CN116502976A - Multi-type intermodal junction process layout method and system - Google Patents

Multi-type intermodal junction process layout method and system Download PDF

Info

Publication number
CN116502976A
CN116502976A CN202310766207.9A CN202310766207A CN116502976A CN 116502976 A CN116502976 A CN 116502976A CN 202310766207 A CN202310766207 A CN 202310766207A CN 116502976 A CN116502976 A CN 116502976A
Authority
CN
China
Prior art keywords
index
junction
area
indexes
loading
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.)
Granted
Application number
CN202310766207.9A
Other languages
Chinese (zh)
Other versions
CN116502976B (en
Inventor
张琨
贺宜
光振雄
董云松
雷崇
殷勤
邱绍峰
周明翔
李加祺
刘辉
张俊岭
彭方进
李成洋
张煜
万程鹏
梅杰
罗小华
范沛
张涛
张银龙
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.)
China Railway Siyuan Survey and Design Group Co Ltd
Original Assignee
Wuhan Guide Intelligent Technology Co ltd
China Railway Siyuan Survey and Design Group 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 Wuhan Guide Intelligent Technology Co ltd, China Railway Siyuan Survey and Design Group Co Ltd filed Critical Wuhan Guide Intelligent Technology Co ltd
Priority to CN202310766207.9A priority Critical patent/CN116502976B/en
Publication of CN116502976A publication Critical patent/CN116502976A/en
Application granted granted Critical
Publication of CN116502976B publication Critical patent/CN116502976B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • 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
    • G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Educational Administration (AREA)
  • Biophysics (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Physiology (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Genetics & Genomics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a multi-type intermodal hub process layout method and system, which belong to the technical field of multi-type intermodal layout and comprise the following steps: the indexes are sequenced, and then the loading and unloading process scheme is evaluated by using a mutation progression method, so that the loading and unloading process scheme is optimized; after the geographic position, the task amount, the operation flow and the like of the multi-type intermodal junction point are analyzed, the area of each operation area is calculated according to the throughput; analyzing the logistics relationship and the non-logistics relationship among the operation areas to obtain an initial layout scheme of the operation areas; the objective function with the lowest cargo handling cost, the shortest transportation time and the greatest layout area utilization rate is established, related constraint is set to reduce potential safety hazards caused by transportation equipment path interference caused by the fact that a storage yard is divided by a track or a highway, and an improved genetic algorithm is used for solving the potential safety hazards to obtain the plane layout of an optimized operation area, so that effective support is provided for matching different transportation modes of the intermodal junction through a layout process, and the operation efficiency of the intermodal junction is improved.

