Port logistics AGV path planning method, device, equipment and medium

Abstract

The invention relates to the technical field of port AGV path planning. The invention discloses a port logistics AGV path planning method, device and equipment and a medium, and the method comprises the steps: constructing a vertical container wharf port logistics system model which comprises a quay crane, an automatic guided vehicle and a plurality of container areas; constructing a port logistics system basic database and a mapping relation between the port logistics system basic database and the vertical container wharf port logistics system model to obtain a port logistics system simulation model; and based on a preset improved genetic algorithm, according to the port logistics system simulation model, planning a target moving path of the automated guided vehicle between the quay crane and the plurality of box areas. According to the method, the port logistics system simulation model is constructed, the target moving path of the automatic guided vehicle between the quay crane and the multiple box areas is planned based on the improved genetic algorithm, the transportation time of the automatic guided vehicle can be remarkably shortened, and the overall efficiency of port operation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of port AGV path planning, in particular to a port logistics AGV path planning method, device, equipment and medium. BACKGROUND

[0002] Under the background of accelerating globalization and digitization, port logistics systems, as the core hub of global trade networks, bear an increasingly growing logistics task. With the continuous prosperity of international trade and the increasing variety of goods, everyone generally expects to improve logistics efficiency, want to be superior in fierce market competition, and want to promote high-quality economic development and efficient use of resources through optimizing logistics efficiency.

[0003] However, in an increasingly complex and dynamic environment, port logistics faces multiple challenges such as port throughput growth not keeping up with the surge in cargo flow, low resource allocation efficiency, and extended ship operation time, which not only limits port operation efficiency but also significantly affects the stable growth of the global economy. Therefore, optimizing the port logistics system has become an urgent task.

[0004] Therefore, it is of great significance to find a port logistics AGV path planning optimization method based on intelligent optimization algorithm in theory and practice, and it has broad application prospects. SUMMARY

[0005] In view of the above problems, the embodiments of the present application provide a port logistics AGV path planning method, device, equipment and medium, which aims to solve the above problems or at least partially solve the above problems.

[0006] In a first aspect, the present application provides a port logistics AGV path planning method, comprising: constructing a vertical container terminal port logistics system model, the port logistics system model comprising a shore bridge, an automatic guided vehicle and a plurality of box areas; constructing a port logistics system database and a mapping relationship between the port logistics system database and the vertical container terminal port logistics system model to obtain a port logistics system simulation model; based on a preset improved genetic algorithm, planning a target moving path of the automatic guided vehicle between the shore bridge and the plurality of box areas according to the port logistics system simulation model.

[0007] Illustratively, constructing a port logistics system database and a mapping relationship between the port logistics system database and the vertical container terminal port logistics system model to obtain a port logistics system simulation model comprises: obtaining a straight-line distance from the shore-based crane to each container yard, a Euclidean distance between each container yard, an automated guided vehicle transport speed, and a container yard yard crane operation response time, and constructing a port logistics system basic database; obtaining a port logistics empowerment network diagram according to the vertical container wharf port logistics system model, wherein the shore-based crane and each container yard are nodes, and a connection line between adjacent nodes is a movement path of the automated guided vehicle; empowering the connection line between adjacent nodes in the port logistics empowerment network diagram according to the straight-line distance from the shore-based crane to each container yard and the Euclidean distance between each container yard, and obtaining the port logistics system simulation model.

[0008] For example, based on a preset improved genetic algorithm, the movement path of the automated guided vehicle between the shore-based crane and the plurality of container yards is planned according to the obtained port logistics system simulation model, including: the movement path planning problem of the automated guided vehicle between the shore-based crane and the plurality of container yards is converted into a traveling salesman problem with constraints; based on the improved genetic algorithm, the traveling salesman problem is solved under the constraints according to the obtained port logistics system simulation model, and the movement path of the automated guided vehicle between the shore-based crane and the plurality of container yards is obtained.

[0009] For example, the movement path planning problem of the automated guided vehicle between the shore-based crane and the plurality of container yards is converted into a traveling salesman problem with constraints, including: the constraint condition includes the operation sequence of the automated guided vehicle when moving between the shore-based crane and the plurality of container yards, and also includes that the automated guided vehicle starts from the shore-based crane node and returns to the shore-based crane node after traversing all container yard nodes; a target function is constructed, which is to minimize the movement and transport time of the automated guided vehicle between the shore-based crane and the plurality of container yards.

[0010] For example, based on the improved genetic algorithm, the traveling salesman problem is solved under the constraints according to the obtained port logistics system simulation model, and the target movement path of the automated guided vehicle between the shore-based crane and the plurality of container yards is obtained, including: population initialization, generating a path vector set, the path vector set including a plurality of path vectors, each path vector being a movement path of the automated guided vehicle between the shore-based crane and the plurality of container yards; based on a pre-set fitness function, the fitness of each path vector is calculated; based on a pre-set roulette algorithm, the path vector that enters the next generation of genetics is determined according to the fitness of each path vector; The path vectors of the next generation of the genetic algorithm are crossed based on a preset crossing algorithm, to obtain crossed path vectors; The crossed path vectors are mutated based on a preset mutation algorithm, to obtain mutated path vectors; The target path vectors are determined from the path vectors of the next generation of the genetic algorithm and the mutated path vectors based on a preset optimization mechanism; The target path vectors are decoded to obtain the target moving path of the automated guided vehicle between the quay crane and the plurality of container areas.

[0011] The target path vectors are determined from the path vectors of the next generation of the genetic algorithm and the mutated path vectors based on a preset optimization mechanism, and the method comprises the following steps of: The initial screening path vectors are determined from the path vectors of the next generation of the genetic algorithm and the mutated path vectors based on a preset elite reservation mechanism; The updated path vectors are determined from the initial screening path vectors based on a preset swarm search optimization algorithm; The population is updated according to the updated path vectors until the iteration is terminated, to determine the target path vectors.

[0012] The method further comprises the following steps of: A port logistics simulation model based on Plant Simulation is constructed, and a target moving path of an automated guided vehicle between a quay crane and a plurality of container areas is planned based on a genetic algorithm, to obtain an estimated moving path and first iteration process parameters; A target moving path of an automated guided vehicle between a quay crane and a plurality of container areas is planned based on a preset improved genetic algorithm according to the port logistics system simulation model, to obtain the target moving path and second iteration process parameters; The port logistics AGV path planning method is verified according to the estimated moving path and the first iteration process parameters, and the target moving path and the second iteration process parameters.

