Self-adaptive anti-explosion monitoring method and system based on multi-source data fusion

Abstract

The invention relates to the technical field of explosion-proof data fusion, in particular to a self-adaptive explosion-proof monitoring method and system based on multi-source data fusion, and the method comprises the steps: querying an explosion-proof monitoring distribution node set in an explosion-proof monitoring environment, carrying out the explosion-proof importance analysis of the explosion-proof monitoring distribution node set, and obtaining an explosion-proof importance vector set; performing data fusion node clustering based on the explosion-proof monitoring distribution node set to obtain a plurality of data fusion nodes, determining a plurality of to-be-fused distribution nodes in the explosion-proof monitoring distribution node set based on the data fusion nodes, performing monitoring data communication on the extracted data fusion nodes by using the plurality of to-be-fused distribution nodes to obtain data receiving nodes, and sending the data receiving nodes to the explosion-proof monitoring distribution node set. And performing explosion-proof data fusion according to the plurality of data receiving nodes and the explosion-proof importance vector set to obtain an explosion-proof monitoring report. According to the invention, the accuracy and reliability of identifying the abnormal event in explosion-proof monitoring can be improved, and the risk of missing report of the abnormal event is reduced.

Description

Technical Field

[0001] This invention relates to the field of explosion-proof data fusion technology, and in particular to an adaptive explosion-proof monitoring method and system based on multi-source data fusion. Background Technology

[0002] In high-risk industrial environments such as chemical plants and oil storage tank areas, accurate and effective explosion-proof monitoring is a core element in ensuring the safety of life and property. With the increase in the number of monitoring nodes and the increasing complexity of data types, how to adaptively identify real risk signs from multi-source heterogeneous data and achieve efficient and reliable data transmission and fusion has become a key technical challenge for improving the level of industrial safety monitoring.

[0003] Traditional explosion-proof monitoring methods typically employ centralized data collection or simple polling mechanisms. Their drawbacks include the inability to differentiate the importance of monitoring nodes, resulting in insufficient early warning sensitivity; uneven node communication loads, which can easily lead to network congestion and data loss; and the overload of information in the explosion-proof center caused by the reporting of all data, which affects decision-making efficiency. Summary of the Invention

[0004] This invention provides an adaptive explosion-proof monitoring method based on multi-source data fusion and a computer-readable storage medium. Its main purpose is to improve the accuracy and reliability of identifying abnormal events in explosion-proof monitoring and reduce the risk of missed abnormal events.

[0005] To achieve the above objectives, the present invention provides an adaptive explosion-proof monitoring method based on multi-source data fusion, comprising: Once the explosion-proof monitoring environment is identified, the explosion-proof monitoring distribution node set in the explosion-proof monitoring environment is queried. The explosion-proof monitoring distribution node set includes multiple explosion-proof monitoring distribution nodes, and each explosion-proof monitoring distribution node contains a monitoring sensor. An explosion-proof importance analysis is performed on the explosion-proof monitoring distribution node set to obtain an explosion-proof importance vector set, which includes multiple explosion-proof importance vectors. Data fusion nodes are clustered based on the explosion-proof monitoring distributed node set to obtain multiple data fusion nodes. Each data fusion node corresponds to multiple explosion-proof monitoring distributed nodes, and the data fusion node contains a data storage repository. Data fusion nodes are extracted sequentially from multiple data fusion nodes, and multiple distribution nodes to be fused are determined from the explosion-proof monitoring distribution node set based on the extracted data fusion nodes. By using multiple distributed nodes to be merged to monitor data communication with the extracted data fusion nodes, the data receiving nodes are obtained; The data receiving nodes are aggregated to obtain multiple data receiving nodes. Explosion-proof data is fused based on the multiple data receiving nodes and the explosion-proof importance vector set to obtain an explosion-proof monitoring report. Adaptive explosion-proof monitoring based on multi-source data fusion is completed based on the explosion-proof monitoring report.

[0006] Optionally, the step of performing explosion-proof importance analysis on the explosion-proof monitoring distribution node set to obtain an explosion-proof importance vector set includes: Perform the following operations on each explosion-proof monitoring distribution node in the explosion-proof monitoring distribution node set: Query the monitoring node anomaly dataset corresponding to the explosion-proof monitoring distribution node in the pre-built anomaly sensor database. The monitoring node anomaly dataset includes anomaly data from multiple monitoring nodes. Based on the abnormal dataset of monitoring nodes, the explosion-proof importance of the distributed nodes of explosion-proof monitoring is analyzed to obtain the explosion-proof importance vector; The explosion-proof importance vectors corresponding to each explosion-proof monitoring distribution node are summarized to obtain the explosion-proof importance vector set.

[0007] Optionally, before querying the monitoring node anomaly dataset corresponding to the explosion-proof monitoring distribution node in the pre-built anomaly sensor database, the method further includes: Configure multiple alarm event types, and perform the following operation for each of the multiple alarm event types: Based on the types of alarm events and the preset query period, the alarm events in the explosion-proof monitoring environment are queried to obtain a set of historical alarm events, which includes multiple historical alarm events. Extract historical alarm events sequentially from the historical alarm event set; Based on the extracted historical alarm events and the preset backtracking period, the explosion-proof monitoring distribution node set is subjected to source tracing analysis to obtain abnormal sensor data. The abnormal sensor data includes: abnormal monitoring distribution node set and abnormal node acquisition parameter set. The abnormal monitoring distribution nodes in the abnormal monitoring distribution node set correspond one-to-one with the abnormal node acquisition parameters in the abnormal node acquisition parameter set. Summarize the abnormal sensor data corresponding to each historical alarm event to obtain the abnormal sensor dataset; The abnormal sensor datasets corresponding to each alarm event type are aggregated to obtain the abnormal sensor database, which includes multiple abnormal sensor data.

[0008] Optionally, the step of performing explosion-proof importance analysis on the explosion-proof monitoring distribution nodes based on the monitoring node anomaly dataset to obtain an explosion-proof importance vector includes: Extract abnormal data of monitoring nodes sequentially from the abnormal dataset of monitoring nodes; Based on the explosion-proof monitoring distributed nodes, an abnormal monitoring collection parameter set is identified in the extracted abnormal monitoring node data, wherein the abnormal monitoring collection parameter set includes one or more abnormal monitoring collection parameters; The abnormal monitoring and collection parameter set is divided according to multiple alarm event types to obtain multiple alarm collection parameter sets, in which each alarm collection parameter set corresponds one-to-one with an alarm event type. The alarm collection parameter sets are extracted sequentially from multiple alarm collection parameter sets, and the node alarm importance of the extracted alarm collection parameter sets is calculated. Summarize the alarm importance of each node corresponding to each alarm collection parameter set to obtain the alarm importance of multiple nodes; Construct a node explosion-proof importance vector based on the alarm importance of multiple nodes; The explosion-proof importance vector of each monitoring node is summarized to obtain the node explosion-proof importance vector set. The node explosion-proof importance vector set is then averaged to obtain the explosion-proof importance vector.

[0009] Optionally, the calculation of the node alarm importance of the extracted alarm acquisition parameter set includes: Identify the total frequency of alarm data occurrences of the explosion-proof monitoring distribution nodes in the abnormal sensor database; Based on the query period, abnormal data statistics are performed on the distributed nodes of explosion-proof monitoring to obtain the total frequency of abnormal data occurrences. Obtain the normal sensor parameter range based on the explosion-proof monitoring distribution nodes; Based on the normal sensor parameter range, the deviation of the alarm acquisition parameter set is calculated to obtain the abnormal deviation value set of alarm parameters. The importance of a node alarm is calculated based on the abnormal deviation value set of alarm parameters, the total frequency of alarm data occurrence, and the total frequency of abnormal data occurrence.

