Port intelligent horizontal transportation equipment optimization scheduling method and system based on data driving

Abstract

The invention discloses a port intelligent horizontal transportation equipment optimization scheduling method and system based on data driving, and relates to the technical field of port logistics scheduling. The method comprises the following steps: firstly, acquiring port transportation related multi-dimensional data, preprocessing, and constructing a dynamic transportation task model to determine a task set; determining an optimization target in combination with the actual demand of a port, and establishing a target function and a scheduling optimization model with constraint conditions; and finally, carrying out multi-objective optimization calculation on the model by adopting a heuristic algorithm to obtain an optimal scheduling scheme of the horizontal transportation equipment. According to the method, uncertainty in port transportation operation can be accurately dealt with, the scheduling real-time performance and the optimization effect are improved, the operation efficiency of transportation equipment and the overall operation benefit of port logistics are improved, and the method is suitable for various complex port transportation scenes.

Description

Technical Field

[0001] This invention relates to the field of port logistics scheduling technology, and more specifically to a data-driven method and system for optimizing the scheduling of intelligent horizontal transportation equipment in ports. Background Technology

[0002] With the rapid development of the port logistics industry and the continuous growth of port throughput, horizontal transport equipment (such as container trucks and unmanned transport vehicles) is the core tool for port cargo transfer, and its scheduling efficiency directly affects the overall operational efficiency of the port. Traditional port horizontal transport equipment scheduling methods mostly rely on manual experience or simple static scheduling rules, which are difficult to cope with many uncertainties in port operations, such as fluctuations in cargo arrival time, sudden equipment failures, and temporary increases or decreases in work tasks.

[0003] While some dynamic optimization algorithms have been applied to scheduling, they suffer from insufficient real-time performance and poor optimization results in complex port scenarios. On one hand, traditional algorithms struggle to quickly process massive amounts of transportation task data and equipment status data, leading to delays in scheduling plan generation and an inability to respond promptly to changes in operational demands. On the other hand, most algorithms only optimize single objectives such as transportation time or cost, failing to comprehensively consider multi-dimensional requirements such as loading and unloading efficiency, equipment utilization, and delay losses, making it difficult to maximize the overall port benefits. Furthermore, existing scheduling methods do not comprehensively consider the port's geographical environment and equipment performance limitations, easily leading to problems such as equipment transportation path conflicts and tasks exceeding equipment operating capacity, further reducing scheduling reliability and operational efficiency.

[0004] Therefore, how to propose a data-driven intelligent horizontal transportation equipment optimization scheduling method and system for ports that can accurately cope with port operation uncertainties and improve scheduling real-time performance and multi-objective optimization effects is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, the present invention provides a data-driven method and system for optimizing the scheduling of intelligent horizontal transportation equipment in ports. By constructing a dynamic task model and a multi-objective optimization scheduling model through data-driven methods, and combining heuristic algorithms, efficient scheduling is achieved, thereby improving the operational efficiency and overall operational benefits of port transportation equipment. To achieve the above objectives, the present invention adopts the following technical solution: A data-driven method for optimizing the scheduling of intelligent horizontal transport equipment in ports, comprising: Acquire geographic information of the target operating area of ​​the port, historical data of similar transportation tasks, and performance parameters of horizontal transportation equipment; The acquired geographic information and historical data are preprocessed, and the transportation coverage and operational restrictions of the equipment are determined by combining the performance parameters of the horizontal transportation equipment. A dynamic transportation task model is constructed, and the transportation task information is updated in real time through the dynamic transportation task model to determine the transportation task set; The scheduling optimization objective is determined based on the port transportation operation requirements. An objective function is established based on the optimization objective. A scheduling optimization model is constructed based on the objective function, and constraints are set for the scheduling optimization model. A heuristic algorithm is used to perform multi-objective optimization calculations based on the aforementioned scheduling optimization model to obtain the optimal scheduling scheme for horizontal transportation equipment.

[0006] Optionally, the geographic information of the target port operation area includes the boundary coordinates of the operation area, obstacle location and height data, and the distribution of loading and unloading points; the historical data of the same type of transportation task includes the coordinates of the start and end points of the transportation task, cargo weight and volume, transportation time, delay records, and unit time delay cost; the performance parameters of the horizontal transportation equipment include maximum load capacity, maximum travel speed, endurance, and loading and unloading operation efficiency.