[0013] In a second aspect, the application provides a port logistics AGV path planning device, comprising: A first construction module is configured to construct a vertical container wharf port logistics system model, and the port logistics system model comprises a quay crane, an automated guided vehicle and a plurality of container areas; A second construction module is configured to construct a port logistics system database and a mapping relationship between the port logistics system database and the vertical container wharf port logistics system model, to obtain a port logistics system simulation model; The solving module is configured to plan a target moving path of the AGV between the shore-based crane and the multiple container areas based on the preset improved genetic algorithm and the port logistics system simulation model.

[0014] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the port logistics AGV path planning method according to the first aspect when executing the computer program.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the port logistics AGV path planning method according to the first aspect when executed by a processor.

[0016] The above at least one technical solution adopted by the embodiments of the present application can achieve the following beneficial effects: In the present application, the port logistics system simulation model is constructed, and the target moving path of the AGV between the shore-based crane and the multiple container areas is planned based on the improved genetic algorithm, which intelligently optimizes the AGV path planning method at a practical level, significantly reduces the transportation time of the AGV, improves the overall efficiency of the port operation, has great significance for relieving port congestion and shortening the ship's stay time in port, and improves the port competitiveness and economic benefits. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application and illustrate the illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings: Figure 1 is a schematic diagram of an application environment of the port logistics AGV path planning method in an embodiment of the present application; Figure 2 is a flowchart of the port logistics AGV path planning method in an embodiment of the present application; Figure 3 is a port logistics weighted network diagram in an embodiment of the present application; Figure 4 is a schematic diagram of an AGV target moving path in an embodiment of the present application; Figure 5 is a model framework diagram constructed based on Plant Simulation in an embodiment of the present application; Figure 6 is a schematic diagram of an optimization result solved by a default genetic algorithm in Plant Simulation in an embodiment of the present application; Figure 7is a space distribution and AGV driving direction visualized and displayed by a default genetic algorithm in Plant Simulation in an embodiment of the present application; Figure 8 is a schematic diagram of an improved genetic algorithm solving optimization result in an embodiment of the present application; Figure 9 is a structural schematic diagram of a port logistics AGV path planning device in an embodiment of the present application; Figure 10 is a structural schematic diagram of a computer device in an embodiment of the present application; Figure 11 is another structural schematic diagram of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described below in conjunction with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0019] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that such use can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" and its variants are to be interpreted as meaning "including but not limited to" an open term.

[0020] The technical solutions provided by the embodiments of the present application will be described in detail below in conjunction with the drawings.

[0021] As introduced above, the current medical guide service is realized by manual or a webpage or APP with fixed symptoms, diseases, etc. options, and these methods have some limitations. In order to solve this technical problem, the embodiments of the present application provide a port logistics AGV path planning method.

[0022] The port logistics AGV path planning method provided by the embodiments of the present application can be applied to, for example, Figure 1In an application environment of the application, a device end communicates with a service end through a network. The service end can construct a vertical container wharf port logistics system model through the device end, the port logistics system model comprising a shore crane, an automated guided vehicle and a plurality of container areas; construct a port logistics system basic database and a mapping relationship between the port logistics system basic database and the vertical container wharf port logistics system model to obtain a port logistics system simulation model; and based on a preset improved genetic algorithm, a target moving path of the automated guided vehicle between the shore crane and the plurality of container areas is planned according to the port logistics system simulation model. In the application, the port logistics system simulation model is constructed, the target moving path of the automated guided vehicle between the shore crane and the plurality of container areas is planned based on the improved genetic algorithm, the AGV path planning method is intelligently optimized at a practical level, the automated guided vehicle transportation time is significantly reduced, the overall port operation efficiency is improved, the port congestion is alleviated, the ship stay time in the port is shortened, the port competitiveness and economic benefits are improved, and the like. The device end can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices. The service end can be implemented by an independent server or a server cluster composed of multiple servers. The application will be described in detail below through specific embodiments.

[0023] Referring to Figure 2 as shown, Figure 2 A flowchart of a port logistics AGV path planning method provided by an embodiment of the application is shown in the figure, comprising the following steps: S10: Construct a vertical container wharf port logistics system model, the port logistics system model comprising a shore crane, an automated guided vehicle and a plurality of container areas.

[0024] In an embodiment, according to the analysis of the distribution type of the port container yard, the vertical layout is more suitable for AGV operation than the horizontal layout, the AGV transportation only needs 90° turning, the travel distance and horizontal transportation distance can be shortened, and the vertical layout is highly compatible with the automation system, so the vertical container wharf is determined as the research object. The core of the port logistics system model comprises a shore crane, an AGV and a plurality of container areas, and the port logistics system model is constructed according to the spatial layout relationship of each functional area (shore crane, automated guided vehicle (AGV) and a plurality of container areas), wherein the shore crane is located in the upper front area of the port logistics system model, the AGV fixed container connection point is arranged below the land side stretch of the shore crane, and the shore crane is used as a "ship-vehicle" container transfer hub, the unloading operation is started only when the AGV arrives, and the AGV is used as a core transportation carrier connecting the shore crane and the container area.

[0025] S20: Construct a port logistics system basic database and a mapping relationship between the port logistics system basic database and the vertical container wharf port logistics system model to obtain a port logistics system simulation model.

[0026] In one embodiment, step S20 comprises: S21: obtaining the straight-line distance from the quay crane to each container yard, the Euclidean distance between each container yard, the automated guided vehicle transport speed, and the container yard yard crane operation response time, and constructing a basic database of the port logistics system.

[0027] S22: obtaining a port logistics empowerment network diagram from the vertical container terminal port logistics system model, wherein the quay crane and each container yard are nodes, and the connecting line between adjacent nodes is the moving path of the automated guided vehicle; S23: empowering the connecting line between adjacent nodes in the port logistics empowerment network diagram according to the straight-line distance from the quay crane to each container yard and the Euclidean distance between each container yard, to obtain the port logistics system simulation model.