[0010] Optionally, the importance of the node alarm is represented as: in, Indicates the importance of node alarms. This indicates the number of abnormal deviation values ​​for alarm parameters within the set of abnormal deviation values. This represents the first value in the set of abnormal deviation values ​​of alarm parameters. Abnormal deviation values ​​of alarm parameters This indicates the total frequency of abnormal data occurrences. This indicates the total frequency of alarm data occurrences.

[0011] Optionally, the data fusion node clustering based on the explosion-proof monitoring distributed node set yields multiple data fusion nodes, including: Obtain the location of each explosion-proof monitoring distribution node in the explosion-proof monitoring distribution node set to obtain the distribution node location set; The explosion-proof monitoring distribution node set is classified into two categories based on the distribution node location set to obtain classified monitoring distribution node clusters. Each classified monitoring distribution node cluster includes two classified monitoring distribution node clusters, and each classified monitoring distribution node cluster includes multiple explosion-proof monitoring distribution nodes. In the classification monitoring distribution node cluster group, the classification monitoring distribution node clusters are extracted sequentially, and the data transmission congestion of the extracted classification monitoring distribution node clusters is evaluated to obtain the data transmission congestion degree; If the data transmission congestion is greater than the preset standard congestion, the extracted classified monitoring distribution node clusters are taken as the explosion-proof monitoring distribution node set, and the step of binary classification of the explosion-proof monitoring distribution node set based on the distribution node location set is returned until the data transmission congestion is not greater than the standard congestion. If the data transmission congestion is not greater than the standard congestion, the extracted classified monitoring distribution node clusters are recorded as the same type of monitoring distribution node clusters. Data fusion nodes are constructed based on clusters of similar monitoring distribution nodes; The data fusion nodes are aggregated to obtain multiple data fusion nodes.

[0012] Optionally, the step of using multiple distributed nodes to be fused to monitor data communication with the extracted data fusion nodes to obtain data receiving nodes includes: Multiple automatic polling instruction frames are generated based on multiple distributed nodes to be merged. Each automatic polling instruction frame corresponds one-to-one with a distributed node to be merged, and each automatic polling instruction frame includes: node address code, function code, register start address and check code. Based on the data fusion node, multiple automatic polling command frames are sent to multiple distributed nodes to be fused, resulting in multiple data monitoring nodes; Data acquisition is performed based on multiple data monitoring nodes to obtain multiple raw sensor data, where each raw sensor data corresponds one-to-one with a data monitoring node. Multiple raw sensor data are packaged to obtain multiple sensor response data frames, which are then returned to the data fusion node to obtain the data receiving node.

[0013] Optionally, the step of fusing explosion-proof data based on multiple data receiving nodes and an explosion-proof importance vector set to obtain an explosion-proof monitoring report includes: Perform the following operation on each of the multiple data receiving nodes: Multiple receive response data frames are identified in the data receiving node. The multiple receive response data frames are parsed to obtain multiple receiving node data. The receiving node data includes: receiving node address code and receiving node acquisition parameters. Perform the following operation on each of the multiple receiving node data: The receiving distribution nodes are determined based on the receiving node address codes in the receiving node data, and the receiving importance vector is determined based on the receiving distribution nodes in the explosion-proof importance vector set. The node anomaly index is calculated based on the received importance vector and the received node acquisition parameters in the received node data. If the node anomaly index is greater than the preset anomaly index threshold, the received node data is marked using the node anomaly index to obtain marked node data. By aggregating the labeled node data, multiple labeled node data sets are obtained. By aggregating the multiple labeled node data sets corresponding to each data receiving node, a labeled node dataset is obtained. Generate an explosion-proof monitoring report based on the marked node dataset.

[0014] To achieve the above objectives, the present invention also provides an adaptive explosion-proof monitoring system based on multi-source data fusion, comprising: The monitoring environment determination module is used to identify the explosion-proof monitoring environment and query the explosion-proof monitoring distribution node set in the explosion-proof monitoring environment. The explosion-proof monitoring distribution node set includes multiple explosion-proof monitoring distribution nodes, and each explosion-proof monitoring distribution node contains a monitoring sensor. The fusion node clustering module is used to perform explosion-proof importance analysis on the explosion-proof monitoring distribution node set to obtain an explosion-proof importance vector set. The explosion-proof importance vector set includes multiple explosion-proof importance vectors. Based on the explosion-proof monitoring distribution node set, data fusion node clustering is performed to obtain multiple data fusion nodes. Each data fusion node corresponds to multiple explosion-proof monitoring distribution nodes, and the data fusion node contains a data storage repository. The distributed node setting module is used to extract data fusion nodes sequentially from multiple data fusion nodes, and determine multiple distributed nodes to be fused in the explosion-proof monitoring distributed node set based on the extracted data fusion nodes; The monitoring report generation module is used to communicate monitoring data with the extracted data fusion nodes using multiple distributed nodes to be fused, obtain data receiving nodes, summarize the data receiving nodes, obtain multiple data receiving nodes, and perform explosion-proof data fusion based on multiple data receiving nodes and explosion-proof importance vector set to obtain an explosion-proof monitoring report.

[0015] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: Memory, storing at least one instruction; The processor executes the instructions stored in the memory to implement the adaptive explosion-proof monitoring method based on multi-source data fusion described above.

[0016] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned adaptive explosion-proof monitoring method based on multi-source data fusion.

[0017] To address the problems described in the background art, this invention first performs explosion-proof importance analysis on the distributed explosion-proof monitoring node set to obtain an explosion-proof importance vector set. This step generates a dynamic importance vector for each monitoring node through explosion-proof importance analysis. Compared to the static approach in existing technologies where all nodes are treated equally, this method can more accurately identify nodes with a critical impact on explosion-proof early warning, thereby optimizing the allocation of monitoring resources and improving the sensitivity of abnormal event identification. Furthermore, this scheme performs data fusion node clustering based on the distributed explosion-proof monitoring node set to obtain multiple data fusion nodes. This step uses an adaptive clustering algorithm to group the monitoring nodes, and... Dynamically adjusting cluster size based on data transmission congestion effectively solves the network congestion problem caused by dense node deployment in existing technologies, reduces packet loss rate and communication latency, and enhances the stability and real-time performance of the monitoring system. Finally, explosion-proof data is fused based on multiple data receiving nodes and explosion-proof importance vector sets to obtain an explosion-proof monitoring report. This step combines importance vectors to fuse and analyze the collected data, and uses node anomaly indices to filter high-risk information and generate explosion-proof monitoring reports. This avoids system overload caused by reporting all data in existing technologies, making the reported content more targeted and improving the accuracy and response speed of the explosion-proof center's decisions. Therefore, this invention can improve the accuracy and reliability of identifying abnormal events in explosion-proof monitoring and reduce the risk of missed anomaly reports. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating an adaptive explosion-proof monitoring method based on multi-source data fusion provided in an embodiment of the present invention. Figure 2 A functional block diagram of an adaptive explosion-proof monitoring system based on multi-source data fusion provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device that implements the adaptive explosion-proof monitoring method based on multi-source data fusion, according to an embodiment of the present invention.

