Workshop data integration control model optimization method based on graph mining algorithm

Abstract

The invention discloses a workshop data integrated control model optimization method based on a graph mining algorithm, which comprises the following steps of: firstly, acquiring workshop equipment data, preprocessing, defining a node for each piece of equipment, distributing a unique identifier for each node, determining attribute information of each node, and constructing a workshop equipment relation network model based on the attribute information; and finally, carrying out importance evaluation on nodes in the workshop equipment relation network model based on a PageRank algorithm, and optimizing the constructed workshop equipment relation network model by utilizing a social network analysis algorithm. According to the scheme, the graph mining algorithm is used for generating the ship intelligent cabin workshop relation social network model for the equipment of the whole ship intelligent cabin workshop, the ship intelligent cabin workshop relation social network model is optimized, the production process is deeply understood by deeply mining the relation between the equipment, evaluating the importance of the equipment and discovering the group relation, and the production efficiency is improved. The method has real-time performance and dynamic adaptability, can be updated at any time to adapt to the change of the workshop, and can enable workshop workers to conveniently analyze the importance degree of workshop equipment and the dynamic relationship between the workshop equipment.

Description

Technical Field

[0001] The present invention belongs to the field of real-time data integration, and in particular relates to a workshop data integration control model optimization method based on a graph mining algorithm. Background Art

[0002] A large number of devices are involved in the intelligent compartment workshop of a ship. The relationship between each device is intricate, making it difficult to use traditional methods to clearly integrate and understand the data, and traditional data integration algorithms cannot meet the real-time requirements of workshop production. The operation of some equipment may depend on the status and data of other equipment. In such a complex dependency, it is difficult to effectively analyze and control it through traditional data set integration methods. The data of the intelligent compartment workshop of a ship may have complex structures, such as graph structures, hierarchical structures, etc. Traditional methods cannot well integrate the complex business logic of the workshop, and it is difficult to achieve comprehensive intelligent control of the entire production process.

[0003] After reviewing some previous studies and results, we found that the application of graph databases, real-time data integration and processing technology, and the development of Internet of Things technology have provided new ideas and methods for solving this problem. Graph databases such as Neo4j and TigerGraph can efficiently store and query graph structured data with complex relationships, providing a more intuitive and efficient solution for the management and analysis of workshop equipment relationships. At the same time, real-time data processing technologies such as Apache Kafka and Apache Flink can process high-throughput data streams to meet the requirements of real-time and efficiency in workshop production. The development of Internet of Things technology has made the equipment in the workshop more intelligent and interconnected, and through the Internet of Things platform, real-time monitoring and management of equipment status and data can be achieved.

[0004] However, although existing research and technology have solved the problem of workshop equipment data integration and control to a certain extent, some challenges still exist. Traditional methods are difficult to meet the requirements of real-time and complex dependencies in workshop production, and existing graph databases and real-time processing technologies also need to be further combined to better realize intelligent control of workshop production processes. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide a workshop data integration control model optimization method based on a graph mining algorithm. We use a graph mining algorithm to improve the traditional workshop data integration algorithm, and use the graph mining algorithm to generate a ship intelligent compartment workshop relationship social network model for the equipment and personnel of the entire ship intelligent compartment workshop and optimize it.

[0006] The specific technical solution for achieving the purpose of the present invention is:

[0007] A method for optimizing a workshop data integration control model based on a graph mining algorithm comprises the following steps:

[0008] Step 1: Obtain workshop equipment data and perform preprocessing;

[0009] Step 2: define a node for each device, assign a unique identifier to each node, and determine the attribute information of each node;

[0010] Step 3: Construct a workshop equipment relationship network model;

[0011] Step 4: Evaluate the importance of nodes in the workshop equipment relationship network model based on the PageRank algorithm, and use the social network analysis algorithm to optimize the constructed workshop equipment relationship network model.

