Dynamic intensive scheduling decision-making method for port horizontal transportation tools

Abstract

The invention discloses a port horizontal transportation tool dynamic intensive scheduling decision method, and relates to the technical field of port logistics transportation management, and the method comprises the steps: firstly collecting port transportation related data in real time, then determining the weight based on the port transportation related data, calculating the priority coefficient of each transportation task, sorting the coefficients from large to small to form a task sequence, and carrying out the scheduling of the task sequence; according to the vehicle state data and the task sequence, constructing a multi-objective optimization function which aims at minimizing the total task completion time, minimizing the total transportation cost and maximizing the vehicle average load rate, and solving and generating an optimal scheduling scheme by adopting an improved genetic algorithm; the task priority is determined, so that emergency and important tasks can be preferentially processed, and the task execution reasonability is improved; a multi-objective optimization function can overall plan efficiency, cost and resource utilization, the problem that traditional scheduling only focuses on a single objective is solved, and the port green and efficient development requirements are met.

Description

Technical Field

[0001] This invention relates to the field of port logistics and transportation management technology, and more specifically to a dynamic and intensive scheduling decision-making method for port horizontal transportation vehicles. Background Technology

[0002] Currently, Automated Guided Transport (ART) vehicles are the core equipment for horizontal transportation in automated terminals. Their dynamic and intensive scheduling is a key solution for optimizing the operational efficiency and reducing operating costs of existing automated terminal upgrades. As global logistics hubs, the scheduling efficiency of port ARTs directly determines terminal throughput, equipment utilization, and overall operating costs, and is a crucial indicator of the core competitiveness of automated terminals. Existing port ART scheduling methods have the following shortcomings: Static scheduling is the main method, with poor dynamic adaptability: Most methods generate fixed scheduling schemes based on preset work plans. Port ARTs have weak response capabilities to real-time road conditions, node congestion, and sudden changes in tasks. They cannot flexibly adjust driving routes and task allocation, which can easily lead to task backlog or empty runs of port ARTs, and even affect the smoothness of the terminal transportation link. Low resource utilization: The rated load characteristics, overlapping travel paths and task coordination of port ARTs were not fully considered, resulting in problems such as insufficient cargo capacity of a single port ART, multiple vehicles repeatedly traveling to and from the same area, and route planning not being combined with real-time node status. The overall utilization rate of port ARTs is low and resources are wasted significantly. Lack of multi-objective optimization: Traditional scheduling only focuses on the single objective of task completion time, without taking into account the multi-dimensional needs of port ART, such as power consumption cost, maintenance cost, collaborative efficiency of loading and unloading equipment, and carbon emission control, which is inconsistent with the needs of green and efficient port development.

[0003] Therefore, how to provide a port ART scheduling decision-making method that can perceive dynamic information in real time, realize intensive resource utilization, and take into account multiple objectives is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, the present invention provides a dynamic and intensive scheduling decision-making method for port horizontal transport vehicles to solve the problems existing in the background art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: A dynamic and intensive scheduling decision-making method for port horizontal transport vehicles includes: S1. Real-time collection of port transportation-related data, including vehicle status data, task requirement data, and port node status data; S2. Based on the task requirement data and port node status data, calculate the priority coefficient of each transportation task, and sort them from largest to smallest to form a task sequence. S3. Based on the vehicle status data and task sequence, construct a multi-objective optimization function with the objectives of minimizing the total task completion time, minimizing the total transportation cost, and maximizing the average vehicle load rate. S4. An improved genetic algorithm is used to solve a multi-objective optimization function with the objectives of minimizing total task completion time, minimizing total transportation cost, and maximizing average vehicle load rate, and the optimal scheduling scheme is generated.

[0006] Optionally, the real-time collection of port transportation-related data specifically includes: collecting the following data in real time through the port IoT system, vehicle GPS positioning terminals, loading and unloading equipment sensors, and the port management system: Vehicle status data: Vehicle ID, real-time location, current load rate, remaining battery power, vehicle health status, and historical operating efficiency; Task requirements data: Task ID, cargo type, cargo weight, departure node, destination node, task urgency, latest completion time; Port node status data: node ID, number of currently operating equipment, equipment busyness, node congestion coefficient, travel distance between nodes and real-time traffic conditions.

