Spatiotemporal coupling collaborative analysis system based on multi-layer complex network

Abstract

The present invention relates to a spatiotemporal coupling collaborative analysis system based on a multi-layer complex network, including an information preprocessing module, a multi-layer complex network modeling module, and a spatiotemporal coupling collaborative analysis module for processing areas and equipment, wherein the information preprocessing module is used to collect material status information, equipment status information, and process status information and to perform unified status information encoding on the collected information; the multi-layer complex network modeling module is used to extract nodes and relationship models through classified coding information to construct a data model of a semiconductor manufacturing system; the spatiotemporal coupling collaborative analysis module for processing areas and equipment is used to extract spatial network features and temporal network features of the relationship model related to the extracted nodes from the constructed semiconductor manufacturing system data model and perform collaborative analysis to obtain the coupling synergy degree of the system in each period. The characteristics of regional processing in a wafer manufacturing workshop are taken into consideration, and a dynamic reference index of synergy is provided for the decision-making of optimized control of semiconductor manufacturing systems.

Description

Technical Field

[0001] The invention relates to a semiconductor manufacturing technology, and in particular to a spatiotemporal coupling collaborative analysis system based on a multi-layer complex network. Background Art

[0002] The wafer manufacturing workshop has the characteristics of multiple processing areas and multiple processing sections. Its process is complex, and there are many workshop equipment and a large number of work-in-progress. Uncertain and dynamic events run through the wafer production process. The spatial flow and processing time of the workpiece in each device are coupled and affect each other, making it difficult to optimize the control of the semiconductor manufacturing system. Since the wafer manufacturing workshop has the obvious characteristics of partitioned processing, it is very necessary to evaluate the coordination of each area of ​​the wafer manufacturing workshop.

[0003] At present, the existing analysis and evaluation of the overall dynamic characteristics of a wafer manufacturing workshop is usually implemented based on the expert experience of system engineers. There are also some evaluations based on mathematical methods. However, the existing methods do not take into account the indicators of the coordination of various processing areas in the wafer manufacturing workshop, and therefore cannot obtain an effective optimization control solution. Summary of the invention

[0004] Aiming at the problem of difficulty in optimizing control of semiconductor manufacturing systems, a spatiotemporal coupling collaborative analysis system based on multi-layer complex networks was proposed. On the basis of considering the complex spatiotemporal coupling relationship of wafer manufacturing workshops, the synergy between various processing areas and equipment was analyzed, which provided a decision-making basis for the optimal control of semiconductor manufacturing systems, thereby improving the collaborative ability of various parts in the system.

[0005] The technical solution of the present invention is: a spatiotemporal coupling collaborative analysis system based on a multi-layer complex network, comprising an information preprocessing module, a multi-layer complex network modeling module and a spatiotemporal coupling collaborative analysis module for processing areas and equipment,

[0006] The information preprocessing module is used to collect material status information, equipment status information and process status information and to perform unified status information coding on the collected information;

[0007] The multi-layer complex network modeling module: extracts nodes and relationship models through classification coding information to construct a data model of the semiconductor manufacturing system;

[0008] The spatiotemporal coupling collaborative analysis module of the processing area and the equipment extracts the spatial network characteristics and temporal network characteristics of the relationship model related to the extracted nodes from the constructed semiconductor manufacturing system data model and performs collaborative analysis to obtain the coupling coordination degree of the system in each period.

[0009] Preferably, in the state information coding, the process state information coding collects and counts the relevant data of each production process in order of time dimension, provides relevant data resources for real-time process state modeling of wafer manufacturing, and constructs a unified coding system for processing state information, wherein each feature describes a process, specifically describing the material number, processing time, and process information of the previous process;

[0010] Equipment status information coding is to encode the current status of equipment resources, collect equipment-related information, and obtain real-time processing data of each equipment resource by describing the production resources in a standardized manner;

[0011] Material status information coding is a unified coding for material flow status information. Each feature describes an attribute, including the previous process, current process, current equipment, and current processing layer information.

