Material dispensing control method, server, and storage medium

Abstract

The application provides a material distribution control method, a server and a computer readable storage medium. The material distribution control method comprises the following steps: acquiring first distribution data of each work equipment in a material distribution control area, wherein the first distribution data comprises a distribution route congestion degree of each work equipment; obtaining a target material delivery time length of each work equipment based on prediction of the first distribution data; determining a material demand time point of each work equipment based on the target material delivery time length and a predicted completion time point of each work equipment; and executing a material distribution task of each work equipment based on the material demand time point of each work equipment. The application can ensure the timeliness of material reaching the work equipment, thereby reducing the probability of the work equipment being forced to stop working and improving work efficiency.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a material distribution control method, a server, and a computer-readable storage medium. Background Technology

[0002] In material distribution areas (such as production workshops), multiple delivery devices (such as robots) typically operate simultaneously, transporting materials to processing equipment (such as semiconductor manufacturing equipment) for operation. When multiple delivery devices (such as robots) operate in the same workshop, similar to vehicles navigating traffic lights and one-way streets in daily life, they encounter one-way routes and navigate complex road conditions such as intersections and T-junctions.

[0003] Therefore, delivery equipment inevitably encounters unexpected situations such as traffic jams, which makes it impossible to guarantee the timely arrival of materials at the operating equipment, thus forcing the operating equipment to stop operating. Summary of the Invention

[0004] This application provides a material dispatch control method, a server, and a computer-readable storage medium, which can ensure the timeliness of material arrival at the operating equipment, thereby reducing the probability of the operating equipment being forced to stop operation and improving operating efficiency.

[0005] In a first aspect, this application provides a material distribution control method, the method comprising:

[0006] Acquire the first dispatch data for each operating device in the material dispatch control area, wherein the first dispatch data includes the congestion level of the dispatch route of each operating device;

[0007] Based on the first distribution data, the target material delivery time for each operating device is predicted.

[0008] Based on the target material delivery time and the estimated completion time of each work equipment, the material requirement time point of each work equipment is determined.

[0009] Based on the material demand time point of each operating device, execute the material delivery task of each operating device.

[0010] Secondly, this application also provides a server, which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes any of the material distribution control methods provided in this application when it calls the computer program in the memory.

[0011] Thirdly, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to execute the material dispensing control method described above.

[0012] In this application, the target material delivery time for each operating device is predicted by acquiring the first dispatch data of each operating device in the material dispatch control area. Since the first dispatch data includes the congestion level of the dispatch route for each operating device, the target material delivery time for each operating device can be estimated by combining the congestion level of the dispatch route, thereby improving the accuracy of the target material delivery time for each operating device. Thus, the material demand time point for each operating device is determined by using the target material delivery time of each operating device, which is used to execute the material delivery task of each operating device. On the one hand, this can ensure the timeliness of material arrival at the operating device, thereby reducing the probability of the operating device being forced to stop operation and improving operating efficiency. On the other hand, it can avoid the problem of materials arriving too early and occupying the distribution equipment resources for a long time, thereby avoiding the problem of low material handling efficiency caused by the ineffective occupation of distribution equipment resources, and improving material handling efficiency to a certain extent. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic block diagram of a material distribution system provided in an embodiment of this application;

[0015] Figure 2 This is a schematic block diagram of a server structure provided in an embodiment of this application;

[0016] Figure 3 This is a schematic flowchart of a material distribution control method provided in an embodiment of this application;

[0017] Figure 4 This is a schematic diagram illustrating a scenario for determining the congestion level of a delivery route, provided in an embodiment of this application.

[0018] Figure 5 This is a schematic diagram illustrating a specific embodiment of the material distribution control process provided in this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0021] In the description of the embodiments of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0022] To enable any person skilled in the art to implement and use this application, the following description is provided. In this description, details are set forth for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be implemented without using these specific details. In other instances, well-known processes will not be described in detail to avoid obscuring the description of the embodiments of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in the embodiments of this application.

[0023] This application provides a material distribution control method, a server, and a computer-readable storage medium.

[0024] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0025] Figure 1 This is a schematic block diagram of a material distribution system provided in an embodiment of this application.

[0026] like Figure 1 As shown, the material distribution system 100 includes a server 101, multiple distribution devices 102 and multiple operating devices 103, wherein the server 101 integrates a task dispatching device 1011 and a transportation scheduling device 1012.

[0027] The task dispatching device 1011 is used to determine the material demand time of the operating equipment; and to allocate material delivery tasks to the transportation scheduling device 1012 according to the material demand time of the operating equipment. For example, the task dispatching device 1011 may be a transportation management system (TMS).

[0028] The capacity scheduling device 1012 is used to schedule the delivery equipment 102 to transport materials from the storage area to the operating equipment according to the material delivery tasks assigned to the capacity scheduling device 1012. For example, the capacity scheduling device 1012 may be a fleet management system (Fleet).

[0029] The delivery equipment 102 is used to transport materials from the storage area to the operating equipment. For example, the delivery equipment 102 may be an autonomous mobile robot (AMR).

[0030] The server 101 can be implemented using software or hardware. When implemented using hardware, the server 101 can be an electronic device such as a mobile phone or computer. The server 101 integrates a task dispatching device (such as a TMS) and a capacity scheduling device (such as a Fleet). Figure 2 This is a schematic block diagram of the structure of a server provided in an embodiment of this application.