[0028] In one embodiment, the vertical container terminal port logistics system model is abstracted into the form of an empowerment network diagram, as shown in Figure 3 The nodes in the diagram are quay cranes and container yards, the connecting line between adjacent nodes is an edge, representing different functional areas of the terminal and the logistics flow between them, and the automated guided vehicle moves along the edge. As shown in Figure 3 Specifically, the five-star nodes 1 to 4 represent automated quay cranes, and the circular nodes 5 to 24 represent container yards. The lines connecting the nodes are the running paths of the automated guided vehicles (AGVs), and the numbers on the marked lines between the two lines represent the weight of the path, which corresponds to the distance, for example, the weight of the line between the horizontal line where node 1 is located and the horizontal line where node 5 is located is 12, the weight of the line between the horizontal line where node 5 is located and the horizontal line where node 9 is located is 12, the weight of the line between the horizontal line where node 9 is located and the horizontal line where node 13 is located is 60, the weight of the line between the horizontal line where node 13 is located and the horizontal line where node 17 is located is 12, the weight of the line between the horizontal line where node 17 is located and the horizontal line where node 21 is located is 12, the weight of the line between the vertical line where node 1 is located and the vertical line where node 2 is located is 16, the weight of the line between the vertical line where node 2 is located and the vertical line where node 3 is located is 24, and the weight of the line between the vertical line where node 3 is located and the vertical line where node 4 is located is 16. The weight, i.e., the path has a certain distance, is configured according to the straight-line distance from the quay crane to each container yard and the Euclidean distance between each container yard. The nodes are connected to other nodes through lines, reflecting the flow process of goods within the terminal, Figure 3 The lines in the middle are horizontal and vertical lines, and in other embodiments, there can also be diagonal lines, and the weight of the diagonal line is obtained by calculating the weight of the corresponding horizontal and vertical lines. The container yard yard crane operation response time is also configured at each node.

[0029] In one embodiment, the present application is directed to a moving path planning of an automated guided vehicle (AGV) between a quay crane and multiple container yard areas, and the planning result can be referenced Figure 4 as shown in Figure 4 Node 1 is a quay crane, nodes 2 to 9 are container yard areas, and the lines between two nodes are the paths of the AGV.

[0030] S30: Based on a preset improved genetic algorithm, a target moving path of the AGV between the quay crane and the multiple container yard areas is planned according to the port logistics system simulation model.

[0031] In one embodiment, step S30 plans the moving path of the AGV between the quay crane and the multiple container yard areas based on a preset improved genetic algorithm according to the port logistics system simulation model, including: S31: The moving path planning problem of the AGV between the quay crane and the multiple container yard areas is converted into a traveling salesman problem with constraints; S32: Based on the improved genetic algorithm, the traveling salesman problem is solved under the constraints according to the obtained port logistics system simulation model, and the moving path of the AGV between the quay crane and the multiple container yard areas is obtained.

[0032] In one embodiment, the optimization problem of the AGV transporting back and forth between the quay crane and the multiple container yard areas is discussed based on the principle of average allocation of the multiple container yard areas. Since the path distances between the quay crane and each container yard area are different, and the running times of each container yard area are inconsistent, the processing times of each container yard area are different. Therefore, determining the optimal container yard processing order to reduce the transportation time between each two container yard areas and further reduce the total transportation time becomes the optimization goal of the present application.

[0033] In one embodiment, the constraint conditions include the operation sequence of the AGV when moving between the quay crane and the multiple container yard areas, and also include that the AGV departs from the quay crane node and returns to the quay crane node after traversing all the container yard nodes.

[0034] In one embodiment, the operation sequence of the AGV when moving between the quay crane and the multiple container yard areas includes: a. The quay crane crane lifts the specified import container from the ship according to the loading and unloading sequence table, and transfers it to the AGV at the specified loading and unloading node, and the quay crane continues to perform the next operation task; b. The AGV delivers the container to the specified loading and unloading container yard node in the target container yard, and hands over the container to the yard crane at the node. Then, the AGV continues to go to the next container yard node; c. The yard crane precisely places the container lifted from the AGV at the designated location in the yard. The yard crane returns to the loading and unloading node, ready for the next loading and unloading operation.

[0035] The operation sequence constraint condition of the AGV when moving between the quay crane and the plurality of container yard nodes is embodied in the operation response time.

[0036] The constraint condition that the AGV departs from the quay crane node and returns to the quay crane node after traversing all the container yard nodes is a path constraint condition.

[0037] In one embodiment, a target function is constructed, which minimizes the transport time of the AGV when moving between the quay crane and the plurality of container yard nodes.

[0038] In one embodiment, under the premise of meeting the constraint condition, an optimal path is sought that departs from the quay crane, traverses all the container yard nodes, and finally returns to the quay crane, so that the total transport time T(R) is minimized, and the target function is as follows:

[0039] In the formula, represents the transport time of the node to the node in the distance matrix D; the distance matrix D is obtained according to the port logistics weighted network graph, n is the number of container yard nodes, and satisfies the non-negativity (≥0), symmetry = and diagonal zero value =0, where the subscripts i and j in the distance matrix are different container yard nodes, and it can be understood that i represents the node and j represents the node R=[r1,r2,…,r9,r 10 ]=[1,P,1] is the expanded complete path, where P represents the sequence of all intermediate nodes in the path except the first and last quay crane nodes. The fixed first and last quay crane nodes are added to the individual P to construct the closed path R. First, initialize the path R from node 1. Add the nodes of the individual P to the path R in turn. Add the quay crane node 1 at the end of the path R to form the closed path R.

[0040] For example, in one embodiment, the AGV needs to be planned to move between a quay crane node 1 and eight container yard nodes 2 to node 9. The path must start and end at node 1 (quay crane), i.e., the path is in the form of 1→ →…→ →1, where , is the full permutation of nodes 2 to 9. Let the path sequence be wherein , is the number of bay areas.

[0041] In one embodiment, in step S30, the TSP is solved under the constraint condition according to the obtained port logistics system simulation model based on the improved genetic algorithm, to obtain the target moving path of the AGV between the quay crane and the plurality of bay areas, including: S321: population initialization, generating a path vector set, the path vector set including a plurality of path vectors, each path vector being a moving path of the AGV between the quay crane and the plurality of bay areas.

[0042] In one embodiment, the path vector set is generated by encoding design in view of the discrete combination characteristics of the AGV path planning, and the specific process is as follows: The encoding design is an integer permutation encoding (IPE) mode in view of the discrete combination characteristics of the AGV path planning. The encoding definition is that an individual is represented as a permutation vector (path vector) P=[p1, p2, …, pn] of length n, wherein p i ∈{2, 3, …, n} and satisfies , Herein i , j is the node in the vector; the individual is a vector not containing the quay crane node. It can be understood that the mapping relationship between the actual quay crane node code, the actual bay area node code and the individual in the population can be pre-set, so that the subsequent population generation can effectively call the related basic data.

[0043] From the physical meaning level, each individual corresponds to the order of n bay areas visited by the AGV in turn after starting from the quay crane, and this encoding mode naturally satisfies the path constraint of “no repeated access”; The generation of the initial population is completed by uniform random sampling. First, permutation generation is performed, and for each individual, P=randperm(n)+1 is called, wherein randperm(n) can generate a random permutation of 1 to n, and after adding 1, it is mapped to the bay area number of 2 to n. Subsequently, legality verification is performed to ensure that all individuals in the population are legal permutations.

