WO2023216561A1

WO2023216561A1 - Completion time-based method and system for dispatching vehicle in advance and computer device

Info

Publication number: WO2023216561A1
Application number: PCT/CN2022/135188
Authority: WO
Inventors: 申国莉; 谭璜; 缪峰
Original assignee: 弥费科技(上海)股份有限公司
Priority date: 2022-05-11
Filing date: 2022-11-29
Publication date: 2023-11-16
Also published as: CN114613710B; CN114613710A; TW202344461A

Abstract

Some embodiments of the present application provide a completion time-based method and system for dispatching a vehicle in advance and a computer device. In the embodiments of the present application, the method comprises: predicting the current wafer completion time of each machine, and obtaining all machines of which the current wafer completion time is within a first preset time range, so as to obtain a machine set; predicting the driving time of each trolley from the current position to each machine in the machine set, and obtaining all trolleys of which the driving time is within a second preset time range, so as to obtain a trolley set; and performing optimal matching on the machine set and the trolley set to obtain a trolley and machine dispatching scheme having the minimum sum of all transportation time.

Description

Method, system and computer equipment for dispatching vehicles in advance based on completion time

This application is filed based on a Chinese patent application with application number "202210506018.3" and a filing date of May 11, 2022, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated by introduction. Apply.

Technical field

This application belongs to the technical field of wafer manufacturing and material transportation, and more specifically relates to a vehicle dispatching method, system and computer equipment based on completion time in advance.

Background technique

In the actual production process, the material control system (MCS) will issue a moving instruction only after the machine completes the processing task. At this time, the AMHS system will match the idle crane and the issued moving task. Planning the transportation path makes the wafers occupy the machine longer and the wafers wait longer during transportation, which affects the transportation efficiency of the AMHS system.

Based on this, this application provides technical solutions to solve the above technical problems.

Summary of the invention

This application provides an early dispatching method based on completion time, which includes the following steps: predicting the current wafer completion time on each machine, and obtaining all the machines whose current wafer completion time is within the first preset time range. , obtain the machine set; predict the travel time of each car starting from the current position to each machine in the machine set, obtain all the cars whose travel time is within the second preset time range, and obtain the car set ; Optimally match the machine set and the trolley set to obtain the trolley and machine assignment plan that minimizes the sum of all transportation times.

The embodiment of the present application provides an advance dispatching system based on completion time, including: a machine set acquisition module, used to predict the wafer completion time on each machine, and obtain the predicted wafer completion time in the first A set of machines within a preset time range; a car set acquisition module, used to predict the travel time of each car starting from the current position to each machine in the machine set, and obtain the predicted car travel time at the 2. A set of trolleys within a preset time range; a matching module for optimally matching the set of machines and the set of trolleys to obtain a trolley and machine assignment plan that minimizes the sum of all transportation times.

This application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned completion time-based advance dispatch is implemented. car method.

Description of the drawings

The preferred embodiments will be described below in a clear and easy-to-understand manner with reference to the accompanying drawings, and the above-mentioned characteristics, technical features, advantages and implementation methods will be further described.

Figure 1 is a schematic flow chart of an embodiment of the present application;

Figure 2 is an example of a bipartite diagram constructed from a machine set and a trolley set in the embodiment of the present application;

Figure 3 is a schematic structural diagram of the early dispatch system according to the embodiment of the present application;

Figure 4 is a schematic structural diagram of the computer equipment of the present application.

Embodiments of the invention

In order to explain the embodiments of the present application or the technical solutions in the prior art more clearly, the specific implementation manner of the present application will be described below with reference to the accompanying drawings. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without exerting creative efforts, other drawings can also be obtained based on these drawings, and obtain Other embodiments.

Based on this application, those skilled in the art will appreciate that one aspect described herein can be implemented independently of any other aspect, and that two or more of these aspects can be combined in various ways. For example, apparatuses may be implemented and/or methods practiced using any of the numbers and aspects set forth herein. Additionally, such apparatus may be implemented and/or methods practiced using other structures and/or functionality in addition to one or more of the aspects set forth herein.

It should also be noted that the diagrams provided in the following embodiments are only schematically illustrating the basic concept of the present application. The drawings only show the components related to the present application and are not based on the number, shape and number of components during actual implementation. Dimension drawing, in actual implementation, the type, quantity and proportion of each component can be arbitrarily changed, and the component layout type may also be more complex.

Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, one skilled in the art will understand that the described aspects may be practiced without these specific details. The terms "first", "second", etc. are used for descriptive purposes only and shall not be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Thus, features qualified by descriptions such as "first", "second", etc. may explicitly or implicitly include one or more of these features. In the description of this application, unless otherwise stated, "plurality" means two or more.