[0031] like Figure 2 As shown, server 101 includes a task dispatching device 1011, a capacity scheduling device 1012, a processor 1013, and a memory 1014. The processor 1013 and the memory 1014 are connected via a bus 1015, such as an I2C (Inter-integrated Circuit) bus.

[0032] Specifically, processor 1013 provides computing and control capabilities to support the operation of the entire server 101. Processor 1013 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0033] Specifically, the memory 1014 can be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a portable hard drive, etc.

[0034] Those skilled in the art will understand that Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the embodiments of this application, and does not constitute a limitation on the server to which the embodiments of this application are applied. A specific server may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0035] The processor 1013 is configured to run a computer program stored in the memory 1014, and implement any of the material dispensing control methods provided in the embodiments of this application when executing the computer program. For example, the processor 1013 is configured to run a computer program stored in the memory 1014, and can implement the following steps when executing the computer program:

[0036] Acquire first dispatch data for each work device in the material dispatch control area, wherein the first dispatch data includes the congestion level of the dispatch route of each work device; predict the target material delivery time for each work device based on the first dispatch data; determine the material demand time point for each work device based on the target material delivery time and the estimated completion time point of each work device; and execute the material delivery task for each work device based on the material demand time point of each work device.

[0037] In some embodiments, the method is applied to a server in a material dispatching system, the material dispatching system including a server, multiple delivery devices, and multiple operating devices, wherein the processor 1013 is configured to run a computer program stored in a memory 1014, and when executing the computer program, the following steps can be performed:

[0038] Based on the material demand time point of each operating device, the task dispatching device of the server issues a material delivery task for each operating device to the capacity scheduling device of the server; through the capacity scheduling device, the target delivery device is called to complete the material delivery task of each operating device, so as to deliver the next batch of materials to each operating device.

[0039] In some embodiments, the processor 1013 is configured to run a computer program stored in the memory 1014, and when executing the computer program, it may perform the following steps:

[0040] A total timeliness difference function is established for the material dispatch system, wherein the total timeliness difference function indicates the sum of the timeliness differences of all operating equipment in the material dispatch system; a first constraint condition is established that the material dispatch time of each operating equipment is earlier than or equal to the material demand time of each operating equipment, and a second constraint condition is established that each delivery equipment is available at the material dispatch time; based on the first constraint condition and the second constraint condition, the total timeliness difference function is optimized using the material dispatch time of each operating equipment as the variable to be optimized, to obtain the target value of the material dispatch time of each operating equipment; according to the target value of the material dispatch time of each operating equipment, the material delivery task of each operating equipment is issued to the capacity scheduling device of the server through the task dispatch device of the server.

[0041] In some embodiments, the processor 1013 is configured to run a computer program stored in the memory 1014, and when executing the computer program, it may perform the following steps:

[0042] Based on the first and second constraints, the total time difference function is optimized using the material dispatch time point of each operating device and the number of delivery devices deployed in the material dispatch system as variables to be optimized, so as to obtain the target value of the material dispatch time point of each operating device.

[0043] In some embodiments, the processor 1013 is configured to run a computer program stored in the memory 1014, and when executing the computer program, it may perform the following steps:

[0044] Under the condition of satisfying the first constraint and the second constraint, with the goal of minimizing the total time difference function and the number of delivery equipment deployed, the material dispatch time point of each operating equipment and the number of delivery equipment deployed in the material dispatch system are solved to obtain the target value of the material dispatch time point of each operating equipment and the target value of the number of delivery equipment deployed.

[0045] In some embodiments, the processor 1013 is configured to run a computer program stored in the memory 1014, and when executing the computer program, it may perform the following steps:

[0046] The target material delivery time for each operating device is obtained by predicting the delivery time based on the first distribution data using a trained duration prediction model.

[0047] In some embodiments, the processor 1013 is configured to run a computer program stored in the memory 1014, and when executing the computer program, it may perform the following steps:

[0048] Acquire the second dispatch data of the sample operation equipment and the actual material delivery time of the sample operation equipment; predict the predicted material delivery time of the sample operation equipment based on the second dispatch data using a preset time prediction model; determine the training loss value of the preset time prediction model based on the actual material delivery time and the predicted material delivery time; adjust the model parameters of the preset time prediction model based on the training loss value to obtain the trained time prediction model.

[0049] In some embodiments, the processor 1013 is configured to run a computer program stored in the memory 1014, and when executing the computer program, it may perform the following steps:

[0050] Obtain the start time of the current batch of materials for each work equipment and the standard processing time for each work equipment; determine the expected completion time for each work equipment based on the start time and the standard processing time; determine the material demand time for each work equipment based on the expected completion time and the target material delivery time.

[0051] In some embodiments, the processor 1013 is configured to run a computer program stored in the memory 1014, and when executing the computer program, it may perform the following steps:

[0052] The system obtains the number of delivery devices currently operating on the common road segment of each operating device; the system obtains the route overlap length between each operating device and other operating devices in the material distribution control area; the system obtains the interval between the current time point and the estimated completion time point of each operating device as the first interval length of each operating device; the system obtains the interval between the estimated completion time point of each operating device and the estimated completion time points of other operating devices as the second interval length of each operating device; and determines the congestion degree of the distribution route of each operating device based on the number of delivery devices operating, the first interval length, the second interval length, and the route overlap length.

[0053] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the server described above can be referred to the corresponding process in the following material distribution control method embodiment, and will not be repeated here.