Description

Multi-type intermodal junction process layout method and system
Technical Field
The invention relates to the technical field of multi-type intermodal distribution, in particular to a multi-type intermodal hub process distribution method and system.
Background
In the multi-modal scenario, there is a certain requirement for the layout of the overall hub, since the transportation mode is usually complicated, such as container dispatch transportation.
The existing multi-type intermodal hub process layout is usually manually planned and scheduled, so that the problems of serious mismatching of scheduling resources, low scheduling efficiency and the like exist, and the problems of unbalanced development of infrastructure, old intermodal organization mode and the like also exist, so that the daily logistics transportation efficiency is greatly reduced, and the rapid development of logistics industry is restricted.
Therefore, there is a need to propose a rational, highly automated, guidance method for the process layout of a multi-modal intermodal junction.
Disclosure of Invention
The invention provides a multi-type intermodal junction process layout method and system, which are used for solving the defects that the layout planning for the multi-type intermodal junction process in the prior art is too dependent on manpower, and the planning layout is low in efficiency and low in accuracy.
In a first aspect, the present invention provides a multi-modal junction process layout method comprising:
constructing an index system according to operation equipment, loading and unloading processes and operation modes of the multi-type intermodal junction, and sequencing indexes in the index system to obtain sequenced indexes;
Performing standardization processing on the sequenced indexes to obtain standardized indexes, calculating the standardized indexes by using a mutation level number method to obtain mutation level values, and screening the historical container throughput of the multi-type intermodal junction according to the mutation level values;
inputting the historical container throughput into a preset neural network model to obtain the predicted throughput of the multi-type intermodal junction and the area of each operation area;
and constructing an objective function based on the predicted throughput, determining a preset constraint condition to solve the objective function, and combining the areas of the working areas through a preset genetic algorithm to obtain the optimized planar layout of the working areas.
According to the method for arranging the multi-type intermodal junction technology provided by the invention, an index system is constructed according to the operation equipment, the loading and unloading technology and the operation mode of the multi-type intermodal junction, indexes in the index system are ordered to obtain ordered indexes, and the method comprises the following steps:
determining a carbon emission index according to the energy consumption of the loading and unloading equipment and the carbon emission coefficient of the fuel oil;
the sound pressure and the reference sound pressure are generated by the operation of the replacement equipment, and the noise pollution index is determined;
based on the cargo misalignment coefficient, cargo load, cargo sliding distance and primary breaking coefficient, obtaining cargo wear rate, and determining cargo safety indexes according to the cargo wear rate;
Determining an operation personnel safety index according to the casualties of the loading and unloading personnel;
determining loading and unloading efficiency indexes of the reloading equipment according to the workload of the reloading equipment and the operation time of the reloading equipment;
according to the unloading time of the container from the ship, the time from the ship to the yard and the time from the yard to the train, the loading and unloading total time is obtained, and the loading and unloading time index is determined according to the loading and unloading total time;
determining equipment failure rate indexes according to the actual loading and unloading time of the loading and unloading equipment and the planned loading and unloading time of the loading and unloading equipment;
acquiring operation cost, loading and unloading cost and operator wages, and determining an operation cost index;
determining a site utilization index by the occupied area of the container in the storage yard and the total area of the storage yard;
and sorting the carbon emission index, the noise pollution index, the cargo safety index, the worker safety index, the replacement equipment loading and unloading efficiency index, the loading and unloading time index, the equipment failure rate index, the operation cost index and the site utilization rate index respectively to obtain the sorted indexes.
According to the multi-joint transportation hub process layout method provided by the invention, the standardized processing is carried out on the sequenced indexes to obtain standardized indexes, and the method comprises the following steps:
Acquiring any index maximum value, any index minimum value, total loading and unloading processes and total indexes;
and calculating the standardized index based on the maximum value of any index, the minimum value of any index, the total number of loading and unloading processes and the total number of indexes.
According to the method for arranging the multi-type intermodal junction technology provided by the invention, the mutation level number is obtained by calculating the standardized index by using a mutation level number method, and the historical container throughput of the multi-type intermodal junction is screened according to the mutation level number, and the method comprises the following steps:
dividing any standardized index by the sum of any standardized index in all loading and unloading processes to obtain a dimensionless data value of any standardized index;
obtaining a first weight of any index based on the dimensionless data value of any standardized index, the total number of unloading processes and the total number of indexes;
obtaining weight vectors of all indexes, and weighting by utilizing the weight vectors of all indexes and the standardized indexes to obtain a standardized decision matrix;
determining the dispersion sum of the index value of any index and the index values of all other schemes, and summing the dispersion sums of all the indexes to obtain total dispersion;
Constructing a dispersion optimization model according to the total dispersion, and determining a second weight of any index by the dispersion optimization model;
averaging the first weight of any index and the second weight of any index to obtain weight of any index;
the historical container throughput of the multi-modal junction is filtered based on the arbitrary index weight.
According to the multi-modal junction process layout method provided by the invention, the objective function is constructed based on the predicted throughput, and the method comprises the following steps:
the product of the daily goods carrying frequency, the Manhattan distance and the single unit distance carrying cost between any two operation areas is summed in the range of all the operation areas and then multiplied by a first weight factor and a first dimensionality factor respectively to obtain a first objective subfunction;
multiplying the daily average cargo carrying frequency between any two working areas by Manhattan distance, dividing the Manhattan distance by carrying speed, summing the Manhattan distance and the Manhattan distance by carrying speed in the whole working area, and multiplying the Manhattan distance and the Manhattan distance by a second weight factor and a second dimensionless factor respectively to obtain a second objective subfunction;
multiplying the length of the horizontal side of any operation area with the length of the vertical side of any operation area, dividing the length by the total length of the multi-type intermodal junction and the total width of the multi-type intermodal junction in sequence, summing the lengths in the whole operation area range, and multiplying the sum with a third weight factor to obtain a third objective subfunction;
Adding the first objective subfunction, the second objective subfunction and the third objective subfunction to obtain the objective function;
the first dimensionless factor is obtained by multiplying the single unit distance conveying cost between any two working areas by the daily cargo conveying frequency and the maximum Manhattan distance respectively, then internally dividing the sum in the range of all the working areas, and then obtaining the reciprocal;
the second dimensionless factor is obtained by dividing the average value of the cargo carrying speed between any two working areas by the sum of the product of the average daily cargo carrying frequency and the maximum Manhattan distance in the whole working area range.
According to the multi-junction process layout method provided by the invention, the determining of the preset constraint condition solves the objective function, and the method comprises the following steps:
determining that the absolute value of the difference between the x axis of any operation area and the x axis of any other area is larger than or equal to the average value of the sum of the lengths of the horizontal edges of any operation area and the lengths of the horizontal edges of any other area plus the minimum distance in the horizontal direction, and the absolute value of the difference between the y axis of any operation area and the y axis of any other area is larger than or equal to the average value of the sum of the lengths of the vertical edges of any operation area and the lengths of the vertical edges of any other area plus the minimum distance in the vertical direction, so as to obtain the non-overlapping constraint condition of the operation area;
Determining that the x-axis of any operation area is larger than or equal to the sum of half of the length of the horizontal edge of the any operation area and the minimum distance in the horizontal direction, and the y-axis of any operation area is larger than or equal to the sum of half of the length of the vertical edge of the any operation area and the minimum distance in the vertical direction, so as to obtain the operation area channel constraint condition;