[0007] Optionally, the preprocessing includes: Identify missing values ​​in geographic information and historical data, and re-collect data or fill them in using interpolation methods based on the location of the port operation area or the task period corresponding to the missing data. Outliers in historical data are identified through statistical analysis, and data with excessively long transportation times or abnormally high delay costs are removed. Geographic information is converted into different formats and stored as a two-dimensional grid or a three-dimensional geographic information model. Historical data is standardized and data units are unified.

[0008] Optionally, determining the transportation coverage and operational limitations of the equipment by combining its performance parameters includes: determining the transportation coverage of the equipment within the port operation area by combining its performance parameters, such as maximum speed and range, and determining its operational limitations based on its maximum load capacity and loading / unloading efficiency.

[0009] Optionally, the construction of a dynamic transportation task model, which updates transportation task information in real time and determines the transportation task set, includes: S11: Determine the location, quantity, and attribute information of the initial transportation tasks within the target operation area of ​​the port, and denot this as the initial transportation task set: ,in, This represents a single transportation task, where n is the initial number of transportation tasks, and each task... The attribute information is as follows: ; in, These are the coordinates of the task's start and end points, respectively. , These are the weight and volume of the goods, respectively. The deadline for the task. As a task priority, Task status; S12: Introduce a dynamic transportation task model to monitor changes in transportation tasks within the port operation area in real time and remove completed tasks. The task is to obtain a new set of transportation tasks: Where m is the number of new tasks; S13: Combining the removed task set with the newly added task set, we obtain the dynamic transportation task set: And dynamically adjust task priorities based on task deadlines and urgency: ; in, For the current time, Where k is the time threshold and k is the priority adjustment coefficient. As the highest priority task, This indicates that the task is an urgent task; S14: Based on the transportation coverage of the horizontal transport equipment and the adjusted task priority, select tasks within the equipment's operational capacity and generate the final set of transport tasks. ; in, This is the distance calculation function. The current location of the transport equipment. This refers to the coverage area for equipment transportation.

[0010] Optionally, the determined scheduling optimization objectives include the shortest loading and unloading time, the shortest transportation time, the lowest unit time delay cost, and maximizing equipment utilization. The objective function is: ; in, To optimize the weight parameters of the objective, and , For cargo loading and unloading time, For transportation time, Cost per unit of time delay For equipment utilization rate.

[0011] Optionally, the constraints set for the scheduling optimization model include: Equipment load constraints: ,in, This is the maximum load capacity of the transport equipment; Device battery life constraints: ; in, For the task The transportation distance This refers to the device's maximum battery life. Task time constraints: ; Path obstacle avoidance constraint: The travel path of transport equipment must not cross obstacles within the port operation area, that is, the distance between any point on the path and an obstacle must be greater than the safe distance threshold.

[0012] Optionally, the adjustment strategy for the weighting parameters is as follows: when port operations prioritize improving loading and unloading efficiency, increase... The weighting; when demand focuses on shortening transportation cycles, increase Weighting; when demand focuses on reducing delay losses, increase The weighting; when the demand focuses on making full use of equipment resources, increase The weight.

[0013] Optionally, the step of using a heuristic algorithm to perform multi-objective optimization calculations based on the scheduling optimization model to obtain the optimal scheduling scheme for horizontal transport equipment includes: using a non-dominated sorting genetic algorithm II for multi-objective optimization calculations, specifically including the following steps: S21: Population initialization. An initial population is generated using a greedy algorithm. Each individual in the population represents a horizontal transportation equipment scheduling scheme, including equipment allocation and transportation path planning. During initialization, high-priority tasks are prioritized for allocation to currently idle equipment with the highest operating efficiency. Within the equipment's transportation coverage area, the scheme with the shortest path is selected to generate the initial solution. S22: Objective function calculation. Based on the established objective function, calculate the objective function value of each individual in the initial population, and conduct multi-objective evaluation from four dimensions: loading and unloading time, transportation time, delay cost, and equipment utilization rate. S23: Non-dominated sorting, sorting individuals in the population according to the objective function value, determining the Pareto optimal solution, dividing the non-dominated solution into different levels, and retaining the better solutions at the lower levels; S24: Calculate the crowding distance, calculate the crowding degree of each individual in the population, and prioritize individuals with high crowding degree as high-quality individuals to ensure the diversity of solutions; S25: Selection, crossover and mutation. Select high-quality individuals to enter the next generation of the population. Perform crossover operations on the selected individuals to exchange some equipment allocation or path planning information to generate new solutions. Perform mutation operations on some individuals to randomly adjust equipment allocation or path nodes and explore a better solution space. S26: Iterative Update: Repeat steps S22-S25 until the maximum number of iterations is reached or the objective function value converges, then stop updating and output the optimal scheduling scheme for the horizontal transportation equipment.

