Equipment collaborative scheduling method in sea-railway combined transport port mixed mode and electronic equipment

Abstract

The invention relates to an equipment collaborative scheduling method in a sea-railway combined transport port mixed mode and electronic equipment, and belongs to the technical field of port engineering. The method comprises the following steps: by taking preset operation sequence connection, safe operation of a rail-mounted gantry crane and waiting time of each device as constraints, unloading a container onto a container truck by the rail-mounted gantry crane, and then transporting the container to a wharf by the container truck to wait for quay crane operation; a scheduling model is established according to the working condition of a transfer mode that the rail-mounted gantry crane stacks the containers needing to be stacked to the designated container positions of the railway storage yard; the scheduling model is solved based on the grey wolf algorithm introducing the chromosome uniform crossover strategy, a final equipment cooperative scheduling scheme is obtained, and the problem that in the prior art, research on the scheduling mode is single in actual work is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of port engineering technology, and in particular to a method for collaboratively dispatching equipment in a sea-rail transport port hybrid mode and electronic equipment. Background Art

[0002] In recent years, my country has actively promoted the development of container multimodal transport, and sea-rail transport has gradually occupied an increasingly important position in the comprehensive transportation system because it integrates the advantages of safety, environmental protection, large capacity and speed of both sea and rail transport modes.

[0003] In sea-rail transport, the port's railway operating area plays a crucial role in connecting rail and water transport, and is a critical node in the sea-rail transport process. Efficient sea-rail transport operations can significantly improve container loading and unloading efficiency and reduce turnaround time, thereby directly improving the operational efficiency and cargo flow speed of the entire sea-rail transport system. Currently, there are certain problems with the operational connection between container trains and ports, such as uncoordinated configuration and unreasonable quantity of loading and unloading equipment, uncertain train arrival and departure times, non-standard operating procedures, and unscientific organizational management, which in turn have a negative impact on the overall competitiveness of sea-rail transport. Therefore, the rational configuration and management of port loading and unloading equipment is both a prerequisite for sea-rail transport and an essential guarantee for the smooth and efficient completion of port operations. It is necessary to rationally configure and coordinate the scheduling of loading and unloading equipment at sea-rail transport ports.

[0004] Most existing research on equipment scheduling in sea-rail intermodal ports focuses on the coordinated scheduling of equipment under a single operating mode: the "ship-yard-train" or "ship-train" mode. Few studies have explored both modes in a comprehensive manner. Research on equipment scheduling in sea-rail intermodal ports that considers both modes is more consistent with practical port operations. Furthermore, few studies have examined sea-rail intermodal ports where railway yards are located closely alongside loading and unloading lines. Most research focuses on a shared yard layout for both railway and port containers. Furthermore, with the continuous development of sea-rail intermodal transport, the collaborative operation capabilities between trains and ships have significantly improved, enabling more direct and efficient transfer of containers from railway operating areas to ships waiting at the dock. However, current research on this issue mostly employs static scheduling between trains and ships, assuming that one or more railway container trains are already waiting at the port's railway loading and unloading line for container loading and unloading when sea-rail intermodal transport operations begin. Few scholars have considered the constraint of train arrival time when scheduling equipment in sea-rail transport ports, and have linked the port's original export container operation tasks before the train arrives with the train operation tasks after the train arrives. Summary of the Invention

[0005] In view of this, it is necessary to provide a method for collaborative scheduling of equipment in a hybrid mode of sea-rail transport ports to solve the problem that the existing technology has a relatively single research on scheduling modes in actual work.

[0006] In order to solve the above problems, the present invention provides a method for coordinated dispatching of equipment in a hybrid mode of sea-rail transport ports, comprising: Taking minimizing the maximum completion time within the entire operation planning cycle as the objective function, and using the preset operation sequence, safe operation of the rail crane, and the waiting time of each equipment as constraints, a scheduling model was established for the following working conditions: a direct pickup mode in which the rail crane unloads the container onto a container truck, which then transports the container to the terminal to wait for the quay crane to operate, and a transshipment mode in which the rail crane stores the required containers at a designated container location in the railway yard. The scheduling model is solved based on the grey wolf algorithm that introduces the chromosome uniform crossover strategy, and the final equipment collaborative scheduling solution is obtained.

[0007] In a possible implementation, the objective function includes:

[0008] in, represents the objective function, Represents a collection of container tasks, Indicates the collection of containers in the original railway yard after rescheduling. Indicates the container collection on the train shore. Indicates the collection of containers stored in the train yard. Indicates the collection of containers in the railway yard before rescheduling, , Represents the quay crane collection, indexed by , Represents the rail door crane collection, indexed by , Represents a card collection, indexed by , Indicates quay crane q For containers i End of work time, Indicates rail crane g For containers i End of work time, Indicates card collection b For containers i End of work time; It is related to whether the train arrives at the preset time. If it arrives, ,otherwise .