determining that the total length of any operation area x-axis is smaller than or equal to the total length of the multi-type intermodal junction, sequentially reducing half of the length of the horizontal edge of any operation area and the minimum distance in the horizontal direction, and the total width of any operation area y-axis is smaller than or equal to the total width of the multi-type intermodal junction, sequentially reducing half of the length of the vertical edge of any operation area and the minimum distance in the vertical direction, so as to obtain a junction field size constraint condition;
determining that the half of the length of the horizontal side of any operation area is subtracted from the x axis of any operation area, the half of the length of the horizontal side of any operation area is added to the x axis of any operation area, the half of the length of the vertical side of any operation area is subtracted from the y axis of any operation area, and the half of the length of the vertical side of any operation area is not in a preset fixed area range in the hinge, so as to obtain a fixed area constraint condition;
and multiplying the daily average cargo carrying frequency between any two working areas by the single unit distance carrying cost and the carrying speed in sequence, dividing the daily average cargo carrying frequency between any two working areas by the average cargo carrying speed between any two working areas, and summing the daily average cargo carrying frequency between any two working areas to obtain the objective function adjustment factor.
According to the multi-type intermodal junction process layout method provided by the invention, the optimized operation area plane layout is obtained by combining the areas of the operation areas through a preset genetic algorithm, and the method comprises the following steps:
determining an intermodal junction scheme as a chromosome of the preset genetic algorithm, wherein each operation area is a gene of the preset genetic algorithm;
acquiring an initial layout scheme of the intermodal hub, taking the initial layout scheme of the intermodal hub as an initial code, and randomly generating other codes;
determining an operator by using the roulette strategy by taking the objective function as an adaptive function;
if any operator is determined to be smaller than or equal to an individual average adaptation value, dividing the difference between any operator and an individual minimum adaptation value by the difference between the individual average adaptation value and the individual minimum adaptation value, adding an initial lower limit parameter of the crossover probability to obtain an adaptive crossover operator, otherwise, dividing the difference between any operator and the individual average adaptation value by the difference between an individual maximum adaptation value and the individual average adaptation value, and adding an initial upper limit parameter of the crossover probability to obtain the adaptive crossover operator;
determining a mutation probability initial lower limit parameter and a mutation probability initial upper limit parameter of each round, taking an adaptive crossover operator of each round as an initial operator, and repeating the calculation process of the adaptive crossover operator to obtain an adaptive mutation operator;
If the adaptability before the individual operation is determined to be greater than the adaptability after the individual operation, randomly determining genes at any two positions to carry out exchange sequencing, otherwise, not executing the exchange sequencing operation;
iteratively generating an initial layout of the operation area plane based on the preset constraint condition;
and decoding the initial layout of the operation area plane, and outputting the optimized operation area plane layout.
In a second aspect, the present invention also provides a multiple intermodal hub process layout system comprising:
the construction module is used for constructing an index system according to the operation equipment, the loading and unloading process and the operation mode of the multi-type intermodal junction, and sequencing the indexes in the index system to obtain sequenced indexes;
the standardized module is used for carrying out standardized treatment on the sequenced indexes to obtain standardized indexes, calculating the standardized indexes by using a mutation level number method to obtain mutation level values, and screening the historical container throughput of the multi-type intermodal junction according to the mutation level values;
the calculation module is used for inputting the historical container throughput into a preset neural network model to obtain the predicted throughput of the multi-type intermodal junction and the area of each operation area;
And the optimization module is used for constructing an objective function based on the predicted throughput, determining a preset constraint condition to solve the objective function, and combining the areas of the working areas through a preset genetic algorithm to obtain the optimized plane layout of the working areas.
In a third aspect, the present invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing any of the above-described multi-junction process layout methods when the program is executed.
In a fourth aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a multi-modal junction process layout method as described in any one of the above.
According to the multi-joint transportation hub process layout method and system, indexes are ordered, and then the loading and unloading process scheme is evaluated by using a mutation progression method, so that the loading and unloading process scheme is optimized; after the geographic position, the task amount, the operation flow and the like of the multi-type intermodal junction point are analyzed, the area of each operation area is calculated according to the throughput; analyzing the logistics relationship and the non-logistics relationship among the operation areas to obtain an initial layout scheme of the operation areas; the objective function with the lowest cargo handling cost, the shortest transportation time and the greatest layout area utilization rate is established, related constraint conditions are set to reduce potential safety hazards caused by transportation equipment path interference caused by the fact that a storage yard is divided by a track or a highway, and an improved genetic algorithm is used for solving the potential safety hazards to obtain the plane layout of an optimized operation area, so that effective support is provided for matching different transportation modes of the intermodal junction through a layout process, and the operation efficiency of the intermodal junction is improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a multi-modal junction process layout method provided by the present invention;
FIG. 2 is a schematic diagram of a multi-junction process layout system according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
FIG. 1 is a flow chart of a multi-junction process layout method according to an embodiment of the present invention, as shown in FIG. 1, including:
step 100: constructing an index system according to operation equipment, loading and unloading processes and operation modes of the multi-type intermodal junction, and sequencing indexes in the index system to obtain sequenced indexes;
step 200: performing standardization processing on the sequenced indexes to obtain standardized indexes, calculating the standardized indexes by using a mutation level number method to obtain mutation level values, and screening the historical container throughput of the multi-type intermodal junction according to the mutation level values;
step 300: inputting the historical container throughput into a preset neural network model to obtain the predicted throughput of the multi-type intermodal junction and the area of each operation area;
step 400: and constructing an objective function based on the predicted throughput, determining a preset constraint condition to solve the objective function, and combining the areas of the working areas through a preset genetic algorithm to obtain the optimized planar layout of the working areas.
It should be noted that "multi-type intermodal" in the embodiments of the present invention refers to a transportation process that is jointly completed by two or more vehicles being engaged with each other and transported, which is also called compound transportation.
Specifically, the embodiment of the invention firstly acquires the operation equipment, the loading and unloading process and the operation mode of the multi-type intermodal junction, constructs an index system and sorts indexes in the index system, wherein the loading and unloading process is formed by mutually combining the loading and unloading equipment.
And secondly, carrying out standardization treatment on indexes in an index system, calculating mutation grade values of the indexes subjected to standardization treatment by using a mutation grade method, and screening schemes of the multi-type intermodal junction process layout according to the mutation grade values.
And taking the historic container throughput of the railway logistics center, the port and the aviation logistics station as the input of the neural network, respectively obtaining the predicted throughput of the railway logistics center, the port and the aviation logistics station, and obtaining the area of each operation area.
Finally, by establishing an objective function and setting constraint conditions of the objective function, the goods handling cost, the transportation time and the layout area utilization rate of the multi-type intermodal hub process layout are the lowest according to the logistics relation and the non-logistics relation among all the operation areas, and the optimized plane layout of the operation areas is obtained by combining the areas of all the operation areas through a genetic algorithm.
According to the invention, indexes are sequenced, and then the loading and unloading process scheme is evaluated by using a mutation progression method, so that the loading and unloading process scheme is optimized; after the geographic position, the task amount, the operation flow and the like of the multi-type intermodal junction point are analyzed, the area of each operation area is calculated according to the throughput; analyzing the logistics relationship and the non-logistics relationship among the operation areas to obtain an initial layout scheme of the operation areas; the objective function with the lowest cargo handling cost, the shortest transportation time and the greatest layout area utilization rate is established, related constraint conditions are set to reduce potential safety hazards caused by transportation equipment path interference caused by the fact that a storage yard is divided by a track or a highway, and an improved genetic algorithm is used for solving the potential safety hazards to obtain the plane layout of an optimized operation area, so that effective support is provided for matching different transportation modes of the intermodal junction through a layout process, and the operation efficiency of the intermodal junction is improved.
