Intelligent industrial production equipment management system based on data monitoring

Abstract

An intelligent industrial production equipment management system based on data monitoring relates to the technical field of data monitoring and comprises a monitoring center which is in communication connection with a manual point burying module, a data storage module, a model construction module, an automatic point burying presetting module, a data analysis module, a space prediction module and an automatic point burying module. The manual point burying module is used for setting a fixed monitoring node; the data storage module is used for storing historical index monitoring results; the model construction module is used for constructing a digital twinborn model; the automatic buried point presetting module is used for presetting elastic monitoring nodes; the data analysis module is used for marking index abnormal nodes; the space prediction module is used for constructing a space prediction model; and the automatic point burying module is used for setting an elastic monitoring node according to the occurrence probability of the abnormal index nodes in other areas of the abnormal index nodes, so that prediction, maintenance and replacement are performed before equipment fails, and expensive production interruption is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and specifically to an intelligent industrial production equipment management system based on data monitoring. Background Art

[0002] With the rise of the Industrial 4.0 revolution, the application scope of big data technology in the intelligent production process has been further expanded. Mastering big data technology is of great significance for the manufacturing industry to achieve intelligent production.

[0003] Comparative document CN108803542A, "Industrial production data management system", collects production data generated by various industrial equipment at the industrial site by using a data collector, and then the data storage server stores the production data in the corresponding storage area according to the processing level of the production data, so that the data processing server can quickly obtain the required production data from the data storage server according to the preset analysis instructions, and analyze and process the obtained production data to generate a report corresponding to the analysis instructions, realizing the ability to collect data generated during the production operations of various industrial equipment at the industrial site in real time, quickly and accurately, and quickly and accurately generate various production and management reports during the production process of industrial equipment for the convenience of management personnel to view.

[0004] Comparative document CN111898917A, "Intelligent manufacturing management system based on big data", the intelligent manufacturing shared cloud platform includes a registration and parsing module, an online simulation module, a differential analysis module and a database. The registration and parsing module performs object identification and parsing on object metadata according to the object identifier; the online simulation module configures a simulation environment according to the device attribute information of the machine tool terminal, and performs production simulation in the simulation environment according to the object metadata to obtain production simulation data; the differential analysis module generates a production simulation vector and a production standard vector, calculates the production simulation qualification degree, and then compares the production simulation qualification degree with the production specification value. The present invention realizes the sharing of production information and production lines among manufacturing factories by connecting different machine tool terminals and machine tool user terminals, improving the utilization rate of production resources; In industrial application scenarios, most current real-time data monitoring systems simply use fixed monitoring points for monitoring. However, when faced with a huge data collection workload on the production line, the speed and efficiency of data monitoring will significantly decrease. At the same time, how to use the redundant data generated during the industrial production process for predictive analysis, so as to predict and maintain replacements before equipment failures to avoid expensive production interruptions, is an urgent problem for us to solve. Summary of the Invention

[0005] To solve the above technical problems, the purpose of the present invention is to provide an intelligent industrial production equipment management system based on data monitoring, including a monitoring center, which is communicatively connected with a manual data logging module, a data storage module, a model construction module, an automatic data logging preset module, a data analysis module, a spatial prediction module, and an automatic data logging module; The manual data logging module is used to pre-determine key monitoring indicators to be tracked according to the process flow characteristics of each industrial production equipment in the current industrial production process, and set fixed monitoring nodes in the corresponding industrial production equipment; The data storage module is used to store the historical index monitoring results of each industrial production equipment in several historical monitoring cycles; The model construction module is used to construct a digital twin model according to the physical entities, configuration information, and multi-source heterogeneous data of industrial production equipment in the current industrial production process; The automatic data logging preset module is used to preset elastic monitoring nodes according to the real-time data flow of each instance three-dimensional model in the digital twin model; The data analysis module is used to analyze the index monitoring results of each fixed monitoring node and elastic monitoring node, and mark the nodes that do not meet the threshold standard as index abnormal nodes; The spatial prediction module is used to perform data mining on the index monitoring results in several historical monitoring cycles, construct a spatial prediction model, and obtain the occurrence probability of index abnormal nodes in other regions of the index abnormal nodes according to the spatial prediction model; The automatic data logging module is used to automatically set elastic monitoring nodes according to the occurrence probability of index abnormal nodes in other regions of the index abnormal nodes.