[0019] Explanation of reference numerals in the attached figures: 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0020] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0022] This application provides an adaptive explosion-proof monitoring method based on multi-source data fusion. The executing entity of the adaptive explosion-proof monitoring method based on multi-source data fusion includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the adaptive explosion-proof monitoring method based on multi-source data fusion can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0023] Reference Figure 1 The diagram shown is a flowchart illustrating an adaptive explosion-proof monitoring method based on multi-source data fusion according to an embodiment of the present invention. In this embodiment, the adaptive explosion-proof monitoring method based on multi-source data fusion includes: S1. Confirm the explosion-proof monitoring environment and query the explosion-proof monitoring distribution node set in the explosion-proof monitoring environment. The explosion-proof monitoring distribution node set includes multiple explosion-proof monitoring distribution nodes, and each explosion-proof monitoring distribution node contains a monitoring sensor.

[0024] It is clear that the explosion-proof monitoring environment refers to industrial sites or areas requiring explosion protection, such as chemical plant production workshops, oil storage tank areas, coal mine underground tunnels, and gas transmission pipelines. The explosion-proof monitoring distribution node set refers to the set of nodes in the explosion-proof monitoring environment used to monitor for abnormal situations. Each explosion-proof monitoring distribution node refers to a specific monitoring point within the explosion-proof monitoring environment, including monitoring sensors, communication equipment, power supply units, and protective enclosures. Monitoring sensors are sensors used to collect specific parameters; for example, if the explosion-proof monitoring distribution node is located at a gas pipeline pressure monitoring point, then the monitoring sensor in that node is a pressure sensor. The communication equipment refers to devices that transmit data with the data fusion node, such as ZigBee wireless modules and LoRa long-range radio modules.

[0025] S2. Perform explosion-proof importance analysis on the explosion-proof monitoring distribution node set to obtain the explosion-proof importance vector set, which includes multiple explosion-proof importance vectors.

[0026] Understandably, the explosion-proof importance vector set refers to a collection of multiple explosion-proof importance vectors. The explosion-proof importance vector refers to the importance vector of a certain explosion-proof monitoring distribution node for explosion-proof early warning. Each vector element in the explosion-proof importance vector corresponds to an alarm event type. The alarm event types and the method of obtaining the explosion-proof importance vector will be detailed in subsequent embodiments.

[0027] In detail, the explosion-proof importance analysis of the explosion-proof monitoring distribution node set to obtain the explosion-proof importance vector set includes: Perform the following operations on each explosion-proof monitoring distribution node in the explosion-proof monitoring distribution node set: Query the monitoring node anomaly dataset corresponding to the explosion-proof monitoring distribution node in the pre-built anomaly sensor database. The monitoring node anomaly dataset includes anomaly data from multiple monitoring nodes. Based on the abnormal dataset of monitoring nodes, the explosion-proof importance of the distributed nodes of explosion-proof monitoring is analyzed to obtain the explosion-proof importance vector; The explosion-proof importance vectors corresponding to each explosion-proof monitoring distribution node are summarized to obtain the explosion-proof importance vector set.

[0028] It is clear that the aforementioned abnormal sensor database refers to a collection of data collected in the past by multiple artificially constructed explosion-proof monitoring distribution nodes. This abnormal sensor database consists of data from multiple abnormal sensors, and the specific construction method of this abnormal sensor database will be detailed in subsequent embodiments. The monitoring node abnormal dataset refers to the abnormal sensor data in the abnormal sensor database that contains explosion-proof monitoring nodes. The presence of explosion-proof monitoring nodes means that the abnormal monitoring distribution node set in the abnormal sensor data contains explosion-proof monitoring nodes.

[0029] Specifically, before querying the monitoring node anomaly dataset corresponding to the explosion-proof monitoring distribution node in the pre-built anomaly sensor database, the method further includes: Configure multiple alarm event types, and perform the following operation for each of the multiple alarm event types: Based on the types of alarm events and the preset query period, the alarm events in the explosion-proof monitoring environment are queried to obtain a set of historical alarm events, which includes multiple historical alarm events. Extract historical alarm events sequentially from the historical alarm event set; Based on the extracted historical alarm events and the preset backtracking period, the explosion-proof monitoring distribution node set is subjected to source tracing analysis to obtain abnormal sensor data. The abnormal sensor data includes: abnormal monitoring distribution node set and abnormal node acquisition parameter set. The abnormal monitoring distribution nodes in the abnormal monitoring distribution node set correspond one-to-one with the abnormal node acquisition parameters in the abnormal node acquisition parameter set. Summarize the abnormal sensor data corresponding to each historical alarm event to obtain the abnormal sensor dataset; The abnormal sensor datasets corresponding to each alarm event type are aggregated to obtain the abnormal sensor database, which includes multiple abnormal sensor data.

[0030] It should be explained that the alarm event types refer to the types of abnormal events that may cause an explosion in the explosion-proof monitoring environment, which are set by humans. For example, the alarm event types are: excessive concentration of combustible gas, abnormal increase in ambient temperature, sudden change in pressure, insufficient oxygen concentration, etc. These alarm event types can be set by summarizing the alarms that occurred in the explosion-proof monitoring environment in the past period. For example, by analyzing the safety logs of a chemical plant in the past year, it was found that the main alarm causes were methane leakage (corresponding to excessive concentration of combustible gas) and reactor overpressure (corresponding to sudden change in pressure). Therefore, these two types are set as the main alarm event types.

[0031] Furthermore, the query period refers to a manually set time interval for statistically analyzing the frequency of historical alarm events, such as one month or one quarter. The historical alarm event set refers to a collection of multiple alarm events related to alarm event types found in the explosion-proof monitoring environment within the query period. For example, if an alarm event type is "combustible gas concentration exceeding the standard," and within the query period, the explosion-proof monitoring environment experiences: a combustible gas concentration exceeding the standard event at point A in the reaction zone and a combustible gas concentration exceeding the standard event at point B in the storage tank area, then the historical alarm event set corresponding to this alarm event type is: {combustible gas concentration exceeding the standard event at point A in the reaction zone and combustible gas concentration exceeding the standard event at point B in the storage tank area}.

[0032] Understandably, the backtracking period refers to a manually set period for querying the parameters collected by all explosion-proof monitoring distribution nodes before a historical alarm event occurs. For example, 24 hours before each historical alarm event occurs. The purpose is to analyze which explosion-proof monitoring distribution nodes' parameters have shown abnormal signs before the abnormal event occurs. The abnormal sensor data refers to the set of average values ​​of parameters collected by all explosion-proof monitoring distribution nodes within the backtracking period. The abnormal monitoring distribution node set refers to the set of all explosion-proof monitoring distribution nodes within the backtracking period, and the abnormal node collected parameter set refers to the set of average values ​​of parameters collected by all explosion-proof monitoring distribution nodes within the backtracking period. The abnormal node collected parameter set corresponds one-to-one with the abnormal monitoring distribution node. The aforementioned source analysis of the explosion-proof monitoring distribution node set refers to querying the set of average values ​​of parameters collected by all explosion-proof monitoring distribution nodes within a past backtracking period (i.e., abnormal sensor data).

