CN115526405A - Container multi-type intermodal transportation scheduling method and system based on timeliness - Google Patents
Container multi-type intermodal transportation scheduling method and system based on timeliness Download PDFInfo
- Publication number
- CN115526405A CN115526405A CN202211226220.7A CN202211226220A CN115526405A CN 115526405 A CN115526405 A CN 115526405A CN 202211226220 A CN202211226220 A CN 202211226220A CN 115526405 A CN115526405 A CN 115526405A
- Authority
- CN
- China
- Prior art keywords
- transportation
- whale
- model
- cost
- timeliness
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 241000283153 Cetacea Species 0.000 claims abstract description 142
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 48
- 230000006870 function Effects 0.000 claims description 43
- 239000013598 vector Substances 0.000 claims description 17
- 230000014759 maintenance of location Effects 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 3
- 206010039203 Road traffic accident Diseases 0.000 description 19
- 230000007246 mechanism Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002028 premature Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000013070 direct material Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 229960005486 vaccine Drugs 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-type intermodal container dispatching method and system based on timeliness, which can improve dispatching efficiency by optimizing whale algorithm and considering dispatching timeliness and dispatching cost. The technical scheme is as follows: the coordinates of the starting point and the target point generate a global optimal path through an improved whale algorithm avoiding local optimal, and the global optimal path is used as a multi-type container intermodal transportation scheduling scheme to increase diversity and improve optimizing capacity. And introducing an optimal whale position updating parameter to enlarge a local optimizing range, adjusting attenuation degree of the adjustment threshold parameter according to whale fitness condition in a classified manner, adding a whale position selection strategy to replace random selection, and selecting a whale updating population with high fitness. In the invention, a self-adaptive multi-mode joint operation scheduling model is established, the model considers two aspects of timeliness and cost, and the weight of the two models is determined firstly when the objective function is determined. The invention also gives priority to special requirements of customers, establishes an experience switching mode if the customers have no special requirements, sets weights for the timeliness model and the cost model according to historical cargo transportation experiences, and can determine the objective function according to specific requirements when in use.
Description
Technical Field
The invention relates to a multi-type container intermodal transportation technology, in particular to a multi-type container intermodal transportation scheduling method and system based on timeliness.
Background
The development of economic globalization makes the original transportation mode unable to meet the current social demand, the mobility of goods in the region is further strengthened, the direct expression is that the efficiency of container transportation is required to be higher, the transportation cost is lower, the timeliness is stronger, so this needs to cooperate each other between various transportation modes, accomplishes this transportation task jointly. The multi-type container intermodal system can improve the integrity and the efficiency of transportation, fully exert the advantages of various transportation modes and reduce the required transportation cost.
In the dispatching process of the multi-type container intermodal transportation, a whale algorithm is generally used, and the whale algorithm is an intelligent algorithm based on a meta-heuristic biological group, and has an early convergence problem, namely that the population converges to a local optimal point in advance. Typically, early convergence is due to a lack of global search. The scheduling effect of the container multimodal transport system can be influenced by the premature convergence problem of the whale algorithm.
Disclosure of Invention
The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
The invention aims to solve the problems and provides a multi-type intermodal transportation scheduling method and system for containers based on timeliness.
The technical scheme of the invention is as follows: the invention discloses a time-efficiency-based multi-mode container intermodal transport scheduling method, which comprises the following steps:
the method comprises the following steps: defining types according to the classification of the cargo characteristics, and setting retention cost and delay cost of different types of cargos; defining different transportation modes, and setting corresponding transportation shift and transportation cost; establishing a transportation network under each transportation mode according to the transportation modes owned by the cities and road data, and connecting the cities according to communication information among nodes to form a multi-mode combined transportation network; pre-estimating according to weather factors in a time demand range, screening transportation modes which cannot be carried out in the time demand range according to the influence of the weather factors on the transportation modes, and updating the established multi-mode transport network;
step two: establishing a self-adaptive multimodal transport scheduling model, wherein the weight of two models, namely a timeliness model and a cost model, is determined firstly when a self-adaptive cargo punctuality objective function is determined;
step three: and generating a global optimal path through an improved whale algorithm avoiding local optimal according to the coordinates of the starting point and the target point, taking the generated global optimal path as a multimodal transport scheduling scheme of the goods, introducing an optimal whale position updating parameter into the improved whale algorithm to enlarge a local optimizing range, adjusting attenuation degree of the adjustment threshold parameter according to whale fitness condition classification, adding a whale judgment operator to select a whale updating population with high fitness, and solving the self-adaptive multimodal transport scheduling model established in the step two by using the improved whale algorithm.
According to an embodiment of the time-based multimodal transportation scheduling method for containers of the invention, the pre-estimating according to the weather factors within the time demand range in the first step further comprises:
setting decision variables between the nodes ij in an automobile transportation mode:
setting decision variables between nodes ij in a railway transportation mode:
setting decision variables between the nodes ij in an air transportation mode;
setting decision variables between nodes ij in a waterway transportation mode:
under the condition of extreme weather natural disasters, decision variables under each transportation mode between the nodes ij are set:
according to an embodiment of the timeliness-based multi-type intermodal container scheduling method, in the second step, special requirements of customers are considered preferentially when the weights are determined, if the customers have no special requirements, an experience switching mode is established, namely, the timeliness model and the cost model are weighted according to historical freight experience.
According to an embodiment of the time-based multimodal transportation scheduling method for containers of the invention, the second step further comprises: in the process of setting weights for the timeliness model and the cost model, when the self-adaptive goods punctuality objective function is used, the self-adaptive goods punctuality objective function is determined according to specific requirements, the timeliness model considers goods retention waiting and goods delay, and the cost model considers transportation cost, transit cost and external cost.