[0054] The following will be based on Figure 2 Taking the server shown as the execution entity of the material distribution control method as an example, this application provides a detailed description of the material distribution control method provided in this embodiment. For simplicity and ease of description, the execution entity will be omitted in subsequent method embodiments. It should be noted that... Figure 2 The scenarios described are only used to explain the material distribution control method provided in the embodiments of this application, but do not constitute a limitation on the application scenarios of the material distribution control method provided in the embodiments of this application.

[0055] Please see Figure 3 , Figure 3 This is a flowchart illustrating a material dispatch control method provided in an embodiment of this application. The material dispatch control method includes steps 301 to 304, wherein:

[0056] 301. Obtain the first dispatch data for each operating device in the material dispatch control area.

[0057] Among them, the material distribution control area is the area that needs to coordinate the distribution of materials. For example, if materials need to be distributed to the production equipment in the semiconductor production workshop when the production equipment is short of materials, then it can be the semiconductor production workshop.

[0058] Among them, operating equipment refers to equipment that needs to use materials to perform operations, such as production equipment in a semiconductor manufacturing workshop.

[0059] The first dispatch data for each work equipment includes the congestion of the dispatch route for each work equipment, and may further include at least one of the following: the busyness of the dispatch task in the material dispatch control area, and the average delivery time of the task for each work equipment.

[0060] The delivery route refers to the route along which materials are transported from the storage area to the operating equipment.

[0061] The dispatch route for each operating device is the route along which materials are transported from the storage area to each operating device.

[0062] The congestion level of each work equipment's dispatch route refers to the degree of congestion along each work equipment's dispatch route. For example, the congestion level of each work equipment's dispatch route can be obtained through the following steps A1 to A5:

[0063] A1. Obtain the number of delivery devices operating on the common road segment of each of the operating devices at the current time.

[0064] In this context, a shared road segment refers to the overlapping section between the dispatch routes of each work equipment and the dispatch routes of other work equipment. For example, such as... Figure 4 As shown, there are 8 operating devices in the material dispatch control area carrying out production tasks. The dispatch routes for operating devices 1, 2, 3, 4, 5, 6, 7, and 8 are routes 1, 2, 3, 4, 5, 6, 7, and 8, respectively. Taking operating device 1 as an example, the common road segments for operating device 1 include overlapping road segments 1, 2, and 3.

[0065] The number of operational delivery equipment refers to the number of delivery equipment (such as AMRs used for transporting materials) currently on public road sections. For example, ... Figure 4 As shown, taking each operating device as operating device 1 as an example, assuming that the number of transport devices in overlapping road segments 1, 2, and 3 at the current time is 3, 4, and 5 respectively, then the number of operating delivery devices is 3+4+5=12.

[0066] A2. Obtain the route overlap length between each operating device and other operating devices in the material distribution control area.

[0067] The route overlap length refers to the length of the section where the dispatch route of each work equipment overlaps with the dispatch routes of other work equipment. For example, ... Figure 4 As shown, taking operating equipment 1 as an example, the overlap length of the routes of operating equipment 1 and operating equipment 2 is the total length of overlapping road segment 1, overlapping road segment 2 and overlapping road segment 3.

[0068] A3. Obtain the interval between the current time point and the expected completion time point of each work equipment, and use it as the first interval duration of each work equipment.

[0069] The first interval duration is the interval between the current time point and the expected completion time point of each working device.

[0070] For example, if the current time is 6:00 and the estimated completion time for each piece of equipment is 6:30, then the first interval duration is 30 minutes.

[0071] A4. Obtain the interval between the estimated completion time of each work equipment and the estimated completion time of other work equipment, and use it as the second interval of each work equipment.

[0072] The second interval duration refers to the interval between the expected completion time of each work equipment and the expected completion time of other work equipment.

[0073] For example, such as Figure 4 As shown, taking work equipment 1 as an example, assuming that the estimated completion times of work equipment 1, 2, 3, 4, 5, 6, 7, and 8 are 6:30, 6:35, 6:40, 6:45, 6:50, 6:55, 7:00, and 7:05 respectively, then the intervals between the estimated completion time of work equipment 1 and the estimated completion times of other work equipment 2, 3, 4, 5, 6, 7, and 8 are 5 minutes, 10 minutes, 15 minutes, 20 minutes, 25 minutes, 30 minutes, and 35 minutes respectively.

[0074] A4. Based on the number of delivery devices in operation, the first interval duration, the second interval duration, and the route overlap length, determine the congestion level of the delivery route for each operating device.

[0075] There are several ways to determine the congestion level of the dispatch route in step A4, including, for example:

[0076] (1) The congestion vector formed by the number of delivery equipment in operation, the first interval duration, the second interval duration, and the route overlap length is used as the congestion degree of the dispatch route for each work equipment. At this time, step A4 may specifically include: concatenating the number of delivery equipment in operation, the first interval duration, the second interval duration, and the route overlap length to form the congestion vector of each work equipment, which is used as the congestion degree of the dispatch route for each work equipment.

[0077] For example, the number of delivery equipment in operation, the first interval duration, the second interval duration, and the route overlap length can be concatenated according to a preset vector format (such as [number of delivery equipment in operation, first interval duration, second interval duration between the expected completion time of the work equipment j, and route overlap length with the work equipment j]) to form a congestion degree representation vector for each work equipment.