[0033] In detail, the explosion-proof importance analysis of the distributed explosion-proof monitoring nodes based on the anomaly dataset of monitoring nodes, to obtain the explosion-proof importance vector, includes: Extract abnormal data of monitoring nodes sequentially from the abnormal dataset of monitoring nodes; Based on the explosion-proof monitoring distributed nodes, an abnormal monitoring collection parameter set is identified in the extracted abnormal monitoring node data, wherein the abnormal monitoring collection parameter set includes one or more abnormal monitoring collection parameters; The abnormal monitoring and collection parameter set is divided according to multiple alarm event types to obtain multiple alarm collection parameter sets, in which each alarm collection parameter set corresponds one-to-one with an alarm event type. The alarm collection parameter sets are extracted sequentially from multiple alarm collection parameter sets, and the node alarm importance of the extracted alarm collection parameter sets is calculated. Summarize the alarm importance of each node corresponding to each alarm collection parameter set to obtain the alarm importance of multiple nodes; Construct a node explosion-proof importance vector based on the alarm importance of multiple nodes; The explosion-proof importance vector of each monitoring node is summarized to obtain the node explosion-proof importance vector set. The node explosion-proof importance vector set is then averaged to obtain the explosion-proof importance vector.

[0034] It should be explained that the anomaly monitoring parameter set refers to the set of parameters collected from the anomaly data of the monitoring nodes corresponding to the explosion-proof monitoring distribution nodes. The alarm parameter set refers to the set of multiple anomaly monitoring parameters corresponding to a certain type of alarm event in the anomaly monitoring parameter set. For example, if an explosion-proof monitoring distribution node is a node that monitors temperature in an explosion-proof monitoring environment, the anomaly monitoring parameter set of this explosion-proof monitoring distribution node is: {85.5°C, 88.1°C, 86.1°C, 80.1°C}, where the values ​​85.5°C and 88.1°C were collected when an abnormal increase in ambient temperature occurred, and the values ​​86.1°C and 80.1°C were collected when a sudden change in pressure occurred. Therefore, the alarm parameter set for the alarm event type of abnormal increase in ambient temperature is: {85.5°C, 88.1°C}.

[0035] Furthermore, the node alarm importance refers to the numerical value that quantifies the monitoring importance of the explosion-proof monitoring distribution node for the extracted alarm event types. The greater the node alarm importance, the stronger the indicative effect of the parameters collected by the explosion-proof monitoring distribution node on whether an abnormal event of the extracted alarm event type has occurred.

[0036] Understandably, the node explosion-proof importance vector refers to a numerical vector composed of the alarm importance of multiple nodes. For example, if the alarm importance of multiple nodes are A1, A2, and A3, then the node explosion-proof importance vector is... The term "vector averaging" for the node explosion-proof importance vector refers to averaging multiple node explosion-proof importance vectors from anomaly data of different monitoring nodes for the same explosion-proof monitoring distribution node to obtain a comprehensive and stable importance assessment vector. For example, for a certain explosion-proof monitoring distribution node, three node explosion-proof importance vectors are calculated from three different sets of anomaly data of monitoring nodes, namely (A1, A2, A3), (B1, B2, B3), and (C1, C2, C3). Then the averaged explosion-proof importance vector is ((A1+B1+C1) / 3, (A2+B2+C3) / 3, (A3+B3+C3) / 3).

[0037] Specifically, the calculation of the node alarm importance of the extracted alarm acquisition parameter set includes: Identify the total frequency of alarm data occurrences of the explosion-proof monitoring distribution nodes in the abnormal sensor database; Based on the query period, abnormal data statistics are performed on the distributed nodes of explosion-proof monitoring to obtain the total frequency of abnormal data occurrences. Obtain the normal sensor parameter range based on the explosion-proof monitoring distribution nodes; Based on the normal sensor parameter range, the deviation of the alarm acquisition parameter set is calculated to obtain the abnormal deviation value set of alarm parameters. The importance of a node alarm is calculated based on the abnormal deviation value set of alarm parameters, the total frequency of alarm data occurrence, and the total frequency of abnormal data occurrence.

[0038] It should be explained that the total frequency of alarm data occurrences refers to the total number of times the explosion-proof monitoring distribution node appears in the abnormal sensor database. This total frequency reflects the correlation strength between the abnormal parameters collected by the explosion-proof monitoring distribution node and the actual abnormal event that ultimately occurs. The higher the total frequency of alarm data occurrences, the more frequently the abnormal data of the explosion-proof monitoring distribution node is traced before the historical alarm event occurs, and the stronger its correlation with the abnormal event. The total number of abnormal data occurrences refers to the number of times the explosion-proof monitoring distribution node has data anomalies within the query period but has not triggered an alarm. For example, if an explosion-proof monitoring distribution node records temperature values ​​exceeding the normal sensor parameter range (e.g., 20℃-60℃) 50 times in a year, but only 10 of these times do subsequent abnormal events such as "abnormal increase in ambient temperature" or "sudden change in pressure" actually occur, then its total frequency of abnormal data occurrences is 50 times, and its total frequency of alarm data occurrences is 10 times.

[0039] Furthermore, in the formula for calculating the importance of subsequent node alarms, The term represents the number of times that parameters collected by the explosion-proof monitoring distribution nodes showed anomalies, but no abnormal events occurred within a follow-up period after the anomalies occurred (i.e., The ratio of the number of times the parameter was abnormal to the total number of times (i.e.) The larger this value is, the broader the scope of abnormal parameters collected by the explosion-proof monitoring distribution node. In other words, the less the abnormal parameters collected by the explosion-proof monitoring distribution node have as a reference for whether subsequent abnormal events will occur, and the less important the node alarm is.

[0040] Furthermore, the normal sensor parameter range refers to the normal value range of parameters collected by the monitoring sensors in the explosion-proof monitoring distribution nodes, which are set manually. The alarm parameter abnormal deviation value set refers to a collection of multiple alarm parameter abnormal deviation values, where each alarm parameter abnormal deviation value is a numerical value quantifying the degree of deviation between a certain alarm collected parameter and the normal sensor parameter range. The calculation method for this alarm parameter abnormal deviation value is as follows: in, Represents the maximum value function. Indicates the first in the alarm collection parameter set One alarm collection parameter, This represents the maximum value within the normal range of sensor parameters. This represents the minimum value within the normal range of sensor parameters.

[0041] In detail, the importance of the node alarm is expressed as follows: in, Indicates the importance of node alarms. This indicates the number of abnormal deviation values ​​for alarm parameters within the set of abnormal deviation values. This represents the first value in the set of abnormal deviation values ​​of alarm parameters. Abnormal deviation values ​​of alarm parameters This indicates the total frequency of abnormal data occurrences. This indicates the total frequency of alarm data occurrences.

[0042] S3. Based on the explosion-proof monitoring distribution node set, cluster the data fusion nodes to obtain multiple data fusion nodes. Each data fusion node corresponds to multiple explosion-proof monitoring distribution nodes, and the data fusion node contains a data storage repository.

[0043] It should be explained that the data fusion node refers to a computing node that receives parameters collected by multiple explosion-proof monitoring distributed nodes, merges these received parameters, and uploads them to the explosion-proof center. Examples include edge gateways or industrial-grade routers deployed in a factory area. If a data fusion node needs to receive parameters from a large number of explosion-proof monitoring distributed nodes, it may lead to data transmission congestion, resulting in packet loss, increased network latency, and increased node energy consumption. Therefore, this solution introduces a node clustering operation. This clustering operation groups multiple explosion-proof monitoring distributed nodes that are close together and simultaneously transmit data with the data fusion node without excessive congestion into a cluster of similar monitoring distributed nodes. All explosion-proof monitoring distributed nodes within this cluster transmit data with the same data fusion node. The data repository refers to the database in the data fusion node used to store data.