In chip foundries, wafers are processed on various machines according to specific process flows, and the flow of wafers between different machines is handled by the overhead crane system. When the machine completes the processing task, the system issues a transportation instruction. AMHS (Automatic Material Handling System) matches the idle crane with the assigned transportation task and plans the transportation path. After receiving the instruction, the crane goes to the location. The machine loads the wafers and transports the wafers to the next designated machine.

The embodiment of the present application uses a method of dispatching vehicles in advance based on the completion time. Based on the historical data of machine processing, the completion time of wafers on the machine is predicted, and the vehicle is dispatched in advance to the machine that is about to be completed, thereby reducing the wafer occupation of the machine. The time of the station and the waiting time of the wafer during transportation are reduced to reduce the transportation time, improve the transportation efficiency of the AMHS system, and achieve efficient and stable material transportation. The early dispatching method based on completion time may include the following steps: predict the current wafer completion time on each machine, obtain all the machines whose current wafer completion time is within the first preset time range, and obtain the machine set of machines; predict the travel time of each car starting from the current position to each machine in the machine set, obtain all the cars whose travel time is within the second preset time range, and obtain the car set; The machine set and the car set are optimally matched to obtain the car and machine assignment plan with the smallest sum of all transportation times.

The following describes the technical solutions provided by each embodiment of the present application with reference to the accompanying drawings.

As shown in Figure 1, the embodiment of the present application provides an early dispatching method based on completion time. The main method of this method is to predict the current wafer completion time on each machine and obtain the current wafer completion time in For all the machines within the first preset time range, a machine set is obtained; then the driving time of each car starting from the current position to each machine in the machine set is predicted, and the car driving time in the second time range is obtained. All the trolleys within the preset time range are obtained to obtain the trolley set; finally, the machine set and the trolley set are optimally matched to obtain the trolley and machine assignment plan with the smallest sum of all transportation times.

The embodiment of this application is to predict the completion time of the wafer on the machine based on the historical data of machine processing, and send a vehicle to the machine that is about to be completed in advance to solve the problem of the long time the wafer occupies the machine and the problem of wafer transportation. The problem of long waiting time in the process is reduced to reduce the handling time and improve the handling efficiency of the AMHS system.

The first embodiment of this application includes the following steps:

Step 101: Predict the current wafer completion time on each machine, obtain all the machines whose current wafer completion time is within the first preset time range, and obtain the machine set;

When the machine completes the processing task, the material control system MCS issues a transportation instruction, and the system needs to match the transportation task with the idle trolley. Therefore, in this embodiment, the completion time of the ongoing wafer processing on the machine is predicted, and a vehicle is dispatched in advance to the machine that is about to be completed, thereby reducing the time that the wafers occupy the machine and the time that the wafers are in the transportation process. waiting time.

First, predict the current wafer completion time on each machine. Optionally, use the exponential smoothing method to predict. The basis for using the exponential smoothing method to predict the current wafer completion time is that in the generation schedule, the trend of the time series is considered to be stable or regular, so the time series can be reasonably postponed; that is, the recent past trend, to some extent will continue into the future; and the longer the experience data, the less impact it will have on future trends.

In some implementations, the method of predicting the current wafer completion time on each tool includes:

S201. Perform statistical analysis on the historical processing information of the machine, extract specific process information and calculate the average completion time of the specific process;

When performing statistical analysis on the historical processing information of the machine, first count the historical completion times of multiple specific processes of the machine in the most recent working period, and then calculate the average completion time;

S202. Predict based on the current feedback processing information of the machine to obtain the predicted completion time of the current actual processing process;

In some implementations, the current feedback processing information of the machine includes the current processing progress of the machine.

Among them, the feedback progress is the feedback from the machine to the control system. The current processing progress can be obtained by recording the processing time. For example, wafer A starts processing on machine B at 8:00, and the current time is 8:20, then wafer A has been processed for 20 minutes. Assume that the average processing time of wafers of the same type as wafer A is 100 minutes based on historical information. Then the current processing progress of machine B is 20%.

S203. Perform a weighted average of different proportions on the average completion time and the predicted completion time of the current actual processing process to obtain the final current wafer completion time.

In some implementations, the final predicted wafer completion time t=α·t _h + (1-α)·t _r ;

Among them, t _h is the average completion time, t _r is the predicted completion time of the current actual processing process, and α is the historical completion time weighting factor.