On the basis of the above embodiment, according to the operation equipment, the loading and unloading process and the operation mode of the multi-type intermodal junction, an index system is constructed, and the indexes in the index system are ordered to obtain ordered indexes, including:
determining a carbon emission index according to the energy consumption of the loading and unloading equipment and the carbon emission coefficient of the fuel oil;
The sound pressure and the reference sound pressure are generated by the operation of the replacement equipment, and the noise pollution index is determined;
based on the cargo misalignment coefficient, cargo load, cargo sliding distance and primary breaking coefficient, obtaining cargo wear rate, and determining cargo safety indexes according to the cargo wear rate;
determining an operation personnel safety index according to the casualties of the loading and unloading personnel;
determining loading and unloading efficiency indexes of the reloading equipment according to the workload of the reloading equipment and the operation time of the reloading equipment;
according to the unloading time of the container from the ship, the time from the ship to the yard and the time from the yard to the train, the loading and unloading total time is obtained, and the loading and unloading time index is determined according to the loading and unloading total time;
determining equipment failure rate indexes according to the actual loading and unloading time of the loading and unloading equipment and the planned loading and unloading time of the loading and unloading equipment;
acquiring operation cost, loading and unloading cost and operator wages, and determining an operation cost index;
determining a site utilization index by the occupied area of the container in the storage yard and the total area of the storage yard;
and sorting the carbon emission index, the noise pollution index, the cargo safety index, the worker safety index, the replacement equipment loading and unloading efficiency index, the loading and unloading time index, the equipment failure rate index, the operation cost index and the site utilization rate index respectively to obtain the sorted indexes.
Specifically, after the operation equipment, the loading and unloading process and the operation mode of the multi-mode intermodal junction are obtained, the related index system is constructed, indexes in the index system are ordered, and the loading and unloading process is formed by mutually combining the loading and unloading equipment.
The index system is constructed by the following steps:
(1) Carbon emission index:
wherein, the liquid crystal display device comprises a liquid crystal display device,is carbon emission amount->For the energy consumption of the loading and unloading device, +.>Is the carbon emission coefficient of the fuel.
(2) Noise pollution index:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing noise pollution value, < >>Indicating replacement of equipmentSound pressure generated during the industrial process +.>The reference sound pressure is shown.
(3) Cargo safety index:
wherein Q represents the wear rate of the cargo,representing the misalignment coefficient of the goods, +.>Indicating load of goods->Indicating the sliding distance of the goods->Representing the primary snap-off coefficient.
(4) Safety index of operators:
wherein, the liquid crystal display device comprises a liquid crystal display device,safety index for loading and unloading personnel>Indicating the casualties of loading and unloading personnel.
(5) Loading and unloading efficiency indexes:
wherein, the liquid crystal display device comprises a liquid crystal display device,representation exchangeMounting and dismounting efficiency of mounting equipment->Indicating the amount of work of the replacement device +.>Indicating the operation time of the reloading equipment.
(6) Loading and unloading time index:
wherein, the liquid crystal display device comprises a liquid crystal display device, Indicating total loading and unloading time,/->Indicating the time required for the container to be removed from the ship, < >>Indicating the time to hang the container from the ship to the yard,/->Representing the space required to hoist a container from a yard to a train.
(7) The equipment failure rate index:
wherein, the liquid crystal display device comprises a liquid crystal display device,indicating the failure rate of the respective handling device, +.>Indicating the actual loading and unloading time of the loading and unloading device, < >>Indicating the planned loading and unloading time of the loading and unloading equipment.
(8) Operation cost index:
the operation cost refers to the operation cost, the loading and unloading cost and the wages of operators.
(9) The field utilization index:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing the area occupied by the container in the yard +.>And the total area of the storage yard->Ratio of the two components.
Further, the indexes are respectively sequenced to obtain an overall sequenced index.
On the basis of the above embodiment, performing normalization processing on the sorted indexes to obtain normalized indexes includes:
acquiring any index maximum value, any index minimum value, total loading and unloading processes and total indexes;
and calculating the standardized index based on the maximum value of any index, the minimum value of any index, the total number of loading and unloading processes and the total number of indexes.
Specifically, in order to facilitate comparison and subsequent data processing, the embodiment of the invention performs standardization processing on the indexes in the index system, calculates mutation level values of the indexes after standardization processing by using a mutation level method, and screens a scheme of the multi-junction transportation hub process layout according to the mutation level values.
The standardized processing of the indexes in the index system comprises the following steps:
wherein, the liquid crystal display device comprises a liquid crystal display device,indicate->Maximum value of row; />Indicate->The minimum value of the row, m, represents the number of handling processes and n represents the number of indexes.
On the basis of the above embodiment, calculating the standardized index by using a mutation level method to obtain a mutation level value, and screening the historical container throughput of the multi-type intermodal junction according to the mutation level value, including:
dividing any standardized index by the sum of any standardized index in all loading and unloading processes to obtain a dimensionless data value of any standardized index;
obtaining a first weight of any index based on the dimensionless data value of any standardized index, the total number of unloading processes and the total number of indexes;
obtaining weight vectors of all indexes, and weighting by utilizing the weight vectors of all indexes and the standardized indexes to obtain a standardized decision matrix;
determining the dispersion sum of the index value of any index and the index values of all other schemes, and summing the dispersion sums of all the indexes to obtain total dispersion;
constructing a dispersion optimization model according to the total dispersion, and determining a second weight of any index by the dispersion optimization model;
Averaging the first weight of any index and the second weight of any index to obtain weight of any index;
the historical container throughput of the multi-modal junction is filtered based on the arbitrary index weight.
Specifically, the embodiment of the invention calculates the standardized index by adopting a mutation progression method, integrates two weight determining methods to obtain the average value, and comprises the following steps:
the first is to determine the weights by entropy weighting:
is the data value of the index after dimensionless treatment.
Calculating the weight of the j index
Wherein the method comprises the steps ofAnd->，/>。
The second is to determine the weights by the dispersion maximization method:
let the weight vector of each index beRecording the decision matrix after the standardization processing asThen a weighted normalized decision matrix can be obtained>
For index k, letFor a certain scheme->The total dispersion of the index value of (c) and the index value of all other schemes is:
constructing a dispersion optimization model:
combining the two weights, and determining the index combination weight:
。
and screening each index by using the obtained index combination weight, and comprehensively obtaining the historical container throughput of the multi-type intermodal junction.
On the basis of the embodiment, the historical container throughput of the railway logistics center, the port and the aviation logistics station are used as the input of the neural network, the predicted throughput of the railway logistics center, the port and the aviation logistics station is obtained respectively, and the area of each working area is obtained.
It should be noted that, the preset neural network model adopted in the embodiment of the present invention may be adopted in a predicted neural network model, for example, a feedforward neural network (Feedforward Neural Networks, FNN), a convolutional neural network (Convolutional Neural Networks, CNN), a cyclic neural network (Recurrent Neural Networks, RNN), a Long Short-term memory network (Long Short-Term Memory Networks, LSTM), etc., which is not particularly limited, and the embodiment of the present invention inputs the screened historical container throughput into any one of the above neural network models to obtain the predicted container throughput in a set period of time, and obtains the area of each operation area.
On the basis of the above embodiment, constructing an objective function based on the predicted throughput includes:
the product of the daily goods carrying frequency, the Manhattan distance and the single unit distance carrying cost between any two operation areas is summed in the range of all the operation areas and then multiplied by a first weight factor and a first dimensionality factor respectively to obtain a first objective subfunction;
multiplying the daily average cargo carrying frequency between any two working areas by Manhattan distance, dividing the Manhattan distance by carrying speed, summing the Manhattan distance and the Manhattan distance by carrying speed in the whole working area, and multiplying the Manhattan distance and the Manhattan distance by a second weight factor and a second dimensionless factor respectively to obtain a second objective subfunction;
Multiplying the length of the horizontal side of any operation area with the length of the vertical side of any operation area, dividing the length by the total length of the multi-type intermodal junction and the total width of the multi-type intermodal junction in sequence, summing the lengths in the whole operation area range, and multiplying the sum with a third weight factor to obtain a third objective subfunction;
adding the first objective subfunction, the second objective subfunction and the third objective subfunction to obtain the objective function;
the first dimensionless factor is obtained by multiplying the single unit distance conveying cost between any two working areas by the daily cargo conveying frequency and the maximum Manhattan distance respectively, then internally dividing the sum in the range of all the working areas, and then obtaining the reciprocal;
the second dimensionless factor is obtained by dividing the average value of the cargo carrying speed between any two working areas by the sum of the product of the average daily cargo carrying frequency and the maximum Manhattan distance in the whole working area range.
It should be noted that, in the embodiment of the present invention, each operation area includes: dock fronts (or air freight stations), arrival boxes, transmission boxes, transfer boxes, special boxes, rail yard sites, container freight stations, auxiliary operation areas, comprehensive mating areas, reserved development areas, and the like.
The logistics and non-logistics relations exist between the working areas, the logistics relation degree is mainly comprehensively influenced by factors such as the cargo transportation size and the distance between the two working areas, and the non-logistics relation degree is determined by factors such as whether the working areas are continuous, personnel safety and convenience in management exist between the working areas.
Specifically, assume that each working area is a standard rectangle and coplanar; assuming that the edges of each working area are respectively bordered by the inner periphery of the intermodal junction、/>The axes are parallel; assuming that the cargo conveyance speed and unit transportation cost are known and different between the work areas; let->And->Work area->And->Is the center point coordinates of (c), then the objective function is:
wherein, the liquid crystal display device comprises a liquid crystal display device,are all the numbers of the operation areas, and +.>，/>For the number of working areas>Is->To->Daily average frequency of cargo handling between +.>Is a job area->To the working area->Manhattan distance between->Is a work area->To the working area->Cost of single unit distance transport between +.>Is a work area->To the working area->The conveying speed is increased between the two conveying speeds,is a weight factor and satisfies->，/>Is a job area->Is provided with a pair of side edges having a length,is a job area->Length of vertical edge- >Is the total length of the multi-modal junction, +.>Is the total width of the multi-modal junction;
and->Is dimensionless factor,/->Is the maximum Manhattan distance between two working areas, < >>Is a multi-type intermodal in-junction operation area +.>To the working area->And the average value of the cargo carrying speed.
On the basis of the above embodiment, determining a preset constraint condition to solve the objective function includes:
determining that the absolute value of the difference between the x axis of any operation area and the x axis of any other area is larger than or equal to the average value of the sum of the lengths of the horizontal edges of any operation area and the lengths of the horizontal edges of any other area plus the minimum distance in the horizontal direction, and the absolute value of the difference between the y axis of any operation area and the y axis of any other area is larger than or equal to the average value of the sum of the lengths of the vertical edges of any operation area and the lengths of the vertical edges of any other area plus the minimum distance in the vertical direction, so as to obtain the non-overlapping constraint condition of the operation area;
determining that the x-axis of any operation area is larger than or equal to the sum of half of the length of the horizontal edge of the any operation area and the minimum distance in the horizontal direction, and the y-axis of any operation area is larger than or equal to the sum of half of the length of the vertical edge of the any operation area and the minimum distance in the vertical direction, so as to obtain the operation area channel constraint condition;
Determining that the total length of any operation area x-axis is smaller than or equal to the total length of the multi-type intermodal junction, sequentially reducing half of the length of the horizontal edge of any operation area and the minimum distance in the horizontal direction, and the total width of any operation area y-axis is smaller than or equal to the total width of the multi-type intermodal junction, sequentially reducing half of the length of the vertical edge of any operation area and the minimum distance in the vertical direction, so as to obtain a junction field size constraint condition;
determining that the half of the length of the horizontal side of any operation area is subtracted from the x axis of any operation area, the half of the length of the horizontal side of any operation area is added to the x axis of any operation area, the half of the length of the vertical side of any operation area is subtracted from the y axis of any operation area, and the half of the length of the vertical side of any operation area is not in a preset fixed area range in the hinge, so as to obtain a fixed area constraint condition;
and multiplying the daily average cargo carrying frequency between any two working areas by the single unit distance carrying cost and the carrying speed in sequence, dividing the daily average cargo carrying frequency between any two working areas by the average cargo carrying speed between any two working areas, and summing the daily average cargo carrying frequency between any two working areas to obtain the objective function adjustment factor.
Specifically, constraint conditions set for the objective function in the embodiment of the present invention include:
(1) Job region non-overlapping constraint:
wherein, the liquid crystal display device comprises a liquid crystal display device,is the minimum distance in the horizontal direction,/->Is the minimum distance in the vertical direction, < >>Is a job area->Is arranged in the x-axis of (a),is a job area->Y-axis of>Is a job area->X-axis of>Is a job area->Is defined by the y-axis of (2);
(2) Job area channel constraint conditions:
(3) Pivot site size constraints:
(4) Fixed area constraint:
wherein, the liquid crystal display device comprises a liquid crystal display device,indicating that there is a fixed area such as railway or highway in the hub, the limited operation area cannot be present in the fixed area +.>And (3) inner part.
In addition, the embodiment of the invention also sets an objective function adjustment factor for adjusting the objective function, wherein the objective function adjustment factor is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing the target function adjustment factor,/->Indicating the work area +.>To the working area->Number of shipments between.
On the basis of the above embodiment, by combining the areas of the working areas with a preset genetic algorithm, an optimized working area plane layout is obtained, including:
determining an intermodal junction scheme as a chromosome of the preset genetic algorithm, wherein each operation area is a gene of the preset genetic algorithm;
Acquiring an initial layout scheme of the intermodal hub, taking the initial layout scheme of the intermodal hub as an initial code, and randomly generating other codes;
determining an operator by using the roulette strategy by taking the objective function as an adaptive function;
if any operator is determined to be smaller than or equal to an individual average adaptation value, dividing the difference between any operator and an individual minimum adaptation value by the difference between the individual average adaptation value and the individual minimum adaptation value, adding an initial lower limit parameter of the crossover probability to obtain an adaptive crossover operator, otherwise, dividing the difference between any operator and the individual average adaptation value by the difference between an individual maximum adaptation value and the individual average adaptation value, and adding an initial upper limit parameter of the crossover probability to obtain the adaptive crossover operator;
determining a mutation probability initial lower limit parameter and a mutation probability initial upper limit parameter of each round, taking an adaptive crossover operator of each round as an initial operator, and repeating the calculation process of the adaptive crossover operator to obtain an adaptive mutation operator;
if the adaptability before the individual operation is determined to be greater than the adaptability after the individual operation, randomly determining genes at any two positions to carry out exchange sequencing, otherwise, not executing the exchange sequencing operation;
Iteratively generating an initial layout of the operation area plane based on the preset constraint condition;
and decoding the initial layout of the operation area plane, and outputting the optimized operation area plane layout.
Specifically, the genetic algorithm solving step in the embodiment of the invention comprises the following steps:
and adding an adaptive crossover operator and an adaptive mutation operator into the original genetic algorithm to dynamically adjust crossover probability and mutation probability, and matching with evolution reversal operation, so that the optimization solving efficiency is improved.
The first step is coding, wherein the scheme of the multi-junction transport junction is taken as a chromosome, and the corresponding operation areas are taken as genes.
And the second step is initializing, obtaining an initial layout scheme of the intermodal junction through the comprehensive relation of all the operation areas, and randomly generating other codes by taking the initial layout scheme of the intermodal junction as an initial code.
The third step is an adaptive function, where the objective function is taken as the adaptive function.
And fourthly, selecting operators, wherein the roulette strategy is adopted according to individual adaptability so as to improve the convergence rate.
The fifth step is to calculate the self-adaptive crossover operator, the serial number of the operation area adopts the partial matching crossover operation:
Wherein, the liquid crystal display device comprises a liquid crystal display device,representing the crossover probability; />And->The initial upper and lower limit parameters respectively representing the crossover probability can be obtained by experiments; />、/>And->The maximum adaptation value, the minimum adaptation value and the average adaptation value of the individual are respectively obtained.
The sixth step is to calculate the adaptive mutation operator, as an auxiliary means to accelerate the convergence rate of the algorithm:
the remaining variables are similar to the above, < +.>And->Initial upper and lower parameters respectively representing mutation probability, ">For any operator of the current wheel, +.>，/>And->The maximum adaptation value, the minimum adaptation value and the average adaptation value of the current round of individuals are respectively obtained.
And the seventh step is the evolution reversion operation, namely, randomly selecting two position genes on an individual to exchange and sort, and if the fitness before the individual operation is judged to be greater than the fitness after the individual operation, carrying out the evolution reversion operation, otherwise, determining that the operation is invalid.
The eighth step is iterative operation, wherein a new gene generated by evaluation is reasonably laid out under the condition that the constraint condition is met; otherwise, repeating the above operation steps.
And a ninth step is decoding operation, decoding the generated new genes to obtain the optimized work area plane layout.
The multi-modal junction process layout system provided by the present invention is described below, and the multi-modal junction process layout system described below and the multi-modal junction process layout method described above can be referred to correspondingly with each other.
FIG. 2 is a schematic structural diagram of a multi-junction process layout system according to an embodiment of the present invention, as shown in FIG. 2, including: a construction module 21, a normalization module 22, a calculation module 23 and an optimization module 24, wherein:
the construction module 21 is used for constructing an index system according to the operation equipment, the loading and unloading process and the operation mode of the multi-type intermodal junction, and sequencing the indexes in the index system to obtain sequenced indexes; the normalization module 22 is configured to perform normalization processing on the sorted indexes to obtain normalized indexes, calculate the normalized indexes by using a mutation level method to obtain mutation level values, and screen historical container throughput of the multi-type intermodal junction according to the mutation level values; the calculation module 23 is configured to input the historical container throughput into a preset neural network model to obtain a predicted throughput of the multi-type intermodal junction and an area of each operation area; the optimization module 24 is configured to construct an objective function based on the predicted throughput, determine a preset constraint condition, solve the objective function, and combine the areas of the working areas through a preset genetic algorithm to obtain an optimized plane layout of the working area.
Fig. 3 illustrates a physical schematic diagram of an electronic device, as shown in fig. 3, where the electronic device may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. The processor 310 may invoke logic instructions in the memory 330 to perform a multi-junction process layout method comprising: constructing an index system according to operation equipment, loading and unloading processes and operation modes of the multi-type intermodal junction, and sequencing indexes in the index system to obtain sequenced indexes; performing standardization processing on the sequenced indexes to obtain standardized indexes, calculating the standardized indexes by using a mutation level number method to obtain mutation level values, and screening the historical container throughput of the multi-type intermodal junction according to the mutation level values; inputting the historical container throughput into a preset neural network model to obtain the predicted throughput of the multi-type intermodal junction and the area of each operation area; and constructing an objective function based on the predicted throughput, determining a preset constraint condition to solve the objective function, and combining the areas of the working areas through a preset genetic algorithm to obtain the optimized planar layout of the working areas.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the multi-modal junction process layout method provided by the methods described above, the method comprising: constructing an index system according to operation equipment, loading and unloading processes and operation modes of the multi-type intermodal junction, and sequencing indexes in the index system to obtain sequenced indexes; performing standardization processing on the sequenced indexes to obtain standardized indexes, calculating the standardized indexes by using a mutation level number method to obtain mutation level values, and screening the historical container throughput of the multi-type intermodal junction according to the mutation level values; inputting the historical container throughput into a preset neural network model to obtain the predicted throughput of the multi-type intermodal junction and the area of each operation area; and constructing an objective function based on the predicted throughput, determining a preset constraint condition to solve the objective function, and combining the areas of the working areas through a preset genetic algorithm to obtain the optimized planar layout of the working areas.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A method of multi-modal junction process layout, comprising:
constructing an index system according to operation equipment, loading and unloading processes and operation modes of the multi-type intermodal junction, and sequencing indexes in the index system to obtain sequenced indexes;
performing standardization processing on the sequenced indexes to obtain standardized indexes, calculating the standardized indexes by using a mutation level number method to obtain mutation level values, and screening the historical container throughput of the multi-type intermodal junction according to the mutation level values;
inputting the historical container throughput into a preset neural network model to obtain the predicted throughput of the multi-type intermodal junction and the area of each operation area;
And constructing an objective function based on the predicted throughput, determining a preset constraint condition to solve the objective function, and combining the areas of the working areas through a preset genetic algorithm to obtain the optimized planar layout of the working areas.
2. The method of claim 1, wherein the constructing an index system according to the operation equipment, the loading and unloading process and the operation mode of the multi-modal junction, and sorting the index in the index system to obtain the sorted index comprises:
determining a carbon emission index according to the energy consumption of the loading and unloading equipment and the carbon emission coefficient of the fuel oil;
the sound pressure and the reference sound pressure are generated by the operation of the replacement equipment, and the noise pollution index is determined;
based on the cargo misalignment coefficient, cargo load, cargo sliding distance and primary breaking coefficient, obtaining cargo wear rate, and determining cargo safety indexes according to the cargo wear rate;
determining an operation personnel safety index according to the casualties of the loading and unloading personnel;
determining loading and unloading efficiency indexes of the reloading equipment according to the workload of the reloading equipment and the operation time of the reloading equipment;
according to the unloading time of the container from the ship, the time from the ship to the yard and the time from the yard to the train, the loading and unloading total time is obtained, and the loading and unloading time index is determined according to the loading and unloading total time;
Determining equipment failure rate indexes according to the actual loading and unloading time of the loading and unloading equipment and the planned loading and unloading time of the loading and unloading equipment;
acquiring operation cost, loading and unloading cost and operator wages, and determining an operation cost index;
determining a site utilization index by the occupied area of the container in the storage yard and the total area of the storage yard;
and sorting the carbon emission index, the noise pollution index, the cargo safety index, the worker safety index, the replacement equipment loading and unloading efficiency index, the loading and unloading time index, the equipment failure rate index, the operation cost index and the site utilization rate index respectively to obtain the sorted indexes.
3. The multi-modal junction process layout method of claim 1, wherein the normalizing the ranked metrics to obtain normalized metrics includes:
acquiring any index maximum value, any index minimum value, total loading and unloading processes and total indexes;
and calculating the standardized index based on the maximum value of any index, the minimum value of any index, the total number of loading and unloading processes and the total number of indexes.