[0044] In detail, the data fusion node clustering based on the explosion-proof monitoring distributed node set yields multiple data fusion nodes, including: Obtain the location of each explosion-proof monitoring distribution node in the explosion-proof monitoring distribution node set to obtain the distribution node location set; The explosion-proof monitoring distribution node set is classified into two categories based on the distribution node location set to obtain classified monitoring distribution node clusters. Each classified monitoring distribution node cluster includes two classified monitoring distribution node clusters, and each classified monitoring distribution node cluster includes multiple explosion-proof monitoring distribution nodes. In the classification monitoring distribution node cluster group, the classification monitoring distribution node clusters are extracted sequentially, and the data transmission congestion of the extracted classification monitoring distribution node clusters is evaluated to obtain the data transmission congestion degree; If the data transmission congestion is greater than the preset standard congestion, the extracted classified monitoring distribution node clusters are taken as the explosion-proof monitoring distribution node set, and the step of binary classification of the explosion-proof monitoring distribution node set based on the distribution node location set is returned until the data transmission congestion is not greater than the standard congestion. If the data transmission congestion is not greater than the standard congestion, the extracted classified monitoring distribution node clusters are recorded as the same type of monitoring distribution node clusters. Data fusion nodes are constructed based on clusters of similar monitoring distribution nodes; The data fusion nodes are aggregated to obtain multiple data fusion nodes.

[0045] It should be explained that the distribution node location set refers to the set of specific location coordinates of all explosion-proof monitoring distribution nodes. The classified monitoring distribution node cluster refers to the set of two classified monitoring distribution node clusters after binary classification, wherein each classified monitoring distribution node cluster contains multiple explosion-proof monitoring distribution nodes, and the explosion-proof monitoring distribution nodes in the same classified monitoring distribution node cluster have similar distribution node locations. The above-mentioned binary classification of the explosion-proof monitoring distribution node set based on the distribution node location set means: using a clustering algorithm (such as the K-means algorithm, let K=2) to divide the entire explosion-proof monitoring distribution node set into two spatially relatively clustered (i.e., relatively close) clusters according to the distribution node locations of the explosion-proof monitoring distribution nodes. The data transmission congestion refers to the numerical value of the degree of congestion in data transmission when all explosion-proof monitoring distribution nodes in the categorized monitoring distribution node cluster transmit data simultaneously. The specific steps for evaluating the data transmission congestion of the extracted categorized monitoring distribution node cluster to obtain the data transmission congestion are as follows: Select a central distribution node in the categorized monitoring distribution node cluster. This central distribution node has the minimum distance to all other categorized monitoring distribution nodes. The selection method is as follows: Calculate the sum of the Euclidean distances from each explosion-proof monitoring distribution node (denoted as the central node) in the categorized monitoring distribution node cluster to all other nodes (all explosion-proof monitoring distribution nodes except the central node). Select the central node with the smallest sum of Euclidean distances as the central distribution node. Then, calculate the data packet size (unit: bytes), communication frequency (unit: packets / second), and available communication bandwidth (unit: bytes / second) of each explosion-proof monitoring distribution node in the categorized monitoring distribution node cluster. Finally, calculate the data transmission congestion using the following formula: in, This indicates the data transmission congestion level, and m represents the number of explosion-proof monitoring distribution nodes in the classification monitoring distribution node cluster. , and These represent the number of nodes in the cluster of classified monitoring distribution nodes. The data packet size of each explosion-proof monitoring distribution node, the communication frequency between it and the central distribution node, and the available communication bandwidth between it and the central distribution node.

[0046] Furthermore, the standard congestion level refers to a manually set constant. When the data transmission congestion level exceeds this standard congestion level, it indicates that the number of nodes in the classified monitoring distribution node cluster is too large or the communication demand is too high, which may lead to increased network latency and packet loss rate, affecting the reliability of data transmission. In this case, it is necessary to reclassify the classified monitoring distribution node cluster, that is, return to the above steps of binary classification of the explosion-proof monitoring distribution node set based on the distribution node location set. The construction of a data fusion node based on the same type of monitoring distribution node cluster refers to: selecting a central monitoring node in the same type of monitoring distribution node cluster and using this central monitoring node as the data fusion node. The method of selecting the central monitoring node is the same as the method of selecting the central distribution node mentioned above.

[0047] S4. Extract data fusion nodes sequentially from multiple data fusion nodes, and determine multiple distribution nodes to be fused in the explosion-proof monitoring distribution node set based on the extracted data fusion nodes.

[0048] Understandably, the multiple distribution nodes to be merged refer to multiple explosion-proof monitoring distribution nodes in the same type of monitoring distribution node cluster corresponding to the data fusion node.

[0049] S5. Use multiple distributed nodes to be merged to monitor data communication with the extracted data fusion nodes to obtain the data receiving nodes.

[0050] It is clear that the data receiving node refers to the data fusion node that receives the collected data (such as subsequent multiple sensor response data frames) uploaded by multiple distributed nodes to be fused.

[0051] In detail, the step of using multiple distributed nodes to be fused to monitor data communication with the extracted data fusion nodes to obtain data receiving nodes includes: Multiple automatic polling instruction frames are generated based on multiple distributed nodes to be merged. Each automatic polling instruction frame corresponds one-to-one with a distributed node to be merged, and each automatic polling instruction frame includes: node address code, function code, register start address and check code. Based on the data fusion node, multiple automatic polling command frames are sent to multiple distributed nodes to be fused, resulting in multiple data monitoring nodes; Data acquisition is performed based on multiple data monitoring nodes to obtain multiple raw sensor data, where each raw sensor data corresponds one-to-one with a data monitoring node. Multiple raw sensor data are packaged to obtain multiple sensor response data frames, which are then returned to the data fusion node to obtain the data receiving node.

[0052] It should be explained that the automatic polling instruction frame refers to a command data frame generated by the data fusion node that can initiate a data read request to a specific distributed node to be fused. One automatic polling instruction frame corresponds to one distributed node to be fused. The node address code refers to the unique logical identifier (such as a device address) of the corresponding distributed node to be fused in the network, which is used to ensure that the instruction is received by the correct node. The function code indicates the type of operation to be performed. For example, in industrial protocols such as Modbus, function code 03 represents "read holding register". The register start address refers to the starting position of the data to be read from the data storage area of ​​the distributed node to be fused (which is used to store data collected by monitoring sensors). The check code refers to a check sequence (such as a CRC cyclic redundancy check code) used to verify whether the automatic polling instruction frame has errors during transmission. For example, if the automatic polling instruction frame corresponding to a distribution node to be merged is (in hexadecimal): 010300000001840A, then its meaning can be: send a data request instruction to the distribution node to be merged with address 01, using function code 03, requesting to read data from register 0001 (i.e., 1 register) starting from address 0000, with checksum 840A.

[0053] Furthermore, the data monitoring node refers to the distributed node to be fused that receives the corresponding automatic polling instruction frame. The raw sensor data refers to the parameters obtained by a data monitoring node after data acquisition. Data acquisition refers to the parameter collection performed by the monitoring sensors within the data monitoring node. For example, after receiving an automatic polling instruction, a data monitoring node uses its monitoring sensors to collect a set of temperature values, and the average of multiple temperature values ​​(the number of which is a manually set fixed length) located after the register start address is used as the raw sensor data. The sensor response data frame refers to the data frame obtained after the data monitoring node encapsulates the raw sensor data according to a predefined communication protocol format, and one sensor response data frame corresponds to one set of raw sensor data. Data packaging refers to the process of assembling the raw sensor data, node address code, corresponding function code, data length, and other information into a complete data frame conforming to the protocol specifications, and calculating and adding a checksum.