The value range of α is (0,1), and the size of the weight factor affects the size of the relationship between the predicted value and the nearest actual value. The larger the value of α, the greater the influence of the predicted value on the actual value in history; the smaller the value of α, the greater the influence of the predicted value on the actual value of the recent time.

Step 102: Predict the travel time of each car starting from the current position to each machine in the machine set, obtain all the cars whose travel time is within the second preset time range, and obtain the car set;

After predicting the wafer completion time of each machine, it is also necessary to predict the travel time of the transport vehicle, and calculate the time when the vehicle reaches the task point of each machine based on the conflict-free remaining path. In this embodiment, in the process of predicting the travel time of each trolley starting from the current position to each machine in the machine set, the trolleys include idle trolleys and trolleys undergoing transportation operations;

The car travel time of the idle car is the shortest path travel time of the car starting from the current position to each machine in the machine set;

The driving time of the car undergoing transportation operations is the sum of the remaining time for the car to complete the current transportation task and the shortest path driving time from the terminal machine of the current transportation task to each machine in the machine set.

For example, the travel time can be calculated from the shortest path and the average speed of the car.

Step 103: Optimally match the machine set and the trolley set, and obtain the trolley and machine assignment plan with the smallest sum of all transportation times.

In this embodiment, the machine set and the trolley set are first used as two independent subsets to construct a bipartite graph, and then the Hungarian algorithm is used to optimally match the bipartite graph.

The Hungarian algorithm is mainly used to solve problems related to bipartite graph matching. Bipartite graph is a special type of graph that can be divided into two parts, and the points in each part are not connected to each other. The Hungarian algorithm is mainly used to solve two problems: finding the maximum matching number and the minimum point coverage number of the bipartite graph.

The bipartite graph is also called a bipartite graph, which is a special model in graph theory. Suppose G = (V, E) is an undirected graph. If the vertex V can be divided into two disjoint subsets (A, B), and each edge (i, j) in the graph is associated with the two Vertices i and j belong to these two different vertex sets (i in A, j in B) respectively, then the graph G is called a bipartite graph. In this embodiment, the bipartite graph can be constructed by treating the car set and the machine set as two independent subsets.

The bipartite graph has two vertex sets: the car set and the machine set. Select any element from the two sets to form (car, machine), which is an edge of the bipartite graph. The travel time from the car to the machine is the weight of the edge.

In some implementations, for an idle car, the shortest travel time from the current position to each machine is used as the weight of the edge; for the car v that is undergoing transportation operations, it is assumed that the time it takes to complete the remaining path of the current transportation task is t ₁ , the shortest road travel time from the end machine of the current transportation task to the starting machine of the next transportation task j is t ₂ , then t ₁ + t ₂ is used as the weight of the edge between the car v and the task j, and two Department map. Assume that there are n machines and m cars, and a bipartite graph consisting of m*n is established. As shown in Figure 2, it is an example of a bipartite graph with 3 cars and 4 tasks. Finally, the Hungarian algorithm is used to optimally match the bipartite graph and obtain the overhead crane assignment plan that minimizes the sum of all transportation times.

The Hungarian algorithm is the most common algorithm for bipartite graph matching. The core of this algorithm is to find the augmented path. The Hungarian algorithm is the optimal matching algorithm, that is, the minimum assignment scheme for the sum of transportation times can be obtained through the Hungarian algorithm.

As shown in Figure 3, the embodiment of the present application also provides an early vehicle dispatching system 200 based on completion time, including: a machine set acquisition module 201, a trolley set acquisition module 202, and a matching module 203. The machine set acquisition module 201 predicts the current wafer completion time on each machine, acquires all the machines whose current wafer completion time is within the first preset time range, and obtains the machine set; the car set acquisition module 202 , used to predict the travel time of each car starting from the current position to each machine in the machine set, obtain all the cars whose travel time is within the second preset time range, and obtain the car set; matching module 203. Used to optimally match the set of machines and the set of trolleys to obtain a trolley and machine assignment plan that minimizes the sum of all transportation times.

The machine set acquisition module 201 is communicated with the car set acquisition module 202 and the matching module 203 respectively. The machine set acquisition module 201 transmits the obtained machine set and the prediction information corresponding to each machine to the matching module 203. The car set acquisition module 202 Communicating with the matching module 203, the car set acquisition module 202 transmits the obtained car set and prediction information corresponding to each car to the matching module 203. The matching module 203 performs optimal matching based on the obtained car set and machine set.

The early dispatching system 200 based on completion time in the embodiment of the present application predicts the completion time of wafers on the machine and dispatches vehicles in advance to the machine that is about to be completed, thereby reducing the time the wafers occupy the machine and the number of wafers. The waiting time during the transportation process improves the transportation efficiency of the AMHS system.