[0006] Further, the process of the manual data logging module pre-determining key monitoring indicators to be tracked according to the process flow characteristics of each industrial production equipment in the current industrial production process and setting fixed monitoring nodes in the corresponding industrial production equipment includes: Obtain the process flow characteristics of the current industrial production equipment, extract process information according to the industrial process characteristics, split the industrial production process according to the process information, and divide it into several process subsequences; Select evaluation indicators according to the process flow characteristics of each process subsequence, set the index weights of the evaluation indicators, and obtain the membership matrix of each process subsequence to the preset importance level through fuzzy comprehensive evaluation; Obtain the importance level of each process subsequence according to the membership matrix and index weights, preset a level threshold, obtain the process subsequences whose importance level is greater than or equal to the level threshold, and set fixed monitoring nodes on the process subsequences; Obtain the key monitoring indicators of each fixed monitoring node by using data retrieval according to the functional characteristics in the process characteristics of the process subsequence.

[0007] Further, the process of the model construction module constructing a digital twin model based on the physical entity, configuration information, and multi-source heterogeneous data of industrial production equipment in the current industrial production process includes: Create a digital space, obtain the physical entity, configuration information, and multi-source heterogeneous data of industrial production equipment in the physical space during the current industrial production process, perform three-dimensional modeling on the industrial production equipment and map it to the data space, and assign attributes to each three-dimensional model according to the configuration information to obtain the corresponding instance three-dimensional model; Obtain the assembly sequence and assembly relationship between each process subsequence in the current industrial production process, use the assembly sequence and assembly relationship between each process subsequence as the connection relationship between nodes, use the instance three-dimensional models of each process subsequence as the nodes of a directed topological graph, and construct a directed topological graph; Set API interfaces on each instance three-dimensional model. The API interfaces are used to connect various monitoring nodes, convert the multi-source heterogeneous data of each process subsequence in the current industrial production process into twin data, and match the twin data with the instance three-dimensional models in the directed topological graph to generate a digital twin model.

[0008] Further, the process of the automatic buried point preset module presetting elastic monitoring nodes according to the real-time data traffic of each instance three-dimensional model in the digital twin model includes: Obtain the real-time data traffic generated by each instance three-dimensional model in the digital twin model during the current monitoring period, set a data traffic threshold, compare the real-time data traffic with the data traffic threshold, and obtain the cumulative time when the real-time data traffic is greater than the data traffic threshold during the current monitoring period; Set a cumulative time threshold, obtain the instance three-dimensional models with a cumulative time greater than the cumulative time threshold, and set elastic monitoring nodes on the API interfaces of the instance three-dimensional models. The elastic monitoring nodes are used to collect all monitoring indicators generated by the instance three-dimensional models.

[0009] Further, the process of the data analysis module analyzing the index monitoring results of each fixed monitoring node and elastic monitoring node and marking the nodes that do not meet the threshold standard as index abnormal nodes includes: Obtain the index monitoring results of each fixed monitoring node and elastic monitoring node, obtain the monitoring index threshold range corresponding to the index monitoring results, compare the index monitoring results with the corresponding monitoring index threshold range, and judge whether each index is within the corresponding monitoring index threshold range; If the said indicator is not within the corresponding monitoring indicator threshold range, mark the corresponding fixed monitoring node or elastic monitoring node as an indicator abnormal node.

[0010] Further, the process of the spatial prediction module performing data mining on the indicator monitoring results in several historical monitoring cycles and constructing a spatial prediction model includes: Obtain the indicator monitoring results in the historical monitoring cycle from the data storage module, locate the positions of the indicator abnormal nodes based on the indicator monitoring results, obtain the historical monitoring cycle to which the indicator abnormal nodes belong, perform data mining on other indicator abnormal nodes within the historical monitoring cycle to which the indicator abnormal nodes belong, and map the said indicator abnormal nodes and other indicator abnormal nodes to the directed topological graph in the digital twin model; Under the condition of obtaining the indicator monitoring results of the indicator abnormal nodes, use the directed path length between other indicator abnormal nodes and the indicator abnormal nodes as input features, and use the occurrence probability of other indicator abnormal nodes when the directed path lengths from the indicator abnormal nodes are different as output features to construct a spatial prediction model based on deep learning, and use the indicator monitoring results in several historical monitoring cycles to train the said spatial prediction model to obtain a spatial prediction model that has completed iterative training.