[0009] In a possible implementation, the constraint of the job sequence continuation includes:

[0010]

[0011]

[0012] in, If the container j For rail gantry crane g The start task is If it is the end of the task, then ; If the container i For rail gantry crane g If the task ends, , if it is a start task, then ; If the container j For quay crane q The start task is If it is the end task, then ; If the container i For quay crane q The start task is If it is the end task, then ; If the container j For card collection b The start task is If the task is to be completed, ; If the container i For card collection b The start task is ; If it is to end the task, then ; If the container i By rail crane g Homework, then ,otherwise ; If the container i By Jika b Homework, then ,otherwise ; If the container i By quay crane q Homework, then ,otherwise .

[0013] In a possible implementation, the constraint of safe operation of the rail crane includes: Set rail crane safe operating distance constraints, rail crane operation constraints, container truck operation constraints, and quay crane operation constraints.

[0014] In a possible implementation, the rail crane safe operating distance constraint includes:

[0015] in, represents the initial position of the container, Indicates the target location of the container, Indicates the train car number corresponding to the container; when the rail crane For containers i While working, the rail crane For containers j Homework, then The value of is 1, otherwise the value is 0; The safe operating distance of rail cranes and the distance between rail cranes cannot be crossed; The rail crane operation constraints include:

[0016] in, Indicates rail crane For containers i Start time of work, Indicates rail crane For containers i End of work time, Indicates card collection The end time of operation for container k, Indicates rail crane From the previous task i Target location to subsequent tasks j Time of initial position, Indicates card collection From the previous task k Target location to subsequent tasks i Time of initial position, Indicates rail crane Homework tasks i The waiting time for the truck is Indicates rail crane Self-pick up container i The time required to reach the target location and place the container; if the rail crane For containers i and containers j Perform operations and i and j If it is a continuous operation, The value is 1, otherwise the value is 0; The trucking operation constraints include:

[0017]

[0018] in, Indicates card collection For containers j Start time of work, Indicates quay crane For containers k Start time of work, Indicates card collection For containers i End of work time, Indicates card collection From the previous task i Target location to subsequent tasks j Time of initial position, Indicates card collection Homework tasks j Waiting time for rail crane time, Indicates card collection b Homework tasks j Waiting for the quay crane q time, Indicates rail crane Self-pick up container j The time required to drop the container at the target location, Indicates the time when the quay crane completes loading and unloading; if the container truck For containers i and containers j Perform operations and i and j If it is a continuous operation, The value is 1, otherwise the value is 0; The quay crane operation constraints include:

[0019] in, Indicates quay crane For containers i Start time of work, Indicates quay crane q For containers i Start time of work, Indicates card collection For containers k End of work time, Indicates card collection From the previous task kTarget location to subsequent tasks i Time of initial position, Indicates quay crane Homework tasks i Waiting time for container truck b time, Indicates the time when the quay crane completes loading and unloading; if the quay crane For containers i and containers j Perform operations and i and j If it is a continuous operation, The value is 1, otherwise the value is 0.

[0020] In a possible implementation, the constraint of the waiting time of each device includes:

[0021] in, Indicates card collection For containers i The time required to transport from the starting location to the target location at the front of the dock.

[0022] In a possible implementation, the gray wolf algorithm based on introducing the chromosome uniform crossover strategy to solve the scheduling model includes: Step 1: Read data, wherein the data includes: the number of containers to be dispatched and the number of dispatching equipment, wherein the dispatching equipment includes: quay cranes, rail cranes, and container trucks; Step 2: Initialize the wolf pack and set the maximum number of iterations. The wolf pack represents all scheduling solutions, and the gray wolf represents a single scheduling solution. Step 3: Calculate the fitness of all individuals in the wolf pack based on the objective function, and select a leader wolf based on the fitness; Step 4: Adjust the convergence factor based on the random adjustment strategy; Step 5: performing an encirclement search on the prey based on the convergence factor; Step 6: Update the positions of all gray wolves; Step 7: Using the wolf pack with updated positions as the parent generation, a progeny population that satisfies the constraints is generated based on a chromosome uniform crossover strategy; Step 8: Calculate the fitness of all individuals in the parent generation and the offspring generation based on the objective function, and reselect the leader wolf based on the fitness; Step 9: Determine whether the train arrives at the preset time. If not, return to step 4. If yes, proceed to step 10. Step 10: Determine whether the rescheduling strategy has been implemented for the updated wolf pack. If not, proceed to step 11; if so, proceed to step 12. Step 11: Implement the rescheduling strategy and return to step 2; Step 12: Check whether the maximum number of iterations has been reached. If not, return to step 4. If so, proceed to step 13. Step 13: Output the individual with the highest fitness as the optimal solution.

[0023] In a possible implementation, initializing the wolf pack includes: Encode each container and regard the encoded containers as genes. Under the condition of satisfying the constraints, any combination is performed to obtain several first chromosomes representing the scheduling schemes. The chromosomes are distributed one by one to different individuals to form the initial wolf pack.

[0024] In one possible implementation, implementing the rescheduling strategy and returning to step 2 includes: Search all containers that were undergoing work on the rail yard at the time of train arrival; Record the total operation time of all containers in progress before the train arrives and update the working position of the dispatching equipment; The containers that have not been operated on the railway yard, the train-side containers transported by train, and the containers stored in the train yard are mixed and re-encoded to obtain a new wolf pack.

[0025] The present invention further provides an electronic device, comprising: Memory, used to store programs; A processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps of the equipment collaborative scheduling method under the hybrid mode of sea-rail intermodal port described in any one of the above method items.