[0078] For example, such as Figure 4As shown, taking equipment 1 as an example, assuming the number of delivery devices is 12, the first interval is 30 minutes, the second interval (e.g., the interval between the estimated completion time of equipment 1 and the estimated completion time of other equipment 2, 3, 4, 5, 6, 7, and 8 is 5 minutes, 10 minutes, 15 minutes, 20 minutes, 25 minutes, 30 minutes, and 35 minutes respectively), and the route overlap length (e.g., the length of the overlapping section between the delivery route of equipment 1 and the delivery routes of other equipment 2, 3, 4, 5, 6, 7, and 8 respectively). The following parameters are given: 15 meters, 10 meters, 10 meters, 5 meters, 5 meters, 5 meters, 5 meters. According to the preset vector format (such as [number of delivery equipment in operation, first interval duration, second interval duration between the expected completion time of the work equipment j, and route overlap length with the work equipment j]), the number of delivery equipment in operation, the first interval duration, the second interval duration, and the route overlap length are concatenated to form the congestion degree representation vector of work equipment 1, namely: [12,30,5,10,15,20,25,30,35,15,10,10,5,5,5,5].

[0079] (2) The congestion level of each work unit's dispatch route is predicted by using a congestion level representation vector formed by the number of delivery equipment in operation, the first interval duration, the second interval duration, and the route overlap length. Specifically, step A4 may include: concatenating the number of delivery equipment in operation, the first interval duration, the second interval duration, and the route overlap length to form a congestion level representation vector for each work unit; and using a trained congestion level prediction model to predict the congestion level of each work unit's dispatch route based on the congestion level representation vector.

[0080] For example, firstly, based on a training dataset (which includes multiple sample data, each sample data including the congestion representation vector of the work equipment sample and the congestion of the dispatch route of the work equipment sample), a pre-defined congestion prediction model is trained. This allows the pre-defined congestion prediction model to learn the characteristics of the delivery device when it is in different levels of congestion, thus obtaining the trained congestion prediction model. At this point, the trained congestion prediction model can predict the congestion of the dispatch route of the work equipment based on the congestion representation vector of the work equipment. The pre-defined congestion prediction model includes, but is not limited to, neural network models, random forest models, and support vector machines (SVM), such as ResNet, VGG networks, etc. Specifically, an open-source network with default model parameters can be used as the pre-defined congestion prediction model.

[0081] Then, the congestion representation vector of each work device is input into the trained congestion prediction model, so that the trained congestion prediction model can be invoked to predict the congestion of the dispatch route of each work device based on the congestion representation vector of each work device.

[0082] Since the congestion of the delivery route is inversely correlated with the first interval duration (i.e., the longer the first interval duration, the lower the congestion of the delivery route may be), positively correlated with the second interval duration (i.e., the longer the second interval duration, the higher the congestion of the delivery route may be), positively correlated with the number of delivery equipment in operation (i.e., the higher the number of delivery equipment in operation, the higher the congestion of the delivery route may be), and positively correlated with the route overlap length (i.e., the higher the route overlap length, the higher the congestion of the delivery route may be), by constructing a congestion representation vector for each operating equipment using the number of delivery equipment in operation, the first interval duration, the second interval duration, and the route overlap length, the accuracy of the delivery route congestion can be improved, thereby improving the accuracy of material demand time point prediction.

[0083] Here, the dispatch task busyness refers to the level of activity of material delivery tasks within the material dispatch control area. For example, the number of currently pending material delivery tasks within the material dispatch control area can be obtained as the dispatch task busyness. For instance, this material dispatch control method can be applied to... Figure 1 Taking the material distribution system shown as an example, the task distribution device 1011 currently has the number of material distribution tasks to be issued.

[0084] Among them, the material distribution task refers to the task of delivering each batch of materials from the storage area to each operating equipment.

[0085] The average delivery time refers to the average delivery time of historical material delivery tasks for each operating device. For example, the actual delivery time of each historical material delivery task for each operating device can be obtained; then, the average of the actual delivery times of each historical material delivery task can be calculated as the average delivery time of each operating device.

[0086] 302. Based on the first distribution data, a prediction is made to obtain the target material delivery time for each operating device.

[0087] Among them, the delivery time of the target material (denoted as T) A () is the time required for the next batch of materials to be delivered from the storage area to each work unit.

[0088] Specifically, the target material delivery time for each work unit can be predicted based on the first distribution data using a trained duration prediction model. For example, firstly, the first distribution data is concatenated according to a preset vector format to form a distribution data representation vector for each work unit; then, the distribution data representation vector for each work unit is input into the trained duration prediction model, so that the trained duration prediction model can predict the target material delivery time for each work unit based on the distribution data representation vector for each work unit.

[0089] For example, the trained duration prediction model is trained through the following steps B1 to B4, wherein:

[0090] B1. Obtain the second dispatch data of the sample operation equipment and the actual material delivery time of the sample operation equipment.

[0091] Among them, the sample operation equipment refers to the operation equipment used to train the duration prediction model.

[0092] The second distribution data includes the distribution task busyness of the material distribution control area where the sample operation equipment is located, the congestion of the distribution route of the sample operation equipment in the material distribution control area, and the average delivery time of the sample operation equipment. The acquisition method of the second distribution data is similar to that of the first distribution data in step 301. For details, please refer to the relevant instructions above, which will not be repeated here.

[0093] B2. Using a preset time prediction model, the predicted material delivery time of the sample operation equipment is obtained by predicting based on the second distribution data.

[0094] The preset duration prediction model includes, but is not limited to, neural network models, random forest models, and support vector machines (SVM), such as ResNet and VGG networks. Specifically, an open-source network with default model parameters can be used as the preset duration prediction model.