According to an embodiment of the time-based container multimodal transportation scheduling method, the improved whale algorithm in the third step comprises the following processing steps:
(1) Initializing algorithm parameters, taking independent variables of an objective function as position information X of whale individuals, randomly initializing population positions in a solution space, and initializing parameters including population number N, logarithmic spiral shape constant b, random number l, iteration number T and maximum iteration number T max ；
(2) Calculating the fitness of the population, recording the fitness as g (t), finding and recording the optimal individual position in the population
(3) And entering an iteration stage, sequencing the current population fitness, dividing the sequenced population into n groups, extracting one member from each group, and calculating the position of each member. Calculating average fitness g (t) a Comparing the individual fitness and the average fitness of whales, selecting different convergence factor functions, and if T is less than T max Updating the mean value a, the randomly varying system vector A, the system vector C, [ -1,1 [ ]]Random number l in (1), random number p between 0 and 1;
(4) Calculating an optimal whale position updating parameter alpha according to the iteration times, and when p is less than 0.5, if A is less than 1, determining the whale position again; if A is more than or equal to 1, determining the whale individual position X in the current population range r Meanwhile, updating the current whale position;
(5) When p is more than or equal to 0.5, re-determining the individual position of the whale;
(6) Recording the location of the best individual whale at that time
And its fitness if T > T max Then, the step (7) is carried out; otherwise, t = t +1, and repeating the steps (3) to (6) until the condition is met;
(7) Outputting optimal individual positions
And its fitness.
The invention also discloses a multi-type container intermodal transportation scheduling system based on timeliness, which comprises:
a multimodal transport network establishment module configured to: defining types according to the classification of the cargo characteristics, and setting retention cost and delay cost of different types of cargos; defining different transportation modes, and setting corresponding transportation shifts and transportation costs; establishing a transportation network under each transportation mode according to the transportation modes owned by the cities and road data, and connecting the cities according to communication information among nodes to form a multi-mode combined transportation network; pre-estimating in advance according to weather factors in a time demand range, screening transportation modes which cannot be carried out in the time demand range according to the influence of the weather factors on the transportation modes, and updating the established multimodal transportation network;
the system comprises a multimodal transport scheduling model establishing module, a time efficiency model establishing module and a cost model establishing module, wherein the multimodal transport scheduling model establishing module is configured to establish a self-adaptive multimodal transport scheduling model, and the weight of the time efficiency model and the cost model is firstly determined when a self-adaptive cargo punctuality objective function is determined;
and the multimodal transportation network scheduling model solving module is configured to generate a global optimal path through an improved whale algorithm avoiding local optimization according to coordinates of a starting point and a target point, the generated global optimal path is used as a multimodal transportation scheduling scheme of goods, an optimal whale position updating parameter is introduced into the improved whale algorithm to expand a local optimization range, meanwhile, attenuation degrees are adjusted according to whale fitness condition classification on an adjustment threshold parameter, a whale judgment operator is added to select a whale updating population with high fitness, and then the improved whale algorithm is used for solving the self-adaptive multimodal transportation scheduling model established in the step two.
According to an embodiment of the time-efficient multi-type intermodal container scheduling system, the pre-estimation processing according to weather factors within a time demand range in the multi-type intermodal network establishing module further comprises:
setting decision variables between nodes ij in an automobile transportation mode:
setting decision variables between the nodes ij in a railway transportation mode:
setting decision variables between the nodes ij in an air transportation mode;
setting decision variables between nodes ij in a waterway transportation mode:
under the condition of extreme weather natural disasters, decision variables between the nodes ij under each transportation mode are set:
according to an embodiment of the timeliness-based multi-type container intermodal dispatching system, special requirements of customers are considered preferentially in the multi-type intermodal dispatching model building module when the weight is determined, if the customers have no special requirements, an experience switching mode is built, namely the timeliness model and the cost model are weighted according to historical freight transport experiences.
According to an embodiment of the multi-type intermodal dispatching system for the container based on timeliness, in the multi-type intermodal dispatching model establishing module, in the process of setting weights for the timeliness model and the cost model, when the multi-type intermodal dispatching model establishing module is used, the self-adaptive goods punctuality objective function is determined according to specific requirements, the timeliness model considers goods retention waiting and goods delay, and the cost model considers transportation cost, transportation cost and external cost.
According to an embodiment of the timeliness-based multi-type intermodal container scheduling system, in the multi-type intermodal network scheduling model solving module, the processing steps of the improved whale algorithm comprise:
(1) Initializing algorithm parameters, taking independent variables of an objective function as position information X of whale individuals, randomly initializing population positions in a solution space, and initializing parameters including population number N, logarithmic spiral shape constant b, random number l, iteration number T and maximum iteration number T max ；
(2) Calculating the fitness of the population, recording the fitness as g (t), finding and recording the optimal individual position in the population
(3) And entering an iteration stage, sequencing the current population fitness, dividing the sequenced population into n groups, extracting one member from each group, and calculating the position of each member. Calculating average fitness g (t) a Comparing the individual fitness and the average fitness of whales, selecting different convergence factor functions, and if T is less than T max Updating the mean value a, the randomly varying system vector A, the system vector C, [ -1,1 [ ]]Random number l in (1), random number p between 0 and 1;
(4) Calculating an optimal whale position updating parameter alpha according to the iteration times, and when p is less than 0.5, if A is less than 1, determining the whale position again; if A is more than or equal to 1, then the current group isDetermining individual position X of whale in body range r Meanwhile, updating the current whale position;
(5) When p is more than or equal to 0.5, re-determining the individual position of the whale;
(6) Recording the location of the best individual whale at that time
And its fitness if T > T max Then, the step (7) is carried out; otherwise, t = t +1, and repeating the steps (3) to (6) until the condition is met;
(7) Outputting optimal individual positions
And its fitness.