[0012] Preferably, the multi-layer complex network modeling module: establishes the relationship between the resources of the equipment layer, the equipment and parts of the material layer and the processes of the process layer in the wafer manufacturing process, and defines three types of nodes, namely, resource node V b 、Equipment material node V M and active node V A , the node attribute is to store the real-time processing attribute information of each network node, which receives the various state coding information of the information preprocessing module, and classifies the nodes according to the equipment, process and material, and arranges the nodes of the same category into the network of the same level, thereby establishing a multi-level complex network to characterize the various relationships between materials, equipment resources and process activities; according to the three types of nodes, 6 relationship models are constructed to describe the intra-layer and inter-layer relationships, namely: activity-activity relationship model, thereby describing the logical and temporal relationship between activities; establishing an activity-resource relationship model, thereby describing the corresponding relationship between them; establishing a resource-resource relationship model, thereby describing the constraint relationship between resources; establishing a material-material relationship model, thereby describing the process intrinsic connection between materials; establishing a material-activity relationship model, thereby describing the corresponding relationship between materials and process activities, and establishing a material-resource relationship model, thereby establishing the corresponding relationship between materials and resources.

[0013] Preferably, the spatiotemporal coupling collaborative analysis module includes a system operation status feature extraction processing unit and a spatiotemporal coupling region and equipment collaborative analysis processing unit.

[0014] The system operation status feature extraction processing unit obtains the spatial feature set X of each layer of the network from the semiconductor manufacturing system data model constructed by the multi-layer complex network modeling module. A and the time feature set X B , extracting temporal features from the complex network constructed by the relational model associated with the activity nodes and storing them in XA In the process, spatial features are extracted from the complex network constructed by the relationship model related to resource nodes and stored in X B Then, the features in the two feature sets are dimensionless processed to obtain the dimensionless feature set r ik ;

[0015] The device collaborative analysis processing module in the spatiotemporal coupling region and device collaborative analysis processing unit obtains a dimensionless feature set from the system operation status feature extraction processing unit, and then uses the entropy weight method to obtain the entropy H of the spatial network feature and the temporal network feature ik and entropy weight ω ik , the entropy weight is input into the coupling synergy model to obtain the contribution of spatial attribute and temporal attribute characteristics u i , contribution u i The coupling coordination model is input to obtain the system's coupling degree D and coordination degree T.

[0016] Preferably, the system also includes a GUI result output module, which displays the coupling synergy degree of the system in each period, and displays the analysis results of the spatiotemporal coupling synergy analysis module to the user in a table.

[0017] The beneficial effects of the present invention are as follows: the present invention is based on a spatiotemporal coupling collaborative analysis system of a multi-layer complex network, and takes into account the complex spatiotemporal coupling relationship of the semiconductor manufacturing system, and conducts a collaborative analysis of each processing area and equipment in a wafer manufacturing workshop. Compared with the existing indicators for evaluating semiconductor manufacturing systems, this indicator takes into account the characteristics of regional processing in a wafer manufacturing workshop, thereby providing a dynamic reference indicator that takes into account the coordination of processing areas for decision-making on optimizing control of semiconductor manufacturing systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a structural diagram of the spatiotemporal coupling collaborative analysis system based on a multi-layer complex network of the present invention;

[0019] Figure 2 This is a multi-layer complex network structure diagram of the present invention;

[0020] Figure 3 This is a structural diagram of the spatiotemporal coupling collaborative analysis module of the processing area and equipment of the present invention. DETAILED DESCRIPTION

[0021] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0022] In order to realize the collaborative analysis of the processing area and equipment of the semiconductor manufacturing system, the present invention proposes a spatiotemporal coupling collaborative analysis system based on a multi-layer complex network. The system is divided into three modules: information preprocessing module, multi-layer complex network modeling module and spatiotemporal coupling collaborative analysis module of the processing area and equipment. Figure 1 As shown, first, the information preprocessing module receives and processes relevant information, including the collection of material status information, equipment status information and process status information and the unified status information encoding of the collected information; the multi-layer complex network modeling module extracts nodes and relationship models through classification and coding information to construct a data model of the semiconductor manufacturing system; the spatiotemporal coupling collaborative analysis module of the processing area and equipment extracts the spatial network characteristics and temporal network characteristics of the relationship model related to the nodes from the constructed semiconductor manufacturing system data model and performs collaborative analysis to obtain the coupling coordination degree of the system in each period.