[0026] The beneficial effects of the present invention are: the present invention provides a method for collaborative equipment scheduling in a hybrid mode of a sea-rail intermodal port, firstly, taking the minimization of the maximum completion time within the entire operation planning cycle as the objective function, and taking the preset operation sequence connection, rail crane safe operation and waiting time of each equipment as constraints, a scheduling model is established, and the complex actual working conditions are converted into a mathematical model, which lays a foundation for subsequent further research and optimization of complex working conditions, and then the scheduling model is solved based on the gray wolf algorithm that introduces the chromosome uniform crossover strategy to obtain the final scheduling plan. The present invention combines the genetic algorithm with the swarm intelligence algorithm, and enriches the initial population in each iteration process on the basis of the swarm intelligence algorithm, so that the global optimal scheduling plan that meets the actual working conditions can be searched, thereby effectively solving the problem that the existing technology has a relatively single research on scheduling modes in actual work. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A method flow chart of an embodiment of a method for coordinated dispatching of equipment in a hybrid mode of sea-rail transport ports provided by the present invention; Figure 2 A schematic diagram of the layout of the sea-rail transport port provided by the present invention; Figure 3 A flow chart of the sea-rail transport port operation process based on train arrival time provided by the present invention; Figure 4 A schematic diagram of chromosome crossover provided by the present invention; Figure 5 for Figure 1 A method flow chart of an embodiment of step S102; Figure 6 for Figure 5 A method flow chart of an embodiment of step S502; Figure 7 for Figure 5 A method flow chart of an embodiment of step S511; Figure 8 This is a structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, and are not used to limit the scope of the present invention.

[0029] In the description of the embodiments of the present invention, unless otherwise specified, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects, indicating that three types of relationships may exist, for example: A and / or B , can mean: exist alone A , and there are A and B , exists alone B These three situations.

[0030] The terms "first," "second," and so on, used in the embodiments of the present invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, technical features designated as "first" or "second" may explicitly or implicitly include at least one such feature.

[0031] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] In order to solve the above problems, Figure 1 As shown, the present invention provides a method for coordinated dispatching of equipment in a hybrid mode of sea-rail transport port, comprising: S101. Taking the minimization of the maximum completion time within the entire operation planning cycle as the objective function, and the preset operation sequence connection, safe operation of the rail crane and the waiting time of each equipment as constraints, a scheduling model is established for the following working conditions: a direct pickup mode in which the rail crane unloads the container onto the container truck, which then transports the container to the terminal to wait for the quay crane operation, and a transshipment mode in which the rail crane stacks the containers to be stored at the designated container position in the railway yard.

[0033] It should be noted that the application scenario of the present invention is the sea-rail transport port operation process that takes into account the arrival time of the train. The sea-rail transport port operation can be divided into two types according to different container operation processes: the "train-ship" direct operation mode and the "train-yard-ship" transshipment operation mode. In the former, due to the mismatch between the train timetable and the ship's sailing schedule, some containers on the train need to be temporarily stored in the railway yard waiting for the export ship of these containers to arrive at the port. In the latter, based on the match between the train timetable and the ship's sailing schedule, the qualified containers on the train are directly transported to the shore without the need for temporary storage in the yard. When the railway loading and unloading line is laid behind the port yard, the operation process of the "train-ship" direct operation mode is as follows. Taking the export container operation process as an example, the export container is unloaded onto the container truck by the rail crane on the railway loading and unloading line, and then the container truck directly transports it to the front of the terminal to wait for the quay crane operation. When the railway yard is arranged closely along the loading and unloading line, the "ship-yard-train" transfer operation mode is as follows: Taking the export container operation process as an example, the export containers that need to be temporarily stored in the railway yard are stacked in the designated container space of the railway yard by rail cranes on the railway loading and unloading line.

[0034] In the actual operation of rail-water transport, due to the uncertainties in the railway transportation process such as weather factors, priority scheduling, traffic flow, and the combined effect of various internal and external factors, the expected arrival time of freight trains fluctuates to a certain extent, which in turn affects the initial scheduling plan of port loading and unloading equipment. Therefore, it is necessary to introduce a dynamic container rescheduling strategy in the coordinated scheduling of port loading and unloading equipment.

[0035] In summary, Figure 2In the sea-rail intermodal port layout model shown, within a transshipment planning cycle, at time t1, the outbound vessel awaiting loading is already berthed at the designated berth at the port terminal, while the container train has not yet arrived. Rail-mounted cranes, container trucks, and quay cranes perform railway yard operations at the railway yard and the terminal front, transporting export containers previously stored in the railway yard to the vessel.

[0036] Secondly, at time t2 when the train arrives, the container train enters the port, and the rail crane, container truck and quay crane need to perform the original railway yard operation tasks and the container train unloading and loading operations at the same time. At this time, the rail crane needs to make a new decision and adopt the container dynamic scheduling plan to reasonably arrange the operation sequence to minimize the total operation time until all the export containers belonging to this voyage in the railway yard are loaded on the ship and the export containers of the container train are unloaded and stored according to the direct or indirect transfer mode. The transfer plan is considered to be completed. Figure 3 shown.