[0012] Compared with the prior art, the present invention has the following beneficial effects:

[0013] (1) The scheme of the present invention improves the traditional workshop data integration algorithm based on the graph mining algorithm, generates a ship intelligent compartment workshop relationship social network model for the equipment of the entire ship intelligent compartment workshop using the graph mining algorithm and optimizes it, which brings significant progress compared with the traditional method; this model deeply mines the relationship between equipment, evaluates the importance of equipment, discovers group relationships, and achieves a deeper understanding of the production process. Compared with the traditional method, the graph mining model of this scheme has real-time and dynamic adaptability, and can be updated at any time to adapt to the changes in the workshop. The decision support system based on graph mining provides operators with more intelligent and accurate decision support. In addition, the model can discover hidden relationships, reveal potential equipment dependencies, and enhance the overall understanding of the production process. The characteristics of being applicable to complex structures enable the graph mining model to handle large-scale, highly connected equipment networks, further improving production efficiency. Therefore, the ship intelligent compartment workshop data integration model based on graph mining provides deeper and more intelligent support for production control and decision-making, and is expected to achieve significant results in improving efficiency and adapting to complex environments;

[0014] (2) The solution of the present invention is based on the generation of a workshop relationship social network by a graph mining algorithm. In order to enable workshop personnel to have a deep understanding of the operation mode of equipment in the workshop, find key equipment, and understand the dependency relationship between equipment, we use the PageRank algorithm to evaluate the importance of equipment based on the original graph mining algorithm to generate a workshop relationship social network, so that workshop personnel can conveniently analyze the importance of workshop equipment. At the same time, a social network analysis algorithm is added to analyze the relationship and dependency between equipment and their interaction in the production process, so that workshop personnel can more intelligently and conveniently analyze the dynamic relationship between workshop equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic flow chart of the workshop data integration control model optimization method based on graph mining algorithm of the present invention.

[0016] Figure 2 Schematic diagram of a workshop equipment relationship network in an embodiment of the present invention.

[0017] Figure 3 It is a schematic diagram of the implementation process of the PageRank algorithm of the present invention.

[0018] Figure 4 Schematic diagram of the implementation flow of the social network analysis algorithm of the present invention. DETAILED DESCRIPTION

[0019] Example

[0020] In order to clearly describe the technical solution and the effects achieved by the present invention, the technical solution of the present invention is clearly explained below in combination with the accompanying drawings and specific embodiments of the present invention, so that technical personnel in the field can implement the invention without performing creative work. The structure shown in the accompanying drawings is not the entire actual structure but only a part of the actual structure. It should be noted that all other embodiments made by ordinary technical personnel in the field on the basis of the embodiments of the present invention without performing creative work should fall within the protection scope of the present invention.

[0021] The following examples are only for better explanation of the present invention, but the content of the present invention is not limited to the application in the examples. Therefore, those skilled in the art can make non-essential modifications to the implementation scheme based on the above invention content and apply it to other embodiments, which is still within the protection scope of the present invention. In addition, the experimental methods without specific conditions in the following examples should be carried out according to the conventional conditions or the conditions recommended by the manufacturer. If the expressions in the text are not specially explained, they are only used for distinction and have no other meanings.

[0022] Combination Figure 1 , a workshop data integration control model optimization method based on graph mining algorithm, comprising the following steps:

[0023] Step 1: Obtain workshop equipment data and preprocess it:

[0024] Collect workshop equipment data. The data source can include equipment operation logs, sensor data, control instructions, equipment alarm records and other diverse data sources to ensure a comprehensive understanding of the interaction between workshop equipment. The comprehensive use of various data sources helps to build a more complete equipment relationship diagram.

[0025] #Define data source

[0026] Data source = ["Equipment operation log", "Sensor data", "Control instructions", "Equipment alarm record"]

[0027] The collected workshop equipment data is preprocessed to ensure the consistency and availability of the data, including removing redundant information, processing missing values, and correcting abnormal data to ensure the accuracy of subsequent analysis.

[0028] This embodiment provides a code example of data preprocessing:

[0029]

[0030]

[0031] Step 2: Define a node for each device, assign a unique identifier to each node, and determine the attribute information of each node:

[0032] Based on the preprocessed data, each device in the workshop is identified and extracted as a node, and a unique identifier is assigned to each node. The uniqueness of the node can be ensured by using the device ID, name or other unique identifier.

[0033]

[0034] For example, in order to make the ID creation rules clear, we choose three types of equipment, sensors, production machines, and control systems, as examples to illustrate the equipment creation rules.

[0035] -Device attribute extraction: Extract key attributes for each type of device.

[0036] Sensor: sensor type, serial number.

[0037] Production machine: equipment type, model, serial number.

