A production line modeling and analysis method and apparatus

Abstract

The application discloses a production line modeling and analyzing method and device, which solves the problems of analyzing and diagnosing the whole operation and local equipment of the production line through the construction of a production line space-time knowledge graph, can simultaneously analyze the spatial structure and diagnose the time sequence of the production line, and has high speed and efficiency. Through the coupling of a relational database and a graph database, the modeling and collection of the production line data are solved. The real-time data collection and structure modeling of the production line can be efficiently and accurately carried out, and are used for subsequent analysis and optimization. Through the combination of a graph analysis method and time sequence data anomaly detection, the problems of abnormal diagnosis and tracing of the production line are solved, and the abnormal components can be quickly and accurately positioned and traced.

Description

Technical Field

[0001] This invention relates to the field of production line modeling and analysis technology, and in particular to a production line modeling and analysis method and apparatus based on spatiotemporal knowledge graphs. Background Technology

[0002] A modern digital production line typically consists of multiple workstations, each using one or more devices to complete a specific process. This generates a large amount of data, which describes a portion of the production line's current operational status. During production line operation, electrical, mechanical, and other malfunctions are unavoidable. Therefore, how to analyze and optimize the production line's operational status in real time and effectively is a crucial issue for improving production efficiency and safety.

[0003] For the above-mentioned production line analysis and optimization problems, one solution is to model the production line in advance, use the virtual production line obtained by modeling to simulate the operation, observe possible faults and optimization situations, implement the simulation results during the design and construction of the production line, and compare the observed quantities with the simulated quantities during the operation of the production line to analyze the operating status of the production line.

[0004] Another approach is to collect equipment data from existing production lines during operation, perform time-series data processing on this continuous data, and analyze the operating status of each component.

[0005] Among the methods described above, simulating a virtual production line obtained through modeling can effectively model the spatial structure of the production line, thereby analyzing problems in the logistics structure design. However, production line modeling and simulation are time-consuming and are often only suitable for analysis and optimization during the early design phase, making it difficult to perform real-time analysis during production line operation. Furthermore, when the actual production line is modified, simulation analysis often needs to be performed again, consuming a significant amount of time.

[0006] While time-series data processing can collect real-time data from components and determine their operating status relatively quickly and accurately, it cannot accurately describe the interrelationships between different parts of the production line, thus making it impossible to perform overall analysis and optimization of the production line.

[0007] Therefore, how to provide a production line modeling and analysis method to achieve effective time and space analysis and optimization of the production line is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0008] In view of the above problems, the present invention provides a production line modeling and analysis method and apparatus for overcoming or at least partially solving the above problems.

[0009] This invention provides the following solution:

[0010] A production line modeling and analysis method, comprising:

[0011] Analyze the logistics relationships of the production line and construct a static logistics relationship map of the production line using these relationships.

[0012] Analyze the status data of all components on the production line, and use the status data of all components on the production line to build an equipment OPCUA data service;

[0013] Obtain production line logistics relationship information and status information of each component of the target production line;

[0014] A spatiotemporal knowledge graph of the production line is constructed using the static logistics relationship graph of the production line and the OPCUA data service of the equipment. The spatiotemporal knowledge graph of the production line includes a coupled graph database and a relational database. The graph database and the relational database are used to store the logistics relationship information of the production line and the status information of each component of the production line. The spatiotemporal knowledge graph of the production line also includes a data acquisition module, a data transformation module, and a data analysis module.

[0015] The data acquisition module is used to obtain the status information of each component of the production line from the OPCUA data service of the equipment and store it in the graph database and relational database.

[0016] The data transformation module is used to convert data between the graph database and the relational database.

[0017] The data analysis module is used to obtain data from the relational database and the graph database, and to perform logistics analysis on the target production line to obtain the overall operation status of the target production line and / or to perform workstation and component diagnosis on the target production line to obtain the timing operation status of components, so as to realize the analysis and optimization of the target production line in time and space.

[0018] Preferably: Analyzing the logistics relationships on the production line and constructing a static logistics relationship map of the production line using the production line logistics relationship diagram includes:

[0019] Analyze the logistics relationships of the production line, create a node for each workstation, and construct the static logistics relationship graph of the production line as an edge for the material flow relationship.

[0020] Preferably: the node includes a node label, a current timestamp, and a list of real-time component data; the material flow relationship of the production line is a directed edge of the production line knowledge graph, pointing from material outflow to material inflow, and the directed edge includes an edge label and the material flow time; the material update data of the production line is an undirected edge, and the undirected edge includes an edge label and the material update time.