[0054] S6. Summarize the data receiving nodes to obtain multiple data receiving nodes. Perform explosion-proof data fusion based on the multiple data receiving nodes and the explosion-proof importance vector set to obtain an explosion-proof monitoring report. Complete adaptive explosion-proof monitoring based on multi-source data fusion based on the explosion-proof monitoring report.

[0055] Understandably, the explosion-proof monitoring report refers to the report obtained after explosion-proof data fusion. The explosion-proof monitoring report contains multiple marker node data, which will be described in detail in subsequent embodiments.

[0056] In detail, the step of fusing explosion-proof data based on multiple data receiving nodes and an explosion-proof importance vector set to obtain an explosion-proof monitoring report includes: Perform the following operation on each of the multiple data receiving nodes: Multiple receive response data frames are identified in the data receiving node. The multiple receive response data frames are parsed to obtain multiple receiving node data. The receiving node data includes: receiving node address code and receiving node acquisition parameters. Perform the following operation on each of the multiple receiving node data: The receiving distribution nodes are determined based on the receiving node address codes in the receiving node data, and the receiving importance vector is determined based on the receiving distribution nodes in the explosion-proof importance vector set. The node anomaly index is calculated based on the received importance vector and the received node acquisition parameters in the received node data. If the node anomaly index is greater than the preset anomaly index threshold, the received node data is marked using the node anomaly index to obtain marked node data. By aggregating the labeled node data, multiple labeled node data sets are obtained. By aggregating the multiple labeled node data sets corresponding to each data receiving node, a labeled node dataset is obtained. Generate an explosion-proof monitoring report based on the marked node dataset.

[0057] It should be explained that the "received response data frame" refers to a sensor response data frame received by the data receiving node. The "received node data" refers to the combination of the receiving node address code and receiving node acquisition parameters obtained after parsing a received response data frame. The receiving node address code refers to the node address code of the data monitoring node that sent the received response data frame, and the receiving node acquisition parameters refer to the raw sensor data collected by the data monitoring node that sent the received response data frame. Parsing the received response data frame means identifying the receiving node address code and receiving node acquisition parameters from the received response data frame. The "received distribution node" refers to the explosion-proof monitoring distribution node corresponding to the receiving node address code. The "received importance vector" refers to the explosion-proof importance vector corresponding to the receiving distribution node. The "node anomaly index" is a numerical value that quantifies the comprehensive risk of an abnormal event occurring in the near future, implied by the currently collected receiving node acquisition parameters of the receiving distribution node. The larger the node anomaly index, the greater the risk of an abnormal event occurring in the subsequent lookback period.

[0058] Importantly, the above-mentioned node anomaly index is calculated as follows: It is determined whether the parameters collected by the receiving node are within the normal sensor parameter range of the receiving distribution node. If the parameters are within this range, the node anomaly index is recorded as 0. Otherwise, the deviation between the received node's collected parameters and the normal sensor parameter range is calculated (this deviation is calculated in the same way as the abnormal deviation value of the alarm parameters mentioned above). This deviation value is multiplied by each element of the receiving importance vector to obtain multiple products. These products represent the risk of a certain type of alarm event occurring in a subsequent backtracking period. These products are summed, and the result is recorded as the node anomaly index. The anomaly index threshold is a manually set constant. When the node anomaly index is greater than this threshold, it indicates a higher risk of an abnormal event occurring in a subsequent backtracking period, requiring the data from the receiving distribution node to be uploaded to the explosion-proof center promptly. The explosion-proof center refers to the superior computer system or control platform responsible for centralized monitoring, alarm analysis, and emergency response scheduling. The marked node data refers to the marked receiving node data, where marking means adding the node anomaly index to the receiving node data. If the node anomaly index is not greater than the anomaly index threshold, the receiving node data will be stored in the data storage repository of the receiving node for subsequent querying and maintenance.

[0059] Furthermore, generating the explosion-proof monitoring report based on the marked node dataset refers to packaging the marked node dataset into a single data package; the packaged data constitutes the explosion-proof monitoring report. Once the explosion-proof monitoring report is obtained, it needs to be uploaded to the explosion-proof center. Through the aforementioned screening process using anomaly index thresholds, the information contained in the explosion-proof monitoring report is ensured to be high-risk information identified through quantitative assessment, thus improving the report's relevance and effectiveness. This helps monitoring personnel at the explosion-proof center quickly focus on the most critical potential threats, making accurate and efficient emergency decisions. Simultaneously, it avoids excessive system load caused by reporting massive amounts of low-risk data, optimizing the utilization of network bandwidth and computing resources.

[0060] To address the problems described in the background art, this invention first performs explosion-proof importance analysis on the distributed explosion-proof monitoring node set to obtain an explosion-proof importance vector set. This step generates a dynamic importance vector for each monitoring node through explosion-proof importance analysis. Compared to the static approach in existing technologies where all nodes are treated equally, this method can more accurately identify nodes with a critical impact on explosion-proof early warning, thereby optimizing the allocation of monitoring resources and improving the sensitivity of abnormal event identification. Furthermore, this scheme performs data fusion node clustering based on the distributed explosion-proof monitoring node set to obtain multiple data fusion nodes. This step uses an adaptive clustering algorithm to group the monitoring nodes, and... Dynamically adjusting cluster size based on data transmission congestion effectively solves the network congestion problem caused by dense node deployment in existing technologies, reduces packet loss rate and communication latency, and enhances the stability and real-time performance of the monitoring system. Finally, explosion-proof data is fused based on multiple data receiving nodes and explosion-proof importance vector sets to obtain an explosion-proof monitoring report. This step combines importance vectors to fuse and analyze the collected data, and uses node anomaly indices to filter high-risk information and generate explosion-proof monitoring reports. This avoids system overload caused by reporting all data in existing technologies, making the reported content more targeted and improving the accuracy and response speed of the explosion-proof center's decisions. Therefore, this invention can improve the accuracy and reliability of identifying abnormal events in explosion-proof monitoring and reduce the risk of missed anomaly reports.

[0061] like Figure 2 The diagram shown is a functional block diagram of an adaptive explosion-proof monitoring system based on multi-source data fusion provided in an embodiment of the present invention.

[0062] The adaptive explosion-proof monitoring system 100 based on multi-source data fusion described in this invention can be installed in an electronic device. Depending on the functions implemented, the adaptive explosion-proof monitoring system 100 based on multi-source data fusion may include a monitoring environment determination module 101, a fusion node clustering module 102, a distributed node setting module 103, and a monitoring report generation module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device. The monitoring environment determination module 101 is used to identify the explosion-proof monitoring environment and query the explosion-proof monitoring distribution node set in the explosion-proof monitoring environment. The explosion-proof monitoring distribution node set includes multiple explosion-proof monitoring distribution nodes, and each explosion-proof monitoring distribution node contains a monitoring sensor. The fusion node clustering module 102 is used to perform explosion-proof importance analysis on the explosion-proof monitoring distribution node set to obtain an explosion-proof importance vector set, wherein the explosion-proof importance vector set includes multiple explosion-proof importance vectors. Based on the explosion-proof monitoring distribution node set, data fusion node clustering is performed to obtain multiple data fusion nodes, wherein each data fusion node corresponds to multiple explosion-proof monitoring distribution nodes, and the data fusion node contains a data storage repository. The distribution node setting module 103 is used to sequentially extract data fusion nodes from multiple data fusion nodes, and determine multiple distribution nodes to be fused in the explosion-proof monitoring distribution node set based on the extracted data fusion nodes; The monitoring report generation module 104 is used to use multiple distributed nodes to be fused to conduct monitoring data communication with the extracted data fusion nodes to obtain data receiving nodes, summarize the data receiving nodes to obtain multiple data receiving nodes, and perform explosion-proof data fusion based on multiple data receiving nodes and explosion-proof importance vector set to obtain an explosion-proof monitoring report.