[0038] Control system: device type, system type, serial number.

[0039] - Unique code generation:

[0040] Sensor ID: The first letter of the sensor type (for example, T for a temperature sensor), and the serial number.

[0041] Production machine ID: device type first letter, model first letter, serial number.

[0042] Control system ID: device type first letter, system type first letter, serial number.

[0043] - Identifier allocation:

[0044] Sensor example: The device ID of a temperature sensor (T) with serial number "001" is "T-001".

[0045] Example of a production machine: The device ID for a device type "M", model "123", and serial number "002" is "M-123-002".

[0046] Control system example: The device ID for device type "C", system type "PLC", and serial number "003" is "C-PLC-003".

[0047] In this way, through the creation rules of device ID, each device has a unique and readable identifier to ensure accurate identification in the workshop equipment relationship network model. Based on the accurate definition of the node, we added attribute information to each device node to further enrich the characteristics of the node.

[0048] The attribute information of each node includes but is not limited to:

[0049] Equipment type: sensors, production machines, control systems, etc.

[0050] Operating status: normal, under maintenance, faulty, etc.

[0051] Performance indicators: such as the working efficiency of production machines, the measurement accuracy of sensors, etc.

[0052] These attribute information give each equipment node more detailed features, making the workshop equipment relationship network model not only a connection relationship graph, but also a complex network that fully describes the characteristics of the equipment. This will provide a more comprehensive and in-depth foundation for subsequent graph mining and analysis.

[0053] Afterwards, the relationship edges between nodes are identified through the information in the data source, namely:

[0054] First, the relationship type needs to be determined. In the data collection of workshop equipment, a clear definition of the relationship type helps to accurately depict the association between equipment. Relationship types can include physical connection, data transmission, energy supply, etc. Clarifying the relationship type helps to establish relationship edges later.

[0055] #Define relationship type

[0056] Relationship type = {physical connection, data transfer, energy supply}

[0057] Identify the relationship between nodes through information in the data source, which may include physical connections, data transmission channels, and control instructions between devices.

[0058] Based on the recognition results, relationship edges are established to represent various relationships between nodes, thereby constructing a node relationship graph:

[0059] Assume that each record in the data source is r, which contains the source device ID S, the target device ID T and the relationship type R, and define the relationship edge set between devices as E, then:

[0060]

[0061] Among them, (S, T, R) represents the relationship edge from the source device S to the target device T, and the relationship type is R;

[0062] The constructed relationship edge set E is used to form a device relationship graph.

[0063] Finally, the attribute information of nodes and relationship edges is extracted from the data, including the device type, operating status, performance indicators, etc. of the device nodes; and the attribute information of the relationship edges may include data transmission speed, connection strength, etc.

[0064]

[0065]

[0066] Through the above steps, we collected and processed the workshop equipment data, identified the equipment nodes and relationship edges, and extracted relevant attribute information, laying a solid foundation for the subsequent construction of the workshop equipment relationship network model.

[0067] Step 3: Build a workshop equipment relationship network model:

[0068] First, an adjacency table is built for each device node to record the connection relationship between the device node and other devices. This data structure is used to represent the connection between devices. Each adjacency table entry contains the connected device ID and possible edge attribute information, such as relationship type and data transmission speed. This process is completed by traversing the actual connection relationship between devices to ensure that the graph model can accurately reflect the actual relationship between devices in the workshop.

[0069] Create an adjacency list:

[0070] # Initialize the node and its adjacency list

[0071] Node = {

[0072] "T-001":{"Type":"Temperature_Sensor","Status":"active","Accuracy":0.5,"Adjacency List":[]},

[0073] "M-123-002":{"Type":"Production_Machine","Status":"idle","Working Efficiency":90,"Adjacency List":[]},

[0074] "C-PLC-003":{"Type":"Control_System","Status":"active","System Type":"PLC","Adjacency List":[]}

[0075] }

[0076] Secondly, through the collaborative relationship between devices, edge connections are established in the adjacency table. Each adjacency table entry represents an edge. The relationship between devices is fully described through the connected device ID and detailed edge attribute information.

[0077]

[0078]

[0079] Finally, the information of the equipment nodes and the adjacency table is used to construct a workshop equipment relationship network model, that is, the adjacency table is used to reflect the association between the nodes, and the combination of the nodes and the adjacency table constitutes the workshop equipment relationship network model. The relationship topology diagram of the workshop network relationship model in this embodiment is as follows: Figure 2 shown.