[0011] Further, the process of the spatial prediction module obtaining the occurrence probability of indicator abnormal nodes appearing in other regions of the indicator abnormal nodes according to the spatial prediction model includes: If an indicator abnormal node is generated in the current monitoring cycle, obtain the indicator monitoring results of the indicator abnormal node, input the indicator monitoring results of the indicator abnormal node into the spatial prediction model, and obtain the occurrence probability of other indicator abnormal nodes when the directed path lengths from the indicator abnormal node are different through the said spatial prediction model.

[0012] Further, the process of the automatic data logging module automatically setting elastic monitoring nodes according to the occurrence probability of indicator abnormal nodes appearing in other regions of the indicator abnormal nodes includes: Set a probability threshold, obtain the occurrence probability of other indicator abnormal nodes when the directed path lengths from the indicator abnormal node are different, and compare the said occurrence probability with the probability threshold; If the said occurrence probability is greater than or equal to the probability threshold, obtain the directed path length from the indicator abnormal node to which the occurrence probability belongs, obtain the target process subsequence according to the said directed path length, and judge whether an elastic monitoring node is set in the target process subsequence in the current monitoring cycle; If no elastic monitoring node is set in the target process subsequence in the current monitoring cycle, set an elastic monitoring node in the target process subsequence in the current monitoring cycle.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Manual data logging is performed on key industrial production equipment, fixed monitoring nodes are set, and key parameters in the fixed monitoring nodes are accurately monitored. For example, special parameters in a certain special process can be used to very precisely control the parameters to be monitored, obtain the required data, thereby evaluating the performance of these devices in real time and predicting maintenance needs in a timely manner. At the same time, by collecting data on key steps in the production process, insights for improving processes, increasing production, and reducing waste can be obtained, such as reducing changeover times or optimizing operating parameters.

[0014] 2. When the workload of data collection on the production line is huge, automatic data logging can reduce the human burden, reduce the error rate, and improve the speed and efficiency of data collection. Analyze a large amount of redundant historical data, use this data to run the spatial prediction module, and then automatically set elastic monitoring nodes according to the probability of occurrence of indicator anomaly nodes in other areas of the indicator anomaly nodes, so as to quickly adapt to changes in indicator anomalies in the production process and improve the flexibility and scalability of data logging.

[0015] 3. Use data logging technology to collect equipment operation data and use this data to run the spatial prediction module, which can predict and maintain replacements before equipment failures to avoid expensive production interruptions. Description of the Drawings

[0016] Figure 1 It is a schematic diagram of an intelligent industrial production equipment management system based on data monitoring according to an embodiment of the present application. Detailed Embodiments

[0017] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0018] As Figure 1 shown, an intelligent industrial production equipment management system based on data monitoring includes a monitoring center, and the monitoring center is communicatively connected to a manual data logging module, a data storage module, a model building module, an automatic data logging preset module, a data analysis module, a spatial prediction module, and an automatic data logging module; The manual data logging module is used to pre-determine key monitoring indicators to be tracked according to the process characteristics of each industrial production equipment in the current industrial production process, and set fixed monitoring nodes in the corresponding industrial production equipment; The data storage module is used to store the historical index monitoring results of each industrial production device in several historical monitoring cycles; The model construction module is used to construct a digital twin model based on the physical entities, configuration information, and multi-source heterogeneous data of industrial production devices in the current industrial production process; The automatic logging preset module is used to preset elastic monitoring nodes according to the real-time data traffic of each instance three-dimensional model in the digital twin model; The data analysis module is used to analyze the index monitoring results of each fixed monitoring node and elastic monitoring node, and mark the nodes that do not meet the threshold standard as index abnormal nodes; The space prediction module is used to perform data mining on the index monitoring results in several historical monitoring cycles, construct a space prediction model, and obtain the occurrence probability of index abnormal nodes in other regions of the index abnormal nodes according to the space prediction model; The automatic logging module is used to automatically set elastic monitoring nodes according to the occurrence probability of index abnormal nodes in other regions of the index abnormal nodes.