[0007] Optionally, determining the weights specifically includes: A hierarchical model for the dynamic and intensive scheduling of port horizontal transport vehicles is constructed. The hierarchical structure of the dynamic and intensive scheduling model for port horizontal transport vehicles specifically includes: target layer: task priority coefficient; criteria layer: task urgency, time urgency, node coordination, and cargo importance; and solution layer: the set of transport tasks to be evaluated. Based on the scaling relationships between the various dimensions of the hierarchical model of the dynamic intensive scheduling scenario of port horizontal transport vehicles, the judgment matrix of the criterion layer is determined. The weights of each element at each level are determined based on the judgment matrix.

[0008] Optionally, it also includes using the similarity matrix method and questionnaire survey method, based on the hierarchical structure model of the dynamic intensive scheduling scenario of port horizontal transport vehicles, to determine the scaling relationship values ​​between the dimensions of the criterion layer according to the scaling method of 1-9, and to calculate the average value to obtain the judgment matrix. Calculate the largest eigenvalue of the judgment matrix and its corresponding eigenvector, and normalize the eigenvector to obtain the ranking weight vector. Then, sort and verify similarity. The ranking weight vector is used as the weight value of the relative importance between the dimensions of the criterion layer.

[0009] Optionally, the similarity verification steps include: The similarity index is calculated using the following first formula based on the largest eigenvalue of the judgment matrix and the order of the judgment matrix; ; Where CI represents the similarity index. Let q represent the largest eigenvalue of the judgment matrix, q represent the order of the judgment matrix, CI=0 indicates complete similarity, and CI close to 0 indicates satisfactory similarity. Based on the preset correspondence between the order and the random similarity index, the random similarity index corresponding to the order of the judgment matrix is ​​determined. Based on the similarity index and the random similarity index, the similarity deviation verification coefficient is calculated using the following second calculation formula: ; Wherein, CR represents the similarity deviation verification coefficient, and RI represents the random similarity index; If the similarity deviation verification coefficient is less than 0.1, the similarity verification is deemed to have passed; otherwise, the similarity verification fails, and the judgment matrix is ​​readjusted.

[0010] Optionally, the step of calculating the priority coefficient of each transportation task and sorting them in descending order of priority coefficient to form a task sequence specifically includes: The priority coefficient is a combination of the quantified values ​​from four dimensions, and the formula is as follows: ; in, This represents the urgency coefficient of the task. Time urgency coefficient; Node collaboration coefficient; This is the importance coefficient of the goods; These are the weight values ​​for the four dimensions; Calculate the priority coefficient P of all tasks to be assigned using the formula above; Sort the P-values ​​from largest to smallest to form a task sequence. ,in This is the highest priority task.

[0011] Optionally, the construction of the multi-objective optimization function with the objectives of minimizing the total task completion time, minimizing the total transportation cost, and maximizing the average vehicle load rate is specifically as follows: Suppose there are n tasks to be assigned. m available vehicles Define the core variables: As decision variables, =1 indicates a vehicle Assign tasks ; =0 indicates that no allocation has been made; For vehicles Execute the task Travel time; For vehicles Execute the task Loading and unloading time; For vehicles Execute the task Total transportation costs; For the task The weight of the goods; For vehicles Rated load capacity; Objective 1: Minimize the total task completion time The total task completion time is the sum of the travel time and loading / unloading time for all tasks, taking task priority into account. ; in For the task The priority coefficient is determined by the time weight of higher priority tasks, which are given priority to ensure their rapid completion. Objective 2: Minimize total transportation costs Total transportation costs include electricity costs, maintenance costs, and empty-running surcharges: ; Maximize vehicle average load rate Objective 3: Load factor reflects vehicle resource utilization and is defined as the ratio of actual total cargo weight to the vehicle's rated total load capacity. .