[0095] For example, firstly, the second distribution data is concatenated according to a preset vector format to form a distribution data representation vector of the sample operation equipment; then, the distribution data representation vector of the sample operation equipment is input into a preset duration prediction model so that the preset duration prediction model can make a prediction based on the distribution data representation vector of the sample operation equipment to obtain the predicted material delivery time of the sample operation equipment.

[0096] B3. Based on the actual material delivery time and the predicted material delivery time, determine the training loss value of the preset time prediction model.

[0097] B4. Adjust the model parameters of the preset duration prediction model based on the training loss value to obtain the trained duration prediction model.

[0098] In some embodiments, a time loss function can be constructed between the actual material delivery time and the predicted material delivery time; the model parameters of a preset time prediction model are adjusted with the goal of minimizing the time loss function to obtain a trained time prediction model.

[0099] In some embodiments, to improve the performance of the trained duration prediction model, the congestion level of the predicted route of the sample operation equipment is predicted using a preset congestion prediction model, referring to the method in step A5. In step B4, a duration loss function can be constructed regarding the actual material delivery time and the predicted material delivery time; and a congestion loss function can be constructed regarding the actual route congestion level and the predicted route congestion level. The objective function of the duration prediction model is constructed using the duration loss function and the congestion loss function. With the goal of minimizing the objective function of the duration prediction model, the model parameters of the preset duration prediction model and the preset congestion prediction model are adjusted to obtain the trained duration prediction model.

[0100] 303. Based on the delivery time of the target material and the estimated completion time of each work equipment, determine the material demand time point of each work equipment.

[0101] Among them, the start processing time (denoted as T) S () refers to the time point at which the current batch of materials is input into each work unit.

[0102] Among them, the standard processing time (denoted as T) O () refers to the time required for each operating device to complete the processing of each batch of materials.

[0103] The estimated completion time for each piece of equipment (denoted as T) E () is the estimated time point at which the current batch of materials processed by each operating equipment is expected to be completed.

[0104] Material demand time point (denoted as T) R This is used to indicate the point in time when the next batch of materials needs to be delivered.

[0105] There are several ways to determine the material requirement time point for each work unit in step 303, including, for example:

[0106] (1) The estimated completion time of each workpiece is unknown. In this case, step 303 may specifically include: obtaining the start processing time of the current batch of materials for each workpiece and the standard processing time for each workpiece; determining the estimated completion time of each workpiece based on the start processing time and the standard processing time; and determining the material requirement time for each workpiece based on the estimated completion time and the target material delivery time. For example, the start processing time of each workpiece (i.e., T...) can be... S ) plus the standard processing time for each workpiece (i.e., T) O The time point obtained is used as the estimated completion time (T) for each working device. E =T S +T O ); the estimated completion time (T) of each piece of equipment. E Subtract the delivery time of the target material (i.e., T) A The obtained time point is used as the material requirement time point (T) for each operating device. R ), that is: T R =T E -T A Similarly, the material demand time point for each operating device in the material distribution control area can be determined based on T. R =T E -T A It was calculated.

[0107] For example, as shown in Table 1 below, assuming the material distribution control area includes equipment 1, 2, 3, and 4, the start processing time of equipment 1 (i.e., T) can be set. S1 ) plus the standard processing time of equipment 1 (i.e., T) O1 The time point obtained is used as the expected completion time of equipment 1 (i.e., T). E1 =T S1 +T O1 The estimated completion time of equipment 1 (i.e., T) E1 Subtract the material delivery time of equipment 1 (i.e., T) A1 The time point obtained is used as the material requirement time point for equipment 1 (i.e., T). R1 =T E1 -T A1 ); and so on, the material requirement time points for equipment 2, 3, and 4 can be obtained, respectively: T R2 =T E2 -T A2 T R3 =T E3 -T A3 T R4 =T E4 -TA4 .

[0108] Table 1

[0109]

[0110] (2) The estimated completion time of each workpiece is known. In this case, the estimated completion time (T) of each workpiece can be directly obtained. E ); the estimated completion time (T) of each piece of equipment. E Subtract the delivery time of the target material (i.e., T) A The obtained time point is used as the material requirement time point (T) for each operating device. R ), that is: T R =T E -T A .

[0111] 304. Based on the material demand time point of each operating device, execute the material delivery task of each operating device.

[0112] In step 304, there are multiple ways to execute the material delivery task for each work device. Taking the application of this material dispatch control method to the server in the material dispatch system as an example, these include:

[0113] (1) The server directly calls the delivery equipment to complete the material delivery task. At this time, step 304 may specifically include: generating the material delivery task for each operating equipment; based on the material demand time point of each operating equipment, calling the target delivery equipment from the multiple delivery equipment to complete the material delivery task of each operating equipment, so as to deliver the next batch of materials to each operating equipment.

[0114] (2) The server integrates a task dispatching device and a transportation scheduling device. After the task dispatching device generates a material delivery task, it calls the target delivery equipment through the transportation scheduling device to complete the material delivery task of each operating device, so as to deliver the next batch of materials to each operating device. At this time, step 304 may specifically include: based on the material demand time point of each operating device, issuing the material delivery task of each operating device to the transportation scheduling device of the server through the task dispatching device of the server; and calling the target delivery equipment through the transportation scheduling device to complete the material delivery task of each operating device, so as to deliver the next batch of materials to each operating device.

