CN113378337A - Urban public transport network optimization method based on passenger flow analysis - Google Patents

Urban public transport network optimization method based on passenger flow analysis Download PDF

Info

Publication number
CN113378337A
CN113378337A CN202110617753.7A CN202110617753A CN113378337A CN 113378337 A CN113378337 A CN 113378337A CN 202110617753 A CN202110617753 A CN 202110617753A CN 113378337 A CN113378337 A CN 113378337A
Authority
CN
China
Prior art keywords
algorithm
network optimization
public transport
bus
passenger flow
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.)
Pending
Application number
CN202110617753.7A
Other languages
Chinese (zh)
Inventor
刘磊
任子晖
王晓娟
赵玉坤
倪金林
曾永李
王井邵
王晓曦
陈习岺
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.)
Anhui Fuhuang Technology Co ltd
Original Assignee
Anhui Fuhuang Technology Co ltd
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 Anhui Fuhuang Technology Co ltd filed Critical Anhui Fuhuang Technology Co ltd
Priority to CN202110617753.7A priority Critical patent/CN113378337A/en
Publication of CN113378337A publication Critical patent/CN113378337A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Pure & Applied Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Analysis (AREA)
  • Physiology (AREA)
  • Genetics & Genomics (AREA)
  • Computational Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a city public transport network optimization method based on passenger flow analysis, which comprises the following steps: establishing a bus network optimization model, and inputting and checking related data; coding a genetic algorithm, initializing and generating a feasible bus line set; calculating population fitness; if the convergence requirement is met, the algorithm is ended, then decoding is carried out, and a bus network scheme is output; and if the convergence requirement is not met, replacing the previous generation group with the new generation group obtained by selection operation, crossover operation and mutation operation, and returning to the selection operation for circular execution until the algorithm is finished after the convergence requirement is met. The invention provides a passenger flow-based urban public transport network optimization model, and utilizes the traditional genetic algorithm to solve the model, so as to make a more reasonable public transport network and improve the operation efficiency of a public transport system.