[0023] The information preprocessing module includes: a material status information processing submodule, an equipment status information processing submodule, and a process status information processing submodule. The material status information processing submodule collects and stores the current status information of each work-in-progress, including the current process, the next process, the current number of processing layers, the current equipment used, whether to wait in the queue, and other information. The obtained work-in-progress processing information of the wafer manufacturing system is output to the multi-layer complex network modeling module and the time-space coupling collaborative analysis module.

[0024] The equipment status information processing submodule collects and stores the current processing status information of the equipment, including the current work-in-progress, the current materials waiting to be processed, the equipment utilization rate and other information, and calculates the average productivity of all equipment through the weighted mean calculation method, and outputs it to the multi-layer complex network modeling module and the time-space coupling collaborative analysis module.

[0025] The process status information processing submodule collects and stores the current processing status information of the process, including the number of processes in which all current WIPs are located, the processes of all WIPs, and other information, and outputs it to the layer complex network modeling module and the spatiotemporal coupling collaborative analysis module.

[0026] The collected information includes: a four-layer metadata architecture of meta-metamodel (i.e. ontology), metamodel, metadata and user data. First, based on ontology, the metamodel instances contained in the meta-metamodel of products, systems and equipment are described, and the vocabulary, rules and relationships in the metamodel instances are used to semantically describe the involved heterogeneous data such as structured, semi-structured and unstructured data, and the multi-dimensional context definition of data is realized at the metamodel level. The data output of the collected information processing is processed by state coding. The process state information coding is to collect and count the relevant data of each production process in the order of time dimension, and provide relevant data resources for the real-time process state modeling of wafer manufacturing; by constructing a unified coding system for processing state information, each feature describes a process, and specifically describes the process information such as material number, processing time, and previous process. Equipment state information coding is to encode the current state of equipment resources, collect some information related to the equipment, and obtain real-time processing data of each equipment resource by standardized description of production resources. Material status information coding is a unified coding for material flow status information. Each feature describes an attribute, including information such as the previous process, current process, current equipment, current processing layer, etc., and then the data is stored after status coding processing.

[0027] Multi-layer complex network modeling modules such as Figure 2 As shown in the figure, in order to establish the relationship between the resources of the equipment layer, the equipment and parts of the material layer, and the processes of the process layer in the wafer manufacturing process, three types of nodes are defined, namely, resource node V b 、Equipment material node V M and active node V A , the node attribute is to store the real-time processing attribute information of each network node. It receives the various state coding information of the information preprocessing module, and classifies the nodes according to the equipment, process and material, and arranges the nodes of the same category into the network of the same level, thereby establishing a multi-level complex network to characterize the various relationships between materials, equipment resources and process activities. Since there are three types of nodes, it is necessary to construct 6 relationship models to describe the intra-layer and inter-layer relationships, namely: activity-activity relationship model, so as to describe the logical and temporal relationship between activities; establish activity-resource relationship model, so as to describe the corresponding relationship between them; establish resource-resource relationship model, so as to describe the constraint relationship between resources; establish material-material relationship model, so as to describe the intrinsic process connection between materials; establish material-activity relationship model, so as to describe the corresponding relationship between materials and process activities, and establish material-resource relationship model, so as to establish the corresponding relationship between materials and resources. The relationship models of each part are as follows:

[0028] (1) Activity-activity relationship model. In order to improve the utilization rate of equipment, the wafer manufacturing system generally has multiple orders being processed on the production line at the same time. Therefore, from the overall perspective, the wafer manufacturing processing area can be regarded as a mixed assembly line processing method, which may process multiple orders with different process steps at the same time. For the manufacturing process of the entire workshop, the relationship between activities has several structures such as sequence, parallel, selection, and loop. Therefore, the relationship between activities can be described as five connection relationships: sequence, combination, or separation, combination and separation, and combination. Therefore, the connection between activities can be described by five relationships. In order to simplify the model, a Boolean matrix is ​​used to construct an undirected and unweighted network to express this connection. Let V A ={a 1 ,a 2 ,…,a j ,…,a n} is a specific set of activities in the complex network framework during the wafer manufacturing system processing, with two combinations (a i ,a j ) as the complex relationship element in the complex network model, and the connection relationship between nodes is taken as the path in the complex network model, denoted by P k {a i ,a j},k{1,2,3,4,5}. Then the activity-activity relationship model is