[0021] Preferably, the status information of each component in the production line includes at least the component label, the workstation to which it belongs, the update timestamp, and the real-time collected data.

[0022] Preferably, the relational database includes a node data table, an undirected edge data table, and a directed edge data table;

[0023] The node data table is used to store the status information of each component of the production line. Each data entry in the undirected edge data table includes the labels of the two end nodes and the update time in the middle. Each data entry in the directed edge data table includes the label of the start node, the label of the end node, and the logistics time.

[0024] The graph database contains nodes, directed edges, and undirected edges;

[0025] The nodes are used to store the status information of each component of the production line. The undirected edge connects two nodes and contains update time data from the two nodes. The directed edge points from one node to another and contains logistics time data from both nodes.

[0026] Preferably, in storage priority mode, the data acquisition module reads the equipment component information from the equipment OPCUA data service and stores it in the node data table of the relational database. The data conversion module queries the workstation logistics relationship in the relational database according to the static logistics relationship graph of the production line, and stores the structured data obtained in the query into the directed edge data table and the undirected edge data table, and at the same time stores it into the graph database.

[0027] In the analysis-first mode, the data acquisition module reads equipment component information from the equipment OPCUA data service and stores it directly as node data in the graph database. It also constructs directed and undirected edges according to the workstation logistics relationship in the static logistics relationship graph of the production line and stores them in the graph database. The data conversion module queries the graph database by node and stores the obtained node data in the node data table of the relational database.

[0028] Preferably: using the spatiotemporal knowledge spectrum of the production line to perform logistics analysis on the target production line to obtain the overall operating status of the target production line, and / or to perform workstation and component diagnosis on the target production line to obtain the timing operation status of components, including:

[0029] Data is obtained from the spatiotemporal knowledge graph of the production line; the data includes time-series data and structured data.

[0030] Path search is performed on the structured data. If a non-connected graph is obtained, it is further distinguished from independent workstations and logistics anomalies by combining it with the static logistics relationship graph. If a circular subgraph is obtained, it is identified as a ring unit. The remaining paths obtained by the search are material flow lines.

[0031] The degree centrality matrix and betweenness centrality matrix are calculated from the structured data. Combined with the material flow line, the workstations with high degree centrality are identified as important processing workstations, and the workstations with high betweenness centrality are identified as important logistics workstations.

[0032] The time-series data is analyzed using various analysis interfaces to detect anomalies, obtain component anomalies and their occurrence times, determine the component and its corresponding workstation, and if it is determined to be an important processing workstation, then the component anomaly is diagnosed and analyzed to determine whether the component is faulty; if it is an important logistics workstation, then the logistics anomaly is located in conjunction with the material flow line to find the location of the logistics fault.

[0033] Preferably, the analysis interface includes anomaly detection methods based on statistical features, machine learning methods based on decision trees, and deep learning methods based on neural networks.

[0034] Preferably, the formula for calculating the degree centrality is as follows:

[0035]

[0036] In the formula: DC represents degree centrality, k i N represents the number of edges connected to node i, and N represents the total number of nodes in the graph.

[0037] The formula for calculating the betweenness centrality is as follows:

[0038]

[0039] In the formula: BC represents betweenness centrality, and N represents the total number of nodes in the graph. This represents the number of paths that pass through node i and are the shortest paths. This represents the number of shortest paths connecting s and t.

[0040] A production line modeling and analysis apparatus, comprising:

[0041] A static logistics relationship graph construction unit is used to analyze the logistics relationships of the production line and construct a static logistics relationship graph using the logistics relationships of the production line.

[0042] The OPCUA data service construction unit is used to analyze the status of each component in the production line and construct the equipment OPCUA data service using the status of each component in the production line.

[0043] The target production line information acquisition unit is used to acquire production line logistics relationship information and status information of various components of the target production line.

[0044] A production line spatiotemporal knowledge graph construction unit is used to construct a production line spatiotemporal knowledge graph using the static logistics relationship graph of the production line and the OPCUA data service of the equipment. The production line spatiotemporal knowledge graph includes a coupled graph database and a relational database. The graph database and the relational database are used to store the logistics relationship information of the production line and the status information of each component of the production line. The production line spatiotemporal knowledge graph also includes a data acquisition module, a data transformation module, and a data analysis module.