Description

Urban public transport network optimization method based on passenger flow analysis
Technical Field
The invention relates to the technical field of public transport networks, in particular to a city public transport network optimization method based on passenger flow analysis.
Background
In recent years, economic construction of various large cities in China has achieved tremendous achievement, but the sustainable development of the cities is limited by the delay of construction of traffic infrastructure, and the problem of urban traffic congestion is urgently solved. The optimization of the public traffic network just adopts the form of subtraction to solve the problem, and compared with the 'addition' operation of expanding roads and increasing scale, the optimization has the advantages of small investment, quick effect, high efficiency and the like.
Genetic Algorithm (GA) is an adaptive global optimization probability search Algorithm formed by simulating the inheritance and evolution process of organisms in natural environment. The method uses the biological evolution law of survival, excellence and decline of the fittest for reference, and the basic idea is based on Darwin's evolutionary theory and Mendel's genetics. This algorithm was first proposed by professor j. holland, university of Michigan, usa, in the 70's 20 th century. As a global optimization search algorithm, GA has been successfully applied in the fields of combination optimization, function optimization, automatic control, production scheduling, image processing, machine learning, artificial life, data mining and the like due to the advantages of simplicity, universality, strong robustness, suitability for parallel processing, wide application range and the like.
The invention provides a passenger flow-based urban public transport network optimization model and solves the model by utilizing the traditional genetic algorithm aiming at the problem that the operation efficiency of a public transport system in the traditional public transport network optimization model is not too high, and the characteristic that the passenger flow characteristic dynamically changes along with time is combined, so that a more scientific and reasonable public transport network can be made.
Disclosure of Invention
The invention aims to provide a city public traffic network optimization method based on passenger flow analysis, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a city public transport network optimization method based on passenger flow analysis comprises the following steps:
establishing a bus network optimization model, and inputting and checking related data;
coding a genetic algorithm, initializing and generating a feasible bus line set;
calculating population fitness;
if the convergence requirement is met, the algorithm is ended, then decoding is carried out, and a bus network scheme is output;
and if the convergence requirement is not met, replacing the previous generation group with the new generation group obtained by selection operation, crossover operation and mutation operation, and returning to the selection operation for circular execution until the algorithm is finished after the convergence requirement is met.
As a further scheme of the invention: the bus network optimization model is as follows:
Figure BDA0003098252350000021
where w1, w2 are the corresponding coefficients: n is the number of traffic cells; vij is the amount of public traffic from traffic zone i to traffic zone j; tij is the total time (h) of bus trips from the traffic zone i to the traffic zone j, and Tij ═ S1 × T1+ S2 × T2+ S3 × T3+ S4 × T4, T1 is the walking time from the trip point to the corresponding station, T2 is the waiting time at the station, T3 is the transfer time, T4 is the on-vehicle time, Si is the correction coefficient, i ═ 1, 2, 3, 4; m is the number of bus lines; mk is the number of departure of the kth line; lk is the length of the k line
As a further scheme of the invention: the genetic algorithm encodes the following: encoding the decision variables into binary strings, namely a chromosome Xi; the relationship between precision and code length is as follows 2β-1＜(Xmax-Xmin)10α≤2β-1Precision, i.e. alpha bits after the decimal point, length, i.e. binary string dimension beta, where Xmax、XminRespectively, the upper and lower limits of the variable, for the decoding of the chromosome there is the following formula:
Figure BDA0003098252350000022
the individual codes are b1, b2, b3.
As a further scheme of the invention: the selection operation is also called replication or regeneration, and aims to directly inherit the optimized individuals to the next generation or generate new individuals through pairing exchange and then inherit the new individuals to the next generation, and adopts a method combining an optimal individual preservation method and a tournament selection method; the best individual preservation method is to directly copy the individuals with the highest fitness in the population to the next generation without pairing exchange; the tournament selection method comprises randomly selecting individuals from a group according to a certain number, and storing the individuals with high fitness in the next generation, wherein the number is called the scale of the tournament
As a further scheme of the invention: the cross-selection adopts a partial matching exchange operator suitable for the problem of the travel salesman, in the matching exchange operator operation, two exchange points are randomly generated, the area between the two exchange points is defined as a matching area, and the exchange operation of the matching areas of the two father strings is carried out
As a further scheme of the invention: and the planting condition of the algorithm is judged to be that whether the average fitness value of the individuals of the successive generations is unchanged or whether the variation value is smaller than a certain minimum threshold value is judged before the maximum generation is reached, if so, the iterative process of the algorithm is converged, and the algorithm is ended.
Compared with the prior art, the invention provides the passenger flow-based urban public transport network optimization model, and utilizes the traditional genetic algorithm to solve the model, so as to make a more reasonable public transport network, thereby improving the operation efficiency of the public transport system.
Drawings
Fig. 1 is a flow chart of a city bus network optimization method based on passenger flow analysis.
Detailed Description
The technical solution of the present patent will be described in further detail with reference to the following embodiments.
Referring to fig. 1, a city bus network optimization method based on passenger flow analysis includes a bus network optimization model and genetic algorithm optimization.
1. Bus network optimization model
Considering the reasonability and realizability of the model in the practical application process, the model is constructed as follows:
Figure BDA0003098252350000031
where w1, w2 are the corresponding coefficients: n is the number of traffic cells; vij is the amount of public traffic (number of people) from traffic zone i to traffic zone j; tij is the total time (h) of bus trips from the traffic zone i to the traffic zone j, and Tij ═ S1 × T1+ S2 × T2+ S3 × T3+ S4 × T4, T1 is the walking time from the trip point to the corresponding station, T2 is the waiting time at the station, T3 is the transfer time, T4 is the on-vehicle time, and Si is the correction coefficient (i ═ 1, 2, 3, 4); m is the number of bus lines; mk is the number of vehicles dispatched on the kth line (vehicle/h); lk is the length (km) of the kth line.
2. Genetic algorithm
2.1 genetic Algorithm selection
The model of the public traffic network is a combined optimization problem of a plurality of lines, belongs to a multi-constraint 0-1 planning problem in mathematical planning, and constrains the network, the lines and the points by the model, so that the number of feasible networks is reduced, and certain calculation time is saved; because the mathematical programming model is typical, an enumeration method may be adopted to obtain an optimal solution, but the calculation amount is too large, so that the method is unrealistic in many times; the genetic algorithm has strong advantages in solving the problems due to the characteristics of the genetic algorithm, so that the genetic algorithm is adopted for solving the model in the embodiment.
2.2 optimization step of genetic Algorithm
(1) Encoding
The decision variables are encoded as a binary string, i.e. one chromosome Xi. The relationship between precision (alpha bits after a decimal point) and code length (binary string dimension beta) is as follows 2β-1＜(Xmax-Xmin)10α≤2β-1In the formula, Xmax、XminUpper and lower limits of the variables, respectively, for decoding of the chromosomes there is the following formula:
Figure BDA0003098252350000041
the individual code is b1, b2, b3..
(2) And (5) initializing.
(3) And (4) selecting parameters.
(4) And calculating population fitness.
(5) Selection operation
The selection operation is also called replication or regeneration, and aims to directly inherit the optimized individuals to the next generation or generate new individuals through pairing exchange and then inherit the new individuals to the next generation. In this context, a method of combining the best individual preservation method (elitist model) with the tournament selection method (burden selection model) is employed. Wherein: the best individual preservation method is to directly copy the individuals with the highest fitness in the population into the next generation without pairing exchange. The tournament selection method is to randomly select individuals from a group according to a certain number (called the tournament scale) and store the individuals with high fitness in the next generation.
(6) Crossing
A partial matched swap operator (PMX) for use in a Travel Salesman Problem (TSP) is used herein. PMX operations were proposed by Goldberg and line in 1985. In PMX operation, two exchange points are generated randomly, the area between two exchange points is defined as a matching area, and the matching of two father strings is carried out
The switching of the zones is performed.
(7) And (5) performing mutation operation.
(8) Determination of termination condition
Before reaching the maximum generation, judging whether the average fitness value of the individuals of the successive generations is unchanged or the variation value is smaller than a certain minimum threshold value, if so, converging the iterative process of the algorithm, and ending the algorithm; otherwise, replacing the previous generation population with the new generation population obtained through selection, crossing and mutation, and returning to the selection operation for continuous circular execution.
Although the preferred embodiments of the present patent have been described in detail, the present patent is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present patent within the knowledge of those skilled in the art.