[0080] # Initialize the workshop network model

[0081] Workshop network model = {

[0082] "node": node,

[0083] "adjacency list":{node:node[node]["adjacency list"]for node in node}

[0084] }

[0085] #Show the workshop network model

[0086] Print (workshop network model)

[0087] The generated workshop equipment relationship network model is a graph structure based on an adjacency list. In this graph structure, each node represents a device in the workshop, and the adjacency list of each device records the connection relationship between the device and other devices. Each item in the adjacency list includes the connected device ID and possible edge attribute information. This graph-based structure clearly presents the relationship between workshop equipment, allowing us to more comprehensively understand the collaborative relationship, data transmission relationship or control relationship between devices.

[0088] Displaying the generated model through graph visualization tools helps to intuitively understand the collaborative relationship between equipment and further discover potential patterns and rules. We can use the open source software Tableau to visualize the generated workshop equipment relationship network model.

[0089] #Import device relationship data into Tableau

[0090] Tableau.ImportData (workshop network model)

[0091] #Select chart type and attribute mapping

[0092] Tableau.SelectChartType("Network Graph")

[0093] Tableau.MapAttributes(node ​​= "device ID", edge = "relationship type")

[0094] #Visualize the device relationship network model

[0095] Tableau.Visualize()

[0096] #Dive deeper with interactive features

[0097] Tableau.EnableInteraction()

[0098] When using Tableau to visualize the workshop equipment relationship network, you first need to import the equipment relationship data. Through Tableau's graphical interface, we can select the appropriate chart type and attribute mapping, represent the equipment as nodes, the relationship as edges, and present the characteristics of the equipment and the strength of the relationship through different colors, shapes or sizes. With the interactive function of Tableau, users can explore the network structure in depth through hovering, filtering, etc., monitor data changes in real time, quickly identify the collaborative relationship between equipment, and form a more comprehensive visual presentation through dashboard construction. This method not only provides an intuitive network diagram, but also allows users to dynamically adjust and analyze as needed. Through this series of steps, we have established a clear and detailed workshop equipment relationship network model, laying a solid foundation for subsequent graph mining and in-depth analysis.

[0099] Step 4: Evaluate the importance of nodes in the workshop equipment relationship network model based on the PageRank algorithm, and use the social network analysis algorithm to optimize the constructed workshop equipment relationship network model.

[0100] On the basis of constructing a workshop equipment relationship network model based on graph mining, in order to enable workshop personnel to have a deeper understanding of the production process, discover hidden relationships, reveal potential equipment dependencies, and enhance the comprehensive understanding of the production process, in order to improve the completeness and intelligence of the model, the PageRank algorithm and social network analysis algorithm can be introduced.

[0101] Among them, combined Figure 3 , the importance of nodes is evaluated based on the PageRank algorithm. The PageRank algorithm determines the relative importance of nodes in the network by analyzing the link relationship between nodes. In the workshop equipment relationship network, the equipment nodes can be regarded as pages, and the key equipment nodes can be identified through the PageRank algorithm. These devices may play an important role in the production process, specifically:

[0102] The weights of the N nodes in the constructed workshop equipment relationship network model are initialized, that is, for any node i, its initial weight W(i) is:

[0103] W(i)=1 / N

[0104] In this way, each element in the vector W represents the initial weight of each node and is assigned to each node in the network graph.

[0105] In a specific workshop equipment relationship network, the initial weight of the equipment can be appropriately adjusted to increase the importance of the equipment from the beginning. Factors affecting the initial weight of workshop equipment include equipment type, equipment status, equipment performance indicators, equipment historical data, business needs, etc.

[0106] Introduce the damping factor and use the PageRank algorithm to iterate the PageRank value PR(i) of the node:

[0107]

[0108] Where d is the damping factor, which is usually 0.85. M(i) represents the set of nodes pointing to node i, that is, the set of devices directly related to device i. If device j is related to device i, then j belongs to M(i). L(j) represents the out-degree of node j, that is, the number of devices related to device j, reflecting the influence of device j. The initial PageRank value PR(i) of each node is the initial weight W(i).