[0044] For example, in one embodiment, the AGV is required to plan a path from a shore node 1 to eight box nodes 2 to 9, the path vector set includes P=[2, 3, 4, 5, 6, 7, 8, 9], P=[2, 4, 3, 5, 6, 7, 8, 9]…, and the path vector set includes all permutations of 2 to 9.

[0045] S322: Calculate the fitness of each path vector based on the pre-set fitness function.

[0046] In one embodiment, the fitness function f(R) maps the total transport time T(R) to a quantitative optimization objective:

[0047] The fitness value is a quantitative indicator for evaluating the pros and cons of an individual, and is usually directly related to the objective function of the problem.

[0048] S323: Based on the pre-set roulette algorithm, determine the path vectors that enter the next generation of genetics according to the fitness of each path vector.

[0049] In one embodiment, the probability distribution rule for roulette selection is:

[0050] Where p i is the selected probability of individual i; f i is the fitness value of individual i, which is calculated based on the total transport time T(R) corresponding to individual i; and N is the number of individuals in the population. One individual represents one path vector.

[0051] In one embodiment, the fitness values of all individuals are normalized by formula (3) to establish the probability distribution p i of each individual. This step ensures that the sum of the probabilities of all selected individuals is 1, meeting the basic requirements of probability theory. Based on the normalized probability distribution, a cumulative probability vector c=[ ] is generated, where The cumulative probability vector is used for random selection operations in the roulette selection process. For each selection operation, a random number is generated. Then, the individual k that satisfies is selected as the path vector that enters the next generation of genetics.

[0052] All N path vectors that enter the next generation of genetics are determined by step S33.

[0053] In one embodiment, step S33 further comprises: based on an elite reservation mechanism, ranking the fitness of all the path vectors in the initial population from low to high according to the fitness of each of the path vectors, and determining the path vectors of a first part of genetic into next generation according to the ranking result, the path vectors of the first part of genetic into next generation being selected according to a preset fitness value or a preset selection ratio, and the selected path vectors being the path vectors with low fitness; based on a roulette algorithm, determining the path vectors of a second part of genetic into next generation according to the remaining path vectors in the population except the path vectors of the first part of genetic into next generation; and the path vectors of the first part of genetic into next generation and the path vectors of the second part of genetic into next generation constituting all the N path vectors of genetic into next generation.

[0054] S324: performing a crossover operation on the path vectors of genetic into next generation based on a preset crossover algorithm to obtain path vectors after the crossover operation; In one embodiment, the crossover operator is Ox, which is a widely used crossover operator in genetic algorithms. Ox generates new offspring by recombining the chromosome sequences of two parent individuals, and can bring new genetic combinations by exchanging controlled fragments between parent chromosomes while maintaining the relative order of elements. Two parent chromosome sequence individuals are randomly selected from the path vectors of genetic into next generation and These two individuals will serve as the basis for generating new offspring. In the gene sequence of the parent individual , two cutting points s and e are randomly selected (such as s = 3, e = 5), and the fragment F = [P1(e), ···, P1(s)] is retained A new offspring is generated through a multi-point crossover mechanism, which involves selecting multiple crossover points, dividing parent gene fragments, and recombining them to create new genetic combinations.

[0055] Elements not appearing in the fragment F are sequentially selected from and filled into the vacant positions of the offspring in the original order. The offspring structure is This construction method ensures that the offspring individual maintains the relative order of the parent path while introducing new gene mutations.

[0056] For example, two parent individuals are P1 = [2, 4, 3, 5, 9, 7, 6, 8] and P2 = [3, 6, 2, 5, 8, 7, 4, 9]. If s = 3 and e = 5, then F1 = [9, 5, 3] and F2 = [8, 5, 2]. F1 is brought into P2 to obtain offspring C2 = [3, 6, 9, 5, 3, 7, 4, 8], and F2 is brought into P1 to obtain offspring C1 = [2, 4, 8, 5, 2, 7, 6, 9].

[0057] S325: performing mutation operation on the path vector after the crossover based on a preset mutation algorithm to obtain a path vector after mutation.

[0058] In one embodiment, the population diversity is increased by randomly exchanging two elements in the individual gene sequence to avoid the algorithm from falling into a local optimal solution, and introducing new gene combinations helps the algorithm to explore a wider solution space to improve the global search capability: with a preset mutation probability P m (As ) randomly select two different positions s' and e' (for example s' = 2, e' = 6), the elements (i.e. nodes) of the two positions will be used for subsequent element exchange operation. Exchange the elements of the two positions to form a new offspring individual. This step introduces new genetic variation by changing the gene sequence of the individual. For example, consider an original individual [3, 7, 2, 5, 8, 4, 6, 9], after exchanging positions 2 and 6, the offspring individual is [3, 4, 2, 5, 8, 7, 6, 9].

[0059] S326: determining a target path vector from the path vector after the genetic enters the next generation and the path vector after mutation based on a preset optimization mechanism.

[0060] In one embodiment, the optimization mechanism includes updating the population by an optimization algorithm, and after the iteration termination condition is met (such as the maximum number of iterations is met), the target path vector is determined.

[0061] In one embodiment, the path vector after the genetic enters the next generation (i.e. the parent population P t , t ∈ [1, N]) and the path vector after mutation (i.e. the child population C t , t ∈ [1, N]) constitute a temporary population O t , and the optimization algorithm is used to find the individual with the lowest fitness in the temporary population, and the population in step S31 is updated with the individual with the lowest fitness.

[0062] In one embodiment, S3261: determining a preliminary screening path vector from the path vector after the genetic enters the next generation and the path vector after mutation based on a preset elite reservation mechanism; S3262: determining an updated path vector based on the preliminary screening path vector based on a preset swarm search optimization algorithm; S3263: updating the population according to the updated path vector until the iteration terminates, and determining the target path vector.

[0063] In one embodiment, the optimization algorithm includes an elite reservation algorithm, and the temporary population O t is arranged in ascending order according to the fitness values, and the top N individuals are reserved as the preliminary screening path vector to constitute a preliminary screening population Ot The mathematical expression is as follows:

[0064] wherein the Sort function represents sorting the individuals in the temporary population (the parent and offspring individual set) in ascending order of the fitness value. The Top-N function represents selecting the top N individuals with the lowest fitness value from the sorted population to form the preliminary screening population O t ´.