Compared with the prior art, the invention has the following beneficial effects: in the scheme of the invention, the coordinates of the starting point and the target point generate a global optimal path through an improved whale algorithm avoiding local optimization, and the global optimal path is used as a multi-type intermodal transportation scheduling scheme of the container, so that the diversity is increased and the optimizing capability is improved. An optimal whale position updating parameter is introduced to expand a local optimizing range, attenuation degree of the adjustment threshold parameter is adjusted according to whale fitness condition in a classified mode, a whale position selection strategy is added to replace random selection, and whale updating population with high fitness is selected. The invention establishes a self-adaptive multi-type combined transport scheduling model, which considers two aspects of timeliness and cost and determines the weight of an objective function and the first weight of the two models. The invention also gives priority to the special requirements of the customers, and if the customers have no special requirements, the scheme establishes an experience switching mode. Weights are set for the timeliness model and the cost model according to historical cargo transportation experience. When in use, the objective function can be determined according to specific requirements. Wherein the timeliness model takes into account cargo retention latency and cargo delays, and the cost model takes into account transportation costs, transit costs, and external costs. The adaptive multi-type intermodal transportation scheduling model not only considers the special requirements of customers, but also considers timeliness and cost, and has practical significance.
Drawings
The above features and advantages of the present disclosure will be better understood upon reading the detailed description of embodiments of the disclosure in conjunction with the following drawings. In the drawings, components are not necessarily drawn to scale, and components having similar relative characteristics or features may have the same or similar reference numerals.
Fig. 1 shows a flow chart of an embodiment of the time-based container multimodal transportation scheduling method of the present invention.
FIG. 2 shows a flow chart of an improved whale algorithm in the embodiment shown in FIG. 1.
Figure 3 illustrates a schematic diagram of an embodiment of the time-based container multimodal dispatch system of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. It is noted that the aspects described below in connection with the figures and the specific embodiments are only illustrative and should not be construed as imposing any limitation on the scope of the present invention.
Before describing aspects of the present invention, the symbols referred to in the text and their meanings are explained below.
a represents the cargo type;
b represents a transportation mode;
NT b representing the next shift of mode of transport bThe arrival time;
t represents the specified arrival time of the cargo.
C a the corresponding loss cost for a specific type of accident c in a unit road segment;
c =1,2,3 indicates a light traffic accident, a general traffic accident, and a fatal traffic accident, respectively.
C n : management or rescue costs of traffic law enforcement, fire protection, public inspection, insurance companies and rescue centers in traffic accidents;
C t : medical costs of injured personnel in a traffic accident;
n represents the number of containers;
c ld representing unit container handling costs.
Fig. 1 shows a flow of an embodiment of the time-based container multimodal transportation scheduling method of the present invention. Referring to fig. 1, the steps of the method of the present embodiment are detailed as follows.
The method comprises the following steps: defining types according to the classification of the cargo characteristics, and setting retention cost and delay cost of different types of cargos; defining different transportation modes, setting corresponding transportation shift, transportation cost and the like; establishing a transportation network under each transportation mode according to the known transportation modes and road data owned by the cities (the transportation modes and the road data comprise transportation paths and transit point sets), and connecting the cities according to the communication information among the nodes to form a multi-mode combined transportation network; and pre-estimating in advance according to weather factors in a time demand range, and screening transportation modes which cannot be carried out in the time demand range according to the influence of the weather factors on the transportation modes so as to update the established multimodal transportation network.
In the traditional multimodal transport network, the consideration of weather factors is applied to calculating the carbon emission cost to measure the economic loss. The consideration of the embodiment to the weather factor is to measure the delay cost of the weather to the transportation mode. Weather factors are another important external factor affecting multimodal processes. First, mode of transportation selection can be affected by weather factors, such as inclement weather resulting in the termination of air transportation. Therefore, a pre-estimation scheme is introduced in the embodiment, and transportation modes which cannot be carried out within a time demand range are screened according to the influence of weather factors on the transportation modes, so that the multimodal transportation network is updated.
Meanwhile, due to the fact that pre-estimation screening is carried out, the situation that the next link transportation cannot be obtained within a demand range does not exist when a multi-type intermodal transportation scheduling scheme is selected subsequently.
The decision variables for making a priori estimate based on weather factors are as follows.
In rainy (snowy) weather, the road surface is wet and slippery, the friction coefficient of the automobile is reduced, the braking is easy to be out of control, the sliding and swinging of the automobile are caused, and the collision accident is even caused.
The influence of weather on the railway transportation is small, and the railway transportation can be regularly, accurately and timely transported as long as the weather is not particularly severe. The transportation can be performed in any place where a railway can be constructed.
In heavy fog weather, visibility is reduced, the difficulty of judging the distance between the vehicles by a driver is increased, potential dangers around the vehicles are found later, and traffic signs and road facilities are difficult to effectively identify, so that traffic accidents are caused.
Air transportation is greatly affected by climate. The airplane generally takes off and lands against the wind, so that the airplane has large lift force, shortest sliding distance and safest performance. If the wind speed is too high, the upwind taking off and landing are not safe. When the snowfall amount reaches above the middle snow, the pilot cannot ensure safe taking off and landing of the flight due to too low visibility. Snow can lead to aircraft fuselage snow, and snow once freezing will lead to internals such as engine intake duct to freeze, influence flight safety.
Waterway transportation is greatly influenced by natural conditions, inland waterway and certain ports are greatly influenced by seasons, and the inland waterway and certain ports are frozen in winter, so that the water level in a dry season is lowered, and the annual navigation is difficult to guarantee. And transport is difficult to carry out in strong wind and heavy rain.
Meanwhile, extreme weather natural disasters can cut off transportation networks and signals, and the transportation mode is influenced.
Step two: the method comprises the steps of establishing a self-adaptive multi-mode intermodal dispatching model, considering two aspects of transportation timeliness and transportation cost, and determining a self-adaptive cargo punctuality objective function to determine the weights of the timeliness model and the cost model.
When the weight is determined, the special requirements of the client are considered preferentially, if the client has no special requirements, the embodiment establishes an experience switching mode, namely, the weight is set for the timeliness model and the cost model according to the historical goods transportation experience (the historical goods transportation experience comprises the goods type and the time level of the requirement of the client), and the self-adaptive goods timeliness objective function is determined according to the specific requirements when in use. Wherein the timeliness model takes into account cargo retention latency and cargo delays, and the cost model takes into account transportation costs, transit costs and external costs.
The specific processing procedure of step two is as follows.