[0045] The data acquisition unit is used to obtain the status information of each component of the production line from the OPCUA data service of the equipment using the data acquisition module and store it into the graph database and the relational database;

[0046] A data transformation unit is used to transform data between the graph database and the relational database using the data transformation module;

[0047] The data analysis unit is used to obtain data from the relational database and the graph database using the data analysis module, perform logistics analysis on the target production line to obtain the overall operation status of the target production line, and / or perform workstation and component diagnosis on the target production line to obtain the timing operation status of components, so as to realize the analysis and optimization of the target production line in time and space.

[0048] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0049] This application provides a production line modeling and analysis method and apparatus. This method effectively solves the analysis and diagnosis problems of the overall operation of the production line and its local equipment by constructing a spatiotemporal knowledge graph of the production line. It can simultaneously perform spatial structure analysis and time series diagnosis of the production line, with high speed and efficiency. By coupling relational databases and graph databases, it solves the problem of production line data modeling and acquisition. It can efficiently and accurately perform real-time data acquisition and structural modeling of the production line for subsequent analysis and optimization. By combining graph analysis methods and time series data anomaly detection, it effectively solves the problem of anomaly diagnosis and tracing in the production line, enabling rapid and accurate location and tracing of abnormal components.

[0050] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0052] Figure 1 This is a flowchart of a production line modeling and analysis method provided in an embodiment of the present invention;

[0053] Figure 2 This is a flowchart of the spatiotemporal knowledge graph construction process for a production line provided in an embodiment of the present invention;

[0054] Figure 3 This is a simplified diagram of the knowledge graph structure provided in an embodiment of the present invention;

[0055] Figure 4 This is a coupling relationship diagram of the internal database of the spatiotemporal knowledge graph provided in the embodiments of the present invention;

[0056] Figure 5 This is a structured data diagram provided in the embodiments of the present invention;

[0057] Figure 6 This is a schematic diagram of a diagnostic method for a workstation or component provided in an embodiment of the present invention;

[0058] Figure 7 This is a schematic diagram of a production line modeling and analysis device provided in an embodiment of the present invention;

[0059] Figure 8 This is a schematic diagram of a production line modeling and analysis device provided in an embodiment of the present invention. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the present invention.

[0061] See Figure 1 This invention provides a production line modeling and analysis method, such as... Figure 1 As shown, the method may include:

[0062] S101: Analyze the logistics relationship of the production line and construct a static logistics relationship graph of the production line using the logistics relationship graph of the production line; when actually constructing the static logistics relationship graph, the embodiments of this application can provide analysis of the logistics relationship of the production line, create a node for each workstation, and construct the static logistics relationship graph of the production line as an edge.

[0063] A graph database is constructed using the static logistics relationship graph; the graph database consists of nodes, directed edges, and undirected edges.

[0064] Furthermore, the node includes a node label, a current timestamp, and a list of real-time component data; the material flow relationship of the production line is used as a directed edge in the graph database, pointing from material outflow to material inflow, and the directed edge includes an edge label and the material flow time; the material update data of the production line is used as an undirected edge, and the undirected edge includes an edge label and the material update time.

[0065] S102: Analyze the status of each component in the production line and use the status of each component in the production line to build an OPCUA data service for the equipment; specifically, the status information of each component in the production line includes at least the component tag, the workstation to which it belongs, the update timestamp, and the real-time collected data.

[0066] A relational database is constructed using the status of each component of the production line;

[0067] Furthermore, the relational database includes a node data table, an undirected edge data table, and a directed edge data table;

[0068] S103: Obtain the production line logistics relationship information and the status information of each component of the target production line;

[0069] S104: A spatiotemporal knowledge graph of the production line is constructed by combining the production line logistics relationship information and the status information of each component of the production line with the static logistics relationship graph of the production line and the OPCUA data service of the equipment; the spatiotemporal knowledge graph of the production line includes a coupled graph database and a relational database; the graph database and the relational database are used to store the production line logistics relationship information and the status information of each component of the production line; the spatiotemporal knowledge graph of the production line also includes a data acquisition module, a data transformation module and a data analysis module;

[0070] S105: Use the data acquisition module to obtain the status information of each component of the production line from the OPCUA data service of the equipment and store it into the graph database and relational database;

[0071] S106: Use the data conversion module to convert the data in the graph database and the relational database to each other;

[0072] The relational database includes a node data table, an undirected edge data table, and a directed edge data table;

[0073] The node data table is used to store the status information of each component of the production line. Each data entry in the undirected edge data table includes the labels of the two end nodes and the update time in the middle. Each data entry in the directed edge data table includes the label of the start node, the label of the end node, and the logistics time.

