An intelligent warehousing system based on automatic control of cloud system

Abstract

The present invention discloses an intelligent warehousing system based on automatic control of a cloud system, and the present invention relates to the field of intelligent warehousing technology. It comprises the following structures: the intelligent warehousing system comprises a cloud server and a cargo transportation terminal, the cloud server sends a control signal to control the movement of the cargo transportation terminal, and the cloud server comprises: a warehouse environment model generation module, which is used to obtain warehouse cargo storage area environment information and generate an intelligent warehouse environment model; an operation road planning module, which is used to set a magnetic belt on each road and set nodes on the magnetic belt according to the intelligent warehouse environment model; a path selection module, which is used to determine the optimal path through a genetic algorithm; a task allocation module, which generates an automatic guided vehicle work execution coefficient when there is a transportation task, and is used to allocate tasks; an automatic guided vehicle operation module, which is used for the automatic guided vehicle to move through the magnetic belt set on the road according to the optimal path.

Description

Technical Field

[0001] The present invention relates to the field of intelligent warehousing technology, and in particular to an intelligent warehousing system automatically controlled based on a cloud system. Background Art

[0002] Smart warehousing is a part of the logistics process. The application of smart warehousing ensures the speed and accuracy of data input in each link of cargo warehouse management, ensures that enterprises can grasp the real data of inventory in a timely and accurate manner, and reasonably maintain and control enterprise inventory.

[0003] The traditional warehousing and transportation system adopts the "people to goods" picking method, which has problems such as high labor costs, slow picking speed and low transportation efficiency. Modern logistics has the characteristics of large order volume, large storage area and complex picking path. The traditional warehousing and transportation system can no longer meet the needs of modern logistics. At the same time, when transporting heavy and easily damaged goods, such as the storage of tiles, using manpower for transportation is not only inefficient but also has the risk of bumps. Tiles are brittle and are easily broken or cracked due to impact or improper carrying during handling, loading and unloading. If the transporters do not wear appropriate protective equipment, such as gloves and protective shoes, they may be injured by the sharp edges of the tiles.

[0004] Therefore, comprehensively building an unmanned intelligent warehousing system, reducing labor costs and error rates, and improving the overall operating efficiency of the system have become the primary goals of modern logistics development.

[0005] In the prior art, the publication number CN110040412A discloses an intelligent warehousing system, a processing terminal, a warehousing robot and an intelligent warehousing method, wherein the intelligent warehousing system includes: a warehousing robot and a picking device; the warehousing robot includes a first warehousing robot and / or a second warehousing robot; the first warehousing robot is used to receive a first dispatching instruction and transport a cargo box to a first target location according to the first dispatching instruction; the second warehousing robot is used to receive a second dispatching instruction and transport a portable shelf to a second target location according to the second dispatching instruction; the picking device is used to receive a picking instruction and take out the goods from the cargo box and / or the portable shelf according to the picking instruction. This system can realize the automation of warehouse picking and placing, thereby improving efficiency. However, two different types of warehousing robots (the first warehousing robot and the second warehousing robot) are mentioned in this system, which may increase the complexity of the system, reduce the flexibility of the intelligent warehousing system, and require more and more complex scheduling algorithms in terms of operating efficiency. At the same time, the robot's running route is not planned, which reduces the system's operating efficiency and consumes more energy.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an intelligent warehousing system based on automatic control of a cloud system to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] The intelligent warehousing system includes a cloud server and a cargo transportation terminal, wherein the cloud server sends a control signal to control the movement of the cargo transportation terminal, and further includes:

[0010] A warehouse environment model generation module is used to obtain warehouse cargo storage area environment information and generate an intelligent warehouse environment model. The environment information includes the location coordinates of each shelf, and the road length and width information;

[0011] A road planning module is run to set a magnetic belt on each road according to the intelligent warehouse environment model, wherein the starting point of the magnetic belt is set at the cargo entrance, and the coverage of the magnetic belt includes all road areas in the intelligent warehouse environment model; nodes are set at the intersections covered by each magnetic belt, the road turns and the starting point of the magnetic belt, and at least one cargo transportation terminal is set at each node;

[0012] The path selection module is used to obtain the coordinates of the task start node and the destination node after receiving the task information, generate a set of several feasible paths that meet the task requirements, determine the optimal path through a genetic algorithm, and upload it to the cloud server.