[0037] The dynamic container scheduling solution retrieves containers currently undergoing operations at the time of train arrival, marks them, and, after the operations are completed, reschedules the order of operations for the remaining containers in the railway yard and the sea-rail intermodal containers on the train. This creates a dynamic container rescheduling strategy that minimizes total operation completion time and reduces train waiting time. The incoming containers on the train include both direct transfer containers within the current transfer plan cycle and indirect transfer containers that need to be temporarily stored in the railway yard for the next plan cycle.

[0038] In one possible implementation, the objective function includes: (1) In formula (1), represents the objective function, Represents a collection of container tasks, Indicates the collection of containers in the original railway yard after rescheduling. Indicates the collection of containers on the train shore. Indicates the collection of containers stored in the train yard. Indicates the collection of containers in the railway yard before rescheduling, , Represents the quay crane collection, indexed by , Represents the rail door crane collection, indexed by , Represents a card collection, indexed by , Indicates quay crane q For containers i End of work time, Indicates rail crane gFor containers i End of work time, Indicates card collection b For containers i End of work time; It is related to whether the train arrives at the preset time. If it arrives, ,otherwise .

[0039] In one possible implementation, the constraints of job sequence continuity include: Each train yard storage container, train quayside container and existing railway yard container has only one rail crane to operate it: (2) In formula (2), If the container i By rail crane g Homework, then ,otherwise ; If the container i By Jika b Homework, then ,otherwise ; If the container i By quay crane q Homework, then ,otherwise ; Also, when quay cranes, rail cranes, and container trucks are operating container tasks, each task can only be performed once: (3) In formula (3), If the container j For rail gantry crane g The start task is If it is the end task, then ; If the container i For rail gantry crane g If the task ends, , if it is a start task, then ; If the container j For quay crane q The start task is If it is the end task, then ; If the container i For quay crane q The start task is If it is the end task, then ; If the container j is the starting task of set card b, then ; If it is to end the task, then ; If the container i is the starting task of set card b, then ; If it is to end the task, then ; Furthermore, the quay crane, rail crane, or container truck may start or end operations only once: (4) In one possible implementation, the safe operation of the rail crane is constrained, including: Set rail crane safe operating distance constraints, rail crane operation constraints, container truck operation constraints, and quay crane operation constraints.

[0040] Furthermore, the safe operating distance constraints of the rail cranes specifically include: the safe operating distance of the rail cranes and the prohibition of crossing between rail cranes.

[0041] It can be expressed in the form of a mathematical model: (5) In formula (5), represents the initial position of the container, Indicates the target location of the container, Indicates the train car number corresponding to the container; when the rail crane For containers i While working, the rail crane For containers j Homework, then The value of is 1, otherwise the value is 0; Rail crane operation constraints include: Rail crane post-operation tasks j The start time of the task must not be earlier than that of the previous task i The completion time of the previous container task plus the time it takes for the rail crane to move from the previous container position to the next container position; if the previous container task i For containers that are directly transferred by train and the original railway yard containers before and after rescheduling, and the time for the rail crane to arrive at the location of the previous container is less than the arrival time of the container truck, then the rail crane post-operation task j The start time also needs to include the time the rail crane waits for the container truck.

[0042] Similarly, its mathematical model is: (7) In formula (7), Indicates rail crane For containers i Start time of work, Indicates rail crane For containers i End of work time, Indicates card collection The end time of operation for container k, Indicates rail crane From the previous task i Target location to subsequent tasks j Time of initial position, Indicates card collection From the previous task k Target location to subsequent tasks i Time of initial position, Indicates rail crane Homework tasks i The waiting time for the truck is Indicates rail crane Self-pick up container i The time required to reach the target location and place the container; if the rail crane For containers i and containers j Perform operations and i and j If it is a continuous operation, The value is 1, otherwise the value is 0; Trucking constraints include: (1) If the container task i 、 j It is the post-operation container task of the train direct transshipment container and the original railway yard container before and after rescheduling, and the container truck j The start time must be later than the previous container task i The completion time of the container truck plus the container task from the previous operation i Position to the subsequent operation container task j If the container truck arrives earlier than the rail crane, the subsequent container task j The start time also needs to include the time the container truck waits for the rail crane, and its mathematical model is as follows (8): (8) In formula (8), Indicates card collection For containers j Start time of work, Indicates card collection For containers i End of work time, Indicates card collection From the previous task i Target location to subsequent tasks j Time of initial position, Indicates card collection Homework tasks j Waiting time for rail crane time, Indicates rail crane Self-pick up container j The time required to drop the container at the target location, Indicates the time when the quay crane completes loading and unloading; if the container truck For containers i and containers j Perform operations and i and j If it is a continuous operation, The value is 1, otherwise the value is 0.

[0043] (2) If the container task i 、 j The train directly transfers the shore task box and the original railway yard task box before and after rescheduling. It represents the waiting time of the container truck under the quay crane when the container truck arrives earlier than the rail crane. Its mathematical model is as follows: (9) In formula (9), Indicates quay crane For containers k Start time of work, Indicates card collection b Homework tasks j Waiting for the quay crane q time.