[0074] The graph database contains nodes, directed edges, and undirected edges;

[0075] The nodes are used to store the status information of each component of the production line. The undirected edge connects two nodes and contains update time data from the two nodes. The directed edge points from one node to another and contains logistics time data from both nodes.

[0076] In storage-first mode, the data acquisition module reads equipment component information from the equipment OPCUA data service and stores it in the node data table of the relational database. The data conversion module queries the relational database according to the workstation logistics relationship in the static logistics relationship graph, stores the structured data obtained in the directed edge data table and the undirected edge data table, and stores it in the graph database at the same time.

[0077] In the analysis-first mode, the data acquisition module reads equipment component information from the equipment OPCUA data service, stores it directly as node data in the graph database, and constructs directed and undirected edges according to the workstation logistics relationship in the static logistics relationship graph, and stores them in the graph database. The data conversion module queries the graph database by node and stores the obtained node data in the node data table of the relational database.

[0078] S107: Using the data analysis module, data is obtained from the relational database and the graph database to perform logistics analysis on the target production line to obtain the overall operation status of the target production line and / or to perform workstation and component diagnosis on the target production line to obtain the timing operation status of components, so as to realize the analysis and optimization of the target production line in time and space.

[0079] The data acquisition module is used to acquire data from the device's OPCUA data service; the data conversion module is used to convert data between the relational database and the graph database; the data analysis module is used to use the data acquired from the relational database and the graph database to perform logistics analysis on the target production line to obtain the overall operating status of the target production line, and / or to perform workstation and component diagnosis on the target production line to obtain the timing operation status of components, so as to realize the time and space analysis and optimization of the target production line.

[0080] In practice, analytical data is obtained from the relational database and the graph database; the analytical data includes time-series data and structured data.

[0081] Path search is performed on the structured data. If a non-connected graph is obtained, it is further distinguished from independent workstations and logistics anomalies by combining the knowledge graph. If a circular subgraph is obtained, it is identified as a ring cell. The remaining paths obtained by the search are material flow lines.

[0082] The degree centrality matrix and betweenness centrality matrix of the map are calculated from the structured data. Combined with the material flow line, the workstations with high degree centrality are identified as important processing workstations, and the workstations with high betweenness centrality are identified as important logistics workstations.

[0083] The time-series data is analyzed using various analysis interfaces to detect anomalies, obtain component anomalies and their occurrence times, determine the component and its corresponding workstation, and if it is determined to be an important processing workstation, then the component anomaly is diagnosed and analyzed to determine whether the component is faulty; if it is an important logistics workstation, then the logistics anomaly is located in conjunction with the material flow line to find the location of the logistics fault.

[0084] Furthermore, the analysis interface includes anomaly detection methods based on statistical features, machine learning methods based on decision trees, and deep learning methods based on neural networks.

[0085] The formula for calculating the degree centrality is as follows:

[0086]

[0087] In the formula: DC represents degree centrality, k i N represents the number of edges connected to node i, and N represents the total number of nodes in the graph.

[0088] The formula for calculating the betweenness centrality is as follows:

[0089]

[0090] In the formula: BC represents betweenness centrality, and N represents the total number of nodes in the graph. This represents the number of paths that pass through node i and are the shortest paths. This represents the number of shortest paths connecting s and t.

[0091] The production line modeling and analysis method provided in this application establishes a static logistics relationship graph of the production line and collects real-time data from various components of the production line for real-time expansion, thereby obtaining a spatiotemporal knowledge graph of the production line. Using the obtained spatiotemporal knowledge graph, logistics analysis is performed on the production line to obtain the overall operating status of the production line, and workstation and component diagnostics are conducted to obtain the temporal operating status of the components, thus achieving effective temporal and spatial analysis and optimization of the production line.

[0092] The production line modeling and analysis methods provided in the embodiments of this application will be described in detail below.

[0093] First, the production line is analyzed, and a static logistics relationship graph is constructed based on the logistics relationships of each workstation. Then, an Open Platform Communications Unified Architecture (OPC UA) data service is built based on the status information of each workstation. Next, a graph database and a relational database are constructed using the analysis results, for real-time analysis and persistent storage, respectively. Each component of the production line is mapped to a specific data item in the relational database, and the two databases are coupled into a spatiotemporal knowledge graph of the production line.