[0013] The task allocation module is used for generating an automatic guided vehicle work execution coefficient according to the power, load, working status data of each cargo transport terminal and the distance from the task starting node when there is a transportation task. The cloud server generates an automatic guided vehicle task allocation table according to the automatic guided vehicle work execution coefficient;

[0014] The guided vehicle driving module is used to read the optimal path and the automatic guided vehicle task allocation table inside the cloud server, determine the cargo transport terminal that performs the transportation task according to the automatic guided vehicle task allocation table, and control the cargo transport terminal to travel along the magnetic belt path according to the determined optimal path to reach the task destination node.

[0015] Furthermore, the method for establishing an intelligent warehouse environment model is: using a visual graph method to simulate an actual warehousing environment, taking the node position of the entrance for goods in and out as the origin, taking the vertical direction of the starting direction of the magnetic belt as the X-axis direction, setting the vertical X-axis as the Z-axis, and upward as the positive direction, setting the Y-axis according to the right-hand rule, and determining the position coordinates of each storage unit in each shelf, and the storage unit is used to store goods.

[0016] Furthermore, the method for setting the magnetic belt is: taking the entrance for goods entering and exiting as the starting point, the setting range of the magnetic belt covers the roads in the entire storage environment, two magnetic belts are set in parallel on each road, and at least one connecting belt is set between the two magnetic belts to connect the two magnetic belts set in parallel on each road; nodes are set at the intersections covered by each magnetic belt, the road turns and the starting points of the magnetic belts to feedback the position information of the automatic guided vehicle and plan the operation route.

[0017] Furthermore, the logic of determining the optimal path through the genetic algorithm is as follows: let T represent the set of all feasible paths for all tasks, where T = {P1, P2, …, P n}, where P u ={p u1 ,p u2 ,…,p uk}, P u represents the set of all feasible paths for task u, n represents the number of task requests, and k represents the number of feasible paths for task u.

[0018] Furthermore, randomly select the feasible path set P of the corresponding task i A path selected in is used as a gene in one of the gene positions of the individual chromosome, and n genes are selected to fill in the gene positions of the corresponding individual chromosome to form a complete individual chromosome S i , a total of m chromosomes are formed, and the m individual chromosomes are selected to form an initial population in

[0019]

[0020] Furthermore, the fitness of each individual chromosome in the initial population is calculated by the fitness function, where the formula based on the fitness function is:

[0021]

[0022] In the formula, f(S i ) represents the fitness of the i-th individual chromosome, SL(S i ) is the total number of nodes in the path of the i-th individual chromosome, is the total path length of an individual chromosome, and a and b are the weight coefficients of the total number of path nodes and the total path length, respectively. Both a and b are greater than 0 and a < b.

[0023] Further, selection, crossover, and mutation operations are cyclically performed according to the fitness of each individual chromosome in the initial population, and the population is iteratively updated. The number of iterations is set to 50, and the mutation probability is 0.5. In the population generated in the last iteration, the individual chromosome with the highest fitness is selected as the optimal solution.

[0024] Further, the cloud server issues task instructions based on the real-time position information and working status of the automated guided vehicle (AGV). The AGV executes the instructions and feeds back the execution results to the cloud server, and data exchange and real-time communication are carried out through the communication network. The logic for the cloud server to assign tasks to the AGV is as follows:

[0025] Obtain the position information of each node where the AGV is located, calculate the distance data between the current node position of each AGV and the task node position, and label it as L j , generate the current work execution coefficient of each AGV. The formula for the work execution coefficient of the AGV is:

[0026]

[0027] In the formula, ω j represents the working status of the j-th AGV. When performing a task, ω j is 0, otherwise ω j is 1. E j is the remaining power of the j-th AGV. c, d, and k are the weight coefficients of the maximum load W j of the AGV, the remaining power E j of the AGV, and the distance data L j between the current node position of each AGV and the task node position, respectively. c, d, and k are all greater than 0 and d < k < c. The tasks are sequentially assigned to the AGV with the highest current work execution coefficient.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows: through the warehouse environment model generation module, the environment information of the warehouse cargo storage area is obtained to generate an intelligent warehouse environment model; according to the intelligent warehouse environment model, a magnetic belt is set on each road, and the coverage of the magnetic belt includes all road areas in the intelligent warehouse environment model; nodes are set at the intersection covered by each magnetic belt, the road turning point and the starting point of the magnetic belt; the optimal path is determined by using a genetic algorithm according to the set nodes, and the optimal path is a path with the least number of nodes and the shortest path length; the cloud server generates an automatic guided vehicle work execution coefficient according to the power, load and working status data of each automatic guided vehicle, and the cloud server generates an automatic guided vehicle task allocation table according to the automatic guided vehicle work execution coefficient; the cloud server allocates tasks according to the automatic guided vehicle task allocation table, the automatic guided vehicle runs according to the determined optimal path, and the cloud server sends a control signal to control the automatic guided vehicle to travel along the magnetic belt path to reach the task destination.