[0065] In one embodiment, the optimization algorithm further comprises a group search optimization algorithm (GSO). Based on the pre-set group search optimization algorithm, an update path vector is determined in the preliminary screening population (i.e., searching for the individual with the lowest fitness value in the preliminary screening population), one update path vector is obtained each time screening is performed, N update path vectors are finally obtained, and a new generation population P t+1 is obtained. t+1 The original population (i.e., the population in step S31) is updated until the iteration is terminated, and the target path vector (the individual with the lowest fitness value) is determined.

[0066] After each iteration, the improved genetic algorithm checks whether the termination condition is met, such as reaching the maximum number of iterations, the fitness value no longer significantly improving, etc. If the termination condition is met, the improved genetic algorithm stops iteration and outputs the current optimal solution; otherwise, the improved genetic algorithm continues to perform the next generation iteration. The improved genetic algorithm terminates iteration when the preset number of iterations is reached, and outputs the historical optimal path and the corresponding transportation time.

[0067] S327: Decoding the target path vector to obtain the target movement path of the automated guided vehicle between the shore crane and the plurality of box areas.

[0068] In one embodiment, the target movement path comprises the optimal path sequence of the AGV and the corresponding total transportation distance. The method further comprises visually displaying the spatial distribution of the path and the driving direction of the AGV to provide a decision basis for actual scheduling of port logistics. For example, in one embodiment, the AGV needs to be planned to move between one shore crane node 1 and eight box area nodes 2 to 9, and the format of the output optimal path sequence is "1-4-2-3-8-5-9-6-7-1", wherein r2→r9 is the optimal visiting order of the eight box areas, and the total transportation distance corresponding to the path is 136; the graphical interface displays the optimal path as shown in Figure 4 .

[0069] The key point of the present application is the collaborative design and parameterization of each operation link: coding design: adopt integer permutation coding (IPE), directly represent the access order of the box area, naturally meet the "no repeated access" job constraints, very close to the essence of TSP problem. Selection strategy: adopt roulette selection method, rather than simple random selection. This ensures that the excellent individuals with lower fitness have a greater chance of being selected for genetic, thereby accelerating convergence and improving search efficiency. Cross operation: adopt sequential crossover operator (OX), which can effectively preserve the relative order (i.e. path segment) in the parent gene sequence when generating offspring, which is the key to generating high-quality and legal path solutions. Mutation operation: adopt exchange mutation (fixed mutation probability P m =0.3), by randomly exchanging the positions of two box areas in the path, actively inject new genes into the population, which is the most critical means to maintain population diversity and avoid the algorithm falling into local optimum. Adopt group search optimization algorithm (GSO, Group Search Optimization) or elite reservation strategy to reserve the current optimal individual directly into the next generation in iteration, which is an important mechanism to ensure the convergence of the algorithm and the results will not degrade.

[0070] In one embodiment, the method further comprises: constructing a port logistics simulation model based on Plant Simulation, planning a target moving path of an automated guided vehicle (AGV) between a shore crane and multiple box areas based on a genetic algorithm, to obtain an estimated moving path and first iteration process parameters; planning a target moving path of an AGV between a shore crane and multiple box areas based on a preset improved genetic algorithm according to the port logistics system simulation model, to obtain a target moving path and second iteration process parameters; verifying the port logistics AGV path planning method according to the estimated moving path and the first iteration process parameters, and the target moving path and the second iteration process parameters.

[0071] In one embodiment, a port logistics simulation model framework is built in Plant Simulation based on a vertical container terminal as a framework, as shown in Figure 5 The layout of the framework is as follows: The shore crane (S10) is located in the upper central position of the figure; The box area (S2-S9) position: distributed in the lower part of the figure, a total of 8 box areas; StoreZones: handles the 9 nodes mentioned above, calculates the distances between them. For node information handling and distance calculation, first initialize variables and clear the relevant table data, then traverse the nodes, filter out the nodes belonging to the "Place" class, and record their information to the table, while constructing the node mapping. Then calculate the distance between the nodes and store the results. Finally, display a prompt message to show the path length; Data table Distances: stores the distances between the container zones and the distances between the quays and the container zones; Data table Zones: used to manage and display information about all container zones; GAWizard: a wizard for genetic algorithm in Plant Simulation, used to optimize the logistics operation of the port. The optimization parameter is the sequence in the Zones table, and the fitness calculation is the method LengthOfZone; Method ShowZone: uses connectors to connect the nodes. The code first traverses all nodes, deletes the network arc objects with the internal class name "NwArc", and handles the index update caused by node deletion. Then create a connector object, connect the nodes in the zone table one by one, and close the ring connection.

[0072] LengthOfZone: used to calculate the length of the container zone as the fitness of the genetic code. Implement the calculation of the distance of the ring path. Initialize the total distance, traverse the zone table to calculate the distance between adjacent nodes and accumulate, and finally close the loop and output the total distance.

[0073] Further, the default genetic algorithm solution in Plant Simulation is as follows: In the Plant Simulation environment, the traveling salesman problem is formalized as a TSP variant with constraints. Specifically, the problem involves 8 sites, each representing a container zone, and the AGV needs to start from the quay, visit all container zones in a certain order, and finally return to the quay. The core of the problem is to find a path that satisfies the operation sequence constraint while minimizing the total transportation time.

[0074] In the Plant Simulation environment, the default genetic algorithm parameters are as follows: Population size 100, iteration number 20, selection strategy is to randomly select 1 from 4 offspring for breeding, fitness reference minimum value (the smaller the better), crossover operator is order crossover, crossover probability 0.8; The optimization trend is shown in Figure 6 , and the optimization result is shown in Figure 7 . The result shows the performance of the default genetic algorithm in solving the automatic guided vehicle path planning problem. Figure 6The middle horizontal axis represents the iteration number of the genetic algorithm, and the vertical axis represents the fitness value, wherein the lower the fitness value, the better the path. Figure 6 The middle contains three curves, respectively representing the fitness values of the best individual, the average individual and the worst individual in each iteration with the iteration number. From the figure, it can be observed that: Figure 6 Fast convergence: In the first few generations (about the first 5 generations), the fitness values of the best solution, the average solution and the worst solution all decrease rapidly, which shows that the algorithm can quickly find a better solution in the initial stage and the global search ability of the genetic algorithm makes this stage quickly converge. It can quickly explore the solution space and find a better path through crossover and mutation operations.

[0075] Gradual stability: After about the 5th generation, the downward trend of the three curves begins to slow down and gradually stabilizes, which means that the algorithm gradually approaches the optimal solution and the improvement amplitude is getting smaller. In this stage, the algorithm mainly relies on local search to fine-tune the current solution to further improve the quality of the solution.