[0094] Then, structured data is extracted from this spatiotemporal knowledge graph for logistics analysis and optimization, time-series data is extracted for workstation or component diagnosis, and integrated logistics and component data are used for anomaly localization and diagnosis. The flowchart of the above method is shown below. Figure 2 As shown.

[0095] The specific steps are as follows.

[0096] 1. Analyze the logistics relationships on the production line. Create a node for each workstation and use the material flow relationship as an edge to obtain a static logistics relationship graph.

[0097] 2. Construct a graph database based on the static logistics relationship graph obtained in step 1. Each workstation on the production line is a node in this graph database, containing a node label, a current timestamp, and a list of real-time component data. The material flow relationships on the production line are represented as directed edges in this graph database, pointing from material outflow to material inflow. Each directed edge contains an edge label and the logistics time consumed. The material update data on the production line is represented as undirected edges, containing an edge label and the material update time consumed. A simplified diagram of the constructed graph database structure is shown below. Figure 3 As shown.

[0098] 3. Analyze the status information of each component on the production line and map it to specific items in the database. The status should include information such as component label, workstation, update timestamp, and real-time collected data.

[0099] 4. Construct a relational database based on the component status information obtained in step 3. The relational database includes a node data table, an undirected edge data table, and a directed edge data table. The node data table stores real-time component data; each data entry includes the component tag, its workstation, update timestamp, and real-time data acquisition information. Each data entry in the undirected edge data table includes the tags of the two endpoints and the update time in the middle. Each data entry in the directed edge data table includes the starting node tag, the ending node tag, and the logistics time.

[0100] 5. Construct a spatiotemporal knowledge graph of the production line. For example... Figure 4 As shown, the spatiotemporal knowledge graph of the production line includes two databases: a coupled graph database and a relational database.

[0101] In storage-first mode, the data acquisition module reads equipment component information from the equipment OPCUA server and stores it in the node data table of the relational database. The data transformation module queries the relational database according to the workstation logistics relationship in the knowledge graph, stores the structured data obtained in the directed edge data table and the undirected edge data table, and also stores it in the graph database.

[0102] In analysis-first mode, the data acquisition module reads equipment component information from the equipment OPCUA server and stores it directly as node data in the graph database. It also constructs directed and undirected edges according to the workstation logistics relationships in the knowledge graph and stores them in the graph database. The data transformation module queries the graph database by node and stores the retrieved node data in the node data table of the relational database.

[0103] 6. Obtain and analyze data from knowledge graphs. For example... Figure 4 As shown, time-series data can be retrieved from a relational database by querying by time or device component, or from a graph database by querying undirected edges specified by node labels. Structured data is retrieved by querying directed edges in a graph database. Structured data includes, for example,... Figure 5 As shown.

[0104] 7. Logistics Analysis. The structured data obtained in step 6 represents the production line logistics relationships within a specified time period. This data can be analyzed using methods such as... Figure 6 The method shown is used to analyze and optimize production line logistics.

[0105] First, a path search is performed on the structured data: if a disconnected graph is obtained, it is further distinguished from independent workstations and logistics anomalies by combining the knowledge graph from step 2. If a circular subgraph is obtained, it is identified as a ring cell. The remaining paths obtained from the search are material flow lines.

[0106] The degree centrality matrix and betweenness centrality matrix of the graph are calculated from the structured data. Combined with the material flow line, the workstations with high degree centrality are identified as important processing workstations, and the workstations with high betweenness centrality are identified as important logistics workstations.

[0107] The formula for calculating the degree centrality of a node is as follows:

[0108]

[0109] In the formula: DC represents degree centrality, k i N represents the number of edges connected to node i, and N represents the total number of nodes in the graph.

[0110] The formula for calculating the betweenness centrality is as follows:

[0111]

[0112] In the formula: BC represents betweenness centrality, and N represents the total number of nodes in the graph. This represents the number of paths that pass through node i and are the shortest paths. This represents the number of shortest paths connecting s and t.