[0115] When the material delivery task in step 304 is executed in the manner of "generating a material delivery task through a task dispatching device, and then calling the target delivery equipment through a capacity scheduling device to complete the material delivery task of each operating equipment, so as to deliver the next batch of materials to each operating equipment", the following methods ① and ② can be used as a reference:

[0116] Method ①: Directly use the material demand time point of each operating device as the time point for dispatching the next batch of materials to each operating device. In this case, step 304 may specifically include the following steps 3041A to 3043A:

[0117] 3041A. Generate material delivery tasks for each operating device.

[0118] 3042A. According to the material demand time of each working device, the material delivery tasks of each working device are added to the delivery task queue in sequence from front to back.

[0119] 3043A. Based on the material demand time of each working device, issue material delivery tasks for each working device in the delivery task queue to the capacity scheduling device of the server.

[0120] For example, please refer to Figure 1 First, the task dispatching device in the server can determine the material demand time point for each operating device using steps 301-303. Then, it generates a material delivery task for each operating device. Following the rule that "the closer the material demand time point is to the current time point, the higher the priority for adding the corresponding material delivery task to the delivery task queue," the task dispatching device in the server adds the material delivery task for each operating device to the delivery task queue based on its material demand time point, ensuring that the closer the material demand time point is to the current time point, the higher the delivery priority. Finally, according to the material demand time point of each operating device, the task dispatching device in the server sequentially distributes the material delivery tasks in the task queue to the capacity scheduling device in the server. This allows the capacity scheduling device to call the target delivery device to complete the material delivery task for each operating device, thus delivering the next batch of materials to each operating device. Therefore, it is possible to ensure that the delivery device delivers the next batch of materials precisely when each operating device needs them.

[0121] Method ②: Based on the material demand time point of each operating device and the status of delivery equipment, plan the material dispatch time point for each operating device as the time point for dispatching the next batch of materials. Further, to avoid the situation where all delivery equipment is performing tasks, thus affecting delivery equipment availability, the material dispatch time point for each operating device can be planned with constraints such as the material demand time point for each operating device being earlier than or equal to the material demand time point for each operating device, and the availability of each delivery equipment at the material dispatch time point. This yields the target value for the material dispatch time point for each operating device, ensuring that the delivery equipment delivers the next batch of materials precisely when each operating device needs them, while avoiding the sudden situation where all delivery equipment vehicles are performing tasks, thus preventing delivery availability issues. In this case, step 304 may specifically include the following steps 3041B to 3044B:

[0122] 3041B. Establish the total time difference function of the material distribution system.

[0123] The total time difference function is used to indicate the sum of the time differences of all operating equipment in the material distribution system. The time difference of each operating equipment is equal to the absolute value of the difference between the material distribution time point of each operating equipment and the material demand time point of each operating equipment.

[0124] To facilitate understanding, the planning parameters involved in planning the material dispatch time for each piece of equipment are introduced below, including:

[0125] 1. T i1 : The time point when the material requirements for operating equipment i are met.

[0126] Where 1≤i≤m, m represents the total number of operating devices in the material distribution system.

[0127] 2. T i2 : Material dispatch time of work equipment i.

[0128] 3. t i : Delivery time of the target material for operating equipment i.

[0129] 4. e i The timeliness difference of work equipment i is equal to the material dispatch time T of work equipment i. i2 Material demand time point T for operating equipment i i1 The absolute value of the difference between them, i.e.: e i＝ T i2 -T i1 .

[0130] 5. A jk The time period during which delivery equipment k is occupied by operating equipment j is equal to [T]. j2 ,T j2+t j The time period, i.e., A jk＝ [T j2 ,T j2 +t j ].

[0131] Where 1≤j≤n, and n represents the total number of delivery devices in the material distribution system.

[0132] 6. b ik : A variable that is either 0 or 1, representing the delivery equipment k in T i2 Is it available? i2 ∈A jk At that time, b ik =0 indicates that the delivery equipment k is in T i2 Unavailable; conversely, At that time, b ik =1, indicating that delivery equipment k is in T i2 Available.

[0133] 7. X: Quantity of delivery equipment deployed.

[0134] For example, the total time difference function can be:

[0135] 3042B. Establish a first constraint that the material dispatch time of each operating device is earlier than or equal to the material demand time of each operating device, and a second constraint that determines whether each delivery device is available at the material dispatch time.

[0136] The first constraint condition refers to the constraint condition where the material dispatch time of work equipment i is earlier than or equal to the material demand time i of work equipment. For example, the first constraint condition is: T i2 Earlier than or equal to T i1 .

[0137] The second constraint refers to the delivery equipment k at the material dispatch time T. i2 Whether the constraints are available, for example, the second constraint is: T i2 ∈A jk At that time, b ik =0 indicates that the delivery equipment k is in T i2 Unavailable; conversely, At that time, b ik =1, indicating that delivery equipment k is in T i2 Available.

[0138] 3043B. Based on the first constraint and the second constraint, the material dispatch time point of each operating device is used as the variable to be optimized, and the total time difference function is optimized to obtain the target value of the material dispatch time point of each operating device.

[0139] In some embodiments, taking "the material dispatch time of each work equipment as the variable to be optimized and minimizing the total time difference function as the objective" as an example, step 3043B may specifically include: under the condition of satisfying the first constraint and the second constraint, with the objective of minimizing the total time difference function, solving for the material dispatch time of each work equipment to obtain the target value of the material dispatch time of each work equipment.