[0076] Stability: Since the 10th generation, the three curves generally tend to be stable and the fitness value changes little. This indicates that the algorithm has basically converged and found a better solution. The difference between the best solution, the average solution and the worst solution is small, indicating that the algorithm has good stability and can stably find a better solution.

[0077] Optimal solution: Finally, the fitness value of the best solution stabilizes at about 173, and the fitness values of the average solution and the worst solution also stabilize at about 173. This indicates that the algorithm has successfully found a better AGV path planning solution, significantly reducing the total transportation time.

[0078] Further, the improved genetic algorithm solution results in Matlab are as follows: In Matlab, the parameters of the improved genetic algorithm are as follows: The population size is 100, the iteration number is 25, the selection strategy uses roulette selection, the fitness reference rule is to pursue the minimum value (i.e. the smaller the fitness value, the better), the crossover operator is sequential crossover, the crossover probability is set to 0.7, and the mutation probability is set to 0.3; The optimization trend is shown in Figure 8 , and the optimization result is shown in Figure 4 . With the increase of the iteration number, the total transportation time shows a clear downward trend, indicating that the improved genetic algorithm is constantly searching for a better solution.

[0079] ​In the first 3 generations, the decrease in total transportation time is particularly significant from the second generation, from about 230 units to about 170 units, showing that the algorithm has a faster convergence speed in the early iterations. The rapid convergence in this stage may be due to the higher diversity of the population and the effective exploration of the genetic operators (such as crossover and mutation) of the solution space.

[0080] After the 7th generation, the total transportation time continues to decrease and stabilizes at about 136 units, indicating that the algorithm gradually approaches the optimal solution or local optimal solution, at which time the diversity of the population may decrease and the exploration ability of the genetic operators may weaken, resulting in a decrease in the improvement rate. In this stage, the algorithm mainly further reduces the fitness by fine-tuning the current solution.

[0081] In addition, Figure 8 There is no obvious shock or rebound phenomenon in the improved genetic algorithm, indicating that the algorithm has good stability and can avoid falling into a local optimal solution and remaining in a better solution region. This result is due to reasonable parameter settings and the selection of genetic operators, such as appropriate crossover probability and mutation probability, and optimization strategies.

[0082] Further, the improvements of the genetic algorithm and the comparison of the convergence speed, final total transportation distance, and stability and diversity of the two algorithms are described in detail as follows: The parameter settings in the two environments are basically the same, including population size, iteration number, fitness reference, crossover operator, and crossover probability. The improved algorithm in this application additionally introduces mutation probability and innovatively introduces a roulette selection strategy.

[0083] Further detailed comparison is needed, as follows: Convergence speed: In the improved genetic algorithm, due to the introduction of mutation probability, the convergence speed in the early stage is slightly slower than that of the default genetic algorithm in the Plant Simulation environment. However, this increase in diversity in the early stage helps the algorithm find better solutions in subsequent iterations. The roulette selection strategy shows faster convergence speed, which is due to its ability to more effectively use fitness information, preferentially select individuals with lower fitness, and thus speed up the convergence of the algorithm. Although the "4 to 1" selection strategy in the Plant Simulation default algorithm simplifies the selection process, it may cause individuals with lower fitness to be ignored, thereby affecting the convergence speed of the algorithm.

[0084] Final fitness value: The final fitness value of the improved genetic algorithm is much lower than that of the Plant Simulation default algorithm, which means that the improved genetic algorithm can find better solutions during optimization, and the mutation operation can allow the algorithm to explore a wider solution space during search, thereby avoiding falling into a local optimal solution. The final fitness value under the genetic algorithm is significantly lower than that of the Plant Simulation default algorithm, indicating that the genetic algorithm can find better solutions during optimization. This is because the roulette wheel selection strategy can more accurately reflect the fitness of individuals, thereby improving the accuracy of selection.

[0085] Stability and diversity: The fitness curve in the Plant Simulation default genetic algorithm is relatively stable in the later stage, showing good stability. However, this stability may come at the cost of solution diversity, making it difficult for the algorithm to escape from a local optimal solution. Although the fitness curve of the improved genetic algorithm results tends to be stable in the later stage, the overall fitness value is lower, and the roulette wheel selection strategy helps to maintain population diversity, thereby enhancing the global search ability of the algorithm.

[0086] The impact of mutation rate: The mutation probability introduced in the improved genetic algorithm plays a key role in the optimization process. A proper mutation rate not only helps to increase the diversity of the population, but also prevents the algorithm from converging too early, thereby improving the global search ability of the algorithm.

[0087] The impact of selection strategy: The roulette wheel selection strategy of the improved genetic algorithm plays a key role in the optimization process. This strategy determines the selection probability of individuals by the proportion of fitness values, which can more effectively utilize fitness information and preferentially select individuals with low fitness. Although the "4-to-1" selection strategy in the Plant Simulation default genetic algorithm helps to maintain population diversity, it may affect the convergence speed of the algorithm and the quality of the solution.

[0088] In the optimization process in this application, the elite preservation mechanism combined with the GSO algorithm can significantly improve the optimization performance. The core advantages include accelerating convergence, maintaining solution diversity, enhancing global search ability, and improving resource allocation efficiency.

[0089] As can be seen in the above scheme, in the application, by constructing a port logistics system simulation model, the improved genetic algorithm is used to plan the target moving path of the automatic guided vehicle between the quay crane and multiple container areas. In practice, the AGV path planning method is intelligently optimized, which can significantly reduce the transportation time of the automatic guided vehicle and improve the overall efficiency of port operations. This has great significance for relieving port congestion and shortening the ship's stay time in port, and improves the competitiveness and economic benefits of the port.

[0090] The application can significantly reduce the total transportation time of AGV and improve the efficiency of port operation: by improving the genetic algorithm (combining roulette selection, sequential crossover, exchange mutation and optimization mechanism), the algorithm has stronger global search ability and the ability to avoid premature convergence. This enables the algorithm to find a better AGV path sequence. Through simulation verification and result output, experimental data show that the total transportation time (136 units) obtained by the improved genetic algorithm of the application is significantly lower than the result (about 173 units) of the default genetic algorithm of PlantSimulation, and the transportation efficiency is improved by about 21%. This means that the time required for AGV to complete the same transportation task is greatly shortened, directly reducing the time of the ship in the port, speeding up the flow of goods, and thus improving the throughput and operation efficiency of the port as a whole.