[0113] 8. Component diagnosis and anomaly localization. (Using...) Figure 6 The method described above diagnoses workstations or components: First, it obtains the time-series data of the component from the production line's spatiotemporal knowledge graph. Then, it calls various analysis interfaces to perform anomaly detection on the time-series data, obtaining the component anomaly and its occurrence time. These analysis interfaces can use anomaly detection methods based on statistical features, machine learning methods based on decision trees, or deep learning methods based on neural networks. For the component and its associated workstation, combined with the results from step 7, if it is an important processing workstation, a diagnostic analysis of the component's anomaly is performed to determine if the component is faulty; if it is an important logistics workstation, logistics anomaly localization is performed in conjunction with the material flow line to find the location of the logistics failure.

[0114] As can be seen, the method provided in this application uses a combination of nodes, directed edges, and undirected edges to construct a spatiotemporal knowledge graph for a production line. This method fully preserves the data, temporal, and spatial structure of the production line, facilitating structural optimization and anomaly diagnosis.

[0115] This method employs a coupled approach using relational and graph databases to store a spatiotemporal knowledge graph. This method preserves the temporal and spatial structure of production line data while maintaining both analytical and storage efficiency. It enables rapid and effective data analysis and provides persistent storage. Furthermore, the spatiotemporal knowledge graph is loosely coupled, allowing for mutual extraction and transformation between the two databases, thus increasing data fault tolerance.

[0116] This method combines time-series data and logistics relationships to locate and diagnose anomalies. It can quickly and accurately diagnose and trace the source of production line anomalies, identifying faulty components and the time of occurrence.

[0117] In summary, the production line modeling and analysis method provided in this application effectively solves the analysis and diagnosis problems of the overall operation of the production line and its local equipment by constructing a spatiotemporal knowledge graph of the production line. It can simultaneously perform spatial structure analysis and time series diagnosis of the production line, with high speed and efficiency. By coupling relational databases and graph databases, it solves the problem of production line data modeling and acquisition. It can efficiently and accurately perform real-time data acquisition and structural modeling of the production line for subsequent analysis and optimization. By combining graph analysis methods with time series data anomaly detection, it effectively solves the problem of anomaly diagnosis and tracing in the production line, enabling rapid and accurate location and tracing of abnormal components.

[0118] See Figure 7 This application embodiment can also provide a production line modeling and analysis device, such as... Figure 7 As shown, the device may include:

[0119] The static logistics relationship graph construction unit 701 is used to analyze the logistics relationship of the production line and construct a production line knowledge graph using the production line logistics relationship graph.

[0120] OPCUA data service construction unit 702 is used to analyze the status of each component in the production line and construct equipment OPCUA data service using the status of each component in the production line.

[0121] The target production line information acquisition unit 703 is used to acquire production line logistics relationship information and status information of various components of the target production line.

[0122] The production line spatiotemporal knowledge graph construction unit 704 is used to construct a production line spatiotemporal knowledge graph by combining the production line logistics relationship information and the status information of each component of the production line with the production line knowledge graph and the equipment OPCUA; the production line spatiotemporal knowledge graph includes a coupled graph database and a relational database; the graph database is used to store the production line logistics relationship information, and the relational database is used to store the status information of each component of the production line; the production line spatiotemporal knowledge graph also includes a data acquisition module, a data transformation module, and a data analysis module;

[0123] Data acquisition unit 705 is used to obtain the status information of each component of the production line from the OPCUA data service of the equipment using the data acquisition module and store it into the graph database and relational database;

[0124] The data conversion unit 706 is used to convert data between the graph database and the relational database using the data conversion module;

[0125] The data analysis unit 707 is used to obtain data from the relational database and the graph database using the data analysis module, perform directed graph analysis on the target production line to obtain the overall operating status of the target production line and / or perform undirected graph analysis on the target production line to obtain the timing operation status of the components, so as to realize the time and space analysis and optimization of the target production line.

[0126] This application embodiment can also provide a production line modeling and analysis device, the device including a processor and a memory:

[0127] The memory is used to store program code and transmit the program code to the processor;

[0128] The processor is used to execute the steps of the above-described production line modeling and analysis method according to the instructions in the program code.

[0129] like Figure 8 As shown in the illustration, an embodiment of this application provides a production line modeling and analysis device, which may include: a processor 10, a memory 11, a communication interface 12, and a communication bus 13. The processor 10, memory 11, and communication interface 12 all communicate with each other through the communication bus 13.

[0130] In this embodiment, the processor 10 may be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic devices.

[0131] The processor 10 can call programs stored in the memory 11. Specifically, the processor 10 can execute operations in the embodiments of the production line modeling and analysis method.