[0014] Optionally, a data-driven intelligent horizontal transport equipment optimization scheduling system for ports includes: Data acquisition module: used to acquire geographic information of the target operation area of ​​the port, historical data of similar transportation tasks, and performance parameters of horizontal transportation equipment; Data preprocessing module: used to preprocess the acquired geographic information and historical data, and combine them with the performance parameters of horizontal transport equipment to determine the transport coverage and operational restrictions of the equipment; Dynamic task modeling module: used to construct a dynamic transportation task model, and to update transportation task information in real time through the dynamic transportation task model to determine the transportation task set; Scheduling optimization module: used to determine the scheduling optimization objective based on the port transportation operation requirements, establish an objective function based on the optimization objective, construct a scheduling optimization model in combination with the objective function, and set constraints on the scheduling optimization model; The results output module is used to perform multi-objective optimization calculations based on the scheduling optimization model using heuristic algorithms to obtain the optimal scheduling scheme for horizontal transportation equipment.

[0015] As can be seen from the above technical solution, compared with the prior art, the present invention discloses a data-driven method and system for optimizing the scheduling of intelligent horizontal transport equipment in ports, which has the following beneficial effects: This invention proposes a data-driven method for optimizing the scheduling of intelligent horizontal transport equipment in ports. The method includes: acquiring geographic information of the target operating area of ​​the port, historical data of similar transport tasks, and performance parameters of the horizontal transport equipment; preprocessing the acquired geographic information and historical data, and determining the transport coverage and operational constraints of the equipment based on the performance parameters; constructing a dynamic transport task model, updating transport task information in real time through the dynamic transport task model, and determining the set of transport tasks; determining the scheduling optimization objective based on the port's transport operation requirements, establishing an objective function based on the optimization objective, constructing a scheduling optimization model based on the objective function, and setting constraints on the scheduling optimization model; and using a heuristic algorithm to perform multi-objective optimization calculations based on the scheduling optimization model to obtain the optimal scheduling scheme for the horizontal transport equipment. Data-driven approach improves accuracy: by collecting port geographic information, historical task data, and equipment performance parameters, combined with data preprocessing technology, a reliable data foundation is provided for scheduling optimization, effectively addressing the uncertainties of port operations and reducing human experience errors. This invention achieves (1) multi-objective optimization with comprehensive benefits: constructing a multi-objective function covering loading and unloading time, transportation time, delay costs, and equipment utilization, combined with a dynamic weight adjustment strategy, which can be flexibly optimized according to different port operation needs to maximize overall operational benefits. (2) dynamic response to enhance adaptability: updating task information and priorities in real time through a dynamic transportation task model to ensure that the scheduling scheme can respond to changes such as task additions and subtractions and emergency task insertions in a timely manner, thereby improving scheduling flexibility. (3) heuristic algorithm to ensure efficiency: using a non-dominated sorting genetic algorithm II for optimization calculation, taking into account the quality and diversity of solutions, quickly generating the optimal scheduling scheme to meet the real-time requirements of port operations, while ensuring the feasibility and safety of the scheme through constraints. Attached Figure Description

[0016] 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.

[0017] Figure 1 This invention provides a schematic flowchart of a data-driven method for optimizing the scheduling of intelligent horizontal transportation equipment in ports.

[0018] Figure 2 This invention provides a structural framework diagram of a data-driven intelligent horizontal transportation equipment optimization scheduling system for ports. Detailed Implementation

[0019] 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.

[0020] This invention discloses a data-driven method for optimizing the scheduling of intelligent horizontal transport equipment in ports, such as... Figure 1 As shown, it includes: Acquire geographic information of the target operating area of ​​the port, historical data of similar transportation tasks, and performance parameters of horizontal transportation equipment; The acquired geographic information and historical data are preprocessed, and the transportation coverage and operational restrictions of the equipment are determined by combining the performance parameters of the horizontal transportation equipment. A dynamic transportation task model is constructed, and the transportation task information is updated in real time through the dynamic transportation task model to determine the transportation task set; The scheduling optimization objective is determined based on the port transportation operation requirements. An objective function is established based on the optimization objective. A scheduling optimization model is constructed based on the objective function, and constraints are set for the scheduling optimization model. A heuristic algorithm is used to perform multi-objective optimization calculations based on the aforementioned scheduling optimization model to obtain the optimal scheduling scheme for horizontal transportation equipment.

