍等.基于组合预测模型的铁路货运量预测研究.《铁道科学与工程学报》.2021,第18 卷(第1 期),第243-249页. *
朱木益.物流运输网络优化研究.《中国优秀博硕士学位论文全文数据库（硕士） 社会科学I辑》.2004,(第01期),J145-105. *
段力伟.铁路货运产品设计与服务网络优化理论与方法研究.《中国优秀硕士学位论文全文数据库 工程科技II辑》.2018,(第02期),C033-47. *
白杰.铁路货运产品市场分担率的研究.《铁道货运》.2018,第 36 卷(第 2 期),第10-14页. *

Also Published As

Publication number Publication date
CN113743671A (en) 2021-12-03

Similar Documents

Publication Publication Date Title
US11393341B2 (en) Joint order dispatching and fleet management for online ride-sharing platforms
Sáez et al. Hybrid adaptive predictive control for the multi-vehicle dynamic pick-up and delivery problem based on genetic algorithms and fuzzy clustering
CN113902011A (en) Urban rail transit short-time passenger flow prediction method based on cyclic neural network
CN111754025A (en) Public transport short-time passenger flow prediction method based on CNN + GRU
Qin et al. Reinforcement learning for ridesharing: A survey
CN111242395B (en) Method and device for constructing prediction model for OD (origin-destination) data
CN111242292A (en) OD data prediction method and system based on deep space-time network
CN113743671B (en) High-speed rail express special train transportation network optimization method and system
CN107194605A (en) Energy consumption estimation system and method
Lartey et al. XGBoost: a tree-based approach for traffic volume prediction
Jungel et al. Learning-based online optimization for autonomous mobility-on-demand fleet control
Yang et al. Dynamic Origin‐Destination Matrix Estimation Based on Urban Rail Transit AFC Data: Deep Optimization Framework with Forward Passing and Backpropagation Techniques
Rodríguez-Rueda et al. Origin–Destination matrix estimation and prediction from socioeconomic variables using automatic feature selection procedure-based machine learning model
Castagna et al. Demand-responsive rebalancing zone generation for reinforcement learning-based on-demand mobility
CN110674990B (en) Instant distribution path selection method and system with sliding window updating mechanism
Park et al. Demand forecasting of micro mobility using a gated recurrent unit
CN115170006A (en) Dispatching scheduling method, device, equipment and storage medium
Song et al. Vehicle relocation scheduling method for car sharing service system based on Markov chain and genetic algorithm
Sai et al. Forecasting air passenger data using various models
Agrawal A machine-learning framework for a novel 3-step approach for real-time taxi dispatching
CN113011512A (en) Traffic generation prediction method and system based on RBF neural network model
Papanikolaou Data-driven state space reconstruction of mobility on demand systems for sizing-rebalancing analysis
Ren Intelligent statistical analysis on the influence of industrial agglomeration on innovation efficiency by spatial econometric model
El Ouadi et al. Support vector machines and k-means to build implementation areas of bundling hubs
Li et al. A Multiline Customized Bus Planning Method Based on Reinforcement Learning and Spatiotemporal Clustering Algorithm

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20230825

Address after: 610031 north section of two ring road, Sichuan, Chengdu

Patentee after: SOUTHWEST JIAOTONG University

Patentee after: Chengdu International Railway Train Co.,Ltd.

Address before: 610031 north section of two ring road, Sichuan, Chengdu

Patentee before: SOUTHWEST JIAOTONG University

TR01 Transfer of patent right