[0132] The memory 11 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment, the memory 11 stores at least a program for implementing the following functions:

[0133] Analyze the logistics relationships within the production line, and construct a static logistics relationship map of the production line using these relationships.

[0134] Analyze the status data of all components on the production line, and use the status data of all components on the production line to build an equipment OPCUA data service;

[0135] Obtain production line logistics relationship information and status information of each component of the target production line;

[0136] A spatiotemporal knowledge graph of the production line is constructed using the static logistics relationship graph of the production line and the OPCUA data service of the equipment. The spatiotemporal knowledge graph of the production line includes a coupled graph database and a relational database. The graph database and the relational database are used to store the logistics relationship information of the production line and the status information of each component of the production line. The spatiotemporal knowledge graph of the production line also includes a data acquisition module, a data transformation module, and a data analysis module.

[0137] The data acquisition module is used to obtain the status information of each component of the production line from the OPCUA data service of the equipment and store it in the graph database and relational database.

[0138] The data transformation module is used to convert data between the graph database and the relational database.

[0139] The data analysis module is used to obtain data from the relational database and the graph database, and to perform logistics analysis on the target production line to obtain the overall operation status of the target production line and / or to perform workstation and component diagnosis on the target production line to obtain the timing operation status of components, so as to realize the analysis and optimization of the target production line in time and space.

[0140] In one possible implementation, the memory 11 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function (such as file creation or data read / write). The data storage area may store data created during use, such as initialization data.

[0141] In addition, memory 11 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0142] Communication interface 12 can be an interface for the communication module, used to connect with other devices or systems.

[0143] Of course, it should be noted that, Figure 8 The structure shown does not constitute a limitation on the production line modeling and analysis equipment in the embodiments of this application. In practical applications, the production line modeling and analysis equipment may include more than Figure 8 More or fewer components as shown, or combinations of certain components.

[0144] This application embodiment may also provide a computer-readable storage medium for storing program code for executing the steps of the above-described production line modeling and analysis method.

[0145] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0146] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0147] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0148] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A production line modeling and analysis method, characterized in that, include: Analyze the logistics relationships of the production line and construct a static logistics relationship map of the production line using these relationships. Analyze the status data of all components on the production line, and use the status data of all components on the production line to build an equipment OPCUA data service; Obtain production line logistics relationship information and status information of each component of the target production line; A spatiotemporal knowledge graph of the production line is constructed using the static logistics relationship graph of the production line and the OPCUA data service of the equipment. The production line spatiotemporal knowledge graph includes a coupled graph database and a relational database; the graph database and the relational database are used to store the logistics relationship information of the production line and the status information of each component of the production line; the production line spatiotemporal knowledge graph also includes a data acquisition module, a data transformation module and a data analysis module; The data acquisition module is used to obtain the status information of each component of the production line from the OPCUA data service of the equipment and store it in the graph database and relational database. The data transformation module is used to convert data between the graph database and the relational database. The data analysis module is used to obtain data from the relational database and the graph database, and to perform logistics analysis on the target production line to obtain the overall operation status of the target production line and / or to perform workstation and component diagnosis on the target production line to obtain the timing operation status of components, so as to realize the analysis and optimization of the target production line in time and space.

2. The production line modeling and analysis method according to claim 1, characterized in that, Analyzing the logistics relationships within the production line and constructing a static logistics relationship map of the production line using the aforementioned production line logistics relationship diagram includes: Analyze the logistics relationships of the production line, create a node for each workstation, and construct the static logistics relationship graph of the production line as an edge for the material flow relationship.

3. The production line modeling and analysis method according to claim 2, characterized in that, The nodes include node labels, current timestamps, and a list of real-time component data; the material flow relationships of the production line are directed edges in the production line knowledge graph, pointing from material outflow to material inflow, and the directed edges include edge labels and the material flow time; the material update data of the production line are undirected edges, and the undirected edges include edge labels and the material update time.

4. The production line modeling and analysis method according to claim 1, characterized in that, The status information of each component in the production line includes at least the component label, the workstation it belongs to, the update timestamp, and the real-time collected data.