[0021] In a specific implementation, a data-driven method for optimizing the scheduling of intelligent horizontal transport equipment in ports includes the following steps: S1. Obtain geographic information of the target operation area of ​​the port, historical data of similar transportation tasks, and performance parameters of horizontal transportation equipment.

[0022] Specifically, the geographical information of the target operating area of ​​the port is the basis for determining the equipment transportation route and avoiding obstacles. This includes: the boundary coordinates of the operating area (to clarify the equipment operating range), the location and height data of obstacles (such as fixed buildings and stacked cargo within the port to avoid collisions with the equipment), and the distribution of loading and unloading points (such as quay crane loading and unloading points and yard loading and unloading areas in container terminals to determine the start and end points of the task).

[0023] Historical data on similar transportation tasks provides data support for scheduling optimization, covering the coordinates of the starting and ending points of the transportation task (used to calculate transportation distance), cargo weight and volume (matching equipment load capacity), transportation time (analyzing historical transportation efficiency and optimizing time targets), delay records (statistically analyzing the causes and frequency of delays to reduce the risk of future delays), and unit time delay cost (quantifying delay losses as one of the optimization objectives).

[0024] The performance parameters of horizontal transport equipment determine the boundaries of its operational capabilities, including maximum load (limiting the weight of transportable goods), maximum speed (affecting transport time calculation), range (for electric equipment, determining the maximum mileage of a single operation), and loading and unloading efficiency (such as the operating speed of the equipment's built-in loading and unloading device, affecting the overall task duration).

[0025] S2. Preprocess the acquired geographic information and historical data, and determine the transportation coverage and operational restrictions of the equipment by combining the performance parameters of the horizontal transportation equipment.

[0026] Data preprocessing is crucial for ensuring the accuracy of subsequent modeling and optimization. Specific steps include: S201. Missing Value Handling: Identify missing values ​​in geographic information and historical data, such as missing cargo weight records for some historical tasks, or missing obstacle data for a certain area in geographic information. For cases that can be re-collected, such as supplementing obstacle data through on-site port surveying, conduct on-site collection; for cases that are difficult to re-collect, such as partial attributes of historical tasks, use interpolation methods (such as interpolation based on the mean of data from tasks of the same type and time period) to fill in the missing values.

[0027] S202. Outlier Removal: Statistical analysis (such as setting a standard deviation range for data) is used to filter out outliers in historical data. For example, if the transportation time of a certain task is much longer than the average time of tasks at the same distance, or the unit time delay cost is abnormally high (which may be due to a recording error), these outliers are removed to avoid interfering with the optimization results.

[0028] S203. Data Standardization and Format Conversion: Convert geographic information into two-dimensional grids or three-dimensional geographic information models (such as using GIS system format) to facilitate intuitive display of the work area environment and subsequent route planning; standardize historical data, for example, unify the transportation distance (meters, kilometers) of different units to kilometers, and unify the weight of goods (tons, kilograms) to tons, to eliminate the impact of unit differences on multi-objective optimization.

[0029] S204. Determine the equipment's operational boundaries: Based on the performance parameters of the horizontal transport equipment, such as the maximum speed and the size of the port's operational area, determine the transport coverage area of ​​the equipment within a certain time period (e.g., if the equipment's maximum speed is 30 km / h and it can travel continuously for 2 hours in a single operation, then the transport coverage area is an area with a radius of 60 km centered on the equipment's initial position); at the same time, clarify the operational restrictions based on the equipment's maximum load capacity and loading / unloading efficiency, such as equipment with a maximum load capacity of 50 tons cannot be assigned cargo tasks exceeding that weight.

[0030] S3. Construct a dynamic transportation task model, and use the dynamic transportation task model to update transportation task information in real time to determine the transportation task set.

[0031] Port transportation tasks are characterized by dynamic changes, such as the addition of emergency transportation tasks or the early completion of some tasks. Therefore, it is necessary to construct a dynamic transportation task model to adjust the task set in real time. The specific steps include: S301. Determining the Initial Task Set: Determine the location, quantity, and attribute information of the initial transportation tasks within the target operation area of ​​the port, denoted as the initial transportation task set. ,in, This represents a single transportation task, where n is the initial number of transportation tasks. Each task The attribute information comprehensively reflects the characteristics of the task. These are the coordinates of the task's start and end points, respectively. , These are the weight and volume of the goods, respectively. The deadline for the task (e.g., a batch of goods needs to be transported from the quay crane to the yard within 2 hours). Assign task priority (e.g., dangerous goods transport tasks have a higher priority than ordinary goods tasks, with a range of 1-10, where 10 is the highest). The task status (including pending assignment, in progress, and completed).