[0109] In the workshop equipment relationship network, the role of the damping factor in the PageRank algorithm is mainly to simulate the behavior in the actual production environment, taking into account the randomness and non-linked navigation that may exist in the workflow. This means that the collaborative relationship between equipment is not only determined by direct physical connections and control relationships, but may also be affected by random factors, such as equipment status changes and temporary task changes.

[0110] In each iteration, the new PageRank value of each node is calculated based on the current PageRank value, and the stored PageRank vector is updated. The iteration continues until the change in the PageRank value is less than the set threshold ∈, that is, the condition is met:

[0111] max i |PR(i) (t+1) -PR(i) (t) |<∈

[0112] Where PR(i) (t) and PR(i) (t+1) They represent the PageRank values ​​of node i in the tth and t+1th iterations respectively.

[0113] The commonly used convergence threshold ∈ is set to 10 -6 Or smaller to ensure the accuracy of the results. This condition indicates that the algorithm has converged and the PageRank value has stabilized.

[0114] When the algorithm converges, the final PageRank value PR(i) of node i represents the importance of device i in the workshop equipment relationship network, reflecting the connection relationship and influence of the device in the network.

[0115] During the iteration process, the damping factor d adjusts the PageRank calculation in each iteration so that the PageRank value of a node not only depends on the contribution of its directly linked nodes, but also includes a certain global randomness factor, thereby more accurately reflecting the actual importance of the device in the network.

[0116] By calculating the importance of workshop equipment, we can identify key equipment, optimize performance, predict failures, rationally allocate resources, and optimize production scheduling. This helps improve the availability and intelligence of the entire workshop equipment relationship network model and achieve more efficient and reliable production operations.

[0117] Combination Figure 4 , based on the social network analysis algorithm (SNA), the constructed workshop equipment relationship network model is optimized, and the social network analysis algorithm is used to deeply explore the social relationship between equipment nodes. Social network analysis can reveal the close connection and mutual influence between equipment, and help understand the details of equipment dependency. By identifying key indicators such as social groups and degree centrality between equipment nodes, a more comprehensive understanding of the interaction between equipment can be obtained, specifically:

[0118] The overall modularity Q is an important indicator to measure the rationality of community division in the network. It evaluates the quality of the division by calculating the connection density of nodes within the community and the sparsity between communities under the current division. Specifically, each device node is first initialized as an independent community to form an initial community division, and the overall modularity Q is used to judge the rationality of the division:

[0119]

[0120] Among them: Q represents modularity, A ij Indicates whether there is a connection between node i and node j, k i and k j is the degree of nodes i and j, i.e. the total number of connections), m is the total number of edges in the workshop equipment relationship network, δ(c i ,c j ) is an indicator function, which takes the value of 1 if nodes i and j belong to the same community, otherwise it takes the value of 0;

[0121] In the iteration, in order to maximize the value of the overall modularity Q, nodes with higher degrees (i.e. nodes with more connections) are selected for movement, that is, nodes are moved to communities that can improve the overall modularity Q value.

[0122] Specifically, in each iteration, the initial value of the overall modularity Q is first calculated based on the current community division; then, a node i with a higher degree is selected and tried to be moved to a different community in order to calculate the modularity increment ΔQ after joining the community. If the movement of node i can improve modularity, it is moved to the new community and the Q value is updated; if the modularity does not increase after the move, it remains in the original community. The formula for the modularity increment ΔQ is:

[0123]

[0124] Among them, ∑in represents the total number of edges in the community, k i,in represents the number of connections between node i and other nodes in the community, and ∑tot is the total degree of the community;

[0125] The iteration continues until no node movement can further improve the overall modularity Q value. Specifically, in each iteration, for each node i, the modularity increment ΔQ after moving it to a different community is calculated. If it is found that the movement can improve modularity (that is, ΔQ>0), the node i is retained in the new community and the modularity Q is updated. If the movement no longer improves modularity (that is, ΔQ≤0), the node i continues to stay in the original community.

[0126] This process is repeated for all nodes until each node cannot further improve its modularity, and the iteration stops. At this point, the community partitioning has reached a relatively stable state, and the resulting community structure clearly reveals the social relationships between devices, helping to gain a deeper understanding of the dependencies and interactions between devices. Through this algorithm, the final output community partitioning structure can reveal a group of closely related devices, thereby helping to identify the social relationships between devices and provide structured results for deeper network analysis.