Firstly, for multimodal intermodal transportation of goods, the owner of the goods mainly considers the minimum value of the transportation cost; the consignee then places more emphasis on the timeliness of the goods because time savings result in higher time value and goods may be time-limited and consignee benefits are also guaranteed. However, the transportation cost and the transportation timeliness are in a contradiction relationship to a certain extent, so that the scheme comprehensively considers the cargo type and the cargo owner time requirement, introduces a self-adaptive strategy in the actual multi-mode intermodal transportation, sets a weight parameter according to the actual requirement grade so as to select and use a timeliness model or a cost minimization model, and the expression function of the model is as follows:
W＝ω 1 f(t)+ω 2 C (1)
wherein omega 1 And ω 2 As a weight parameter, ω 1 +ω 2 ＝1，ω 1 ,ω 2 ∈[0,1]
In the above formula (1), W represents an adaptive multimodal transportation scheduling objective function, f (t) represents a cargo transportation punctuality objective function, and C represents a total cost.
In the scheme, the weight parameter omega in the total model (namely the adaptive multimodal transport scheduling model) is used 1 And ω 2 The specific setting of the method firstly gives priority to whether the client has special requirements, if so, the client adopts the settings of the client, and if not, the scheme establishes an experience switching mode function. And setting weights for the timeliness model and the cost model according to the historical cargo transportation experience. The specific operation is as follows:
(1) And performing index evaluation on the cargo type and the customer demand time.
(2) Normalizing the data to obtain a normalized matrix U ij ] n×2 And n represents the number of records of the historical shipment.
(3) Calculating the weight of the attribute to obtain the weight of the jth item as
In the above formula (2), u ij And representing the value of the ith row and the jth column in the normalized matrix, namely attribute weight information corresponding to a certain historical transport cargo record.
Therefore, the objective function of the adaptive multimodal transport switching mode of the present solution can be defined as:
in the above formula (3), f (t) represents the punctuality objective function of cargo transportation, C represents the total cost, and ω is 0 Indicating the customer requirements.
Then, a new transportation punctuality model is established, and risk cost and delay penalty cost of detention waiting for shift arrival of different cargo transportation modes are introduced.
Due to the fact that different goods have special value properties and timeliness values, particularly for certain high-value time-sensitive goods such as vaccines and medicines, punctuality needs to be considered in transportation, and therefore a transportation punctuality model needs to be established. To be more practical, different cargoes are classified first and corresponding residence time penalty cost and delay time penalty cost are established on the basis of different cargo types.
In the multimodal transportation scheduling problem, the transportation punctuality can be considered from two aspects: firstly, if the transportation mode conversion at the node needs to consider the shift, for example, the shift is converted into a shift time fixed transportation mode such as a waterway, an aviation and a railway, the risk cost of staying for waiting the arrival of the shift is introduced; secondly, the goods have the regulated arrival time, and delay penalty cost needs to be introduced. Therefore, the freight transportation punctuality objective function f (t) can be defined as:
where the total cost needs to take into account transportation costs, transportation costs and external costs. The expression is as follows:
total cost C = C 1 +C 2 +C 3 (5)
In the above formula, i belongs to Mb, and M and B in c belongs to B represent a node set and a transportation mode set in the transportation network, respectively.
In actual transportation, there are a lot of external costs that affect the multimodal transportation process. One of the important component factors is the cost of traffic accidents, which not only cause direct material property loss of transport vehicles, goods and the like in the intermodal transportation process, but also influence transportation activities due to traffic delay.
In the above formula, d ij Representing the distance of node ij.
For the selection of the transport mode, the present invention introduces a selection mode considering the operation frequency and the waiting time, which is described in detail below.
Different transportation modes have different transportation frequencies, namely, shifts, and particularly, long retention waiting time exists for three modes of water transportation, railway and aviation, and the road transportation frequency is high and the flexibility is strong. Therefore, when a detention waiting condition is met, the time required for switching over road transportation can be measured and compared to improve the timeliness. The expression mode is as follows:
in the above formula, t 1 ，v 1 Respectively representing the time required for road transportation and the speed of road transportation.
The scheme introduces the cost of traffic accidents and mainly comprises the following aspects: direct economic loss cost, management cost, medical cost, delay cost, and stratify accident types. Considering that the severity of the traffic accident is different, the cost born by the traffic accident is greatly different, so that the economic losses born by different traffic accident types need to be considered during modeling. In order to reduce calculation errors, the traffic accident types are divided into three types of calculation, wherein a light accident (c = 1) is a traffic accident type with property loss only; general accidents (c = 2) there are accidents of persons being injured and traffic with property loss; fatal accidents (c = 3) traffic accidents in which people die and serious property loss accompanies them.
The road accidents in traffic accidents account for the vast majority, the accidents in railway and waterway transportation are relatively few, and the accident rate of air transportation is the lowest, so that the accident probability of different transportation modes is defined differently.
For total traffic accident cost C in multimodal transport 3 Can be expressed as:
thus, the expression of the minimum objective function is:
the constraint of the minimum objective function is:
(1) The starting point to the end point is a complete path
(2) Only one transportation mode can be selected during transferring between two nodes
(3) The number of containers does not exceed the maximum capacity of the transportation mode
(4) At most one transit at a node
In the above formula, m represents a transportation node, r s Denotes the starting point, r e The end point is indicated and the time of the end point,
representing the maximum capacity between nodes ij in the b mode of transportation.
Step three: and generating a global optimal path through an improved whale algorithm for avoiding local optimization according to the coordinates of the starting point and the target point, and taking the generated global optimal path as a multimodal transportation scheduling scheme of the goods. The improved whale algorithm is characterized in that an optimal whale position updating parameter is introduced to expand a local optimization range, meanwhile, attenuation degrees of adjustment threshold parameters are adjusted in a classified mode according to whale fitness conditions, a whale judgment operator is added to select whale update populations with high fitness, and then the improved whale algorithm is used for solving the multimodal transport scheduling model
The whale algorithm is an intelligent algorithm based on meta-heuristic biological groups, and the algorithm has the problem of premature convergence, namely that the population converges to a local optimal point in advance. Typically, early convergence is due to a lack of global search. The embodiment optimizes the traditional whale algorithm to increase diversity and improve optimizing capability.