Figure 4 is a schematic structural diagram of a computer device provided by an embodiment of the present application. The computer device of this embodiment may be a server. The computer device provided by the embodiment of the present application can execute the processing flow provided by the embodiment of the early dispatch method based on completion time. As shown in Figure 4, the computer device 300 includes: a memory 302, a processor 301, a computer program and a communication interface 303; Among them, the processor 301 of the computer device 300 is used to provide computing and control capabilities. The memory 302 of the computer device 300 includes non-volatile storage media and internal memory. The non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The communication interface 303 of the computer device 300 is used to communicate with external terminals through a network. The computer program is configured to use the processor 301 to execute the technical solution of the above completion time-based early dispatch method embodiment.

Those skilled in the art can understand that the structure shown in Figure 4 is a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Specific computer equipment may include There may be more or fewer parts than shown, or certain parts may be combined, or may have a different arrangement of parts.

In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are schematic. For example, the division of modules is a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented. On the other hand, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or modules, and may be in electrical, mechanical or other forms.

In addition, each functional module in various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit modules can be implemented in the form of hardware or in the form of hardware plus software functional unit modules.

The above integrated modules implemented in the form of software function modules can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium and includes a number of instructions to cause an electronic device (which can be a personal computer, server, or network device, etc.) or processor to execute the methods described in various embodiments of this application. Some steps. The aforementioned computer-readable storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, etc. that can store program code. medium.

Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the device The internal structure is divided into different functional modules to complete all or part of the functions described above. For the specific working process of the device described above, reference can be made to the corresponding process in the foregoing method embodiment, which will not be described again here.

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application. All are covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

A method of dispatching vehicles in advance based on completion time includes the following steps:

Predict the current wafer completion time on each machine, obtain all the machines whose current wafer completion time is within the first preset time range, and obtain the machine set;

Predict the travel time of each car starting from its current position to each machine in the machine set, obtain all the cars whose travel time is within the second preset time range, and obtain the car set;

The machine set and the trolley set are optimally matched to obtain the trolley and machine assignment plan with the smallest sum of all transportation times.
The early dispatching method based on completion time according to claim 1, comprising: using an exponential smoothing method to predict the current wafer completion time on each machine.
The early dispatching method based on completion time according to claim 1 or 2, wherein the method of predicting the current wafer completion time on each machine includes:

Perform statistical analysis on the historical processing information of the machine, extract specific process information and calculate the average completion time of the specific process;

Prediction is made based on the current feedback processing information of the machine to obtain the predicted completion time of the current actual processing process;

The average completion time and the predicted completion time of the current actual processing process are weighted and averaged with different proportions to obtain the final current wafer completion time.
The early dispatching method based on completion time according to claim 3, wherein the current feedback processing information of the machine includes the current processing progress of the machine.
The early dispatching method based on completion time according to claim 4, wherein the current processing progress is obtained by recording the time the current wafer has been processed by the machine and the average processing time of similar wafers.
The early dispatching method based on completion time according to claim 3, wherein the final predicted wafer completion time t=α·t h + (1-α)·t r ;

Among them, t h is the average completion time, t r is the predicted completion time of the current actual processing process, and α is the historical completion time weighting factor.
The early dispatching method based on completion time according to claim 1, wherein in the process of predicting the travel time of each car starting from the current position to each machine in the machine set, the car Including idle cars and cars undergoing transportation operations;

The car travel time of the idle car is the shortest path travel time of the car starting from the current position to each machine in the machine set;

The travel time of the car that is undergoing transportation operations is the sum of the remaining time for the car to complete the current transportation task and the shortest path travel time from the terminal machine of the current transportation task to each machine in the machine set.
The early dispatching method based on completion time according to claim 1, wherein the process of optimally matching the machine set and the trolley set includes: first, the machine set and the trolley set are as Two independent subsets construct a bipartite graph, and then the Hungarian algorithm is used to optimally match the bipartite graph.
An advance dispatching system based on completion time, including:

The machine set acquisition module is used to predict the current wafer completion time on each machine, obtain all the machines whose current wafer completion time is within the first preset time range, and obtain the machine set;

The car set acquisition module is used to predict the travel time of each car from the current position to each machine in the machine set, obtain all the cars whose travel time is within the second preset time range, and obtain the car gather;

A matching module is used to optimally match the set of machines and the set of trolleys to obtain a trolley and machine assignment plan that minimizes the sum of all transportation times.
A computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method of any one of claims 1 to 8 is implemented. Method of dispatching vehicles in advance of completion time.