[0063] In detail, the modules in the adaptive explosion-proof monitoring system 100 based on multi-source data fusion described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method uses the same techniques as the adaptive explosion-proof monitoring method based on multi-source data fusion described in the article and can produce the same technical effects, so it will not be repeated here.

[0064] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements an adaptive explosion-proof monitoring method based on multi-source data fusion, according to an embodiment of the present invention.

[0065] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as an adaptive explosion-proof monitoring method program based on multi-source data fusion.

[0066] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of an adaptive explosion-proof monitoring method program based on multi-source data fusion, but also to temporarily store data that has been output or will be output.

[0067] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., an adaptive explosion-proof monitoring method program based on multi-source data fusion) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0068] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0069] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0070] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0071] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0072] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0073] The adaptive explosion-proof monitoring method program based on multi-source data fusion stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following: Once the explosion-proof monitoring environment is identified, the explosion-proof monitoring distribution node set in the explosion-proof monitoring environment is queried. The explosion-proof monitoring distribution node set includes multiple explosion-proof monitoring distribution nodes, and each explosion-proof monitoring distribution node contains a monitoring sensor. An explosion-proof importance analysis is performed on the explosion-proof monitoring distribution node set to obtain an explosion-proof importance vector set, which includes multiple explosion-proof importance vectors. Data fusion nodes are clustered based on the explosion-proof monitoring distributed node set to obtain multiple data fusion nodes. Each data fusion node corresponds to multiple explosion-proof monitoring distributed nodes, and the data fusion node contains a data storage repository. Data fusion nodes are extracted sequentially from multiple data fusion nodes, and multiple distribution nodes to be fused are determined from the explosion-proof monitoring distribution node set based on the extracted data fusion nodes. By using multiple distributed nodes to be merged to monitor data communication with the extracted data fusion nodes, the data receiving nodes are obtained; The data receiving nodes are aggregated to obtain multiple data receiving nodes. Explosion-proof data is fused based on the multiple data receiving nodes and the explosion-proof importance vector set to obtain an explosion-proof monitoring report. Adaptive explosion-proof monitoring based on multi-source data fusion is completed based on the explosion-proof monitoring report.

[0074] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0075] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0076] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: Once the explosion-proof monitoring environment is identified, the explosion-proof monitoring distribution node set in the explosion-proof monitoring environment is queried. The explosion-proof monitoring distribution node set includes multiple explosion-proof monitoring distribution nodes, and each explosion-proof monitoring distribution node contains a monitoring sensor. An explosion-proof importance analysis is performed on the explosion-proof monitoring distribution node set to obtain an explosion-proof importance vector set, which includes multiple explosion-proof importance vectors. Data fusion nodes are clustered based on the explosion-proof monitoring distributed node set to obtain multiple data fusion nodes. Each data fusion node corresponds to multiple explosion-proof monitoring distributed nodes, and the data fusion node contains a data storage repository. Data fusion nodes are extracted sequentially from multiple data fusion nodes, and multiple distribution nodes to be fused are determined from the explosion-proof monitoring distribution node set based on the extracted data fusion nodes. By using multiple distributed nodes to be merged to monitor data communication with the extracted data fusion nodes, the data receiving nodes are obtained; The data receiving nodes are aggregated to obtain multiple data receiving nodes. Explosion-proof data is fused based on the multiple data receiving nodes and the explosion-proof importance vector set to obtain an explosion-proof monitoring report. Adaptive explosion-proof monitoring based on multi-source data fusion is completed based on the explosion-proof monitoring report.

[0077] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0078] The modules described as separate components may or may not be physically separate. The components shown as modules 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.

[0079] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0080] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An adaptive explosion-proof monitoring method based on multi-source data fusion, characterized in that, The method includes: Once the explosion-proof monitoring environment is identified, the explosion-proof monitoring distribution node set in the explosion-proof monitoring environment is queried. The explosion-proof monitoring distribution node set includes multiple explosion-proof monitoring distribution nodes, and each explosion-proof monitoring distribution node contains a monitoring sensor. An explosion-proof importance analysis is performed on the explosion-proof monitoring distribution node set to obtain an explosion-proof importance vector set, which includes multiple explosion-proof importance vectors. Data fusion nodes are clustered based on the explosion-proof monitoring distributed node set to obtain multiple data fusion nodes. Each data fusion node corresponds to multiple explosion-proof monitoring distributed nodes, and the data fusion node contains a data storage repository. Data fusion nodes are extracted sequentially from multiple data fusion nodes, and multiple distribution nodes to be fused are determined from the explosion-proof monitoring distribution node set based on the extracted data fusion nodes. By using multiple distributed nodes to be merged to monitor data communication with the extracted data fusion nodes, the data receiving nodes are obtained; The data receiving nodes are aggregated to obtain multiple data receiving nodes. Explosion-proof data is fused based on the multiple data receiving nodes and the explosion-proof importance vector set to obtain an explosion-proof monitoring report. Adaptive explosion-proof monitoring based on multi-source data fusion is completed based on the explosion-proof monitoring report.

2. The adaptive explosion-proof monitoring method based on multi-source data fusion as described in claim 1, characterized in that, The explosion-proof importance analysis of the explosion-proof monitoring distribution node set yields an explosion-proof importance vector set, including: Perform the following operations on each explosion-proof monitoring distribution node in the explosion-proof monitoring distribution node set: Query the monitoring node anomaly dataset corresponding to the explosion-proof monitoring distribution node in the pre-built anomaly sensor database. The monitoring node anomaly dataset includes anomaly data from multiple monitoring nodes. Based on the abnormal dataset of monitoring nodes, the explosion-proof importance of the distributed nodes of explosion-proof monitoring is analyzed to obtain the explosion-proof importance vector; The explosion-proof importance vectors corresponding to each explosion-proof monitoring distribution node are summarized to obtain the explosion-proof importance vector set.

3. The adaptive explosion-proof monitoring method based on multi-source data fusion as described in claim 2, characterized in that, Before querying the pre-built anomaly sensor database for the anomaly dataset of the monitoring nodes corresponding to the explosion-proof monitoring distribution nodes, the method further includes: Configure multiple alarm event types, and perform the following operation for each of the multiple alarm event types: Based on the types of alarm events and the preset query period, the alarm events in the explosion-proof monitoring environment are queried to obtain a set of historical alarm events, which includes multiple historical alarm events. Extract historical alarm events sequentially from the historical alarm event set; Based on the extracted historical alarm events and the preset backtracking period, the explosion-proof monitoring distribution node set is subjected to source tracing analysis to obtain abnormal sensor data. The abnormal sensor data includes: abnormal monitoring distribution node set and abnormal node acquisition parameter set. The abnormal monitoring distribution nodes in the abnormal monitoring distribution node set correspond one-to-one with the abnormal node acquisition parameters in the abnormal node acquisition parameter set. Summarize the abnormal sensor data corresponding to each historical alarm event to obtain the abnormal sensor dataset; The abnormal sensor datasets corresponding to each alarm event type are aggregated to obtain the abnormal sensor database, which includes multiple abnormal sensor data.