First, in the whale algorithm, the coefficient vector
To represent the capability of local and global searches. As the linearity of the convergence factor decreases, the late stages of the search are easily trapped in a locally optimal situation. Whale optimization is updated based on the position of the optimal whale during updating, and the closer to the optimal position, the smaller the disturbance on the whale at the head is. When the overall optimization is carried out, in order to enable whales to move greatly, a convergence factor low attenuation degree is set; when local optimization is carried out, in order to enable whales to move in a small range, a convergence factor high attenuation degree is set. Calculating individual fitness of the whale and average fitness of the whale, wherein the individual fitness is lower than the average fitness, and the whale is a better whale. Therefore, according to the adaptation degree change of whales, a newly defined convergence factor is introduced
The diversity of the early global search capability and the convergence speed of the later local search can be balanced.
Thus, the adjustment threshold for improving the whale algorithm is
In the above formula:
s t which is indicative of the current convergence factor,
s 0 which represents the initial convergence factor of the image signal,
t represents the current number of iterations,
T max the maximum number of iterations is indicated,
g (t) represents the population fitness,
g(t) a the mean population fitness is expressed as a function of,
Secondly, the operation of local optimization realization by whale algorithm is to carry out local search in prey surrounding and bubble net attack, when whales approach to a local optimal solution, only the local optimal solution can be approached at the time, the range cannot be changed to carry out better local optimization, and the convergence is easy to be too fast. If the optimal whale position is updated according to the whale self-iteration times when the whale approaches the food, the local optimizing capacity of the whale can be improved. Therefore, a new optimal whale position updating parameter eta is introduced, so that whales can randomly move in a small range to promote local optimization:
η∈[-α，α] (22)
in the above equation, tanh represents a hyperbolic tangent function, and T is the maximum number of iterations.
Therefore, in the bubble net attack stage, the contraction surrounding mechanism and the spiral updating position expression which are updated according to the situation of the whale self iteration number are as follows:
in the above formula:
eta optimal whale position update parameters,
e bl b is a constant defining the shape of a logarithmic spiral, and l is [ -1,1]The random number in (1) is selected,
p is a random number between 0 and 1,
l is a random number in [ -1,1 ].
Thirdly, in a shrinkage surrounding mechanism, according to the variation of the fitness of whales, introducing a grouping selection mechanism to replace random selection, wherein the grouping selection step comprises the steps of sequencing populations according to the fitness value; the sorted population is then divided into n groups. Thereafter, a member is randomly selected from each group and calculated using the following formula
Instead of random selection.
In the above formula:
The above equation is related to an enclosed prey, which is considered to be close to the optimal target, while other whales try to update their position relative to this better whale. Wherein,
is the location of the selected member of the group. T is the current number of iterations, T max Is the maximum number of iterations and r is a dynamic random number between 0 and 1.
Then, in the original whale algorithm, the choice of searching for predation method was random based on probability. Some prey may escape from both hunting mechanisms for some time, and therefore a new random location selection method is introduced to improve population diversity and its search capability.
Wherein,
and
is the maximum and minimum, X, in the search domain of individual whales r In that
And
before being uniformly distributed.
In the above formula:
X i p ,
respectively representing an arithmetic mean position and a square mean position,
X r the position is selected at random and the position is selected at random,
X i the current position.
Thus, the search predation expression is updated as:
the multimodal transport problem can be simply represented by a directed graph G = (V, E) with n points, where V = {1, 2.. Multidata, n }, E = { (i, j), i, j ∈ V }, and the goal is to solve the shortest path problem from the starting point to the end point by traversing all the points.
As shown in fig. 2, the specific operation steps of the multimodal transport problem, i.e., the processing steps of the improved whale algorithm, are as follows.
(1) Initializing algorithm parameters, taking independent variables of an objective function as position information X of whale individuals, randomly initializing population positions in a solution space, and initializing parameters including population number N, logarithmic spiral shape constant b, random number l, iteration number T and maximum iteration number T max 。
(2) Calculating the fitness of the population, recording the fitness as g (t), and finding and recording the optimal individual position in the population
(3) Entering an iteration stage to carry out current population fitnessAnd sorting, namely dividing the sorted population into n groups, extracting one member from each group, and calculating the position of each member. Calculating average fitness g (t) a Comparing the individual fitness and the average fitness of whales, selecting different convergence factor functions, and if T is less than T max Updating the mean value a, the randomly varying system vector A, the system vector C, [ -1,1 [ ]]Random number l, random number p between 0 and 1.
(4) Calculating an optimal whale position updating parameter alpha according to the iteration times, and when p is less than 0.5, if A is less than 1, re-determining the whale position through an equation (24); if A is more than or equal to 1, determining the whale individual position X through (27) in the current population range r The current whale position is updated by equation (30).
(5) When p is more than or equal to 0.5, the individual positions of the whales are determined again through the formula (24).
(6) Record the position of the best individual whale at that time
And its fitness. If T > T max Then, go to step (7); otherwise, t = t +1, and the steps (3) to (6) are repeated until the condition is satisfied.
(7) Outputting optimal individual positions
And its fitness.
Figure 3 illustrates the principles of one embodiment of the time-based container multimodal dispatch system of the present invention. Referring to fig. 1, the system of the present embodiment includes: the system comprises a multi-type intermodal network establishing module, a multi-type intermodal scheduling model establishing module and a multi-type intermodal network scheduling model solving module.
The formula intermodal network establishment module is configured to: defining types according to the classification of the cargo characteristics, and setting retention cost and delay cost of different types of cargos; defining different transportation modes, and setting corresponding transportation shift and transportation cost; establishing a transportation network under each transportation mode according to the transportation modes owned by the cities and road data, and connecting the cities according to communication information among nodes to form a multi-mode combined transportation network; and pre-estimating in advance according to weather factors in a time demand range, and screening transportation modes which cannot be carried out in the time demand range according to the influence of the weather factors on the transportation modes so as to update the established multimodal transportation network.