[0012] Optional, constraints may also be included: Task assignment constraint: Each task can only be assigned to one vehicle. ; Vehicle load constraints: Overloading is prohibited; Time window constraints: .

[0013] Optionally, S4 specifically includes: S41. Based on the determined vehicle status data, task requirement data, port node status data, and port vehicle scheduling multi-objective optimization model, generate port scheduling basic list information, and set the population size M, iteration number N, and iteration termination condition. S42. Based on the population size M, the number of transportation tasks n, the number of port vehicles m obtained in S41, and the constraints of the multi-objective optimization model for port vehicle scheduling, randomly generate M chromosomes as the parent population. The chromosomes are encoded in binary format, and the chromosome gene length is m. n, where at most one gene in each of the n genes is encoded as 1, and the rest are 0; S43. Based on the encoding of each chromosome obtained in S42, determine the chromosome responsible for each transport task. Port vehicles ; S44. For the chromosome population obtained in S42, calculate the total completion time of the transportation task for each chromosome based on the port vehicle scheduling multi-objective optimization model obtained in S41. Total transportation cost and vehicle average load rate The non-dominated rank of each chromosome is calculated by non-dominated sorting. and crowding ; S45. Based on the parent population obtained in S42, perform genetic operations using custom crossover and mutation operators to generate a population of M offspring chromosomes. S46. Combine the parent population from S42 with the offspring chromosome population generated in S45 to form a population of size 2M, and calculate the objective function value and perform non-dominated sorting, based on the non-dominated level. and crowding When sorting chromosomes, select M chromosomes as the new parent population; S47. Based on the new parent population obtained in S46, repeat S45 to S46 to determine whether the number of genetic iterations and the termination condition meet the requirements. If the requirements are met, stop the iteration operation to obtain the final chromosome population. S48. The final chromosome population obtained from S47 makes the non-dominant hierarchy... The chromosome is the optimal Pareto solution set. Then, the optimal chromosome is obtained by comprehensively evaluating the total completion time of the transportation task, the total transportation cost, and the average vehicle load rate.

[0014] As can be seen from the above technical solution, compared with the prior art, the present invention discloses a dynamic and intensive scheduling decision-making method for port horizontal transportation vehicles. First, it collects real-time vehicle status data, task demand data, and port node status data related to port transportation. Then, based on the task demand data and port node status data, it determines the weights and calculates the priority coefficients of each transportation task, sorting them from largest to smallest to form a task sequence. Next, based on the vehicle status data and task sequence, it constructs a multi-objective optimization function with the objectives of minimizing total task completion time, minimizing total transportation cost, and maximizing average vehicle load rate. An improved genetic algorithm is used to solve for and generate the optimal scheduling scheme. The real-time data acquisition of this invention breaks the limitations of traditional static scheduling relying on preset plans, making scheduling more accurate and timely, and avoiding task backlog or empty vehicle runs. Determining task priorities ensures that urgent and important tasks are handled first, improving the rationality of task execution. The multi-objective optimization function can coordinate efficiency, cost, and resource utilization, solving the problem that traditional scheduling only focuses on a single objective, and meeting the needs of green and efficient port development. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the method flow provided by the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] This invention discloses a dynamic and intensive scheduling decision-making method for port horizontal transport vehicles, such as... Figure 1 As shown, it includes: S1. Real-time collection of port transportation-related data, including vehicle status data, task requirement data, and port node status data. S2. Determine the weights based on task requirement data and port node status data, calculate the priority coefficient of each transportation task, and sort them from largest to smallest to form a task sequence. S3. Based on vehicle status data and task sequence, construct a multi-objective optimization function with the objectives of minimizing total task completion time, minimizing total transportation cost, and maximizing average vehicle load rate. S4. An improved genetic algorithm is used to solve a multi-objective optimization function with the objectives of minimizing total task completion time, minimizing total transportation cost, and maximizing average vehicle load rate, and the optimal scheduling scheme is generated.