Claims (6)

1. A city public transport network optimization method based on passenger flow analysis is characterized by comprising the following steps:
establishing a bus network optimization model, and inputting and checking related data;
coding a genetic algorithm, initializing and generating a feasible bus line set;
calculating population fitness;
if the convergence requirement is met, the algorithm is ended, then decoding is carried out, and a bus network scheme is output;
and if the convergence requirement is not met, replacing the previous generation group with the new generation group obtained by selection operation, crossover operation and mutation operation, and returning to the selection operation for circular execution until the algorithm is finished after the convergence requirement is met.
2. The city bus network optimization method based on passenger flow analysis as claimed in claim 1, wherein the bus network optimization model is as follows:
Figure FDA0003098252340000011
where w1, w2 are the corresponding coefficients: n is the number of traffic cells; vij is the mass transit passenger from traffic zone i to traffic zone j; tij is the total time (h) of bus trips from the traffic zone i to the traffic zone j, and Tij is S1T 1+ S2T 2+ S3T 3+ S4T 4, T1 is the walking time from the trip point to the corresponding station, T2 is the waiting time at the station, T3 is the transfer time, T4 is the time, Si is the correction coefficient, i is 1, 2, 3, 4; m is the number of bus lines; mk is the number of departure of the kth line; lk is the length of the kth line.
3. The city bus net optimization method based on passenger flow analysis as claimed in claim 1, wherein the genetic algorithm code is as follows: encoding the decision variables into binary strings, namely a chromosome Xi;
the relationship between precision and code length is as follows 2β-1＜(Xmax-Xmin)10α≤2β-1Precision, i.e. alpha bits after the decimal point, length, i.e. binary string dimension beta, where Xmax、XminRespectively, the upper and lower limits of the variable, for the decoding of the chromosome there is the following formula:
Figure FDA0003098252340000012
the individual code is b1, b2, b3..
4. The method as claimed in claim 1, wherein the selection operation is also called replication or regeneration, and aims to directly inherit the optimized individuals to the next generation or generate new individuals through pairing exchange and then inherit the new individuals to the next generation, and adopts a method combining an optimal individual preservation method and a tournament selection method; the best individual preservation method is that the individuals with the highest fitness in the population are directly copied to the next generation without pairing exchange; the tournament selection method is to randomly select individuals from a group according to a certain number, and store the individuals with high fitness in the next generation, wherein the number is called the tournament scale.
5. The method as claimed in claim 1, wherein the cross-selection uses a partial match-exchange operator adapted to the problem of the travel salesperson, and during the match-exchange operator operation, two exchange points are randomly generated, and the area between the two exchange points is defined as a matching area, and the exchange operation of the matching areas of the two father strings is performed.
6. The method as claimed in claim 1, wherein the planting condition for the algorithm end is determined as whether the average fitness value of successive generations is unchanged or the variation value is smaller than a certain minimum threshold before the maximum generation is reached, if so, the iterative process of the algorithm converges, and the algorithm ends.
CN202110617753.7A 2021-06-03 2021-06-03 Urban public transport network optimization method based on passenger flow analysis Pending CN113378337A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110617753.7A CN113378337A (en) 2021-06-03 2021-06-03 Urban public transport network optimization method based on passenger flow analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110617753.7A CN113378337A (en) 2021-06-03 2021-06-03 Urban public transport network optimization method based on passenger flow analysis