[0032] S302, Dynamic Task Update: Introducing a dynamic transportation task model, the port operation monitoring system monitors changes in transportation tasks in real time. First, tasks already completed are removed. The task is to reduce unnecessary calculations; then, the set of new transportation tasks is obtained. , where m is the number of new tasks, such as temporary container transport tasks arriving at the port.

[0033] S303, Task Priority Adjustment: Based on the removed task set With the new task set A dynamic set of transportation tasks is obtained. Priority is dynamically adjusted based on task deadlines and urgency. If there is remaining time for a task... If the time is less than the set time threshold (e.g., 30 minutes), then the formula will be used. Increase priority, where k is the priority adjustment coefficient (set according to the actual needs of the port, such as 5). The shorter the remaining time, the greater the priority increase; if the task is an urgent task ( For example, in the transportation of emergency relief supplies, the priority should be set to the highest. (e.g., 10).

[0034] S304. Final Task Set Generation: Based on the transportation coverage of the horizontal transport equipment and the adjusted task priorities, tasks within the equipment's operational capacity are selected to generate the final transportation task set. ,in, This is a distance calculation function (such as the Euclidean distance formula). This represents the current location of the transport equipment, and range represents the equipment's transport coverage area, ensuring that the filtered tasks can be completed by the equipment.

[0035] S4. Determine the scheduling optimization objective based on the port transportation operation requirements, establish an objective function based on the optimization objective, construct a scheduling optimization model in combination with the objective function, and set constraints on the scheduling optimization model.

[0036] The scheduling optimization objectives must align with the actual operational needs of the port, comprehensively considering multi-dimensional benefits. The determined optimization objectives include: minimizing cargo loading and unloading time (improving loading and unloading efficiency and reducing task waiting time); minimizing transportation time (shortening cargo transshipment cycles and increasing port turnover); minimizing unit-time delay costs (reducing economic losses caused by delays); and maximizing equipment utilization (fully utilizing equipment resources and reducing idle waste). Based on these optimization objectives, the objective function is established as follows: ; in, To optimize the weight parameters of the objective, and satisfy... This is used to balance the importance of different objectives; LoadUnloadTime is the cargo loading and unloading time (calculated using historical loading and unloading efficiency data and current cargo attributes); TransportTime is the transportation time (calculated from the transportation distance and the maximum operating speed of the equipment, i.e., ...). DelayCost is the unit time delay cost (taken from historical data; it is 0 if the task is completed on time); DeviceUtilization is the equipment utilization rate (calculated as the ratio of actual equipment operating time to total available time).

[0037] Furthermore, to ensure the feasibility of the scheduling scheme, the following constraints are set for the scheduling optimization model: Equipment load constraints: Ensure that the weight of the cargo assigned to the equipment does not exceed the equipment's maximum load capacity to avoid overloading and damage.

[0038] Device battery life constraints This ensures that the transportation distance is within the equipment's battery life, preventing the equipment from being unable to complete the task due to insufficient power during operation.

[0039] Task time constraints: This ensures that the total time from loading and unloading to transportation does not exceed the remaining time, reducing the risk of mission delays.

[0040] Path obstacle avoidance constraints: The travel path of transport equipment must not cross obstacles within the port operation area. The distance between any point on the path and an obstacle is calculated using obstacle data in the geographic information model. The distance must be greater than a safe distance threshold (e.g., 5 meters) to ensure the safety of the equipment.

[0041] Furthermore, the weighting parameters need to be flexibly set according to the different operational scenarios of the port. For example, when the port faces cargo accumulation and needs to be quickly evacuated, the operational requirements focus on improving loading and unloading efficiency, in which case increasing the weighting parameters would be more appropriate. The weight (e.g., set to 0.4); when there are urgent goods that need to be transferred to their destination as soon as possible, the demand focuses on shortening the transportation cycle and improving efficiency. The weight (e.g., set to 0.4); when a port faces high economic compensation due to recent delays, the focus should be on reducing delay losses and increasing... The weight (e.g., set to 0.4); when the number of port equipment is small and existing resources need to be fully utilized, the demand focuses on equipment utilization rate and improving it. The weight (e.g., set to 0.4).