[0029] The modular design makes the system more flexible and easy to expand, and modules can be added or reduced according to the specific needs of the warehouse; the modular design makes maintenance easier because a module can be replaced or upgraded individually without making large-scale changes to the entire system; at the same time, genetic algorithms are used to determine the optimal path, improve the system's operating efficiency, and reduce the system's energy consumption. Finally, centralized control and optimization are carried out through cloud servers to improve the operating efficiency and response speed of the entire logistics system. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0031] Figure 2 This is a schematic diagram of the intelligent warehouse environment model of the present invention. DETAILED DESCRIPTION

[0032] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0033] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0034] Example:

[0035] See also Figure 1-Figure 2 , the present invention provides a system structure:

[0036] An intelligent warehousing system based on automatic control of a cloud system, the intelligent warehousing system comprising a cloud server and a cargo transportation terminal, the cloud server sending a control signal to control the movement of the cargo transportation terminal, the system also comprising:

[0037] A warehouse environment model generation module is used to obtain warehouse cargo storage area environment information and generate an intelligent warehouse environment model. The environment information includes the location coordinates of each shelf, and the road length and width information;

[0038] The method for establishing the intelligent warehouse environment model is as follows: using the visual graph method to simulate the actual storage environment, taking the node position of the entrance of the goods in and out as the origin, taking the right as the positive direction of the X-axis, setting the vertical X-axis as the Z-axis, and setting the upward direction as the positive direction, setting the Y-axis according to the right-hand rule, establishing a coordinate system, and determining the position coordinates of each storage unit in each shelf, and the storage unit is used to store goods;

[0039] The specific steps of using the visual graph method to simulate the actual warehouse environment are as follows: first, the warehouse environment needs to be accurately modeled, including the location and size of obstacles such as shelves, pillars, walls, and the layout of accessible roads; obstacles such as shelves, pillars, walls, etc. are represented as mass points and approximate polygons respectively, and finally a visual graph is constructed to simulate the actual warehouse environment.

[0040] A road planning module is run to set a magnetic belt on each road according to the intelligent warehouse environment model, wherein the starting point of the magnetic belt is set at the cargo entrance, and the coverage of the magnetic belt includes all road areas in the intelligent warehouse environment model; nodes are set at each intersection covered by the magnetic belt, at the road turning point and at the starting point of the magnetic belt, and at least one cargo transportation terminal is set at each node; wherein at least one node is set in front of each storage unit, i.e., the shelf.

[0041] The method for setting up the magnetic belt is as follows: taking the entrance for goods entering and exiting as the starting point, the magnetic belt setting range covers the roads in the entire storage environment, two magnetic belts are set in parallel on each road, and when there are tasks of entering and exiting the warehouse at the same time, they can be run on different magnetic belt roads, wherein at least one connecting belt is set between the two magnetic belts to connect the two magnetic belts set in parallel on each road; wherein each storage unit, i.e., in front of the shelf, is provided with at least one magnetic belt connection, i.e., at least one node is set in front of the shelf.

[0042] Nodes are set at each intersection covered by the magnetic belt, road bend and starting point of the magnetic belt to feedback the position information of the automatic guided vehicle and plan the operation route.

[0043] The path selection module is used to obtain the coordinates of the task start node and the destination node after receiving the task information, generate a set of several feasible paths that meet the task requirements, determine the optimal path through a genetic algorithm, and upload it to the cloud server.

[0044] A depth-first search algorithm is used to find a set of feasible paths that meet the communication requirements from the task source node to the destination node for each task request according to the set nodes. T is denoted as the set of all feasible paths for all tasks, where T = {P1, P2, …, P n}, where P u ={p u1 ,p u2 ,…,p uk}, P u represents the set of all feasible paths for task u, n represents the number of task requests, and k represents the number of feasible paths for task u. The depth-first search for node paths requires first determining the source node of the task, then finding all adjacent nodes that meet the conditions for moving to the destination node of the task with the source node of the task, and then performing a depth-first search with each node as the source node until the destination node is found.