[0019] In one specific embodiment, real-time collection of port transportation-related data includes: collecting the following data in real time through the port IoT system, vehicle GPS positioning terminals, loading and unloading equipment sensors, and the port management system: Vehicle status data: Vehicle ID, real-time location, current load rate, remaining battery power, vehicle health status, and historical operating efficiency; Task requirements data: Task ID, cargo type, cargo weight, departure node, destination node, task urgency, latest completion time; Port node status data: node ID, number of currently operating equipment, equipment busyness, node congestion coefficient, travel distance between nodes and real-time traffic conditions.

[0020] In a specific embodiment, determining the weights specifically includes: A hierarchical model for the dynamic and intensive scheduling of port horizontal transport vehicles is constructed. The hierarchical structure of the dynamic and intensive scheduling model for port horizontal transport vehicles specifically includes: target layer: task priority coefficient; criteria layer: task urgency, time urgency, node coordination, and cargo importance; and solution layer: the set of transport tasks to be evaluated. Based on the scaling relationships between the various dimensions of the hierarchical model of the dynamic intensive scheduling scenario of port horizontal transport vehicles, the judgment matrix of the criterion layer is determined. The weights of each element at each level are determined based on the judgment matrix.

[0021] In a specific embodiment, the method further includes determining the scaling relationship values ​​between the dimensions of the criteria layer based on the hierarchical structure model of the dynamic intensive scheduling scenario of port horizontal transport vehicles, using the similarity matrix method and questionnaire survey method, and calculating the average value to obtain the judgment matrix. Calculate the largest eigenvalue of the judgment matrix and its corresponding eigenvector, normalize the eigenvector to obtain the ranking weight vector, and perform ranking and similarity verification. The ranking weight vector is used as the weight value of the relative importance between the dimensions of the criterion layer.

[0022] In one specific embodiment, the similarity verification steps include: The similarity index is calculated using the following first formula based on the largest eigenvalue of the judgment matrix and the order of the judgment matrix; ; Where CI stands for Similarity Index. CI represents the largest eigenvalue of the judgment matrix, q represents the order of the judgment matrix, CI=0 indicates perfect similarity; CI close to 0 indicates satisfactory similarity. Based on the pre-defined correspondence between the order and the random similarity index, determine the random similarity index corresponding to the order of the judgment matrix; Based on the similarity index and the random similarity index, the similarity deviation verification coefficient is calculated using the following second calculation formula: ; Wherein, CR represents the similarity deviation check coefficient, and RI represents the random similarity index; If the similarity deviation check coefficient is less than 0.1, the similarity check is passed; otherwise, the similarity check fails and the judgment matrix is ​​readjusted.

[0023] In a specific embodiment, calculating the priority coefficient of each transportation task and sorting them in descending order of priority coefficient to form a task sequence specifically includes: The priority coefficient is a combination of the quantified values ​​from four dimensions, and the formula is as follows: ; in, These are the weight values ​​for the four dimensions; This represents the urgency coefficient of the task. Definition: Classification based on the urgency of task type Value selection rules: Urgent task: =1.0 Normal tasks: =0.5 Delayable tasks: =0.3 This represents the time urgency coefficient. Definition: The ratio of remaining task time to standard operating time, reflecting time pressure. Calculation formula: ; constraint: If the result is <0, take 0; if the result is >1, take 1. For example, if the latest completion time for a task is 12:00, the current time is 11:30, there are 30 minutes remaining, and the standard duration is 40 minutes, then... =1 - 30 / 40 = 0.25 The node coordination coefficient; Definition: Reflects the busyness of the originating node, avoiding congestion caused by concentrated tasks; Calculation formula:

[0024] Wherein, the node congestion coefficient = the number of vehicles currently waiting / the node's maximum capacity for vehicles.

[0025] For example, if there are currently 2 waiting vehicles in parking space 2, and the maximum capacity is 6 vehicles, then the congestion coefficient = 2 / 6 ≈ 0.33. =1-0.33=0.67.

[0026] This is the importance coefficient of the goods; Definition: Weighted value based on the value or specificity of goods Value selection rules: High-value goods or dangerous goods: =1.0; General cargo: =0.6; Low-value bulk cargo: =0.4.