[0044] The constraints of quay crane operation include: i and j All are operated by quay cranes, and the task is i 、 j When the task is to connect the previous and next tasks, the subsequent container operation task of the quay crane j The start time must be later than the previous container task i The completion time plus the container task of the quay crane from the previous operation i Position to the subsequent operation container task j If the time it takes for the container truck to reach the quay crane position for the preceding container operation is less than the time it takes for the quay crane to reach the operation position, then the quay crane's subsequent container operation task j The start time also needs to include the time the quay crane waits for the container truck.

[0045] Its mathematical model is: (10) In formula (10), Indicates quay crane For containers i Start time of work, Indicates quay crane q For containers i Start time of work, Indicates card collection For containers k End of work time, Indicates card collection From the previous task k Target location to subsequent tasks i The time of the initial position, Indicates quay crane Homework tasks i Waiting time for the truck b time, Indicates the time when the quay crane completes loading and unloading; if the quay crane For containers i and containers j Perform operations and i and j If it is a continuous operation, The value is 1, otherwise the value is 0.

[0046] In one possible implementation, the waiting time of each device is used as a constraint, including: when the container operation task belongs to the direct transfer of containers by train and the original railway yard containers before and after rescheduling, the operation completion time of the rail crane of the same task needs to be earlier than or equal to the start operation time of the container truck, and the operation time of the container truck needs to be earlier than or equal to the start operation time of the quay crane.

[0047] Its mathematical model is: (11) In formula (11), Indicates card collection For containers i The time required to transport from the starting location to the target location at the front of the dock.

[0048] S102. Solve the scheduling model based on the grey wolf algorithm that introduces the chromosome uniform crossover strategy to obtain the final scheduling solution.

[0049] It's important to note that the Gray Wolf Algorithm (GWA) was inspired by the hunting strategies of wolf packs in nature. During a hunt, three lead wolves randomly select two followers to join the hunt. However, when the GWA is applied to the complex optimization problem of container equipment scheduling in sea-rail intermodal ports, the algorithm can face challenges in simulating hunting behavior. It struggles to accurately capture the optimal solution, and there's a high risk of becoming trapped in a local optimum. Therefore, this paper improves on this hunting behavior by incorporating an adaptive operator based on uniform crossover from a genetic algorithm into the chromosome iterations of the hunting behavior, further enhancing the algorithm's global search capabilities.

[0050] The uniform crossover in the genetic algorithm is a special crossover operation that differs from traditional single-point crossover or multi-point crossover. In a uniform crossover, each gene (or trait) has the same probability of being selected from each parent individual, usually close to 50%. This means that when generating offspring, each gene has an equal chance of being inherited from any parent. Specifically, the algorithm generates an index list to control the crossover process. Each index position traverses the corresponding part of the parent chromosome. Based on the index value in the index list, it is determined whether the gene is inherited from the first parent or the second parent, such as Figure 4 As shown in Figure 2, the offspring chromosomes resulting from a crossover may contain gene deletions or duplications, necessitating repair of the offspring chromosomes by deleting duplicated genes and supplementing missing genes. This crossover allows offspring to inherit more genetic variation from their parents, promoting genetic diversity.

[0051] Compared with the existing technology, the present invention provides a method for collaborative equipment scheduling in a hybrid mode of a sea-rail intermodal port. First, the objective function is to minimize the maximum completion time within the entire operation planning cycle, and the preset operation sequence connection, rail crane safe operation and waiting time of each equipment are used as constraints to establish a scheduling model, and convert the complex actual working conditions into a mathematical model, which lays a foundation for further research and optimization of the complex working conditions. Then, the scheduling model is solved based on the gray wolf algorithm that introduces the chromosome uniform crossover strategy to obtain the final scheduling plan. The present invention combines the genetic algorithm with the swarm intelligence algorithm, and enriches the initial population in each iteration process on the basis of the swarm intelligence algorithm, so that the global optimal scheduling plan that meets the actual working conditions can be searched, thereby effectively solving the problem that the existing technology has a relatively single research on scheduling modes in actual work.

[0052] like Figure 5 In a possible implementation, step S102 includes: Step S501: reading data; Specifically, the data includes: the number of containers to be dispatched and the number of dispatching equipment, where dispatching equipment includes: quay cranes, rail cranes, and container trucks; Step S502: Initialize the wolf pack and set the maximum number of iterations; Among them, the wolf pack represents all scheduling plans, and the gray wolf individual represents a single scheduling plan; Step S503: Calculate the fitness of all individuals in the wolf pack based on the objective function, and select a leader wolf based on the fitness; Step S504: Adjust the convergence factor based on the random adjustment strategy.

[0053] It's important to note that when improving the Gray Wolf Optimization algorithm, it's crucial to further ensure a balance between global search and local exploitation. Global search involves exploring a wider range of the solution space, while local exploitation involves in-depth searches within specific regions of the solution space based on the current information available to the swarm. Only when the Gray Wolf Optimization algorithm effectively balances these two capabilities can it achieve higher solution accuracy and faster convergence rates.

[0054] In the traditional gray wolf algorithm, in order to make the algorithm jump out of the local optimum, the tracking process sets a random vector A， | A When |>1, the search agent can stay away from the prey and achieve global search. At the same time, the vector C composed of random values ​​set on [0,2] is a random search coefficient, which increases the randomness of the prey search and avoids the local optimality of the algorithm.