[0127] The application of social network analysis algorithms in the workshop equipment relationship network model can deeply explore the social relationships of equipment nodes and reveal the connections and influences between equipment. By identifying key indicators, fully understanding the interactions between equipment, and dividing equipment nodes into communities, it helps to optimize layout and configuration, improve production efficiency and coordination. This further optimizes workshop equipment management and production processes and improves overall operational efficiency.

[0128] Based on PageRank algorithm and social network analysis, the whole system has made significant progress. First, through these two algorithms, we can accurately identify the key nodes in the workshop equipment relationship network. These nodes may play a vital role in the production process, and their performance and status directly affect the operation of the entire production system. By identifying these key nodes, workshop managers can have a deeper understanding of the key links in the production process, and carry out targeted resource allocation and equipment maintenance, thereby improving production efficiency and product quality.

[0129] Secondly, using graph visualization tools to display the results of the PageRank algorithm and social network analysis provides workshop personnel with an intuitive way to present data. Through visualization, workshop personnel can clearly see the key nodes, social groups, and important relationships between devices. This intuitive data display method enables workshop personnel to have a deeper understanding of the dependencies and mutual influences between devices, so as to more effectively plan production processes, optimize resource allocation, and make timely decisions to cope with various challenges in production.

[0130] Finally, the results of key node identification and visualization are applied to the optimization decision support system, further improving the system's functions and performance. Through node importance analysis and key equipment identification, the system can provide more accurate decision support for workshop managers. The decision support system can not only monitor equipment status in real time and identify abnormal situations, but also provide targeted production optimization suggestions to help workshop managers quickly respond to changes in the production process and optimize production plans to maximize production efficiency.

[0131] In summary, the identification and visualization of key nodes based on PageRank algorithm and social network analysis, as well as the application of optimized decision support system, provide powerful tools and support for workshop production management, which helps to improve production efficiency, reduce costs, optimize resource utilization, and ultimately realize the intelligence and automation of the production process.

[0132] The present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0133] Step 1: Obtain workshop equipment data and perform preprocessing;

[0134] Step 2: define a node for each device, assign a unique identifier to each node, and determine the attribute information of each node;

[0135] Step 3: Construct a workshop equipment relationship network model;

[0136] Step 4: Evaluate the importance of nodes in the workshop equipment relationship network model based on the PageRank algorithm, and use the social network analysis algorithm to optimize the constructed workshop equipment relationship network model.

[0137] The present invention also provides a computer storable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0138] Step 1: Obtain workshop equipment data and perform preprocessing;

[0139] Step 2: define a node for each device, assign a unique identifier to each node, and determine the attribute information of each node;

[0140] Step 3: Construct a workshop equipment relationship network model;

[0141] Step 4: Evaluate the importance of nodes in the workshop equipment relationship network model based on the PageRank algorithm, and use the social network analysis algorithm to optimize the constructed workshop equipment relationship network model.

[0142] The above-mentioned embodiments only express several implementation methods of the present application, 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 a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for optimizing a workshop data integration control model based on a graph mining algorithm, characterized in that: The following steps are involved: Step 1: Obtain workshop equipment data and perform preprocessing; Step 2: define a node for each device, assign a unique identifier to each node, and determine the attribute information of each node; Step 3: Construct a workshop equipment relationship network model; Step 4: Evaluate the importance of nodes in the workshop equipment relationship network model based on the PageRank algorithm, and use the social network analysis algorithm to optimize the constructed workshop equipment relationship network model.

2. The method for constructing a workshop data integration control model based on a graph mining algorithm according to claim 1 is characterized in that: The step 1 of obtaining the workshop equipment data is specifically as follows: Collect workshop equipment data, including equipment operation logs, sensor data, control instructions, and equipment alarm records; The collected workshop equipment data is preprocessed to ensure the consistency and availability of the data, including removing redundant information, processing missing values, and correcting abnormal data.

3. The method for constructing a workshop data integration control model based on a graph mining algorithm according to claim 1, characterized in that: The attribute information of the determined node in step 2 is specifically: Based on the preprocessed data, identify and extract each device in the workshop as a node, and assign a unique identifier to each node; Identify the relationship edges between nodes through the information in the data source; Extract attribute information of nodes and relationship edges from data.