[0045] Each path selected for each task request is encoded as a gene, and an individual chromosome is formed according to the obtained genes. The individual chromosome is composed of n genes, where each feasible path for each task request is a gene, that is, pu1 , p u1 , …, p uk are all optional values of the gene positions on individual chromosomes, and at the same time p u1 , p u1 , …, p uk These k genes are allelic to each other. The individual chromosome S i consists of n genes, and each gene is randomly selected as a path from the set P of feasible paths corresponding to the task i , where i = 1, 2, ..., n;

[0046] Suppose the chromosome S of an individual i = {1, 2, …, 3}, which means that for task 1, the first path in its set P1 of feasible paths is selected, for task 2, the second path in its set P2 of feasible paths is selected, and for task n, the third path in its set P n of feasible paths is selected, and the n genes that make up the chromosome of individual Si are not allelic to each other;

[0047] Randomly select a path from the set P of feasible paths corresponding to the task i as the gene of one of the gene positions of the individual chromosome, and select n genes and fill them into the gene positions of the corresponding individual chromosome to form a complete individual chromosome s i , and a total of m chromosomes are formed. Select the m individual chromosomes formed to form an initial population Among them

[0048] Calculate the fitness of each individual chromosome in the initial population through the fitness function. The formula on which the fitness function is based is:

[0049]

[0050] In the formula, f(S i ) represents the fitness of the i-th individual chromosome, SL(S i ) is the total number of nodes passed by the path of the i-th individual chromosome, is the total length of the path of the individual chromosome, and a and b are the weight coefficients of the total number of nodes passed by the path and the total length of the path, and both a and b are greater than 0 and a < b. The fitness f(S i ) of the individual chromosome is inversely proportional to the total number of nodes passed by the task path, that is, the more nodes the selected path passes through, the smaller its fitness, and f(S i ) is inversely proportional to the length of the selected path, that is, the longer the selected path, the smaller its fitness.

[0051] According to the fitness of each individual chromosome in the initial population, selection, crossover and mutation operations are performed cyclically, and the population is updated iteratively. The number of iterations is set to 50 times, and the mutation probability is set to 0.5. In the population generated by the last iteration, the individual chromosome with the highest fitness is selected as the optimal solution.

[0052] The selection operation is to select two individual chromosomes in the population, and the formula for calculating the probability of being selected is:

[0053]

[0054] In the formula, f(S i ) represents the fitness of the i-th individual chromosome, pro(S i ) is the probability of the i-th individual chromosome being selected. The roulette method is used to select individuals. The system randomly generates a random number in the interval [0, 1]. According to the generated probability of selection, the random number is distributed in the selection interval of the individual chromosome to determine which individual chromosome to select in this round. The process of selecting individuals is based on the fitness of the individual. The greater the fitness of the individual, the greater the possibility of being selected, and vice versa. The possibility of being selected is smaller, and an individual may be selected multiple times;

[0055] A crossover operation is performed on the two selected individuals. The logic of the crossover operation is: a single-point crossover method is used to process the two individual chromosomes in the selection operation, which are represented as and in represents the value of the jth gene of chromosome i of individual i, randomly generates a random integer in the interval [1, n], which is the crossover point on the chromosome, and selects individual S i and individual S j The yth gene position of the chromosome is used as the crossover point, where 1≤y≤n, that is, and Then S i and S j The chromosomes from and The two intersection points are cut off and S i and S j The chromosome segments composed of genes at and after the crossover point are exchanged to obtain two individual chromosomes S' after the crossover i and S′ j , respectively expressed as and The introduction of crossover operation can greatly increase the search range of the algorithm and promote rapid convergence of the algorithm. It is the core operation of the algorithm.

[0056] The logic behind the mutation operation on the chromosomes of two individuals after the crossover is: the mutation operation is performed on the two new individuals S′ generated by the crossover operation i and S′ j To perform the operation, the system first randomly generates an integer in the interval [1, n] to represent the chromosome S′ i A gene position on m The selected gene is mutated into one of its alleles, and the mutated gene is used to replace the gene at the gene position, thereby obtaining a new individual S″ i , expressed as For the mutated allele, the mutation probability is set to 0.5 to avoid local optimal solutions.