The process of pre-estimating according to the weather factors in the time demand range in the multimodal transportation network establishment module further comprises the following steps:
setting decision variables between nodes ij in an automobile transportation mode:
setting decision variables between the nodes ij in a railway transportation mode:
setting decision variables between the nodes ij in an air transportation mode;
setting decision variables between nodes ij in a waterway transportation mode:
under the condition of extreme weather natural disasters, decision variables under each transportation mode between the nodes ij are set:
the remaining details of the multimodal transport network establishing module are the same as the step one in the foregoing method embodiment, and are not described herein again.
The multimodal transport scheduling model building module is configured to build an adaptive multimodal transport scheduling model, wherein the weight of the timeliness model and the cost model is determined firstly when the adaptive cargo punctuality objective function is determined.
In the multi-type intermodal transportation scheduling model establishing module, special requirements of customers are considered preferentially when the weight is determined, if the customers have no special requirements, an experience switching mode is established, namely the weight is set for the timeliness model and the cost model according to historical freight transportation experience. In the process of setting weights for the timeliness model and the cost model, when the self-adaptive goods punctuality objective function is used, the self-adaptive goods punctuality objective function is determined according to specific requirements, the timeliness model considers goods retention waiting and goods delay, and the cost model considers transportation cost, transit cost and external cost.
The remaining details of the multimodal transportation scheduling model building module are the same as the second step in the foregoing method embodiment, and are not described herein again.
And the multimodal transportation network scheduling model solving module is configured to generate a global optimal path through an improved whale algorithm avoiding local optimal according to coordinates of a starting point and a target point, the generated global optimal path is used as a multimodal transportation scheduling scheme of goods, an optimal whale position updating parameter is introduced into the improved whale algorithm to enlarge a local optimizing range, attenuation degrees are adjusted according to whale fitness condition classification on an adjusting threshold parameter, a whale judgment operator is added to select a whale updating population with high fitness, and then the improved whale algorithm is used for solving the self-adaptive multimodal transportation scheduling model established in the step two.
In the multimodal transport network scheduling model solving module, the processing steps of the improved whale algorithm comprise:
(1) Initializing algorithm parameters, taking independent variables of an objective function as position information X of whale individuals, randomly initializing population positions in a solution space, and initializing parameters including population number N, logarithmic spiral shape constant b, random number l, iteration number T and maximum iteration number T max ；
(2) Calculating population fitnessFinding and recording the optimal individual position in the population, denoted as g (t)
(3) And entering an iteration stage, sequencing the current population fitness, dividing the sequenced population into n groups, extracting one member from each group, and calculating the position of each member. Calculating average fitness g (t) a Comparing the individual fitness and the average fitness of whales, selecting different convergence factor functions, and if T is less than T max Updating the mean value a, the randomly varying system vector A, the system vector C, [ -1,1 [ ]]Random number l in (1), random number p between 0 and 1;
(4) Calculating an optimal whale position updating parameter alpha according to the iteration times, and when p is less than 0.5, if A is less than 1, determining the whale position again; if A is more than or equal to 1, determining the whale individual position X in the current population range r Meanwhile, updating the current whale position;
(5) When p is more than or equal to 0.5, re-determining the individual position of the whale;
(6) Record the position of the best individual whale at that time
And its fitness if T > T max Then, the step (7) is carried out; otherwise, t = t +1, and repeating the steps (3) to (6) until the condition is met;
(7) Outputting optimal individual positions
And its fitness.
The remaining details of the multimodal transport network scheduling model are the same as the third step in the foregoing method embodiment, and are not described herein again.
While, for purposes of simplicity of explanation, the methodologies are shown and described as a series of acts, it is to be understood and appreciated that the methodologies are not limited by the order of acts, as some acts may, in accordance with one or more embodiments, occur in different orders and/or concurrently with other acts from that shown and described herein or not shown and described herein, as would be understood by one skilled in the art.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The various illustrative logical blocks, modules, and circuits described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.
In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a web site, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. Disk (disk) and disc (disc), as used herein, includes Compact Disc (CD), laser disc, optical disc, digital Versatile Disc (DVD), floppy disk and blu-ray disc where disks (disks) usually reproduce data magnetically, while discs (discs) reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A multi-type intermodal transportation scheduling method for containers based on timeliness is characterized by comprising the following steps:
the method comprises the following steps: defining types according to the classification of the cargo characteristics, and setting retention cost and delay cost of different types of cargos; defining different transportation modes, and setting corresponding transportation shift and transportation cost; establishing a transportation network under each transportation mode according to the transportation modes owned by the cities and road data, and connecting the cities according to communication information among nodes to form a multi-mode combined transportation network; pre-estimating according to weather factors in a time demand range, screening transportation modes which cannot be carried out in the time demand range according to the influence of the weather factors on the transportation modes, and updating the established multi-mode transport network;
step two: establishing a self-adaptive multimodal transport scheduling model, wherein the weight of two models, namely a timeliness model and a cost model, is determined firstly when a self-adaptive cargo punctuality objective function is determined;
step three: and generating a global optimal path through an improved whale algorithm avoiding local optimization according to the coordinates of the starting point and the target point, taking the generated global optimal path as a multi-type intermodal transportation scheduling scheme of the cargos, introducing an optimal whale position updating parameter into the improved whale algorithm to expand a local optimizing range, classifying and adjusting attenuation degrees of the adjusting threshold parameter according to whale fitness conditions, adding a whale judgment operator to select a whale updating population with high fitness, and solving the self-adaptive multi-type intermodal transportation scheduling model established in the step two by using the improved whale algorithm.