[0055] During the algorithm's iteration process, in the early stages of the algorithm, higher a The value will increase the search stride, which is conducive to global search; in the later stage of the algorithm, smaller a The value of helps the group to focus on searching a specific area, which is beneficial for local search. a It is designed to decrease linearly from the initial 2 to 0 as the number of iterations increases. However, when facing actual optimization problems, due to the complexity of the search process, a simple linear decrease strategy may not be able to effectively adapt to the actual needs of the search process.

[0056] This paper proposes a random adjustment convergence factor strategy to improve the global search capability of the gray wolf optimization algorithm in the early stage while ensuring reliable local search capability in the later stage. The formula is as follows: (12) In formula (12), a initial and a final are the initial and final values ​​of the convergence factor a, rand () is a random number uniformly distributed between [0,1]; σ (variance) is used to measure the random variable aThe degree of deviation from its mathematical expectation (mean); randn () is a random number that obeys the normal distribution.

[0057] Step S505: performing an encirclement search on the prey based on the convergence factor; Step S506: Update the positions of all gray wolves.

[0058] It should be noted that in the search process of the gray wolf algorithm, 、 and Wolves play a key role, leading the pursuit of the optimal solution and guiding other members of the group ( The gray wolf approaches the prey to achieve its hunting goal, so the behavior of gray wolves surrounding and capturing prey is defined as follows: (13) (14) Formula (13) represents the distance between the individual and the prey, and formula (14) is the position update formula of the gray wolf. t is the current iterative algebra, A and C is the coefficient vector, is the position vector of the prey, is the position vector of the gray wolf, D is the distance between the individual gray wolf and its prey.

[0059] The calculation formulas for A and C are as follows: (15) In formula (15), a is the convergence factor, which decreases linearly from 2 to 0 as the number of iterations increases; r 1 and r 2 is a random number between [0,1].

[0060] (16) In formula (16), , , Respectively 、 and the distance between the wolf and other individuals; , , Wolves respectively said 、 and The wolf's current location. , , is a random vector, This is the current location of the Gray Wolf.

[0061] (17) (18) Formula (17) defines the Individual Orientation 、 and The wolf's stride length and direction, Equation (18) defines final position.

[0062] Step S507: Using the wolf pack with updated positions as the parent generation, a child population that satisfies the constraints is generated based on the chromosome uniform crossover strategy; Step S508: Calculate the fitness of all individuals in the parent generation and the offspring generation based on the objective function, and reselect the leader wolf based on the fitness; Step S509: Determine whether the train arrives at the preset time. If not, return to step S504. If yes, proceed to step S510. Step S510: determine whether the rescheduling strategy has been implemented for the updated wolf pack. If not, proceed to step S511; if so, proceed to step S512; Step S511, implement the rescheduling strategy and return to step S502; Step S512: Whether the maximum number of iterations has been reached, if not, return to step S504, if so, proceed to step S513; Step S513: Output the individual with the highest fitness as the optimal solution.

[0063] It should be noted that in each of the above steps, every time a new wolf pack or individual is generated, the population must be screened according to the constraints given by equations (2)-(11) to meet the requirements of the actual working conditions.

[0064] like Figure 6 In a possible implementation, step S502 includes: S601. Encode each container and regard the encoded containers as genes. Arbitrary combinations are performed under the condition that constraints are met to obtain a number of first chromosomes representing scheduling solutions.

[0065] Specifically, a double-layer natural number encoding method can be used for encoding: the first layer is the container operation task number, where the encoding length is the container operation task to be scheduled, and the second layer is the operation attribute of the container operation task. 0 indicates that the container attribute is the original railway yard task box, 1 indicates that the container attribute is the train yard storage task box, and -1 indicates that the container attribute is the train shore task box. Before the train arrives, the railway yard and the sea-rail transport port related equipment carry out the loading, unloading and transportation of the original task boxes in the railway yard. Assuming that there are 6 original task boxes in the railway yard waiting to be transported to the front of the terminal, the chromosome has a total of 6 genes, and the operation attribute of each gene is 0. After the train arrives, it is necessary to perform task box operations with three operation attributes at the same time, and chromosomes are randomly generated. At this time, each gene of the chromosome will have three possible attributes, such as Figure 7 shown.

[0066] S602. Distribute the chromosomes to different individuals one by one to form an initial wolf pack. It's important to note that in the Gray Wolf Optimization Algorithm, population construction is a key starting point for the optimization process. Each chromosome represents a potential scheduling solution. During population initialization, the algorithm randomly generates a sequence of container operation tasks and employs a global search to comprehensively consider the dispersed distribution of initial solutions across the entire solution space. This not only helps discover excellent individuals within the initial solution but also increases population diversity.

[0067] like Figure 7 In a possible implementation, step S511 includes: S701. Search all containers in progress at the railway yard when the train arrives; S702. Record the total operation time of all containers in operation before the train arrives, and update the working position of the dispatching device; S703: Mix the unused containers on the railway yard, the train-side containers transported by train, and the containers stored in the train yard and re-encode them to obtain a new wolf pack.