[0057] After the three major operations, two new individuals are obtained. These three operations are repeated to continuously generate new individuals until the number of individual chromosomes in the iterative population reaches m, forming a new population as a new iterative population to enter the inheritance of the next generation of populations. The above process is repeated for each generation of inheritance. The maximum number of iterations is set to 50 generations. After reaching the maximum number of iterations, the iteration operation is stopped. In the population generated by the last iteration, the individual chromosome with the highest fitness is selected as the optimal solution.

[0058] The task allocation module is used for generating an automatic guided vehicle work execution coefficient according to the power, load, working status data of each cargo transport terminal and the distance from the task starting node when there is a transportation task. The cloud server generates an automatic guided vehicle task allocation table according to the automatic guided vehicle work execution coefficient;

[0059] The cloud server issues task instructions based on the real-time location information and working status of the AGV. The AGV executes the instructions and feeds back the execution results to the cloud server. Data exchange and real-time communication are carried out through the communication network. The logic by which the cloud server assigns tasks to the AGV is as follows:

[0060] Obtain the node location information of each automated guided vehicle, calculate the distance data between the current node location of each automated guided vehicle and the task node location, and calibrate it as L j , generate the current work execution coefficient of each automated guided vehicle. The formula for the work execution coefficient of the automated guided vehicle is:

[0061]

[0062] In the formula, ω j Represents the working state of the j-th automatic guided vehicle. When performing the task, ω j is 0, anyway j Then 1, E jis the remaining power of the j-th automated guided vehicle, and c, d, and k are the maximum load W of the automated guided vehicle j , the remaining power E of the automated guided vehicle j and the distance data L between the current node position of each automated guided vehicle and the task node position j of the weight coefficients, where c, d, and k are all greater than 0 and d < k < c; the tasks are sequentially assigned to the automated guided vehicle with the highest current work execution coefficient.

[0063] The work execution coefficient gz of the automated guided vehicle j is proportional to W j , that is, the automated guided vehicle with a larger maximum load is preferentially assigned tasks. The work execution coefficient gz of the automated guided vehicle j is proportional to the remaining power E of the automated guided vehicle j , and the more sufficient the remaining power, the higher the probability of being preferentially assigned;

[0064] The higher the work execution coefficient of the automated guided vehicle, the closer the current position of the automated guided vehicle is to the task position and the more sufficient the power. The tasks are assigned to the automated guided vehicle with the highest current work execution coefficient;

[0065] When the selected automated guided vehicle is not at the starting node position of the current task, the cloud server publishes a prior task with the node position where the selected automated guided vehicle is located as the starting position and the starting node position of the task to be executed as the destination. The optimal path of the prior task is found through the above genetic algorithm. After the selected automated guided vehicle completes the prior task and reaches the starting node position of the task to be executed, it starts to execute the task.

[0066] Each automated guided vehicle can only execute the next task after the previous task is completed. When the automated guided vehicle is executing a task, that is, when ω j is 0, its work execution coefficient is also 0. When all automated guided vehicles are executing tasks, the cloud service system suspends task assignment.

[0067] The guide vehicle drive module is used to read the optimal path and the automated guided vehicle task assignment table inside the cloud server, determine the cargo transport terminal for executing the transport task according to the automated guided vehicle task assignment table, and control the cargo transport terminal to drive along the magnetic tape path to the task destination node according to the determined optimal path.

[0068] The system is centrally controlled and optimized through the cloud system to improve the operational efficiency and response speed of the entire logistics system. In the centralized control method, there is only one central controller for the entire system, and all modules do not have independent decision-making capabilities and mutual communication capabilities. Task allocation and path planning are all concentrated in the central controller. Each module is responsible for receiving specific instructions from the central controller and feeding back the execution results to the central controller. The advantages of centralized control include simple control methods, low hardware costs, and easy acquisition of the global optimal execution strategy;