[0019] It should be further noted that in the specific implementation process, the process of the manual logging module pre-determining the key monitoring indicators to be traced according to the technological process characteristics of each industrial production device in the current industrial production process and setting fixed monitoring nodes in the corresponding industrial production device includes: Obtain the technological process characteristics of the current industrial production device, extract process information according to the industrial process characteristics, and split the industrial production process according to the process information into several process subsequences; Select evaluation indicators according to the technological process characteristics of each process subsequence, set the index weights of the evaluation indicators, and obtain the membership degree matrix of each process subsequence to the preset importance level through fuzzy comprehensive evaluation; Obtain the importance level of each process subsequence according to the membership degree matrix and index weights, preset a level threshold, obtain the process subsequences whose importance level is greater than or equal to the level threshold, and set fixed monitoring nodes on the process subsequences; Place logs on key mechanical components, such as installing sensors on motors, pumps, or compressors, to monitor their power usage, temperature, vibration, and sound, etc., so as to evaluate the performance of these devices and predict maintenance needs in a timely manner; Utilize data retrieval to obtain the key monitoring indicators of each fixed monitoring node according to the functional characteristics in the technological process characteristics of the process subsequence, such as the on / off state, temperature, pressure, production line speed, etc. of the machine.

[0020] It should be further noted that in the specific implementation process, the process of the model construction module constructing a digital twin model based on the physical entities, configuration information, and multi-source heterogeneous data of industrial production equipment in the current industrial production process includes: Create a digital space, obtain the physical entities, configuration information, and multi-source heterogeneous data of industrial production equipment in the physical space during the current industrial production process, perform three-dimensional modeling on the industrial production equipment and map it to the data space, and assign attributes to each three-dimensional model according to the configuration information to obtain the corresponding instance three-dimensional model; Obtain the assembly sequence and assembly relationship between each process subsequence in the current industrial production process, use the assembly sequence and assembly relationship between each process subsequence as the connection relationship between nodes, use the instance three-dimensional models of each process subsequence as the nodes of a directed topological graph, and construct a directed topological graph; Set API interfaces on each instance three-dimensional model. The API interfaces are used to connect various monitoring nodes, convert the multi-source heterogeneous data of each process subsequence in the current industrial production process into twin data, and match the twin data with the instance three-dimensional models in the directed topological graph to generate a digital twin model.

[0021] It should be further noted that in the specific implementation process, the process of the automatic buried point preset module presetting elastic monitoring nodes according to the real-time data traffic of each instance three-dimensional model in the digital twin model includes: Obtain the real-time data traffic generated by each instance three-dimensional model in the digital twin model during the current monitoring period, set a data traffic threshold, compare the real-time data traffic with the data traffic threshold, and obtain the cumulative time when the real-time data traffic is greater than the data traffic threshold during the current monitoring period; Set a cumulative time threshold, obtain the instance three-dimensional models with the cumulative time greater than the cumulative time threshold, and set elastic monitoring nodes on the API interfaces of the instance three-dimensional models. The elastic monitoring nodes are used to collect all monitoring indicators generated by the instance three-dimensional models.

[0022] It should be further noted that in the specific implementation process, the process of the data analysis module analyzing the index monitoring results of each fixed monitoring node and elastic monitoring node and marking the nodes that do not meet the threshold standard as index abnormal nodes includes: Obtain the index monitoring results of each fixed monitoring node and elastic monitoring node, obtain the monitoring index threshold range corresponding to the index monitoring results, compare the index monitoring results with the corresponding monitoring index threshold range, and judge whether each index is within the corresponding monitoring index threshold range; If the index is not within the corresponding monitoring index threshold range, mark the corresponding fixed monitoring node or elastic monitoring node as an index abnormal node.

[0023] It should be further noted that in the specific implementation process, the process of the spatial prediction module performing data mining on the index monitoring results in a number of historical monitoring cycles and constructing a spatial prediction model includes: Obtaining the index monitoring results in the historical monitoring cycle from the data storage module, locating the position of the index anomaly node based on the index monitoring results, obtaining the historical monitoring cycle to which the index anomaly node belongs, performing data mining on other index anomaly nodes in the historical monitoring cycle to which the index anomaly node belongs, and mapping the index anomaly node and other index anomaly nodes to the directed topological graph in the digital twin model; Under the condition of obtaining the index monitoring results of the index anomaly node, using the directed path length between other index anomaly nodes and the index anomaly node as the input feature, and using the occurrence probability of other index anomaly nodes appearing at different directed path lengths from the index anomaly node as the output feature to construct a spatial prediction model based on deep learning, and training the spatial prediction model with the index monitoring results in a number of historical monitoring cycles to obtain a spatial prediction model that has completed iterative training.