[0042] S5. Using a heuristic algorithm, multi-objective optimization calculations are performed based on the aforementioned scheduling optimization model to obtain the optimal scheduling scheme for horizontal transportation equipment.

[0043] Heuristic algorithms can efficiently handle multi-objective optimization problems. This invention employs the Non-Dominated Sorting Genetic Algorithm II (NSGA-II), which has the advantages of fast convergence speed and good solution diversity. The specific steps include: S501. Population Initialization: An initial population is generated using a greedy algorithm. Each individual in the population represents a horizontal transportation equipment scheduling scheme, including equipment allocation (e.g., which task is assigned to which equipment) and transportation path planning (the route the equipment travels from the starting point to the destination).

[0044] During initialization, high-priority tasks are assigned to currently idle equipment with the highest operating efficiency (such as equipment with fast loading and unloading speed and high travel speed). Within the equipment's transportation coverage area, the shortest path is selected based on the geographic information model to generate an initial solution, ensuring that the initial population has a certain quality and reducing the number of subsequent iterations.

[0045] S502. Objective function calculation: Based on the established objective function, calculate the objective function value of each individual in the initial population. Perform multi-objective evaluation on each scheduling scheme from four dimensions: loading and unloading time, transportation time, delay cost, and equipment utilization rate to obtain the comprehensive performance index of each individual.

[0046] S503. Non-dominated sorting: Sort the individuals in the population according to the objective function value to determine the Pareto optimal solution (non-dominated solution)—that is, no other individual is better than this individual in all objectives. Divide the non-dominated solutions into different levels, for example, the first level is the set of optimal solutions, the second level is the set of suboptimal solutions, retain the better solutions at the lower level, and eliminate individuals with poor performance.

[0047] S504. Calculate Crowding Distance: Calculate the crowding degree of each individual in the population. Crowding distance reflects the distribution density of an individual in the target space. The higher the crowding degree, the fewer solutions are around that individual. Retaining such individuals ensures solution diversity and avoids the algorithm getting trapped in local optima. The calculation method is as follows: For each target dimension, sort the individuals according to their objective function values. Set the crowding distance of boundary individuals to infinity, and the crowding distance of middle individuals is the sum of the differences in objective function values ​​between two adjacent individuals in that dimension.

[0048] S505, Selection, Crossover, and Mutation: Select high-quality individuals (individuals with high crowding and low level) to enter the next generation of the population to ensure the overall quality of the population; perform crossover operations on the selected individuals, such as exchanging task allocation information or some path nodes between two devices to generate new solutions; perform mutation operations on some individuals, such as randomly adjusting the allocation device of a task or modifying a node in the path to explore a wider solution space and avoid premature convergence of the algorithm.

[0049] S506. Iterative Update: Repeat steps S502-S505 until the maximum number of iterations is reached (e.g., 100 times, set according to the real-time requirements of port operations) or the objective function value converges (in multiple consecutive iterations, the change in the objective function value of the optimal solution is less than a set threshold, such as 0.01). Stop updating and output the optimal scheduling scheme for horizontal transport equipment. The scheme includes specific task-equipment allocation relationships, the travel path of each piece of equipment, task execution time planning, etc.

[0050] Furthermore, this invention also provides a data-driven intelligent horizontal transport equipment optimization scheduling system for ports, used to execute the above-mentioned scheduling method, such as... Figure 2 As shown, the system includes: Data acquisition module: Composed of various sensors (such as GPS positioning devices and equipment status sensors in the port operation area) and data interfaces (such as interface with the port management system to obtain historical task data), it is responsible for acquiring the geographic information of the target operation area of ​​the port, historical data of similar transportation tasks, and performance parameters of horizontal transportation equipment, and transmitting the acquired data to the data preprocessing module.

[0051] Data preprocessing module: Employs data processing algorithms (such as interpolation algorithms and outlier detection algorithms) to perform missing value imputation, outlier removal, format conversion, and standardization on the data acquired by the data acquisition module. Combined with equipment performance parameters, it determines the equipment transportation coverage and operational constraints, and transmits the processed data to the dynamic task modeling module and scheduling optimization module.

[0052] Dynamic task modeling module: Based on real-time data monitoring and analysis technology, it constructs a dynamic transportation task model, updates transportation task information in real time, determines the initial transportation task set, dynamic transportation task set and final transportation task set, and transmits the final task set to the scheduling optimization module.