[0027] Calculate the priority coefficient P of all tasks to be assigned using the formula above; Sort the P-values ​​from largest to smallest to form a task sequence. ,in This is the highest priority task.

[0028] In a specific embodiment, the multi-objective optimization function aimed at minimizing the total task completion time, minimizing the total transportation cost, and maximizing the average vehicle load rate is constructed as follows: Suppose there are n tasks to be assigned. m available vehicles Define the core variables: As decision variables, =1 indicates a vehicle Assign tasks ; =0 indicates that no allocation has been made; For vehicles Execute the task Travel time; For vehicles Execute the task Loading and unloading time; For vehicles Execute the task Total transportation costs; For the task The weight of the goods; For vehicles Rated load capacity; Objective 1: Minimize the total task completion time The total task completion time is the sum of the travel time and loading / unloading time for all tasks, taking task priority into account. ; in For the task The priority coefficient is determined by the time weight of higher priority tasks, which are given priority to ensure their rapid completion. Objective 2: Minimize total transportation costs Total transportation costs include electricity costs. Maintenance costs Additional costs for empty runs : ; Maximize vehicle average load rate Objective 3: Load factor reflects vehicle resource utilization and is defined as the ratio of actual total cargo weight to the vehicle's rated total load capacity. .

[0029] In one specific embodiment, constraints are also included: Task assignment constraint: Each task can only be assigned to one vehicle. ; Vehicle load constraints: Overloading is prohibited; Time window constraints: .

[0030] In one specific embodiment, S4 specifically includes: S41. Based on the determined vehicle status data, task requirement data, port node status data, and port vehicle scheduling multi-objective optimization model, generate port scheduling basic list information, and set the population size M, iteration number N, and iteration termination condition. S42. Based on the population size M, the number of transportation tasks n, the number of port vehicles m obtained in S41, and the constraints of the multi-objective optimization model for port vehicle scheduling, randomly generate M chromosomes as the parent population. The chromosomes are encoded in binary format, and the chromosome gene length is m. n, where at most one gene in each of the n genes is encoded as 1, and the rest are 0; S43. Based on the encoding of each chromosome obtained in S42, determine the chromosome responsible for each transport task. Port vehicles ; S44. For the chromosome population obtained in S42, calculate the total completion time of the transportation task for each chromosome based on the port vehicle scheduling multi-objective optimization model obtained in S41. Total transportation cost and vehicle average load rate The non-dominated rank of each chromosome is calculated by non-dominated sorting. and crowding ; S45. Based on the parent population obtained in S42, perform genetic operations using custom crossover and mutation operators to generate a population of M offspring chromosomes. Furthermore, when the crossover requirement is met, two chromosomes are selected from the population for crossover using a binary tournament method. For every n genes, a gene of length n is selected from one chromosome as the offspring gene. When the mutation requirement is met, for every n genes in the chromosome, one gene is randomly selected and set to 1, while the rest are set to 0, thus forming the offspring chromosome.

[0031] S46. Combine the parent population from S42 with the offspring chromosome population generated in S45 to form a population of size 2M, and calculate the objective function value and perform non-dominated sorting, based on the non-dominated level. and crowding When sorting chromosomes, select M chromosomes as the new parent population; Furthermore, when sorting chromosomes, if and only if or and At that time, chromosome 1 was superior to chromosome 2.

[0032] S47. Based on the new parent population obtained in S46, repeat S45 to S46 to determine whether the number of genetic iterations and the termination condition meet the requirements. If the requirements are met, stop the iteration operation to obtain the final chromosome population. S48. The final chromosome population obtained from S47 makes the non-dominant hierarchy... The chromosome is the optimal Pareto solution set. Then, the optimal chromosome is obtained by comprehensively evaluating the total completion time of the transportation task, the total transportation cost, and the average vehicle load rate.