[0068] For example, after solving the preset working conditions by the equipment collaborative scheduling method under the hybrid mode of the sea-rail transport port provided by the present invention, the results shown in Table 1 and Table 2 below are obtained. It can be seen that the present invention can provide a scheduling plan that meets actual requirements while considering both the "ship-yard-train" and "ship-train" operating modes.

[0069]

[0070]

[0071] In Tables 1 and 2, the basic data: * / * / *, represents the total number of containers loaded and unloaded / the number of containers subject to dynamic scheduling / the proportion of containers in direct mode among incoming trains.

[0072] like Figure 8 As shown, the present invention further provides an electronic device 80, comprising: Memory 810, used for storing programs; The processor 820 is coupled to the memory 810 and is used to execute the program stored in the memory 810 to implement the steps of the equipment collaborative scheduling method in the hybrid mode of the sea-rail transport port described in any one of the above embodiments.

[0073] Figure 8 Only some of the components of the electronic device 80 are shown, but it should be understood that implementing all of the shown components is not a requirement, and more or fewer components may alternatively be implemented.

[0074] In some embodiments, the processor 820 can be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run the program code or process data stored in the memory 810, such as the equipment collaborative scheduling method under the hybrid mode of the sea-rail transport port in the present invention.

[0075] In some embodiments, the processor 820 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 820 may be local or remote. In some embodiments, the processor 820 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, multiple clouds, or any combination thereof.

[0076] In some embodiments, the memory 810 may be an internal storage unit of the electronic device 80, such as a hard disk or memory of the electronic device 80. In other embodiments, the memory 810 may also be an external storage device of the electronic device 80, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 80.

[0077] Furthermore, the memory 810 may include both an internal storage unit of the electronic device 80 and an external storage device. The memory 810 is used to store application software installed on the electronic device 80 and various data.

[0078] In one embodiment, when the processor 820 executes the equipment collaborative scheduling program in the sea-rail intermodal port hybrid mode in the memory 810, the following steps may be implemented: Taking minimizing the maximum completion time within the entire operation planning cycle as the objective function, and using the preset operation sequence, safe operation of the rail crane, and the waiting time of each equipment as constraints, a scheduling model was established for the following working conditions: a direct pickup mode in which the rail crane unloads the container onto a container truck, which then transports the container to the terminal to wait for the quay crane to operate, and a transshipment mode in which the rail crane stores the required containers at a designated container location in the railway yard. The scheduling model is solved based on the grey wolf algorithm that introduces the chromosome uniform crossover strategy to obtain the final scheduling solution.

[0079] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 80 mentioned. The electronic device 80 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or the like. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft, or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 80 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0080] The present invention also provides a storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the equipment collaborative scheduling method in the hybrid mode of sea-rail transport port described in any one of the above embodiments.

[0081] Those skilled in the art will appreciate that all or part of the process steps of the above-described method embodiments can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program, and the computer program can be stored in a computer storage medium. The computer storage medium may be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0082] The above is a detailed introduction to the equipment collaborative scheduling method and electronic equipment in the hybrid mode of the sea-rail transport port provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for coordinated dispatching of equipment in a hybrid mode of sea-rail transport port, characterized in that: include: Taking the minimization of the maximum completion time within the entire operation planning cycle as the objective function, and taking the preset operation sequence connection, the safe operation of the rail crane and the waiting time of each equipment as constraints, a scheduling model is established for the working conditions including the direct mode in which the rail crane unloads the container onto the container truck, and then the container truck transports the container to the terminal to wait for the quay crane operation, and the transshipment mode in which the rail crane stores the containers to be stored at the designated container position in the railway yard; The scheduling model is solved by the Grey Wolf Algorithm which introduces the chromosome uniform crossover strategy, and the final equipment collaborative scheduling solution is obtained.

2. The equipment coordinated scheduling method under the hybrid mode of sea-rail transport port according to claim 1 is characterized in that: The objective function includes: in, represents the objective function, Represents a collection of container tasks, It indicates the collection of containers in the original railway yard after redispatch. Indicates the container collection at the train shore. Indicates the collection of containers stored in the train yard. Indicates the collection of containers in the railway yard before redispatch, , Represents the quay crane collection, indexed by , Represents a collection of rail door cranes, indexed by , Represents a collection of cards, indexed by , Indicates quay crane q For container i End of work time, Indicates rail crane g For container i End of work time, Indicates card set b For container i End of work time; It depends on whether the train arrives at the preset time. If it arrives, then ,otherwise .

3. The equipment coordinated scheduling method under the hybrid mode of sea-rail transport port according to claim 1 is characterized in that: The constraint of the operation sequence continuation includes: in, If the container i By rail crane g Homework, then ,otherwise ; If the container i By Jika b Homework, then ,otherwise ; If the container i By quay bridge q Homework, then ,otherwise , If the container j For rail gantry crane g The starting task is , if it is the end task, then ; If the container i For rail gantry crane g If the task is completed, , if it is a start task, then ; If the container j For quay crane q The starting task is , if it is the end task, then ; If the container i For quay crane q The starting task is , if it is the end task, then ; If the container j For card collection b The starting task is ; If it is to end the task, then ; If the container i For card collection b The starting task is ; If it is to end the task, then .