2. The timeliness-based multimodal transportation scheduling method for containers of claim 1, wherein the pre-estimation process according to weather factors within the time demand range in the first step further comprises:
setting decision variables between nodes ij in an automobile transportation mode:
setting decision variables between nodes ij in a railway transportation mode:
setting decision variables between the nodes ij in an air transportation mode;
setting decision variables between nodes ij in a waterway transportation mode:
under the condition of extreme weather natural disasters, decision variables under each transportation mode between the nodes ij are set:
3. the timeliness-based multi-modal intermodal container scheduling method of claim 1, wherein in step two, the customer special needs are prioritized in determining the weight, and if the customer has no special needs, an experience switching mode is established, that is, the timeliness model and the cost model are weighted according to historical freight experience.
4. The time-based container multimodal intermodal dispatch method according to claim 1, wherein step two further comprises: in the process of setting weights for the timeliness model and the cost model, when the self-adaptive goods timeliness objective function is used, the self-adaptive goods timeliness objective function is determined according to specific requirements, the timeliness model considers goods retention waiting and goods delay, and the cost model considers transportation cost, transfer cost and external cost.
5. The time-based container multimodal transportation scheduling method according to claim 1, wherein the processing steps of the improved whale algorithm in the third step comprise:
(1) Initializing algorithm parameters, taking independent variables of an objective function as position information X of whale individuals, randomly initializing population positions in a solution space, and simultaneously initializing parameters including population number N, logarithmic spiral shape constant b, random number l, iteration times T and maximum iteration times T max ；
(2) Calculating the fitness of the population, recording the fitness as g (t), finding and recording the optimal individual position in the population
(3) And entering an iteration stage, sequencing the current population fitness, dividing the sequenced population into n groups, extracting one member from each group, and calculating the position of each member. Calculating average fitness g (t) a Comparing the individual fitness and the average fitness of whales, selecting different convergence factor functions, and if T is less than T max Updating the mean value a, the randomly varying system vector A, the system vector C, [ -1,1] of]Random number l in (1), random number p between 0 and 1;
(4) Calculating an optimal whale position updating parameter alpha according to the iteration times, and when p is less than 0.5, if A is less than 1, determining the whale position again; if A is more than or equal to 1, determining the whale individual position X in the current population range r Meanwhile, updating the current whale position;
(5) When p is more than or equal to 0.5, re-determining the individual position of the whale;
(6) Recording the location of the best individual whale at that time
And its fitness if T > T max Then, the step (7) is carried out; otherwise, t = t +1, and repeating the steps (3) to (6) until the condition is satisfied;
(7) Outputting optimal individual positions
And its fitness.
6. A time-sensitive based multi-type intermodal container scheduling system is characterized by comprising:
a multimodal transport network establishment module configured to: defining types according to the classification of the cargo characteristics, and setting retention cost and delay cost of different types of cargos; defining different transportation modes, and setting corresponding transportation shift and transportation cost; establishing a transportation network under each transportation mode according to the transportation modes owned by the cities and road data, and connecting the cities according to communication information among nodes to form a multi-mode combined transportation network; pre-estimating according to weather factors in a time demand range, screening transportation modes which cannot be carried out in the time demand range according to the influence of the weather factors on the transportation modes, and updating the established multi-mode transport network;
the system comprises a multimodal transport scheduling model establishing module, a time efficiency model establishing module and a cost model establishing module, wherein the multimodal transport scheduling model establishing module is configured to establish a self-adaptive multimodal transport scheduling model, and the weight of the time efficiency model and the cost model is firstly determined when a self-adaptive cargo punctuality objective function is determined;
and the multimodal transportation network scheduling model solving module is configured to generate a global optimal path through an improved whale algorithm avoiding local optimization according to coordinates of a starting point and a target point, the generated global optimal path is used as a multimodal transportation scheduling scheme of goods, an optimal whale position updating parameter is introduced into the improved whale algorithm to expand a local optimization range, meanwhile, attenuation degrees are adjusted according to whale fitness condition classification on an adjustment threshold parameter, a whale judgment operator is added to select a whale updating population with high fitness, and then the improved whale algorithm is used for solving the self-adaptive multimodal transportation scheduling model established in the step two.
7. The timeliness-based multi-modal intermodal container scheduling system of claim 6, wherein the processing of the multi-modal intermodal network building block for a priori prediction based on weather factors within a time demand range further comprises:
setting decision variables between the nodes ij in an automobile transportation mode:
setting decision variables between the nodes ij in a railway transportation mode:
setting decision variables between the nodes ij in an air transportation mode;
setting decision variables between the nodes ij in a waterway transportation mode:
under the condition of extreme weather natural disasters, decision variables under each transportation mode between the nodes ij are set:
8. the multi-type intermodal container scheduling system based on timeliness of claim 6, wherein in the multi-type intermodal scheduling model establishing module, special requirements of customers are prioritized in determining the weight, and if the customers have no special requirements, an experience switching mode is established, namely the timeliness model and the cost model are weighted according to historical freight transport experiences.
9. The multi-type intermodal container scheduling system based on timeliness of claim 6, wherein in the multi-type intermodal scheduling model building module, in the process of setting weights to the timeliness model and the cost model, an adaptive cargo punctuality objective function is determined according to specific requirements when in use, the timeliness model takes cargo retention waiting and cargo delay into account, and the cost model takes transportation cost, transit cost and external cost into account.