[0029] (2) Activity-resource relationship model: There is generally a many-to-many relationship between activities and resource objects, that is, a certain activity can be completed on multiple resources, and correspondingly, a certain resource can complete multiple types of activities. 1 ,b 2 ,...b m} is a basic node containing multiple types of resources, with activity set A as the core, to build an activity-resource Boolean matrix relationship model

[0030] (3) Resource-resource relationship model. The resources in the wafer manufacturing process are various processing equipment. From a physical perspective, there is only a distance relationship between the equipment. Therefore, from a physical perspective, a weighted undirected network can be established between the equipment nodes. However, this is of little significance for describing the production process of the entire manufacturing system. Therefore, it is necessary to consider the internal relationship between each device in the processing process, so as to establish a process-centered complex network model. After considering the relationship between resources and activities, it can be seen that there is a sequential relationship between the equipment due to the flow of processes. Secondly, there are duplicate equipment in some processing areas, so there is a selection relationship. Finally, considering the reentrant nature of wafer manufacturing, there is a cyclic relationship. Since wafer manufacturing processes wafers according to the process, the next process can only be processed after the previous process is completed, so there is no parallel relationship. The resource-resource relationship is analyzed by establishing a Boolean matrix. Let V B = {b 1 ,b 2 ,…,b j ,…,b n} is a specific set of activities in the complex network framework during the wafer manufacturing system processing, which are combined in pairs (b i ,b j ) as the complex relationship element in the complex network model, and the connection relationship between nodes is taken as the path in the complex network model, denoted by P k {b i ,b j},k{1,2,3,4,5}. Then the resource-resource relationship model is:

[0031] (4) Material-material relationship model. In a wafer manufacturing workshop, wafers are processed in the workshop as a LOT. Since there are multiple products in the wafer manufacturing workshop, there are multiple orders with different process steps. For materials of the same process, there is a sequential relationship between materials. Secondly, for materials, if they are processed under the same process at the current moment, there is a selection relationship. Since there are multiple resources corresponding to a process step, there is a parallel relationship. Considering re-entry processing, there is a cyclic relationship between materials. Therefore, five relationships are used to describe the relationship between activities. In order to simplify the model, a Boolean matrix is ​​used to construct an undirected and unweighted network to express this relationship. Let V M ={m 1 ,m 2 ,…,m j ,…,m n} is a specific set of activities in the complex network framework during the wafer manufacturing system processing, with two-by-two combinations (m i ,m j) as the complex relationship element in the complex network model, and the connection relationship between nodes is taken as the path in the complex network model, denoted by P k {m i ,m j},k{1,2,3,4,5}. Then the material-material relationship model is:

[0032] (5) Material-activity relationship model: There is generally a many-to-many relationship between materials and process activity objects, that is, multiple materials are in different process activity states at a certain moment; correspondingly, a process activity is also called by multiple materials. 1 ,m 2 ,...m m} is the basic node that contains the material being processed at the current moment. With process activity set A as the core, a material-activity Boolean matrix relationship model is constructed.

[0033] (6) Material-resource relationship model. Since some equipment can circulate multiple materials at the same time, there is also a many-to-many relationship between materials and equipment resource objects. That is, at a certain moment, multiple materials are in different equipment resource nodes, and there are also multiple materials circulating in the resources. The material node set M = {m 1 ,m 2 ,...m m} is the basic node that contains the material being processed at the current moment. With resource node set B as the core, a material-resource Boolean matrix relationship model is constructed.

[0034] The spatiotemporal coupling collaborative analysis module between the processing area and the equipment is as follows: Figure 3 As shown, the system operation status feature extraction processing unit and the spatiotemporal coupling area and equipment collaborative analysis processing unit, wherein: the system operation status feature extraction processing unit obtains the spatial feature set X of each layer network from the semiconductor manufacturing system data model constructed by the multi-layer complex network modeling module A and the time feature set X B Since objects related to process activities have time attributes and objects related to equipment resources have space attributes, time features are extracted from the complex network constructed by the relationship model related to the activity nodes and stored in X A In the process, spatial features are extracted from the complex network constructed by the relationship model related to resource nodes and stored in X B In order to characterize the global characteristics of the two types of networks, the average path length X is extracted from the network. L , average degree X <k>< / k> 、Network quality X E 、Network density Xρ , the shortest path length X D Five features measure the global performance of the network, and their calculation formulas are as follows:

[0035]

[0036]

[0037]

[0038]

[0039] X D =d min

[0040] Where N is the number of nodes in the network; d ij is the distance from node i to node j; M is the number of all edges in the network; d min is the shortest path length in the network. Thus, we get the spatial feature set With time feature set

[0041] Then, the features in the two feature sets are dimensionless processed to obtain the dimensionless feature r ik For state parameters with larger values, they represent higher priority types. In this case, the conversion is performed as follows:

[0042]

[0043] Among them, x ik is the proportion of the kth state parameter in the ith solution to the index. i represents the ith solution. There are only two solutions here, namely the spatial network solution and the temporal network solution. For the smaller and better state parameters, the following method is used for transformation:

[0044]

[0045] Then, the entropy weight method is used to obtain the entropy H of spatial network features and temporal network features. ik and entropy weight ω ik , based on the basic definition of information entropy, the entropy and entropy weight of the spatiotemporal state parameter factors of the wafer manufacturing system are calculated (the calculation formulas for the entropy and entropy weight of spatial network characteristics and temporal network characteristics are universal). The entropy calculation formula is as follows:

[0046]

[0047] Among them, f ik =r ik / ∑ K rik , when f ik = 0, f ik lnf ik = 0. The entropy weight of the kth state parameter can be defined as: ω ik =1-H ik According to the entropy weight obtained above, the state parameter weight is calculated:

[0048] w ik =ω ik / ∑ k ω ik ∑ k w ik =1

[0049] The entropy weight ω ik Input into the equipment collaborative analysis and processing module to obtain the contribution u of spatial network features and temporal network features i , the weight of the influence of the wafer manufacturing system state parameters on the system coupling level. The equipment collaborative analysis and processing module is used to measure the influence of the state parameter k of the i-th dimension (i.e., the i-th scheme) on the system spatiotemporal coupling level, and the contribution u ik The calculation formula is as follows:

[0050]

[0051] Among them, r i min is the minimum value of the dimensionless characteristic in the ith solution, r i max It is the maximum value of the dimensionless characteristic in the i-th scheme. The spatiotemporal coupling characteristics of the system are in two different subsystems, and the subsystems have an interactive relationship. The integration method can be used to analyze the total influence of each state parameter in the subsystem on the coupling level. In practical applications, the ensemble average method or the linear weighted sum method can generally be used. The linear weighted method is used for calculation below:

[0052] u i =∑ k w ik u ik

[0053] The system contribution u i The coupling coordination model is introduced to obtain the coupling degree D and coordination degree T of the system. Considering that the processes of task and resource coordination in the wafer manufacturing system have their own interlaced dynamic and unbalanced characteristics, the concept of capacity coupling and the capacity coupling coefficient model in physics are borrowed to derive the time-space interaction coupling coordination function, which is:

[0054] C={(u 1 ·u 2 ) / (u1 +u 2 )·(u 1 +u 2 )} 12

[0055] Among them, u 1 is the contribution of spatial network features; u 2 is the temporal network feature contribution.

[0056] From the formula, we can see that C∈[0,1]. When C is larger, the coupling degree between subsystems is higher, and thus the coordination degree of the system is higher, which means that the operation process of the manufacturing system is highly ordered. When C is smaller, the coordination degree between subsystems is lower, the operation process of the system is less ordered, and the system is unstable.

[0057] Since the wafer manufacturing workshop is processed in BAY units, it is necessary to consider the synergy of interval resources. Considering the coupling model, each sub-interval in the resource layer can also be regarded as a subsystem. Therefore, based on the above inter-layer coupling idea, the parameters of each processing area are extracted by analysis, and the u of each sub-processing interval is calculated. i , the coordination degree can be used to calculate the coordination between all sub-regions, and the calculated coordination degree can be used to evaluate the coordination degree of regional resources. The calculation formula is as follows:

[0058]

[0059] T=αu 1 +βu 2

[0060] Among them, D is the coupling degree, and its value range is D∈[0,1]. When D is closer to 1, the degree of coordination between the sub-processing areas is high; T is the synergy degree, and its value range is T∈[0,1]. When T is closer to 1, the synergy between the sub-processing areas is good; α and β are the distribution coefficients of the sub-intervals, which represent the importance of the subsystem in the entire system.