[0053] Scheduling optimization module: It has a built-in multi-objective optimization algorithm (non-dominated sorting genetic algorithm II), which determines the optimization objective based on the port transportation operation requirements, establishes the objective function and scheduling optimization model, sets constraints, performs multi-objective optimization calculations, generates the optimal scheduling scheme, and transmits the scheme to the result output module.

[0054] Results output module: includes a visualization unit (such as using a large screen display system to display the map distribution of the transportation equipment scheduling plan, task execution progress bar, equipment operation status indicator light and the change curve of optimization indicators (loading and unloading time, transportation time, etc.) in real time) and a data export unit (supports exporting the scheduling optimization results in Excel, PDF and other formats for port management personnel to archive, analyze and make decisions).

[0055] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory. When the processor executes the computer program, it implements the aforementioned data-driven port intelligent horizontal transportation equipment optimization scheduling method. This electronic device can use an industrial computer, possesses strong data processing capabilities and stability, and is suitable for the complex industrial environment of ports.

[0056] 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.

[0057] 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 data-driven method for optimizing the scheduling of intelligent horizontal transport equipment in ports, characterized in that, include: Acquire geographic information of the target operating area of ​​the port, historical data of similar transportation tasks, and performance parameters of horizontal transportation equipment; The acquired geographic information and historical data are preprocessed, and the transportation coverage and operational restrictions of the equipment are determined by combining the performance parameters of the horizontal transportation equipment. A dynamic transportation task model is constructed, and the transportation task information is updated in real time through the dynamic transportation task model to determine the transportation task set; The scheduling optimization objective is determined based on the port transportation operation requirements. An objective function is established based on the optimization objective. A scheduling optimization model is constructed based on the objective function, and constraints are set for the scheduling optimization model. A heuristic algorithm is used to perform multi-objective optimization calculations based on the aforementioned scheduling optimization model to obtain the optimal scheduling scheme for horizontal transportation equipment.

2. The data-driven port intelligent horizontal transportation equipment optimization scheduling method according to claim 1, characterized in that, The geographic information of the target port operation area includes the boundary coordinates of the operation area, the location and height data of obstacles, and the distribution of loading and unloading points; the historical data of the same type of transportation task includes the coordinates of the start and end points of the transportation task, the weight and volume of the cargo, the transportation time, delay records, and the unit time delay cost; the performance parameters of the horizontal transportation equipment include the maximum load capacity, maximum speed, range, and loading and unloading efficiency.

3. The data-driven port intelligent horizontal transportation equipment optimization scheduling method according to claim 1, characterized in that, The preprocessing includes: Identify missing values ​​in geographic information and historical data, and re-collect data or fill them in using interpolation methods based on the location of the port operation area or the task period corresponding to the missing data. Outliers in historical data are identified through statistical analysis, and data with excessively long transportation times or abnormally high delay costs are removed. Geographic information is converted into different formats and stored as a two-dimensional grid or a three-dimensional geographic information model. Historical data is standardized and data units are unified.

4. The data-driven port intelligent horizontal transportation equipment optimization scheduling method according to claim 1, characterized in that, The method of determining the transportation coverage and operational limitations of horizontal transport equipment by combining its performance parameters includes: determining the transportation coverage of the equipment within the port operation area by combining the performance parameters of the horizontal transport equipment, such as maximum speed and range, and determining its operational limitations based on the equipment's maximum load capacity and loading / unloading efficiency.

5. The data-driven port intelligent horizontal transportation equipment optimization scheduling method according to claim 1, characterized in that, The construction of a dynamic transportation task model, through which transportation task information is updated in real time, determines the set of transportation tasks, including: S11: Determine the location, quantity, and attribute information of the initial transportation tasks within the target operation area of ​​the port, and denot this as the initial transportation task set: ,in, This represents a single transportation task, where n is the initial number of transportation tasks, and each task... The attribute information is as follows: ； in, These are the coordinates of the task's start and end points, respectively. , These are the weight and volume of the goods, respectively. The deadline for the task. As a task priority, Task status; S12: Introduce a dynamic transportation task model to monitor changes in transportation tasks within the port operation area in real time and remove completed tasks. The task is to obtain a new set of transportation tasks: Where m is the number of new tasks; S13: Combining the removed task set with the newly added task set, we obtain the dynamic transportation task set: And dynamically adjust task priorities based on task deadlines and urgency: ； in, For the current time, Where k is the time threshold and k is the priority adjustment coefficient. As the highest priority task, This indicates that the task is an urgent task; S14: Based on the transportation coverage of the horizontal transport equipment and the adjusted task priority, select tasks within the equipment's operational capacity and generate the final set of transport tasks. ； in, This is the distance calculation function. The current location of the transport equipment. This refers to the coverage area for equipment transportation.