Publications (1)

Publication Number Publication Date
CN113378337A true CN113378337A (en) 2021-09-10

Family

ID=77575483

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110617753.7A Pending CN113378337A (en) 2021-06-03 2021-06-03 Urban public transport network optimization method based on passenger flow analysis

Country Status (1)

Country Link
CN (1) CN113378337A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105205557A (en) * 2015-09-17 2015-12-30 华南理工大学 Design method for conventional urban public transit network
CN105915121A (en) * 2016-05-31 2016-08-31 西安交通大学 Servo system inertia identification method adopting genetic algorithm for optimization
CN106779163A (en) * 2016-11-18 2017-05-31 华南理工大学 A kind of customization transit network planning method based on intelligent search
CN109948865A (en) * 2019-04-01 2019-06-28 东华大学 A kind of TSP problem paths planning method
CN110807525A (en) * 2019-10-29 2020-02-18 中国民航大学 Neural network flight guarantee service time estimation method based on improved genetic algorithm

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105205557A (en) * 2015-09-17 2015-12-30 华南理工大学 Design method for conventional urban public transit network
CN105915121A (en) * 2016-05-31 2016-08-31 西安交通大学 Servo system inertia identification method adopting genetic algorithm for optimization
CN106779163A (en) * 2016-11-18 2017-05-31 华南理工大学 A kind of customization transit network planning method based on intelligent search
CN109948865A (en) * 2019-04-01 2019-06-28 东华大学 A kind of TSP problem paths planning method
CN110807525A (en) * 2019-10-29 2020-02-18 中国民航大学 Neural network flight guarantee service time estimation method based on improved genetic algorithm

Similar Documents

Publication Publication Date Title
WO2022193642A1 (en) Reservoir scheduling multi-objective optimization method based on graph convolutional network and nsga-ii
WO2018161468A1 (en) Global optimization, searching and machine learning method based on lamarck acquired genetic principle
Yadav et al. An overview of genetic algorithm and modeling
CN107122843A (en) A kind of traveling salesman problem method for solving based on improved adaptive GA-IAGA
CN109902808B (en) Method for optimizing convolutional neural network based on floating point digital variation genetic algorithm
CN111526555B (en) Multi-hop routing path selection method based on genetic algorithm
CN108241911B (en) Distribution center site selection method based on bacterial foraging optimization algorithm
CN104867062A (en) Low-loss power distribution network optimization and reconfiguration method based on genetic algorithm
CN115391385A (en) Database query optimization method based on ant colony genetic dynamic fusion algorithm
CN114580762A (en) Hydrological forecast error correction method based on XGboost
CN114158105B (en) Routing method and device of wireless sensor network applied to comprehensive energy system
CN109284818A (en) A kind of blasting vibration control prediction technique based on accident tree and genetic algorithm
CN108665068A (en) The improved adaptive GA-IAGA of water distribution hydraulic model automatic Check problem
CN111724004B (en) Reservoir available water supply amount forecasting method based on improved quantum wolf algorithm
CN109002878A (en) A kind of GA Optimized BP Neural Network
CN113378337A (en) Urban public transport network optimization method based on passenger flow analysis
CN112800673A (en) Method for predicting blasting block degree based on SA-GA-BP algorithm
WO2023088131A1 (en) Traffic state prediction method and apparatus, and device, medium and program
CN107346468A (en) The product design method of case-based reasioning
CN103116805B (en) A kind of segmentation replacement method upgrading genetic groups
CN107679326B (en) A kind of two-value FPRM circuit area and the comprehensive optimization method that is delayed
CN112036654B (en) Photovoltaic power station and electric vehicle charging network planning method based on co-evolution
CN115422823A (en) Wire rod beveling blanking method based on parallel grouping genetic algorithm
CN112183843B (en) Load optimization distribution method for thermal power plant based on hybrid intelligent algorithm
CN111209679B (en) Genetic algorithm-based spatial interpolation method for heavy metal content in soil

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210910

RJ01 Rejection of invention patent application after publication