10. The timeliness-based container multimodal transportation scheduling system of claim 6, wherein in the multimodal transportation network scheduling model solving module, the processing steps of the improved whale algorithm include:
(1) Initializing algorithm parameters, taking independent variables of an objective function as position information X of whale individuals, randomly initializing population positions in a solution space, and simultaneously initializing parameters including population number N, logarithmic spiral shape constant b, random number l, iteration times T and maximum iteration times T max ；
(2) Calculating the fitness of the population, recording the fitness as g (t), and finding and recording the optimal individual position in the population
(3) Entering an iteration stage, sequencing the current population fitness, and dividing the sequenced population into n groupsAnd extracting one member from each group and calculating the position of the member. Calculating average fitness g (t) a Comparing the individual fitness and the average fitness of whales, selecting different convergence factor functions, and if T is less than T max Updating the mean value a, the randomly varying system vector A, the system vector C, [ -1,1 [ ]]Random number l in (1), random number p between 0 and 1;
(4) Calculating an optimal whale position updating parameter alpha according to the iteration times, and when p is less than 0.5, if A is less than 1, determining the whale position again; if A is more than or equal to 1, determining the whale individual position X in the current population range r Meanwhile, updating the current whale position;
(5) When p is more than or equal to 0.5, re-determining the individual position of the whale;
(6) Recording the location of the best individual whale at that time
And its fitness if T > T max If yes, the step (7) is carried out; otherwise, t = t +1, and repeating the steps (3) to (6) until the condition is satisfied;
(7) Outputting optimal individual positions
And its fitness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211226220.7A CN115526405A (en) | 2022-10-09 | 2022-10-09 | Container multi-type intermodal transportation scheduling method and system based on timeliness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211226220.7A CN115526405A (en) | 2022-10-09 | 2022-10-09 | Container multi-type intermodal transportation scheduling method and system based on timeliness |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115526405A true CN115526405A (en) | 2022-12-27 |
Family
ID=84701267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211226220.7A Pending CN115526405A (en) | 2022-10-09 | 2022-10-09 | Container multi-type intermodal transportation scheduling method and system based on timeliness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115526405A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116205472A (en) * | 2023-05-06 | 2023-06-02 | 华清科盛(北京)信息技术有限公司 | Raw material container transportation scheme making method and system based on production task |
| CN116307330A (en) * | 2023-05-10 | 2023-06-23 | 中铁第四勘察设计院集团有限公司 | Multi-mode intermodal organization mode dynamic optimization method based on big data processing |
| CN116523270A (en) * | 2023-07-03 | 2023-08-01 | 南京联畅云科技有限公司 | Logistics transportation task automatic scheduling method, equipment, server and medium |
| CN117010778A (en) * | 2023-10-07 | 2023-11-07 | 北京索云科技股份有限公司 | Data management method based on multi-mode intermodal |
| CN118365104A (en) * | 2024-06-19 | 2024-07-19 | 山东凌岳智能科技有限公司 | Bulk cargo wharf production control method and system based on artificial intelligence |
-
2022
- 2022-10-09 CN CN202211226220.7A patent/CN115526405A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116205472A (en) * | 2023-05-06 | 2023-06-02 | 华清科盛(北京)信息技术有限公司 | Raw material container transportation scheme making method and system based on production task |
| CN116205472B (en) * | 2023-05-06 | 2023-08-04 | 华清科盛(北京)信息技术有限公司 | Raw material container transportation scheme making method and system based on production task |
| CN116307330A (en) * | 2023-05-10 | 2023-06-23 | 中铁第四勘察设计院集团有限公司 | Multi-mode intermodal organization mode dynamic optimization method based on big data processing |
| CN116523270A (en) * | 2023-07-03 | 2023-08-01 | 南京联畅云科技有限公司 | Logistics transportation task automatic scheduling method, equipment, server and medium |
| CN116523270B (en) * | 2023-07-03 | 2023-09-12 | 南京联畅云科技有限公司 | Logistics transportation task automatic scheduling method, equipment, server and medium |
| CN117010778A (en) * | 2023-10-07 | 2023-11-07 | 北京索云科技股份有限公司 | Data management method based on multi-mode intermodal |
| CN117010778B (en) * | 2023-10-07 | 2023-12-15 | 北京索云科技股份有限公司 | Data management method based on multi-mode intermodal |
| CN118365104A (en) * | 2024-06-19 | 2024-07-19 | 山东凌岳智能科技有限公司 | Bulk cargo wharf production control method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115526405A (en) | Container multi-type intermodal transportation scheduling method and system based on timeliness | |
| CN107229973B (en) | Method and device for generating strategy network model for automatic vehicle driving | |
| CN109785618B (en) | Short-term traffic flow prediction method based on combinational logic | |
| CN112732905B (en) | Traffic accident analysis, prevention and control method and system based on knowledge graph | |
| CN107239821B (en) | Method for repairing reliability of urban mass transit network under random attack strategy | |
| CN110288857B (en) | Airport parking lot fast scheduling method based on time-space dimension decomposition | |
| CN109948839B (en) | Method and system for predicting and early warning galloping risk of overhead transmission line | |
| CN113554875B (en) | Variable speed-limiting control method for heterogeneous traffic flow of expressway based on edge calculation | |
| CN114664122B (en) | Conflict minimized flight path planning method considering high altitude wind uncertainty | |
| CN114154850B (en) | Automatic approach sequencing method and system for airport terminal area of urban logistics unmanned aerial vehicle | |
| CN115494810B (en) | AGV online path planning method for automatic wharf | |
| CN115310732B (en) | Flight delay prediction method and system | |
| Liang et al. | Winter road surface status recognition using deep semantic segmentation network | |
| CN112862171A (en) | Flight arrival time prediction method based on space-time neural network | |
| CN116050245A (en) | Highway automatic driving commercial vehicle track prediction and decision method and system based on complex network theory | |
| CN115035739A (en) | Automatic driving vehicle scheduling method applied to intelligent network park | |
| CN114971073B (en) | Method and device for predicting multi-station arrival late points of overline train | |
| CN111780766A (en) | Dynamic diversion planning method integrating dynamic risk graph and improved A-algorithm | |
| US20230339519A1 (en) | Safety measurement for a counterfactual risk in autonomous vehicle driving | |
| Khan et al. | A novel parallel series data-driven model for IATA-coded flight delays prediction and features analysis | |
| CN111907523A (en) | Vehicle following optimization control method based on fuzzy reasoning | |
| CN117711173A (en) | Vehicle path planning method and system based on reinforcement learning | |
| CN117273964B (en) | Intelligent vehicle insurance policy generation system and method for self-adaptive driving data | |
| Teimoori et al. | A multi-objective grey wolf optimization algorithm for aircraft landing problem | |
| CN117273202A (en) | Port berth allocation optimization method, port berth allocation optimization system and storage medium |
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 |