4. The multi-modal hub process layout method of claim 3, wherein calculating the standardized index using a mutation level method to obtain a mutation level value, and screening historical container throughput of the multi-modal hub based on the mutation level value comprises:
Dividing any standardized index by the sum of any standardized index in all loading and unloading processes to obtain a dimensionless data value of any standardized index;
obtaining a first weight of any index based on the dimensionless data value of any standardized index, the total number of unloading processes and the total number of indexes;
obtaining weight vectors of all indexes, and weighting by utilizing the weight vectors of all indexes and the standardized indexes to obtain a standardized decision matrix;
determining the dispersion sum of the index value of any index and the index values of all other schemes, and summing the dispersion sums of all the indexes to obtain total dispersion;
constructing a dispersion optimization model according to the total dispersion, and determining a second weight of any index by the dispersion optimization model;
averaging the first weight of any index and the second weight of any index to obtain weight of any index;
the historical container throughput of the multi-modal junction is filtered based on the arbitrary index weight.
5. The multi-modal junction process layout method of claim 1, wherein the constructing an objective function based on the predicted throughput includes:
The product of the daily goods carrying frequency, the Manhattan distance and the single unit distance carrying cost between any two operation areas is summed in the range of all the operation areas and then multiplied by a first weight factor and a first dimensionality factor respectively to obtain a first objective subfunction;
multiplying the daily average cargo carrying frequency between any two working areas by Manhattan distance, dividing the Manhattan distance by carrying speed, summing the Manhattan distance and the Manhattan distance by carrying speed in the whole working area, and multiplying the Manhattan distance and the Manhattan distance by a second weight factor and a second dimensionless factor respectively to obtain a second objective subfunction;
multiplying the length of the horizontal side of any operation area with the length of the vertical side of any operation area, dividing the length by the total length of the multi-type intermodal junction and the total width of the multi-type intermodal junction in sequence, summing the lengths in the whole operation area range, and multiplying the sum with a third weight factor to obtain a third objective subfunction;
adding the first objective subfunction, the second objective subfunction and the third objective subfunction to obtain the objective function;
the first dimensionless factor is obtained by multiplying the single unit distance conveying cost between any two working areas by the daily cargo conveying frequency and the maximum Manhattan distance respectively, then internally dividing the sum in the range of all the working areas, and then obtaining the reciprocal;
The second dimensionless factor is obtained by dividing the average value of the cargo carrying speed between any two working areas by the sum of the product of the average daily cargo carrying frequency and the maximum Manhattan distance in the whole working area range.
6. The multi-modal junction process layout method of claim 5, wherein the determining the preset constraints solves the objective function, comprising:
determining that the absolute value of the difference between the x axis of any operation area and the x axis of any other area is larger than or equal to the average value of the sum of the lengths of the horizontal edges of any operation area and the lengths of the horizontal edges of any other area plus the minimum distance in the horizontal direction, and the absolute value of the difference between the y axis of any operation area and the y axis of any other area is larger than or equal to the average value of the sum of the lengths of the vertical edges of any operation area and the lengths of the vertical edges of any other area plus the minimum distance in the vertical direction, so as to obtain the non-overlapping constraint condition of the operation area;
determining that the x-axis of any operation area is larger than or equal to the sum of half of the length of the horizontal edge of the any operation area and the minimum distance in the horizontal direction, and the y-axis of any operation area is larger than or equal to the sum of half of the length of the vertical edge of the any operation area and the minimum distance in the vertical direction, so as to obtain the operation area channel constraint condition;
Determining that the total length of any operation area x-axis is smaller than or equal to the total length of the multi-type intermodal junction, sequentially reducing half of the length of the horizontal edge of any operation area and the minimum distance in the horizontal direction, and the total width of any operation area y-axis is smaller than or equal to the total width of the multi-type intermodal junction, sequentially reducing half of the length of the vertical edge of any operation area and the minimum distance in the vertical direction, so as to obtain a junction field size constraint condition;
determining that the half of the length of the horizontal side of any operation area is subtracted from the x axis of any operation area, the half of the length of the horizontal side of any operation area is added to the x axis of any operation area, the half of the length of the vertical side of any operation area is subtracted from the y axis of any operation area, and the half of the length of the vertical side of any operation area is not in a preset fixed area range in the hinge, so as to obtain a fixed area constraint condition;
and multiplying the daily average cargo carrying frequency between any two working areas by the single unit distance carrying cost and the carrying speed in sequence, dividing the daily average cargo carrying frequency between any two working areas by the average cargo carrying speed between any two working areas, and summing the daily average cargo carrying frequency between any two working areas to obtain the objective function adjustment factor.
7. The multi-junction process layout method according to claim 6, wherein the obtaining the optimized job area plan layout by combining the respective job area areas through a preset genetic algorithm includes:
determining an intermodal junction scheme as a chromosome of the preset genetic algorithm, wherein each operation area is a gene of the preset genetic algorithm;
acquiring an initial layout scheme of the intermodal hub, taking the initial layout scheme of the intermodal hub as an initial code, and randomly generating other codes;
determining an operator by using the roulette strategy by taking the objective function as an adaptive function;
if any operator is determined to be smaller than or equal to an individual average adaptation value, dividing the difference between any operator and an individual minimum adaptation value by the difference between the individual average adaptation value and the individual minimum adaptation value, adding an initial lower limit parameter of the crossover probability to obtain an adaptive crossover operator, otherwise, dividing the difference between any operator and the individual average adaptation value by the difference between an individual maximum adaptation value and the individual average adaptation value, and adding an initial upper limit parameter of the crossover probability to obtain the adaptive crossover operator;
determining a mutation probability initial lower limit parameter and a mutation probability initial upper limit parameter of each round, taking an adaptive crossover operator of each round as an initial operator, and repeating the calculation process of the adaptive crossover operator to obtain an adaptive mutation operator;
If the adaptability before the individual operation is determined to be greater than the adaptability after the individual operation, randomly determining genes at any two positions to carry out exchange sequencing, otherwise, not executing the exchange sequencing operation;
iteratively generating an initial layout of the operation area plane based on the preset constraint condition;
and decoding the initial layout of the operation area plane, and outputting the optimized operation area plane layout.
8. A multiple junction process layout system, comprising:
the construction module is used for constructing an index system according to the operation equipment, the loading and unloading process and the operation mode of the multi-type intermodal junction, and sequencing the indexes in the index system to obtain sequenced indexes;
the standardized module is used for carrying out standardized treatment on the sequenced indexes to obtain standardized indexes, calculating the standardized indexes by using a mutation level number method to obtain mutation level values, and screening the historical container throughput of the multi-type intermodal junction according to the mutation level values;
the calculation module is used for inputting the historical container throughput into a preset neural network model to obtain the predicted throughput of the multi-type intermodal junction and the area of each operation area;
And the optimization module is used for constructing an objective function based on the predicted throughput, determining a preset constraint condition to solve the objective function, and combining the areas of the working areas through a preset genetic algorithm to obtain the optimized plane layout of the working areas.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the multi-junction process layout method of any one of claims 1 to 7 when the program is executed.
10. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the multi-modal junction process layout method of any one of claims 1 to 7.
CN202310766207.9A 2023-06-27 2023-06-27 Multi-type intermodal junction process layout method and system Active CN116502976B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310766207.9A CN116502976B (en) 2023-06-27 2023-06-27 Multi-type intermodal junction process layout method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310766207.9A CN116502976B (en) 2023-06-27 2023-06-27 Multi-type intermodal junction process layout method and system