[0069] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0070] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0071] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An intelligent warehousing system based on automatic control of a cloud system, the intelligent warehousing system comprising a cloud server and a cargo transportation terminal, the cloud server sending a control signal to control the movement of the cargo transportation terminal, characterized in that: Also included are: A warehouse environment model generation module is used to obtain warehouse cargo storage area environment information and generate an intelligent warehouse environment model. The environment information includes the location coordinates of each shelf, and the road length and width information; Running a road planning module, which is used to set a magnetic belt on each road according to the intelligent warehouse environment model, wherein the starting point of the magnetic belt is set at the warehouse entrance, and the coverage of the magnetic belt includes all road areas in the intelligent warehouse environment model; Nodes are set at each intersection covered by the magnetic belt, at a road bend and at the starting point of the magnetic belt, and at least one cargo transportation terminal is set at each node; The path selection module is used to obtain the coordinates of the task start node and the destination node after receiving the task information, generate a set of several feasible paths that meet the task requirements, determine the optimal path through a genetic algorithm, and upload it to the cloud server. The task allocation module is used for generating an automatic guided vehicle work execution coefficient according to the power, maximum load, working status data and distance from the task starting node of each cargo transportation terminal when there is a transportation task. The cloud server generates an automatic guided vehicle task allocation table according to the automatic guided vehicle work execution coefficient; The guided vehicle driving module is used to read the optimal path and the automatic guided vehicle task allocation table in the cloud server, determine the cargo transportation terminal that performs the transportation task according to the automatic guided vehicle task allocation table, and control the cargo transportation terminal to drive along the magnetic belt path according to the determined optimal path to reach the task destination node; The method of establishing the intelligent warehouse environment model is to use the visual graph method to simulate the actual storage environment, taking the node position of the cargo entrance as the origin and the vertical direction of the magnetic belt starting point as the Axis direction, vertical Axis set to Axis, upward is the positive direction, set according to the right-hand rule Axis, determining the position coordinates of each storage unit, wherein the storage unit is used to store goods; The method for setting the magnetic belt is as follows: the entrance for goods entering and exiting is used as the starting point for setting, the setting range of the magnetic belt covers the roads of the entire storage environment, two magnetic belts are set in parallel on each road, wherein at least one connecting belt is set between the two magnetic belts, which is used to connect the two magnetic belts set in parallel on each road; the intersection covered by each magnetic belt, the road turning point and the starting point of the magnetic belt are set as nodes, wherein at least one magnetic belt connection is set in front of each storage unit, which is used to feedback the location information of the cargo transportation terminal and plan the operation route, and the cargo transportation terminal is an automatic guided vehicle; The cloud server issues task instructions based on the real-time location information and working status of the AGV. The AGV executes the instructions and feeds back the execution results to the cloud server. Data exchange and real-time communication are carried out through the communication network. The logic by which the cloud server assigns tasks to the AGV is as follows: Obtain the node position information of each automated guided vehicle, calculate the distance data between the current node position of each automated guided vehicle and the task node position, and calibrate it as , generate the current work execution coefficient of each automated guided vehicle. The formula for the work execution coefficient of the automated guided vehicle is: In the formula, Indicates the working state of the jth automatic guided vehicle. When performing a task is 0, anyway Then 1, is the remaining power of the j-th AGV, The maximum load of the automated guided vehicle 、Remaining power of the AGV And the distance data between the current node position of each automated guided vehicle and the task node position The weight coefficient of are greater than 0 and ; Assign tasks in sequence to the automated guided vehicle with the highest current work execution coefficient.

2. According to claim 1, the intelligent warehousing system based on cloud system automatic control is characterized by: The logic of determining the optimal path through genetic algorithm is: represents the set of all feasible paths for all tasks, where ,in , represents the set of all feasible paths for task u, n represents the number of task requests, and k represents the number of feasible paths for task u.

3. According to claim 2, the intelligent warehousing system based on automatic control of the cloud system is characterized by: Randomly select the feasible path set of the corresponding task A path selected in is used as a gene in one of the gene positions of the individual chromosome, and n genes are selected to fill in the gene positions of the corresponding individual chromosome to form a complete individual chromosome , a total of m chromosomes are formed, and the m individual chromosomes are selected to form an initial population ,in .

4. The intelligent warehousing system based on cloud system automatic control according to claim 3 is characterized by: The fitness of each individual chromosome in the initial population is calculated by the fitness function, where the formula based on the fitness function is: In the formula, represents the fitness of the i-th individual chromosome, is the total number of nodes in the chromosome path of the i-th individual, is the total path length of the individual chromosome, is the weight coefficient of the total number of nodes passed by the path and the total length of the path, are greater than 0 and .

5. The intelligent warehousing system based on automatic control of a cloud system according to claim 4 is characterized in that: According to the fitness of each individual chromosome in the initial population, selection, crossover and mutation operations are performed cyclically, and the population is updated iteratively. The number of iterations is set to 50 times, and the mutation probability is set to 0.

5. In the population generated by the last iteration, the individual chromosome with the highest fitness is selected as the optimal solution.

Images