[0140] In some embodiments, taking "the material dispatch time point and the number of delivery equipment deployed for each operating device as variables to be optimized, and minimizing the total time difference function as the objective" as an example, step 3043B may specifically include: under the condition of satisfying the first constraint and the second constraint, with the objective of minimizing the total time difference function, solving for the material dispatch time point of each operating device and the number of delivery equipment deployed in the material dispatch system, to obtain the target value of the material dispatch time point of each operating device.

[0141] In some embodiments, taking "the material dispatch time point and the number of delivery equipment deployed for each operating device as variables to be optimized, and minimizing the total time difference function and the number of delivery equipment deployed as the objective" as an example, step 3043B may specifically include: under the condition of satisfying the first constraint and the second constraint, with the objective of minimizing the total time difference function and the number of delivery equipment deployed, solving for the material dispatch time point of each operating device and the number of delivery equipment deployed in the material dispatch system, to obtain the target value of the material dispatch time point of each operating device and the target value of the number of delivery equipment deployed.

[0142] Therefore, on the one hand, since the goal is to minimize the number of delivery equipment, the material dispatch time point of each operating device and the number of delivery equipment deployed in the material dispatch system are solved. Thus, using the target value of the number of delivery equipment deployed to configure the delivery equipment of the material dispatch system can reduce the number of delivery equipment that needs to be configured, thereby improving the utilization rate of delivery equipment.

[0143] Secondly, since the goal is to minimize the total time difference function, the material dispatch time point of each work equipment and the number of delivery equipment deployed in the material dispatch system are solved. Therefore, the target value of the material dispatch time point of each work equipment is used to issue the material delivery task of each work equipment. This can avoid the problem of materials arriving too early and occupying the delivery equipment resources for a long time. In this way, it can avoid the problem of the delivery equipment resources being ineffectively occupied and the material handling efficiency being low, thereby improving the material handling efficiency to a certain extent.

[0144] Thirdly, since the material dispatch time of each operating device is solved under the condition of satisfying the first constraint, it can be ensured that the material dispatch time of each operating device is earlier than or equal to the material demand time of each operating device, thus avoiding the problem that the time of material arrival at the operating device cannot be guaranteed and improving the overall material delivery timeliness.

[0145] Fourthly, since the material dispatch time of each operating device is solved under the condition of satisfying the second constraint, it can be ensured that at the material dispatch time of each delivery device, the available delivery device is used to perform the material delivery task of each delivery device, thus avoiding the situation where all delivery devices are performing tasks and the delivery devices are unavailable.

[0146] 3044B. According to the target value of the material distribution time point of each operating device, the material distribution task of each operating device is issued to the capacity scheduling device of the server through the task distribution device of the server.

[0147] Generate material delivery tasks for each operating device; sequentially add the material delivery tasks for each operating device to the delivery task queue according to the target value of the material delivery time point for each operating device; issue the material delivery tasks for each operating device in the delivery task queue to the capacity scheduling device of the server according to the material delivery time point for each operating device. The detailed implementation process is similar to steps 3041A to 3043A, and can be referred to the relevant description above. For the sake of simplicity, it will not be repeated here.

[0148] To better understand the embodiments of this application, the material dispatch control process is explained below using the example of "task dispatching device being TMS, delivery equipment being a robot, and operating equipment being a production machine". Please refer to [link / reference]. Figure 5 The material distribution control process can be as follows:

[0149] 1. TMS determines the start time (T) of the processing equipment i. S Standard processing time (T) for work equipment i O First, calculate the estimated completion time (T) of work equipment i. E); and predict the material requirement time point (T) for operating equipment i by referring to steps 301 to 303. R ).

[0150] 2. The TMS determines the execution sequence of the material delivery tasks for work equipment i based on the material demand time point of work equipment i; and dispatches the material delivery tasks according to the execution sequence.

[0151] 3. TMS assigns robots to perform material delivery tasks, transporting materials to the operating equipment i.

[0152] Among them, TMS can directly assign robots to perform material delivery tasks, moving materials to work equipment i; or it can send material delivery tasks to work equipment i to Fleet, and Fleet can schedule and assign robots to perform material delivery tasks, moving materials to work equipment i.

[0153] As can be seen from the above, by acquiring the first dispatch data of each operating device in the material dispatch control area, the target material delivery time of each operating device can be predicted. Since the first dispatch data includes the congestion level of the dispatch route for each operating device, the target material delivery time of each operating device can be estimated by combining the congestion level, thus improving the accuracy of the target material delivery time of each operating device. Therefore, by using the target material delivery time of each operating device, the material demand time point of each operating device can be determined for executing the material delivery task of each operating device. On the one hand, this ensures the timeliness of material arrival at the operating device, thereby reducing the probability of the operating device being forced to stop operation and improving operational efficiency. On the other hand, it avoids the problem of materials arriving too early and occupying the distribution equipment resources for a long time, thus avoiding the problem of ineffective occupation of distribution equipment resources and low material handling efficiency, and improving material handling efficiency to a certain extent. Therefore, the distribution equipment can deliver materials precisely when the operating device needs them, ensuring the maximization of the handling efficiency of the distribution equipment.

[0154] Those skilled in the art will understand that all or part of the steps in the above-described material distribution control method can be accomplished by instructions, or by controlling related hardware with instructions. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0155] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of computer programs that can be loaded by a processor to execute any of the material dispensing control methods provided in embodiments of this application. For example, the computer program can be loaded by a processor to perform the following steps:

[0156] Acquire first dispatch data for each work device in the material dispatch control area, wherein the first dispatch data includes the congestion level of the dispatch route of each work device; predict the target material delivery time for each work device based on the first dispatch data; determine the material demand time point for each work device based on the target material delivery time and the estimated completion time point of each work device; and execute the material delivery task for each work device based on the material demand time point of each work device.