Publications (2)

Publication Number Publication Date
CN116502976A true CN116502976A (en) 2023-07-28
CN116502976B CN116502976B (en) 2023-11-03

Family

ID=87325203

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310766207.9A Active CN116502976B (en) 2023-06-27 2023-06-27 Multi-type intermodal junction process layout method and system

Country Status (1)

Country Link
CN (1) CN116502976B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006011866A2 (en) * 2004-06-25 2006-02-02 Virginia Tech Intellectual Properties, Inc. Cognitive radio engine application of genetic algorithms
CN106651153A (en) * 2016-12-06 2017-05-10 浙江图讯科技股份有限公司 Chemical industry park real-time quantitative risk assessment method based on multi-disaster real-time coupling
CN112700192A (en) * 2020-12-29 2021-04-23 江阴华西化工码头有限公司 Wharf logistics business object processing method based on spark Internet of things
US20220019960A1 (en) * 2020-07-17 2022-01-20 Custody Chain LLC UniTOS Universal Transportation Operating System
WO2022150107A1 (en) * 2021-01-06 2022-07-14 Hyperloop Technologies, Inc. System and method for simulating a multimodal transportation network
CN116151671A (en) * 2023-02-15 2023-05-23 河海大学 Disaster-bearing body vulnerability evaluation method based on mutation level
CN116187599A (en) * 2023-05-04 2023-05-30 中铁第四勘察设计院集团有限公司 Multi-type intermodal railway logistics center point distribution method and system based on genetic algorithm

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006011866A2 (en) * 2004-06-25 2006-02-02 Virginia Tech Intellectual Properties, Inc. Cognitive radio engine application of genetic algorithms
CN106651153A (en) * 2016-12-06 2017-05-10 浙江图讯科技股份有限公司 Chemical industry park real-time quantitative risk assessment method based on multi-disaster real-time coupling
US20220019960A1 (en) * 2020-07-17 2022-01-20 Custody Chain LLC UniTOS Universal Transportation Operating System
CN112700192A (en) * 2020-12-29 2021-04-23 江阴华西化工码头有限公司 Wharf logistics business object processing method based on spark Internet of things
WO2022150107A1 (en) * 2021-01-06 2022-07-14 Hyperloop Technologies, Inc. System and method for simulating a multimodal transportation network
CN116151671A (en) * 2023-02-15 2023-05-23 河海大学 Disaster-bearing body vulnerability evaluation method based on mutation level
CN116187599A (en) * 2023-05-04 2023-05-30 中铁第四勘察设计院集团有限公司 Multi-type intermodal railway logistics center point distribution method and system based on genetic algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李兵祖;: "基于突变理论的多式联运通道安全风险评价研究", 广东交通职业技术学院学报, no. 03 *

Also Published As

Publication number Publication date
CN116502976B (en) 2023-11-03

Similar Documents

Publication Publication Date Title
Hu et al. A three-stage decomposition method for the joint vehicle dispatching and storage allocation problem in automated container terminals
Tavakkoli-Moghaddam et al. An efficient algorithm for solving a new mathematical model for a quay crane scheduling problem in container ports
Yue et al. Optimizing configuration and scheduling of double 40 ft dual-trolley quay cranes and AGVs for improving container terminal services
Wu et al. An integrated programming model for storage management and vehicle scheduling at container terminals
CN115759407B (en) Multi-dimensional scheduling scheme optimization method, system and storage medium based on sorting system
Ayachi et al. A Genetic algorithm to solve the container storage space allocation problem
CN112950091A (en) Vehicle scheduling method, device and storage medium
Zhong et al. Adaptive autotuning mathematical approaches for integrated optimization of automated container terminal
Tao et al. A bi-objective optimization for integrated truck operation and storage allocation considering traffic congestion in container terminals
CN114926118A (en) Method, device and equipment for processing vehicle and cargo loading information and storage medium
Xiang et al. Performance estimation and design optimization of a congested automated container terminal
Nishimura Yard and berth planning efficiency with estimated handling time
Chen et al. A data-driven genetic programming heuristic for real-world dynamic seaport container terminal truck dispatching
CN116502976B (en) Multi-type intermodal junction process layout method and system
CN108959782B (en) Layout optimization method, device and equipment for intelligent workshop
Klerides et al. Modelling and solution approaches to the multi-load AGV dispatching problem in container terminals
Hirashima et al. A Q-learning for group-based plan of container transfer scheduling
Gharehgozli et al. Loading and unloading trains at the landside of container terminals
Konur et al. Loading time flexibility in cross-docking systems
Dotoli et al. An improved technique for train load planning at intermodal rail-road terminals
Semančo et al. Hybrid GA-based improvement heuristic with makespan criterion for flow-shop scheduling problems
CN115330051A (en) Vehicle path optimization method based on hybrid genetic algorithm and application
Liu et al. Fuzzy optimization of storage space allocation in a container terminal
CN113269495A (en) Optimization method and system based on power material distribution
Chen et al. A particle swarm optimization approach for route planning with cross-docking

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
TA01 Transfer of patent application right

Effective date of registration: 20230814

Address after: 430063 No. 745 Heping Avenue, Wuchang District, Hubei, Wuhan

Applicant after: CHINA RAILWAY SIYUAN SURVEY AND DESIGN GROUP Co.,Ltd.

Address before: 430063 No. 745 Heping Avenue, Wuchang District, Hubei, Wuhan

Applicant before: CHINA RAILWAY SIYUAN SURVEY AND DESIGN GROUP Co.,Ltd.

Applicant before: WUHAN GUIDE INTELLIGENT TECHNOLOGY CO.,LTD.

TA01 Transfer of patent application right
CB03 Change of inventor or designer information

Inventor after: Zhang Kun

Inventor after: Liu Hui

Inventor after: Zhang Junling

Inventor after: Peng Fangjin

Inventor after: Li Chengyang

Inventor after: Zhang Yu

Inventor after: Wan Chengpeng

Inventor after: Mei Jie

Inventor after: Luo Xiaohua

Inventor after: Zhang Yinlong

Inventor after: He Yi

Inventor after: Guang Zhenxiong

Inventor after: Dong Yunsong

Inventor after: Lei Chong

Inventor after: Yin Qin

Inventor after: Qiu Shaofeng

Inventor after: Zhou Mingxiang

Inventor after: Li Jiaqi

Inventor before: Zhang Kun

Inventor before: Liu Hui

Inventor before: Zhang Junling

Inventor before: Peng Fangjin

Inventor before: Li Chengyang

Inventor before: Zhang Yu

Inventor before: Wan Chengpeng

Inventor before: Mei Jie

Inventor before: Luo Xiaohua

Inventor before: Fan Pei

Inventor before: Zhang Tao

Inventor before: He Yi

Inventor before: Zhang Yinlong

Inventor before: Guang Zhenxiong

Inventor before: Dong Yunsong

Inventor before: Lei Chong

Inventor before: Yin Qin

Inventor before: Qiu Shaofeng

Inventor before: Zhou Mingxiang

Inventor before: Li Jiaqi

CB03 Change of inventor or designer information
GR01 Patent grant
GR01 Patent grant