[0024] It should be further noted that in the specific implementation process, the process of the spatial prediction module obtaining the occurrence probability of an index anomaly node appearing in other regions according to the spatial prediction model includes: If an index anomaly node is generated in the current monitoring cycle, obtain the index monitoring results of the index anomaly node, input the index monitoring results of the index anomaly node into the spatial prediction model, and obtain the occurrence probability of other index anomaly nodes appearing at different directed path lengths from the index anomaly node through the spatial prediction model.

[0025] It should be further noted that in the specific implementation process, the process of the automatic data logging module automatically setting elastic monitoring nodes according to the occurrence probability of an index anomaly node appearing in other regions of the index anomaly node includes: Set a probability threshold, obtain the occurrence probability of other index anomaly nodes appearing at different directed path lengths from the index anomaly node, and compare the occurrence probability with the probability threshold; If the occurrence probability is greater than or equal to the probability threshold, obtain the directed path length from the index anomaly node to which the occurrence probability belongs, obtain the target process subsequence according to the directed path length, and determine whether an elastic monitoring node is set in the target process subsequence in the current monitoring cycle; If no elastic monitoring node is set in the target process subsequence in the current monitoring cycle, set an elastic monitoring node in the target process subsequence in the current monitoring cycle.

[0026] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent industrial production equipment management system based on data monitoring, including a monitoring center, characterized in that, The monitoring center is communicatively connected with a manual data logging module, a data storage module, a model construction module, an automatic data logging preset module, a data analysis module, a spatial prediction module, and an automatic data logging module; The manual data logging module is used to pre-determine key monitoring indicators to be tracked according to the technological process characteristics of each industrial production device in the current industrial production process, and set fixed monitoring nodes in the corresponding industrial production devices; The data storage module is used to store the historical index monitoring results of each industrial production device in several historical monitoring cycles; The model construction module is used to construct a digital twin model based on the physical entities, configuration information, and multi-source heterogeneous data of industrial production devices in the current industrial production process; The automatic data logging preset module is used to preset elastic monitoring nodes according to the real-time data traffic of each instance three-dimensional model in the digital twin model; The data analysis module is used to analyze the index monitoring results of each fixed monitoring node and elastic monitoring node, and mark the nodes that do not meet the threshold standard as index anomaly nodes; The spatial prediction module is used to perform data mining on the index monitoring results in several historical monitoring cycles, construct a spatial prediction model, and obtain the occurrence probability of index anomaly nodes in other regions based on the spatial prediction model; The automatic data logging module is used to automatically set elastic monitoring nodes according to the occurrence probability of index anomaly nodes in other regions of the index anomaly nodes; 2. The intelligent industrial production equipment management system based on data monitoring according to claim 1, characterized in that, The process by which the manual data logging module pre-determines key monitoring indicators to be tracked according to the technological process characteristics of each industrial production device in the current industrial production process and sets fixed monitoring nodes in the corresponding industrial production devices includes: Obtain the technological process characteristics of the current industrial production device, extract process information according to the industrial process characteristics, split the industrial production process according to the process information, and divide it into several process subsequences; Select evaluation indicators according to the technological process characteristics of each process subsequence, set the index weights of the evaluation indicators, and obtain the membership matrix of each process subsequence for the preset importance level through fuzzy comprehensive evaluation; Obtain the importance level of each process subsequence according to the membership matrix and index weights, preset a level threshold, obtain the process subsequences whose importance level is greater than or equal to the level threshold, and set fixed monitoring nodes on the process subsequences; Use data retrieval to obtain the key monitoring indicators of each fixed monitoring node according to the functional characteristics in the technological process characteristics of the process subsequence; 3. An intelligent industrial production equipment management system based on data monitoring according to claim 2, characterized in that, The process by which the model construction module constructs a digital twin model based on the physical entities, configuration information, and multi-source heterogeneous data of industrial production devices in the current industrial production process includes: Create a digital space, obtain the physical entities, configuration information, and multi-source heterogeneous data of industrial production devices in the physical space in the current industrial production process, map the industrial production devices to the data space through three-dimensional modeling, and assign attributes to each three-dimensional model according to the configuration information to obtain the corresponding instance three-dimensional model; Obtain the assembly sequence and assembly relationship between each process subsequence in the current industrial production process. Take the assembly sequence and assembly relationship between each process subsequence as the connection relationship between nodes, and take the instance three-dimensional models of each process subsequence as the nodes of the directed topological graph to construct a directed topological graph; Set API interfaces on each instance three-dimensional model. The API interfaces are used to connect various monitoring nodes, convert the multi-source heterogeneous data of each process subsequence in the current industrial production process into twin data, and match the twin data with the instance three-dimensional models in the directed topological graph to generate a digital twin model.