4. The adaptive explosion-proof monitoring method based on multi-source data fusion as described in claim 3, characterized in that, The explosion-proof importance analysis of the distributed explosion-proof monitoring nodes based on the abnormal monitoring node dataset yields an explosion-proof importance vector, including: Extract abnormal data of monitoring nodes sequentially from the abnormal dataset of monitoring nodes; Based on the explosion-proof monitoring distributed nodes, an abnormal monitoring collection parameter set is identified in the extracted abnormal monitoring node data, wherein the abnormal monitoring collection parameter set includes one or more abnormal monitoring collection parameters; The abnormal monitoring and collection parameter set is divided according to multiple alarm event types to obtain multiple alarm collection parameter sets, in which each alarm collection parameter set corresponds one-to-one with an alarm event type. The alarm collection parameter sets are extracted sequentially from multiple alarm collection parameter sets, and the node alarm importance of the extracted alarm collection parameter sets is calculated. Summarize the alarm importance of each node corresponding to each alarm collection parameter set to obtain the alarm importance of multiple nodes; Construct a node explosion-proof importance vector based on the alarm importance of multiple nodes; The explosion-proof importance vector of each monitoring node is summarized to obtain the node explosion-proof importance vector set. The node explosion-proof importance vector set is then averaged to obtain the explosion-proof importance vector.

5. The adaptive explosion-proof monitoring method based on multi-source data fusion as described in claim 4, characterized in that, The calculation of the node alarm importance of the extracted alarm acquisition parameter set includes: Identify the total frequency of alarm data occurrences of the explosion-proof monitoring distribution nodes in the abnormal sensor database; Based on the query period, abnormal data statistics are performed on the distributed nodes of explosion-proof monitoring to obtain the total frequency of abnormal data occurrences. Obtain the normal sensor parameter range based on the explosion-proof monitoring distribution nodes; Based on the normal sensor parameter range, the deviation of the alarm acquisition parameter set is calculated to obtain the abnormal deviation value set of alarm parameters. The importance of a node alarm is calculated based on the abnormal deviation value set of alarm parameters, the total frequency of alarm data occurrence, and the total frequency of abnormal data occurrence.

6. The adaptive explosion-proof monitoring method based on multi-source data fusion as described in claim 5, characterized in that, The importance of the node alarm is expressed as follows: in, Indicates the importance of node alarms. This indicates the number of abnormal deviation values ​​for alarm parameters within the set of abnormal deviation values. This represents the first value in the set of abnormal deviation values ​​of alarm parameters. Abnormal deviation values ​​of alarm parameters This indicates the total frequency of abnormal data occurrences. This indicates the total frequency of alarm data occurrences.

7. The adaptive explosion-proof monitoring method based on multi-source data fusion as described in claim 6, characterized in that, The data fusion node clustering based on the explosion-proof monitoring distributed node set yields multiple data fusion nodes, including: Obtain the location of each explosion-proof monitoring distribution node in the explosion-proof monitoring distribution node set to obtain the distribution node location set; The explosion-proof monitoring distribution node set is classified into two categories based on the distribution node location set to obtain classified monitoring distribution node clusters. Each classified monitoring distribution node cluster includes two classified monitoring distribution node clusters, and each classified monitoring distribution node cluster includes multiple explosion-proof monitoring distribution nodes. In the classification monitoring distribution node cluster group, the classification monitoring distribution node clusters are extracted sequentially, and the data transmission congestion of the extracted classification monitoring distribution node clusters is evaluated to obtain the data transmission congestion degree; If the data transmission congestion is greater than the preset standard congestion, the extracted classified monitoring distribution node clusters are taken as the explosion-proof monitoring distribution node set, and the step of binary classification of the explosion-proof monitoring distribution node set based on the distribution node location set is returned until the data transmission congestion is not greater than the standard congestion. If the data transmission congestion is not greater than the standard congestion, the extracted classified monitoring distribution node clusters are recorded as the same type of monitoring distribution node clusters. Data fusion nodes are constructed based on clusters of similar monitoring distribution nodes; The data fusion nodes are aggregated to obtain multiple data fusion nodes.

8. The adaptive explosion-proof monitoring method based on multi-source data fusion as described in claim 7, characterized in that, The process of using multiple distributed nodes to be fused to monitor data communication with the extracted data fusion nodes to obtain data receiving nodes includes: Multiple automatic polling instruction frames are generated based on multiple distributed nodes to be merged. Each automatic polling instruction frame corresponds one-to-one with a distributed node to be merged, and each automatic polling instruction frame includes: node address code, function code, register start address and check code. Based on the data fusion node, multiple automatic polling command frames are sent to multiple distributed nodes to be fused, resulting in multiple data monitoring nodes; Data acquisition is performed based on multiple data monitoring nodes to obtain multiple raw sensor data, where each raw sensor data corresponds one-to-one with a data monitoring node. Multiple raw sensor data are packaged to obtain multiple sensor response data frames, which are then returned to the data fusion node to obtain the data receiving node.

9. The adaptive explosion-proof monitoring method based on multi-source data fusion as described in claim 8, characterized in that, The explosion-proof data fusion based on multiple data receiving nodes and the explosion-proof importance vector set is used to obtain an explosion-proof monitoring report, including: Perform the following operation on each of the multiple data receiving nodes: Multiple receive response data frames are identified in the data receiving node. The multiple receive response data frames are parsed to obtain multiple receiving node data. The receiving node data includes: receiving node address code and receiving node acquisition parameters. Perform the following operation on each of the multiple receiving node data: The receiving distribution nodes are determined based on the receiving node address codes in the receiving node data, and the receiving importance vector is determined based on the receiving distribution nodes in the explosion-proof importance vector set. The node anomaly index is calculated based on the received importance vector and the received node acquisition parameters in the received node data. If the node anomaly index is greater than the preset anomaly index threshold, the received node data is marked using the node anomaly index to obtain marked node data. By aggregating the labeled node data, multiple labeled node data sets are obtained. By aggregating the multiple labeled node data sets corresponding to each data receiving node, a labeled node dataset is obtained. Generate an explosion-proof monitoring report based on the marked node dataset.

10. An adaptive explosion-proof monitoring system based on multi-source data fusion, characterized in that, The system includes: The monitoring environment determination module is used to identify the explosion-proof monitoring environment and query the explosion-proof monitoring distribution node set in the explosion-proof monitoring environment. The explosion-proof monitoring distribution node set includes multiple explosion-proof monitoring distribution nodes, and each explosion-proof monitoring distribution node contains a monitoring sensor. The fusion node clustering module is used to perform explosion-proof importance analysis on the explosion-proof monitoring distribution node set to obtain an explosion-proof importance vector set. The explosion-proof importance vector set includes multiple explosion-proof importance vectors. Based on the explosion-proof monitoring distribution node set, data fusion node clustering is performed to obtain multiple data fusion nodes. Each data fusion node corresponds to multiple explosion-proof monitoring distribution nodes, and the data fusion node contains a data storage repository. The distributed node setting module is used to extract data fusion nodes sequentially from multiple data fusion nodes, and determine multiple distributed nodes to be fused in the explosion-proof monitoring distributed node set based on the extracted data fusion nodes; The monitoring report generation module is used to communicate monitoring data with the extracted data fusion nodes using multiple distributed nodes to be fused, obtain data receiving nodes, summarize the data receiving nodes, obtain multiple data receiving nodes, and perform explosion-proof data fusion based on multiple data receiving nodes and explosion-proof importance vector set to obtain an explosion-proof monitoring report.

Images