4. The equipment coordinated scheduling method under the hybrid mode of sea-rail transport port according to claim 1 is characterized in that: The constraints on safe operation of rail cranes include: Set rail crane safe operating distance constraints, rail crane operation constraints, container truck operation constraints and quay crane operation constraints.

5. The equipment coordinated scheduling method under the hybrid mode of sea-rail transport port according to claim 4 is characterized in that: The rail crane safe operating distance constraint includes: in, represents the initial position of the container, Indicates the target location of the container, Indicates the train car number corresponding to the container; For container i While working, the rail crane For container j Homework, then The value of is 1, otherwise the value is 0; The rail crane operation constraints include: in, Indicates rail crane For container i Start time of work, Indicates rail crane For container i End of work time, Indicates card set b For container k End of work time, Indicates rail crane From the previous task i Target location to subsequent tasks j The time of the initial position, Indicates card set b From the previous task k Target location to subsequent tasks i The time of the initial position, Indicates rail crane Job Tasks i The waiting time for the truck is Indicates rail crane Self pick up container i The time required to reach the target location and drop off the container; if the rail crane For container i and containers j Operate and i and j If it is a continuous operation, The value is 1, otherwise the value is 0; The truck operation constraints include: in, Indicates card set For container j Start time of work, Indicates quay crane For container k Start time of work, Indicates card set For container i End of work time, Indicates card set From the previous task i Target location to subsequent tasks j The time of the initial position, Indicates card set Job Tasks j Waiting for the rail crane time, Indicates card set b Job Tasks j Waiting for the quay crane q time, Indicates rail crane Self pick up container j The time required to drop off the container at the target location, Indicates the time when the quay crane completes loading and unloading; if the container truck For container i and containers j Operate and i and j If it is a continuous operation, The value is 1, otherwise the value is 0; The quay crane operation constraints include: in, Indicates quay crane For container i Start time of work, Indicates quay crane q For container i Start time of work, Indicates card set For container k End of work time, Indicates card set From the previous task k Target location to subsequent tasks i The time of the initial position, Indicates quay crane Job Tasks i Waiting time for the truck b time, Indicates the time when the quay crane completes loading and unloading; if the quay crane For container i and containers j Operate and i and j If it is a continuous operation, The value is 1, otherwise the value is 0.

6. The equipment coordinated scheduling method under the hybrid mode of sea-rail transport port according to claim 1 is characterized in that: The constraint of the waiting time of each device includes: in, Indicates card set For container i The time required to transport from the starting location to the target location at the front of the dock.

7. The equipment coordinated scheduling method under the hybrid mode of sea-rail transport port according to claim 2 is characterized in that: The grey wolf algorithm based on introducing the chromosome uniform crossover strategy solves the scheduling model, including: Step 1: Read data, wherein the data includes: the number of containers to be dispatched and dispatching equipment, wherein the dispatching equipment includes: quay cranes, rail cranes and container trucks; Step 2: Initialize the wolf pack and set the maximum number of iterations, where the wolf pack represents all scheduling plans and the gray wolf individual represents a single scheduling plan; Step 3: Calculate the fitness of all individuals in the wolf pack based on the objective function, and select a leader wolf based on the fitness; Step 4: Adjust the convergence factor based on the random adjustment strategy; Step 5: performing an encirclement search on the prey based on the convergence factor; Step 6: Update the positions of all gray wolves; Step 7: Using the wolf group with updated positions as the parent generation, a descendant population satisfying the constraints is generated based on a chromosome uniform crossover strategy; Step 8: Calculate the fitness of all individuals in the parent generation and the offspring generation based on the objective function, and reselect the leader wolf based on the fitness; Step 9: Determine whether the train arrives at the preset time. If not, return to step 4. If yes, proceed to step 10. Step 10: determine whether the rescheduling strategy has been implemented for the updated wolf pack, if not, proceed to step 11, if yes, proceed to step 12; Step 11: Implement the rescheduling strategy and return to step 2; Step 12: Whether the maximum number of iterations has been reached, if not, return to step 4, if yes, proceed to step 13; Step 13: Output the individual with the highest fitness as the optimal solution.

8. The equipment coordinated scheduling method under the hybrid mode of sea-rail transport port according to claim 7 is characterized in that: The initialization of the wolf pack includes: Encode each container, and regard the encoded containers as genes, and make any combination under the condition of satisfying the constraints to obtain a number of first chromosomes representing the scheduling scheme; The chromosomes are distributed one by one to different individuals to form the initial wolf pack.

9. The equipment coordinated scheduling method under the hybrid mode of sea-rail transport port according to claim 7 is characterized in that: The implementation of the rescheduling strategy and returning to step 2 includes: Search all containers that were undergoing work on the rail yard when the train arrived; Record the total operation time of all containers in operation before the train arrives, and update the working position of the dispatching equipment; The containers on the railway yard that have not been operated, the train-side containers transported by train, and the containers stored in the train yard are mixed and re-encoded to obtain a new wolf pack.

10. An electronic device, characterized in that: include: Memory, used to store programs; A processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the equipment collaborative scheduling method under the hybrid mode of the sea-rail transport port as described in any one of claims 1 to 9 above.

Images