[0157] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0158] In the above embodiments of the material distribution control method, computer-readable storage medium, and server, the descriptions of each embodiment have different focuses. For parts not described in detail in a particular embodiment, please refer to the relevant descriptions of other embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes and beneficial effects of the computer-readable storage medium, server, and their corresponding units described above can be referred to the description of the material distribution control method in the above embodiments, and will not be repeated here.

[0159] The above provides a detailed description of a material distribution control method, server, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A material distribution control method, characterized in that, The method includes: Acquire the first dispatch data for each operating device in the material dispatch control area, wherein the first dispatch data includes the congestion level of the dispatch route of each operating device; Based on the first distribution data, the target material delivery time for each operating device is predicted. Based on the target material delivery time and the estimated completion time of each work equipment, the material requirement time point of each work equipment is determined. Based on the material demand time point of each operating device, execute the material delivery task of each operating device; The method is applied to a server in a material dispatch system, which includes a server, multiple delivery devices, and multiple operating devices. The step of executing the material dispatch task for each operating device based on its material demand time point includes: Based on the material demand time point of each operating device, the material delivery task of each operating device is issued to the capacity scheduling device of the server through the task dispatching device of the server. The transportation scheduling device calls upon the target delivery equipment to complete the material delivery task of each operating equipment, so as to deliver the next batch of materials to each operating equipment; The step of issuing material delivery tasks for each work unit to the server's capacity scheduling device based on the material demand time point of each work unit includes: Establish a total time difference function for the material distribution system, wherein the total time difference function is used to indicate the sum of the time differences of all operating equipment in the material distribution system; Establish a first constraint that the material dispatch time of each operating device is earlier than or equal to the material demand time of each operating device, and a second constraint that each delivery device is available at the material dispatch time. Based on the first constraint and the second constraint, the material dispatch time point of each operating device is used as the variable to be optimized, and the total time difference function is optimized to obtain the target value of the material dispatch time point of each operating device. According to the target value of the material distribution time point for each operating device, the material distribution task for each operating device is issued to the capacity scheduling device of the server through the task dispatching device of the server.

2. The material distribution control method according to claim 1, characterized in that, Based on the first and second constraints, the total time difference function is optimized using the material dispatch time point of each operating device as the variable to be optimized, to obtain the target value of the material dispatch time point of each operating device, including: Based on the first and second constraints, the total time difference function is optimized using the material dispatch time point of each operating device and the number of delivery devices deployed in the material dispatch system as variables to be optimized, so as to obtain the target value of the material dispatch time point of each operating device.

3. The material distribution control method according to claim 2, characterized in that, Based on the first and second constraints, the total time difference function is optimized using the material dispatch time point of each operating device and the number of delivery devices deployed in the material dispatch system as variables to be optimized, to obtain the target value of the material dispatch time point of each operating device, including: Under the condition of satisfying the first constraint and the second constraint, with the goal of minimizing the total time difference function and the number of delivery equipment deployed, the material dispatch time point of each operating equipment and the number of delivery equipment deployed in the material dispatch system are solved to obtain the target value of the material dispatch time point of each operating equipment and the target value of the number of delivery equipment deployed.

4. The material distribution control method according to claim 1, characterized in that, The step of predicting the target material delivery time for each operating device based on the first distribution data includes: The target material delivery time for each operating device is obtained by predicting the delivery time based on the first dispatch data using a trained duration prediction model. The trained duration prediction model is obtained through the following steps: Acquire the second dispatch data of the sample operation equipment and the actual material delivery time of the sample operation equipment; The predicted material delivery time of the sample operation equipment is obtained by using a preset time prediction model based on the second distribution data. Based on the actual material delivery time and the predicted material delivery time, the training loss value of the preset time prediction model is determined. The model parameters of the preset duration prediction model are adjusted based on the training loss value to obtain the trained duration prediction model.

5. The material distribution control method according to claim 1, characterized in that, The step of determining the material requirement time point for each operating device based on the target material delivery time and the estimated completion time of each operating device includes: Obtain the start time of the current batch of materials for each operating device and the standard processing time for each operating device; Based on the start processing time and the standard processing time, the estimated completion time of each workpiece is determined; Based on the estimated completion time and the delivery time of the target materials, the material requirement time for each operating device is determined.

6. The material distribution control method according to claim 1, characterized in that, The first distribution data includes the congestion level of the distribution route for each operating device. The process of acquiring the first distribution data for each operating device in the material distribution control area includes: Get the number of delivery devices operating on the common road segment of each of the operating devices at the current time point; Obtain the route overlap length between each operating device and other operating devices in the material distribution control area; The time interval between the current time point and the estimated completion time point of each work equipment is obtained, and used as the first time interval of each work equipment; The estimated completion time of each work equipment is obtained and the estimated completion time of the other work equipment is obtained, which is used as the second interval time of each work equipment; Based on the number of delivery devices in operation, the first interval duration, the second interval duration, and the route overlap length, the congestion level of the delivery route for each operating device is determined.

7. A server, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the material dispensing control method as described in any one of claims 1 to 6 when it invokes the computer program in the memory.

8. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to execute the material dispensing control method according to any one of claims 1 to 6.

Images