[0033] Furthermore, the comprehensive evaluation index for each individual solution. The calculation is as follows:

[0034] in, Let k be the objective value of the i-th solution individual. It is the optimal value of the k-th objective value for all individual solutions in the Pareto solution set.

[0035] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0036] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A dynamic and intensive scheduling decision-making method for port horizontal transport vehicles, characterized in that, include: S1. Real-time collection of port transportation-related data, including vehicle status data, task requirement data, and port node status data; S2. Determine the weights based on the task requirement data and port node status data, calculate the priority coefficient of each transportation task, and sort them from largest to smallest to form a task sequence. S3. Based on the vehicle status data and task sequence, construct a multi-objective optimization function with the objectives of minimizing the total task completion time, minimizing the total transportation cost, and maximizing the average vehicle load rate. S4. An improved genetic algorithm is used to solve a multi-objective optimization function with the objectives of minimizing total task completion time, minimizing total transportation cost, and maximizing average vehicle load rate, and the optimal scheduling scheme is generated.

2. The dynamic intensive scheduling decision-making method for port horizontal transport vehicles according to claim 1, characterized in that, The real-time collection of port transportation-related data specifically includes: collecting the following data in real time through the port Internet of Things system, vehicle GPS positioning terminals, loading and unloading equipment sensors, and port management system: Vehicle status data: Vehicle ID, real-time location, current load rate, remaining battery power, vehicle health status, and historical operating efficiency; Task requirements data: Task ID, cargo type, cargo weight, departure node, destination node, task urgency, latest completion time; Port node status data: node ID, number of currently operating equipment, equipment busyness, node congestion coefficient, travel distance between nodes and real-time traffic conditions.

3. The dynamic intensive scheduling decision-making method for port horizontal transport vehicles according to claim 1, characterized in that, The determination of weights specifically includes: A hierarchical model for the dynamic and intensive scheduling of port horizontal transport vehicles is constructed. The hierarchical structure of the dynamic and intensive scheduling model for port horizontal transport vehicles specifically includes: target layer: task priority coefficient; criteria layer: task urgency, time urgency, node coordination, and cargo importance; and solution layer: the set of transport tasks to be evaluated. Based on the scaling relationships between the various dimensions of the hierarchical model of the dynamic intensive scheduling scenario of port horizontal transport vehicles, the judgment matrix of the criterion layer is determined. The weights of each element at each level are determined based on the judgment matrix.

4. The dynamic intensive scheduling decision-making method for port horizontal transport vehicles according to claim 3, characterized in that, It also includes determining the scaling relationship values ​​between the dimensions of the criteria layer based on the hierarchical structure model of the dynamic intensive scheduling scenario of port horizontal transport vehicles, using the similarity matrix method and questionnaire survey method, and according to the scaling method of 1-9, and calculating the average value to obtain the judgment matrix; Calculate the largest eigenvalue of the judgment matrix and its corresponding eigenvector, and normalize the eigenvector to obtain the ranking weight vector. Then, sort and verify similarity. The ranking weight vector is used as the weight value of the relative importance between the dimensions of the criterion layer.

5. The dynamic intensive scheduling decision-making method for port horizontal transport vehicles according to claim 4, characterized in that, The similarity verification steps include: The similarity index is calculated using the following first formula based on the largest eigenvalue of the judgment matrix and the order of the judgment matrix; ； Where CI represents the similarity index. Let q represent the largest eigenvalue of the judgment matrix, q represent the order of the judgment matrix, CI=0 indicates perfect similarity, and CI close to 0 indicates satisfactory similarity. Based on the preset correspondence between the order and the random similarity index, the random similarity index corresponding to the order of the judgment matrix is ​​determined. Based on the similarity index and the random similarity index, the similarity deviation verification coefficient is calculated using the following second calculation formula: ； Wherein, CR represents the similarity deviation verification coefficient, and RI represents the random similarity index; If the similarity deviation verification coefficient is less than 0.1, the similarity verification is deemed to have passed; otherwise, the similarity verification fails, and the judgment matrix is ​​readjusted.