[0061] The system also includes a GUI result output module such as Figure 1 As shown, the coupling coordination degree of the system in each period is displayed, and the analysis results of the spatiotemporal coupling coordination analysis module are presented to the user in a table.

[0062] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A spatiotemporal coupling collaborative analysis system based on multi-layer complex networks, characterized in that: It includes information preprocessing module, multi-layer complex network modeling module and spatiotemporal coupling collaborative analysis module between processing area and equipment. The information preprocessing module is used to collect material status information, equipment status information and process status information and to perform unified status information coding on the collected information; The multi-layer complex network modeling module: extracts nodes and relationship models through classification coding information to construct a data model of the semiconductor manufacturing system; The spatiotemporal coupling collaborative analysis module of the processing area and the equipment: extracts the spatial network characteristics and temporal network characteristics of the relationship model related to the extracted nodes from the constructed semiconductor manufacturing system data model and performs collaborative analysis to obtain the coupling coordination degree of the system in each period; The multi-layer complex network modeling module: establishes the relationship between the resources of the equipment layer, the equipment and parts of the material layer and the processes of the process layer in the wafer manufacturing process, and defines three types of nodes, namely, resource node V b 、Equipment material node V M and active node V A ,Node attributes are used to store the real-time processing attribute information of each network node. It receives the various state coding information of the information preprocessing module, and classifies the nodes according to equipment, process and materials, and arranges the nodes of the same category into the network at the same level, thereby establishing a multi-level complex network and then characterizing the various relationships between materials, equipment resources and process activities; According to the three types of nodes, six relationship models are constructed to describe the intra-layer and inter-layer relationships, namely: activity-activity relationship model, so as to describe the logical and temporal relationship between activities; activity-resource relationship model is established to describe the corresponding relationship between them; resource-resource relationship model is established to describe the constraint relationship between resources; material-material relationship model is established to describe the process internal connection between materials; material-activity relationship model is established to describe the corresponding relationship between materials and process activities; material-resource relationship model is established to establish the corresponding relationship between materials and resources; The spatiotemporal coupling collaborative analysis module includes a system operation status feature extraction processing unit and a spatiotemporal coupling region and equipment collaborative analysis processing unit. The system operation status feature extraction processing unit obtains the spatial feature set X of each layer of the network from the semiconductor manufacturing system data model constructed by the multi-layer complex network modeling module. A and the time feature set X B , extracting temporal features from the complex network constructed by the relational model associated with the activity nodes and storing them in X A In the process, spatial features are extracted from the complex network constructed by the relationship model related to resource nodes and stored in X B Then, the features in the two feature sets are dimensionless processed to obtain the dimensionless feature set r ik ; The device collaborative analysis processing module in the spatiotemporal coupling region and device collaborative analysis processing unit obtains a dimensionless feature set from the system operation status feature extraction processing unit, and then uses the entropy weight method to obtain the entropy H of the spatial network feature and the temporal network feature. ik and entropy weight ω ik , the entropy weight is input into the coupling synergy model to obtain the contribution of spatial attribute and temporal attribute characteristics u i , contribution u i The coupling coordination model is input to obtain the system's coupling degree D and coordination degree T.

2. The spatiotemporal coupling collaborative analysis system for multi-layer complex networks according to claim 1, characterized in that: In the state information coding, the process state information coding collects and counts the relevant data of each production process in the order of time dimension, provides relevant data resources for wafer manufacturing real-time process state modeling, and constructs a unified coding system for processing state information. Each feature describes a process, specifically describing the material number, processing time, and process information of the previous process; Equipment status information coding is to encode the current status of equipment resources, collect equipment-related information, and obtain real-time processing data of each equipment resource by describing the production resources in a standardized manner; Material status information coding is a unified coding for material flow status information. Each feature describes an attribute, including the previous process, current process, current equipment, and current processing layer information.

3. The spatiotemporal coupling collaborative analysis system for multi-layer complex networks according to claim 1, characterized in that: The system also includes a GUI result output module, which displays the coupling coordination degree of the system in each period, and displays the analysis results of the spatiotemporal coupling coordination analysis module to the user in a table.

Images