4. An intelligent industrial production equipment management system based on data monitoring according to claim 3, characterized in that, The process of the automatic buried point preset module presetting elastic monitoring nodes according to the real-time data traffic of each instance three-dimensional model in the digital twin model includes: Obtain the real-time data traffic generated by each instance three-dimensional model in the digital twin model during the current monitoring period, set a data traffic threshold, compare the real-time data traffic with the data traffic threshold, and obtain the cumulative time when the real-time data traffic is greater than the data traffic threshold during the current monitoring period; Set a cumulative time threshold, obtain the instance three-dimensional models with the cumulative time greater than the cumulative time threshold, and set elastic monitoring nodes on the API interfaces of the instance three-dimensional models. The elastic monitoring nodes are used to collect all monitoring indicators generated by the instance three-dimensional models.

5. An intelligent industrial production equipment management system based on data monitoring according to claim 4, characterized in that, The process of the data analysis module analyzing the index monitoring results of each fixed monitoring node and elastic monitoring node and marking the nodes that do not meet the threshold standard as index abnormal nodes includes: Obtain the index monitoring results of each fixed monitoring node and elastic monitoring node, obtain the monitoring index threshold range corresponding to the index monitoring results, compare the index monitoring results with the corresponding monitoring index threshold range, and judge whether each index is within the corresponding monitoring index threshold range; If the index is not within the corresponding monitoring index threshold range, mark the corresponding fixed monitoring node or elastic monitoring node as an index abnormal node.

6. An intelligent industrial production equipment management system based on data monitoring according to claim 5, characterized in that, The process of the space prediction module performing data mining on the index monitoring results in several historical monitoring periods and constructing a space prediction model includes: Obtain the index monitoring results in the historical monitoring period from the data storage module, perform location positioning of the index abnormal nodes based on the index monitoring results, obtain the historical monitoring period to which the index abnormal nodes belong, perform data mining on other index abnormal nodes in the historical monitoring period to which the index abnormal nodes belong, and map the index abnormal nodes and other index abnormal nodes to the directed topological graph in the digital twin model; Under the condition of obtaining the index monitoring results of the index abnormal nodes, use the directed path length between other index abnormal nodes and the index abnormal nodes as input features, and use the occurrence probability of other index abnormal nodes when the distance from the index abnormal nodes is different in the directed path length as output features to construct a space prediction model based on deep learning, and train the space prediction model with the index monitoring results in several historical monitoring periods to obtain a space prediction model that has completed iterative training.

7. An intelligent industrial production equipment management system based on data monitoring according to claim 6, characterized in that, The process by which the spatial prediction module obtains the occurrence probability of an index anomaly node in other regions based on the spatial prediction model includes: If an index anomaly node is generated in the current monitoring period, obtain the index monitoring result of the index anomaly node, input the index monitoring result of the index anomaly node into the spatial prediction model, and obtain the occurrence probability of other index anomaly nodes when the directed path lengths from the index anomaly node are different through the spatial prediction model.

8. An intelligent industrial production equipment management system based on data monitoring according to claim 7, characterized in that, The process by which the automatic logging module automatically sets elastic monitoring nodes according to the occurrence probability of an index anomaly node in other regions of the index anomaly node includes: Set a probability threshold, obtain the occurrence probability of other index anomaly nodes when the directed path lengths from the index anomaly node are different, and compare the occurrence probability with the probability threshold; If the occurrence probability is greater than or equal to the probability threshold, obtain the directed path length from the index anomaly node to which the occurrence probability belongs, obtain the target process subsequence according to the directed path length, and determine whether an elastic monitoring node is set for the target process subsequence in the current monitoring period; If no elastic monitoring node is set for the target process subsequence in the current monitoring period, set an elastic monitoring node for the target process subsequence in the current monitoring period.

Images