[0091] The application can enhance the convergence and stability of the algorithm, and ensure the reliability and availability of the optimization result: through the roulette selection strategy, the strategy selects according to the individual fitness value by probability, so that high-quality individuals have a higher probability of being passed on to the next generation, thereby accelerating the convergence speed of the algorithm in the early stage and approaching the optimal solution area faster. Through the introduced optimization mechanism, the mechanism ensures that the optimal individual of each generation will not be destroyed by crossover and mutation operations, and can be unconditionally retained to the next generation. This effectively prevents the algorithm from degenerating due to random operations, ensuring the stability and convergence of the optimization process. Simulation results ( Figure 8 ) show that the curve of the improved algorithm smoothly decreases and tends to be stable, with much smaller fluctuations than the default algorithm ( Figure 6 ), providing a reliable and consistent optimization solution for port scheduling.

[0092] The application can improve the global optimization ability of the algorithm and avoid falling into a local optimal solution: by setting a fixed mutation probability (such as P m =0.3) and exchange mutation operation, new gene combinations are actively introduced into the population, significantly increasing the diversity of the population. This enables the algorithm to continuously explore undiscovered areas in the solution space, effectively breaking the limitation of traditional algorithms that are prone to local optimization, thereby having a higher probability of discovering a global optimal or better path planning solution.

[0093] The application can provide intuitive and scientific decision support for port scheduling: through visualization, the optimal path sequence (such as "1→4→2→3→8→5→9→6→7→1") and its corresponding total transportation time obtained by optimization are graphically displayed in the PlantSimulation interface (marked with different colors or icons for nodes, paths and directions), converting abstract optimization results into intuitive scheduling instructions. This greatly facilitates the understanding and execution of port scheduling personnel, providing them with intuitive and scientific data support and decision basis, reducing the uncertainty and inefficiency caused by relying on experience scheduling.

[0094] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the application.

[0095] In an embodiment, a port logistics AGV path planning device is provided, which corresponds to the port logistics AGV path planning method in the above embodiment. As shown in the figure, the port logistics AGV path planning device comprises a first construction module 101, a second construction module 102, and a solving module 103. The functions of each module are described in detail as follows: Figure 9 The first construction module 101 is used to construct a vertical container terminal port logistics system model, wherein the port logistics system model comprises a shore crane, an automatic guided vehicle, and a plurality of box areas. The second construction module 102 is used to construct a port logistics system basic database and a mapping relationship between the port logistics system basic database and the vertical container terminal port logistics system model, to obtain a port logistics system simulation model. The solving module 103 is used to plan a target moving path of the automatic guided vehicle between the shore crane and the plurality of box areas based on a preset improved genetic algorithm and according to the port logistics system simulation model. Specifically, the second construction module 102 is further used to obtain a straight-line distance from the shore crane to each box area, a Euclidean distance between each box area, a transportation speed of the automatic guided vehicle, and a yard crane operation response time of the box area, and to construct the port logistics system basic database.

[0096] According to the vertical container terminal port logistics system model, a port logistics weighted network graph is obtained, wherein the shore crane and each box area are nodes, and the connecting line between adjacent nodes is the moving path of the automatic guided vehicle. According to the straight-line distance from the shore crane to each box area and the Euclidean distance between each box area, the connecting line between adjacent nodes in the port logistics weighted network graph is weighted to obtain the port logistics system simulation model. Specifically, the solving module 103 is further used to convert the moving path planning problem of the automatic guided vehicle between the shore crane and the plurality of box areas into a traveling salesman problem with constraints. According to the improved genetic algorithm, the traveling salesman problem is solved under the constraints based on the obtained port logistics system simulation model, to obtain the moving path of the automatic guided vehicle between the shore crane and the plurality of box areas.

[0097]

[0098] ​Specifically, the solving module 103 is further configured to construct a constraint condition including an operation sequence of the automated guided vehicle when moving between the quay crane and the plurality of container areas, and including the automated guided vehicle starting from the quay crane node and returning to the quay crane node after traversing all the container area nodes. construct a target function for minimizing a moving and transporting time of the automated guided vehicle between the quay crane and the plurality of container areas.

[0099] Specifically, the solving module 103 is further configured to initialize a population to generate a path vector set, the path vector set including a plurality of path vectors, each of the path vectors being a moving path of the automated guided vehicle between the quay crane and the plurality of container areas. calculate an adaptability of each of the path vectors based on a pre-set adaptability function; determine path vectors for genetic into next generation based on the adaptability of each of the path vectors according to a pre-set roulette algorithm; perform a crossover operation on the path vectors for genetic into next generation based on a pre-set crossover algorithm to obtain path vectors after the crossover operation; perform a mutation operation on the path vectors after the crossover operation based on a pre-set mutation algorithm to obtain path vectors after the mutation operation; determine a target path vector from the path vectors for genetic into next generation and the path vectors after the mutation operation based on a pre-set optimization mechanism; decode the target path vector to obtain a target moving path of the automated guided vehicle between the quay crane and the plurality of container areas.

[0100] Specifically, the solving module 103 is further configured to determine a preliminary screening path vector from the path vectors for genetic into next generation and the path vectors after the mutation operation based on a pre-set elite reservation mechanism; determine updated path vectors according to the preliminary screening path vector based on a pre-set group search optimization algorithm; update the population according to the updated path vectors until iteration termination, and determine the target path vector.

[0101] Specifically, the device further includes a verification module configured to construct a port logistics simulation model based on Plant Simulation, plan a target moving path of the automated guided vehicle between the quay crane and the plurality of container areas based on a genetic algorithm, and obtain an estimated moving path and first iteration process parameters; plan a target moving path of the automated guided vehicle between the quay crane and the plurality of container areas based on a pre-set improved genetic algorithm according to the port logistics simulation model, and obtain the target moving path and second iteration process parameters; According to the estimated moving path and the first iteration process parameter, and the target moving path and the second iteration process parameter, the port logistics AGV path planning method is verified.

[0102] The application provides a port logistics AGV path planning device, which obtains a preliminary sorting result of candidate questions through a semantic matching mode, subsequently proposes a scheme of an entity alignment-based optimization question and answer engine, and sorts the sorting result of the candidate questions again through an entity alignment mode, so that more matched candidate questions are selected, the generalization ability defect of the model is effectively avoided, the entity matching effect is greatly and efficiently improved, and the effect of the question and answer engine is improved.

[0103] The specific limitation of the port logistics AGV path planning device can be referred to the limitation of the port logistics AGV path planning method in the foregoing, and details are not described herein again. Each module in the port logistics AGV path planning device can be realized by software, hardware and a combination thereof in whole or in part. The modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform the operations corresponding to each module.

[0104] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram thereof can be as shown in Figure 10 The computer device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external device through a network connection. The computer program is executed by the processor to implement the functions or steps of a port logistics AGV path planning method server side.