4. The method for constructing a workshop data integration control model based on a graph mining algorithm according to claim 3 is characterized in that: The relationship edge between the identified nodes is specifically: Identify the relationship edges between nodes through information in the data source, including physical connections, data transmission channels, and control instructions between devices; Based on the recognition results, relationship edges are established to represent various relationships between nodes, thereby constructing a node relationship graph: Assume that each record in the data source is r, which contains the source device ID S, the target device ID T and the relationship type R, and define the relationship edge set between devices as E, then: Among them, (S, T, R) represents the relationship edge from the source device S to the target device T, and the relationship type is R; The constructed relationship edge set E is used to form a device relationship graph.

5. The method for constructing a workshop data integration control model based on a graph mining algorithm according to claim 3 is characterized in that: The attribute information includes the device type, operating status, and performance indicators of the device node.

6. The method for constructing a workshop data integration control model based on a graph mining algorithm according to claim 3 is characterized in that: The construction of the workshop equipment relationship network model in step 3 is specifically as follows: First, an adjacency table is constructed for each device node to record the connection relationship between the device node and other devices. Each adjacency table entry contains the connected device ID and possible edge attribute information, such as relationship type and data transmission speed. Secondly, through the collaborative relationship between devices, edge connections are established in the adjacency table. Each adjacency table entry represents an edge. The relationship between devices is fully described through the connected device ID and detailed edge attribute information. Finally, the information of equipment nodes and adjacency lists is used to construct a workshop equipment relationship network model. That is, the adjacency list is used to reflect the association between nodes, and the combination of nodes and adjacency lists constitutes the workshop equipment relationship network model.

7. The method for constructing a workshop data integration control model based on a graph mining algorithm according to claim 1, characterized in that: The node importance evaluation based on the PageRank algorithm in step 4 is specifically as follows: The weights of the N nodes in the constructed workshop equipment relationship network model are initialized, that is, for any node i, its initial weight W(i) is: W(i)=1 / N Introduce the damping factor and use the PageRank algorithm to iterate the PageRank value PR(i) of the node: Where d is the damping factor, M(i) represents the set of nodes pointing to node i, that is, the set of devices that have a direct relationship with device i. If device j has a relationship with device i, then j belongs to M(i); L(j) represents the out-degree of node j, that is, the number of devices that have a relationship with device j, reflecting the influence of device j. The initial PageRank value PR(i) of each node is the initial weight W(i); In each iteration, the new PageRank value of each node is calculated based on the current PageRank value, and the stored PageRank vector is updated. The iteration continues until the change in the PageRank value is less than the set threshold ∈, that is, the condition is met: max i |PR(i) (t+1) -PR(i) (t) |< Where PR(i) (t) and PR(i) (t+1) They represent the PageRank values ​​of node i in the tth and t+1th iterations respectively.

8. The method for constructing a workshop data integration control model based on a graph mining algorithm according to claim 1, characterized in that: The step 4 optimizes the constructed workshop equipment relationship network model based on the social network analysis algorithm, specifically: First, each device node is divided into independent communities to form an initial community, and the overall modularity Q is used to judge the rationality of the division: Among them: Q represents modularity, A ij Indicates whether there is a connection between node i and node j, k i and k j is the degree of nodes i and j, i.e. the total number of connections), m is the total number of edges in the workshop equipment relationship network, δ(c i ,c j ) is an indicator function, which takes the value of 1 if nodes i and j belong to the same community, otherwise it takes the value of 0; In the iteration, nodes with higher selection degree are moved, that is, nodes are moved to communities that can improve the overall modularity Q value. The specific optimization criterion is to calculate the modularity increment ΔQ in each iteration and select the community that can maximize the modularity Q value. The increment formula is as follows: Among them, ∑in represents the total number of edges in the community, k i,in represents the number of connections between node i and other nodes in the community, and ∑tot is the total degree of the community; During the iteration process, the overall community division is optimized by continuously trying to move nodes to different communities. If it is found that the connection strength between some nodes is high and the modularity increases, the algorithm will merge these nodes into the same community. This process is repeated until the modularity Q cannot be further improved, indicating that the algorithm has reached a stable state and the optimization of the workshop equipment relationship network model is completed.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer storable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images