5. The production line modeling and analysis method according to claim 4, characterized in that, The relational database includes a node data table, an undirected edge data table, and a directed edge data table; The node data table is used to store the status information of each component of the production line. Each data entry in the undirected edge data table includes the labels of the two end nodes and the update time in the middle. Each data entry in the directed edge data table includes the label of the start node, the label of the end node, and the logistics time. The graph database contains nodes, directed edges, and undirected edges; The nodes are used to store the status information of each component of the production line. The undirected edge connects two nodes and contains update time data from the two nodes. The directed edge points from one node to another and contains logistics time data from both nodes.

6. The production line modeling and analysis method according to claim 5, characterized in that, In storage-first mode, the data acquisition module reads equipment component information from the equipment OPCUA data service and stores it in the node data table of the relational database. The data conversion module queries the workstation logistics relationship in the relational database according to the static logistics relationship graph of the production line, and stores the structured data obtained in the directed edge data table and the undirected edge data table, and also stores it in the graph database. In the analysis-first mode, the data acquisition module reads equipment component information from the equipment OPCUA data service and stores it directly as node data in the graph database. It also constructs directed and undirected edges according to the workstation logistics relationship in the static logistics relationship graph of the production line and stores them in the graph database. The data conversion module queries the graph database by node and stores the obtained node data in the node data table of the relational database.

7. The production line modeling and analysis method according to claim 1, characterized in that, Using the spatiotemporal knowledge spectrum of the production line, logistics analysis is performed on the target production line to obtain the overall operating status of the target production line, and / or workstation and component diagnostics are performed on the target production line to obtain the timing operation status of components, including: Data is obtained from the spatiotemporal knowledge graph of the production line; the data includes time-series data and structured data. Path search is performed on the structured data. If a non-connected graph is obtained, it is further distinguished from independent workstations and logistics anomalies by combining it with the static logistics relationship graph. If a circular subgraph is obtained, it is identified as a ring unit. The remaining paths obtained by the search are material flow lines. The degree centrality matrix and betweenness centrality matrix are calculated from the structured data. Combined with the material flow line, the workstations with high degree centrality are identified as important processing workstations, and the workstations with high betweenness centrality are identified as important logistics workstations. The time-series data is analyzed using various analysis interfaces to detect anomalies, obtain component anomalies and their occurrence times, determine the component and its corresponding workstation, and if it is determined to be an important processing workstation, then the component anomaly is diagnosed and analyzed to determine whether the component is faulty; if it is an important logistics workstation, then the logistics anomaly is located in conjunction with the material flow line to find the location of the logistics fault.

8. The production line modeling and analysis method according to claim 7, characterized in that, The analysis interface includes anomaly detection methods based on statistical features, machine learning methods based on decision trees, and deep learning methods based on neural networks.

9. The production line modeling and analysis method according to claim 7, characterized in that, The formula for calculating the degree centrality is as follows: In the formula: DC represents degree centrality, k i N represents the number of edges connected to node i, and N represents the total number of nodes in the graph. The formula for calculating the betweenness centrality is as follows: In the formula: BC represents betweenness centrality, and N represents the total number of nodes in the graph. This represents the number of paths that pass through node i and are the shortest paths. This represents the number of shortest paths connecting s and t.

10. A production line modeling and analysis device, characterized in that, include: A static logistics relationship graph construction unit is used to analyze the logistics relationships of the production line and construct a static logistics relationship graph using the logistics relationships of the production line. The OPCUA data service construction unit is used to analyze the status of each component in the production line and construct the equipment OPCUA data service using the status of each component in the production line. The target production line information acquisition unit is used to acquire production line logistics relationship information and status information of various components of the target production line. The production line spatiotemporal knowledge graph construction unit is used to construct and obtain the production line spatiotemporal knowledge graph by utilizing the static logistics relationship graph of the production line and the OPCUA data service of the equipment. The production line spatiotemporal knowledge graph includes a coupled graph database and a relational database; the graph database and the relational database are used to store the logistics relationship information of the production line and the status information of each component of the production line; the production line spatiotemporal knowledge graph also includes a data acquisition module, a data transformation module and a data analysis module; The data acquisition unit is used to obtain the status information of each component of the production line from the OPCUA data service of the equipment using the data acquisition module and store it into the graph database and the relational database; The data transformation unit is used to transform data between the graph database and the relational database using the data transformation module; The data analysis unit is used to obtain data from the relational database and the graph database using the data analysis module, perform logistics analysis on the target production line to obtain the overall operation status of the target production line, and / or perform workstation and component diagnosis on the target production line to obtain the timing operation status of components, so as to realize the analysis and optimization of the target production line in time and space.

Images