6. The dynamic intensive scheduling decision-making method for port horizontal transport vehicles according to claim 1, characterized in that, The calculation of the priority coefficient for each transportation task, and the sorting of tasks in descending order of priority coefficient to form a task sequence, specifically includes: The priority coefficient is a combination of the quantified values ​​from four dimensions, and the formula is as follows: ； in, This represents the urgency coefficient of the task. Time urgency coefficient; Node collaboration coefficient; This is the importance coefficient of the goods; These are the weight values ​​for the four dimensions; Calculate the priority coefficient P of all tasks to be assigned using the formula above; Sort the P-values ​​from largest to smallest to form a task sequence. ,in This is the highest priority task.

7. The dynamic intensive scheduling decision-making method for port horizontal transport vehicles according to claim 1, characterized in that, The construction of the multi-objective optimization function, which aims to minimize the total task completion time, minimize the total transportation cost, and maximize the average vehicle load rate, is specifically as follows: Suppose there are n tasks to be assigned. m available vehicles Define the core variables: As decision variables, =1 indicates a vehicle Assign tasks ; =0 indicates that no allocation has been made; For vehicles Execute the task Travel time; For vehicles Execute the task Loading and unloading time; For vehicles Execute the task Total transportation costs; For the task The weight of the goods; For vehicles Rated load capacity; Objective 1: Minimize the total task completion time The total task completion time is the sum of the travel time and loading / unloading time for all tasks, taking into account task priority: ； in For the task The priority coefficient is determined by the time weight of higher priority tasks, which are given priority to ensure their rapid completion. Objective 2: Minimize total transportation costs Total transportation costs include electricity costs. Maintenance costs Additional costs of empty runs : ； Maximize vehicle average load rate Objective 3: Load factor reflects vehicle resource utilization and is defined as the ratio of actual total cargo weight to the vehicle's rated total load capacity. 。 8. The dynamic intensive scheduling decision-making method for port horizontal transport vehicles according to claim 7, characterized in that, It also includes constraints: Task assignment constraint: Each task can only be assigned to one vehicle. ; Vehicle load constraints: Overloading is prohibited; Time window constraints: .

9. A dynamic and intensive scheduling decision-making method for port horizontal transport vehicles according to claim 7, characterized in that, S4 specifically includes: S41. Based on the determined vehicle status data, task requirement data, port node status data, and port vehicle scheduling multi-objective optimization model, generate port scheduling basic list information, and set the population size M, iteration number N, and iteration termination condition. S42. Based on the population size M, the number of transportation tasks n, the number of port vehicles m obtained in S41, and the constraints of the multi-objective optimization model for port vehicle scheduling, randomly generate M chromosomes as the parent population. The chromosomes are encoded in binary format, and the chromosome gene length is m. n, where at most one gene in each of the n genes is encoded as 1, and the rest are 0; S43. Based on the encoding of each chromosome obtained in S42, determine the chromosome responsible for each transport task. Port vehicles ; S44. For the chromosome population obtained in S42, calculate the total completion time of the transportation task for each chromosome based on the port vehicle scheduling multi-objective optimization model obtained in S41. Total transportation cost and vehicle average load rate The non-dominated rank of each chromosome is calculated by non-dominated sorting. and crowding ; S45. Based on the parent population obtained in S42, perform genetic operations using custom crossover and mutation operators to generate a population of M offspring chromosomes. S46. Combine the parent population from S42 with the offspring chromosome population generated in S45 to form a population of size 2M, and calculate the objective function value and perform non-dominated sorting, based on the non-dominated level. and crowding When sorting chromosomes, select M chromosomes as the new parent population; S47. Based on the new parent population obtained in S46, repeat S45 to S46 to determine whether the number of genetic iterations and the termination condition meet the requirements. If the requirements are met, stop the iteration operation to obtain the final chromosome population. S48. The final chromosome population obtained from S47 makes the non-dominant hierarchy... The chromosome is the optimal Pareto solution set. Then, the optimal chromosome is obtained by comprehensively evaluating the total completion time of the transportation task, the total transportation cost, and the average vehicle load rate.

Images