6. The data-driven port intelligent horizontal transportation equipment optimization scheduling method according to claim 1, characterized in that, The determined scheduling optimization objectives include the shortest loading and unloading time, the shortest transportation time, the lowest unit time delay cost, and maximizing equipment utilization. The objective function is: ； in, To optimize the weight parameters of the objective, and , For cargo loading and unloading time, For transportation time, Cost per unit of time delay For equipment utilization rate.

7. The data-driven port intelligent horizontal transportation equipment optimization scheduling method according to claim 1, characterized in that, The constraints set for the scheduling optimization model include: Equipment load constraints: ,in, This is the maximum load capacity of the transport equipment; Device battery life constraints: ; in, For the task The transportation distance This refers to the device's maximum battery life. Task time constraints: ; Path obstacle avoidance constraint: The travel path of transport equipment must not cross obstacles within the port operation area, that is, the distance between any point on the path and an obstacle must be greater than the safe distance threshold.

8. A data-driven method for optimizing the scheduling of intelligent horizontal transport equipment in ports, as described in claim 6, is characterized in that... The adjustment strategy for the weighting parameters is as follows: when port operations prioritize improving loading and unloading efficiency, increase... The weights; When demand focuses on shortening transportation cycles, improving The weights; When demand focuses on reducing delay losses, improve The weights; When the focus is on making full use of equipment resources, improving The weight.

9. The data-driven port intelligent horizontal transportation equipment optimization scheduling method according to claim 1, characterized in that, The method of using a heuristic algorithm to perform multi-objective optimization calculations based on the scheduling optimization model to obtain the optimal scheduling scheme for horizontal transport equipment includes: using a non-dominated sorting genetic algorithm II for multi-objective optimization calculations, the specific steps of which include: S21: Population initialization. An initial population is generated using a greedy algorithm. Each individual in the population represents a horizontal transportation equipment scheduling scheme, including equipment allocation and transportation path planning. During initialization, high-priority tasks are prioritized for allocation to currently idle equipment with the highest operating efficiency. Within the equipment's transportation coverage area, the scheme with the shortest path is selected to generate the initial solution. S22: Objective function calculation. Based on the established objective function, calculate the objective function value of each individual in the initial population, and conduct multi-objective evaluation from four dimensions: loading and unloading time, transportation time, delay cost, and equipment utilization rate. S23: Non-dominated sorting, sorting individuals in the population according to the objective function value, determining the Pareto optimal solution, dividing the non-dominated solution into different levels, and retaining the better solutions at the lower levels; S24: Calculate the crowding distance, calculate the crowding degree of each individual in the population, and prioritize individuals with high crowding degree as high-quality individuals to ensure the diversity of solutions; S25: Selection, crossover and mutation. Select high-quality individuals to enter the next generation of the population. Perform crossover operations on the selected individuals to exchange some equipment allocation or path planning information to generate new solutions. Perform mutation operations on some individuals to randomly adjust equipment allocation or path nodes and explore a better solution space. S26: Iterative Update: Repeat steps S22-S25 until the maximum number of iterations is reached or the objective function value converges, then stop updating and output the optimal scheduling scheme for the horizontal transportation equipment.

10. A data-driven intelligent horizontal transport equipment optimization scheduling system for ports, characterized in that, include: Data acquisition module: used to acquire geographic information of the target operation area of ​​the port, historical data of similar transportation tasks, and performance parameters of horizontal transportation equipment; Data preprocessing module: used to preprocess the acquired geographic information and historical data, and combine them with the performance parameters of horizontal transport equipment to determine the transport coverage and operational restrictions of the equipment; Dynamic task modeling module: used to construct a dynamic transportation task model, and to update transportation task information in real time through the dynamic transportation task model to determine the transportation task set; Scheduling optimization module: used to determine the scheduling optimization objective based on the port transportation operation requirements, establish an objective function based on the optimization objective, construct a scheduling optimization model in combination with the objective function, and set constraints on the scheduling optimization model; The results output module is used to perform multi-objective optimization calculations based on the scheduling optimization model using heuristic algorithms to obtain the optimal scheduling scheme for horizontal transportation equipment.

Images