[0105] In one embodiment, a computer device is provided, which can be a device, and an internal structure diagram thereof can be as shown in Figure 11As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the computer device is used to communicate with the external server through the network connection. The computer program is executed by the processor to realize the functions or steps of the device side of the port logistics AGV path planning method.

[0106] In one embodiment, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the computer program to implement the following steps: Constructing a vertical container terminal port logistics system model, the port logistics system model comprising a shore crane, an automated guided vehicle and a plurality of box areas; Constructing a port logistics system basic database and a mapping relationship between the port logistics system basic database and the vertical container terminal port logistics system model to obtain a port logistics system simulation model; Based on a preset improved genetic algorithm, the target moving path of the automated guided vehicle between the shore crane and the plurality of box areas is planned according to the port logistics system simulation model.

[0107] In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, the computer program being executed by a processor to implement the following steps: Constructing a vertical container terminal port logistics system model, the port logistics system model comprising a shore crane, an automated guided vehicle and a plurality of box areas; Constructing a port logistics system basic database and a mapping relationship between the port logistics system basic database and the vertical container terminal port logistics system model to obtain a port logistics system simulation model; Based on a preset improved genetic algorithm, the target moving path of the automated guided vehicle between the shore crane and the plurality of box areas is planned according to the port logistics system simulation model.

[0108] It should be noted that the functions or steps that the computer readable storage medium or the computer device can implement above can be referred to the related descriptions of the server side and the device side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0109] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions.

[0111] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features. Such modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A port logistics AGV path planning method, characterized in that, The method comprises the following steps: constructing a vertical container terminal port logistics system model, the port logistics system model comprising a quay crane, an automated guided vehicle and a plurality of container yards; constructing a port logistics system basic database and a mapping relationship between the port logistics system basic database and the vertical container terminal port logistics system model to obtain a port logistics system simulation model; based on a preset improved genetic algorithm, planning a target movement path of the automated guided vehicle between the quay crane and the plurality of container yards according to the port logistics system simulation model.

2. The method of claim 1, wherein the port logistics system basic database and the mapping relationship between the port logistics system basic database and the vertical container terminal port logistics system model are constructed to obtain a port logistics system simulation model, comprising: obtaining a straight-line distance from the quay crane to each container yard, a Euclidean distance between each container yard, a transportation speed of the automated guided vehicle and a yard crane operation response time to construct the port logistics system basic database; obtaining a port logistics weighted network diagram from the vertical container terminal port logistics system model, the quay crane and each container yard being a node in the port logistics weighted network diagram, and a connection between adjacent nodes being a movement path of the automated guided vehicle; weighting the connection between adjacent nodes in the port logistics weighted network diagram according to the straight-line distance from the quay crane to each container yard and the Euclidean distance between each container yard to obtain the port logistics system simulation model.

3. The method of claim 1, wherein the movement path of the automated guided vehicle between the quay crane and the plurality of container yards is planned based on the preset improved genetic algorithm according to the obtained port logistics system simulation model, comprising: transforming the movement path planning problem of the automated guided vehicle between the quay crane and the plurality of container yards into a traveling salesman problem with constraints; solving the traveling salesman problem under the constraints based on the improved genetic algorithm according to the obtained port logistics system simulation model to obtain the movement path of the automated guided vehicle between the quay crane and the plurality of container yards.

4. The method of claim 3, wherein the movement path planning problem of the automated guided vehicle between the quay crane and the plurality of container yards is transformed into a traveling salesman problem with constraints, comprising: constructing constraints including an operation sequence of the automated guided vehicle when moving between the quay crane and the plurality of container yards, and further including the automated guided vehicle starting from the quay crane node and returning to the quay crane node after traversing all container yard nodes; constructing an objective function, the objective function being a minimization of the movement transportation time of the automated guided vehicle between the quay crane and the plurality of container yards.

5. The method of claim 3, wherein the target movement path of the automated guided vehicle between the quay crane and the plurality of container yards is obtained by solving the traveling salesman problem under the constraints based on the improved genetic algorithm according to the obtained port logistics system simulation model, comprising: ​ ​ ​ ​ population initialization, a path vector set is generated, the path vector set includes a plurality of path vectors, each path vector is a moving path of the automated guided vehicle between the quay crane and a plurality of container areas; based on a pre-set fitness function, the fitness of each path vector is calculated; based on a pre-set roulette algorithm, the path vectors that are genetically passed to the next generation are determined according to the fitness of each path vector; based on a pre-set crossover algorithm, the path vectors that are genetically passed to the next generation are subjected to crossover operation to obtain post-crossover path vectors; based on a pre-set mutation algorithm, the post-crossover path vectors are subjected to mutation operation to obtain post-mutation path vectors; based on a pre-set optimization mechanism, a target path vector is determined from the path vectors that are genetically passed to the next generation and the post-mutation path vectors; the target path vector is decoded to obtain a target moving path of the automated guided vehicle between the quay crane and a plurality of container areas.

6. The method of claim 5, wherein determining a target path vector from the path vectors that are genetically passed to the next generation and the post-mutation path vectors based on a pre-set optimization mechanism comprises: determining pre-screening path vectors from the path vectors that are genetically passed to the next generation and the post-mutation path vectors based on a pre-set elite reservation mechanism; determining updated path vectors according to the pre-screening path vectors based on a pre-set swarm search optimization algorithm; updating the population according to the updated path vectors until iteration termination, and determining the target path vector.

7. The method of claim 1, wherein the method further comprises: constructing a port logistics simulation model based on Plant Simulation, planning a target moving path of an automated guided vehicle between a quay crane and a plurality of container areas based on a genetic algorithm to obtain an estimated moving path and first iteration process parameters; planning a target moving path of an automated guided vehicle between a quay crane and a plurality of container areas based on a pre-set improved genetic algorithm according to the port logistics system simulation model to obtain the target moving path and second iteration process parameters; verifying the port logistics AGV path planning method according to the estimated moving path and the first iteration process parameters, and the target moving path and the second iteration process parameters.

8. A port logistics AGV path planning device, characterized in that, comprises: a first construction module configured to construct a vertical container terminal port logistics system model, the port logistics system model including a quay crane, an automated guided vehicle, and a plurality of container areas; a second construction module configured to construct a port logistics system database and a mapping relationship between the port logistics system database and the vertical container terminal port logistics system model to obtain a port logistics system simulation model; a solving module configured to plan a target moving path of an automated guided vehicle between a quay crane and a plurality of container areas based on a pre-set improved genetic algorithm according to the port logistics system simulation model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the port logistics AGV path planning method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by a processor to implement the steps of the port logistics AGV path planning method according to any one of claims 1 to 7.

Images