Remote monitoring method and system for ultrasonic control and measurement equipment

Abstract

The invention discloses a remote monitoring method and system for ultrasonic control and measurement equipment, and relates to the related technical field of pipe network monitoring, and the method comprises the steps: carrying out the layout of the control and measurement equipment according to the historical fault record of a fluid conveying pipeline network, and obtaining K pieces of ultrasonic control and measurement equipment of K pipe network monitoring sites; k edge monitoring nodes are configured; edge node positioning is carried out, and a real-time risk node and real-time association node combination is output; performing data backtracking analysis, and outputting node pipe network check data; and the remote risk type of the real-time risk node is output by comparing the node pipe network verification data with the node pipe network actual measurement data. The technical problems that in the prior art, due to the fact that early warning triggered by pipe network faults or ultrasonic control and measurement equipment faults is difficult to distinguish, the pipe network monitoring reliability and risk monitoring efficiency are not high, and the fault early warning accuracy is poor are solved, and bidirectional monitoring of the equipment and the pipe network is achieved; and the pipe network risk monitoring efficiency, reliability and early warning accuracy are improved.

Description

Technical Field

[0001] This application relates to the technical field of pipeline network monitoring, and specifically relates to a remote monitoring method and system for ultrasonic detection equipment. Background Art

[0002] As a new type of pipeline network monitoring tool, ultrasonic detection equipment has the advantages of high precision, non-invasiveness, strong adaptability, etc., and is gradually applied to the real-time monitoring of pipeline networks. By using ultrasonic sensors to monitor key parameters such as the pressure and flow of the fluid inside the pipeline in real time, it can effectively identify abnormal changes in the pipeline. Currently, there are the following problems in the remote monitoring of ultrasonic detection equipment: when a pipeline network fails, it is impossible to accurately distinguish whether it is caused by problems with the pipeline network itself (such as leaks, blockages, etc.) or monitoring false alarms caused by malfunctions of the ultrasonic measurement and control equipment, resulting in insufficient reliability of the monitoring results, and further affecting the accuracy of the safety assessment and risk warning of the pipeline network. In the face of a complex and changing pipeline network environment, the existing monitoring system cannot respond to actual risks in a timely manner, resulting in a slow warning response speed for pipeline network failures, and reducing the efficiency and accuracy of pipeline network management and maintenance.

[0003] Therefore, in the current related technologies, there are technical problems such as it being difficult to distinguish warnings triggered by pipeline network failures or ultrasonic detection equipment failures, which in turn lead to low reliability of pipeline network monitoring, low efficiency of risk monitoring, and poor accuracy of fault warnings. Summary of the Invention

[0004] By providing a remote monitoring method and system for ultrasonic detection equipment, this application solves the technical problems in the existing technologies, such as it being difficult to distinguish warnings triggered by pipeline network failures or ultrasonic detection equipment failures, which in turn lead to low reliability of pipeline network monitoring, low efficiency of risk monitoring, and poor accuracy of fault warnings, and achieves the technical effect of realizing two-way monitoring of equipment and pipeline networks, and improving the efficiency, reliability, and warning accuracy of pipeline network risk monitoring.

[0005] The present application provides a remote monitoring method for ultrasonic detection equipment. The method includes: arranging detection equipment based on the historical fault records of a fluid transportation pipeline network to obtain K ultrasonic detection devices arranged at K pipeline network monitoring sites; analyzing pipeline network anomalies based on the historical fault records, and configuring K edge monitoring nodes at the K pipeline network monitoring sites according to the analysis results, where the K edge monitoring nodes are in bidirectional communication connection with a remote monitoring cloud, and the K edge monitoring nodes are in unidirectional communication connection with the K ultrasonic detection devices; after receiving a detection risk warning, the remote monitoring cloud locates the edge nodes by parsing the detection risk warning, and outputs a combination of real-time risk nodes and real-time associated nodes; the remote monitoring cloud performs data backtracking analysis on the combination of real-time associated nodes, and outputs node pipeline network verification data; extracting node pipeline network measured data from the detection risk warning, and comparing the node pipeline network verification data and the node pipeline network measured data to output the remote risk type of the real-time risk nodes.

[0006] In a possible implementation manner, the remote monitoring method for ultrasonic detection equipment further performs the following processing: performing operation association analysis based on the historical transportation data of the fluid transportation pipeline network to obtain K groups of associated monitoring nodes; calling K groups of associated operation data of the K groups of associated monitoring nodes from the historical transportation data; generating a transportation deviation calculation network by performing multiple regression analysis on the K groups of associated operation data; associatively storing the K edge monitoring nodes and the K groups of associated monitoring nodes based on a knowledge graph to generate a pipeline network backtracking judgment network; loading the transportation deviation calculation network and the pipeline network backtracking judgment network to the remote monitoring cloud to complete the function configuration of the remote monitoring cloud.

[0007] In a possible implementation manner, the remote monitoring method for ultrasonic detection equipment further performs the following processing: performing multiple regression analysis on the K groups of associated operation data to obtain K flow association functions and K pressure association functions; constructing K flow association analysis channels and K pressure association analysis channels based on the K flow association functions and the K pressure association functions; mapping and paralleling the K flow association analysis channels and the K pressure association analysis channels to complete the construction of K transportation deviation calculation units; paralleling the K transportation deviation calculation units to generate the transportation deviation calculation network.

[0008] In a possible implementation, the remote monitoring method of the ultrasonic control and measurement equipment also performs the following processing: obtaining the first historical fault monitoring data of the first pipeline network monitoring node from the historical fault record call; obtaining multiple first historical fault flows and multiple first historical fault pressures by disassembling the first historical fault monitoring data; using IQR to perform univariate analysis on the multiple first historical fault flows and multiple first historical fault pressures, respectively, to obtain a first flow abnormality threshold and a first pressure abnormality threshold; constructing a first pipeline network heat map according to the time series characteristics of the multiple first historical fault flows and multiple first historical fault pressures; performing a joint regional analysis on the first pipeline network heat map through K-means clustering, and outputting a first collaborative abnormality threshold, wherein the first collaborative abnormality threshold includes a second flow abnormality threshold and a second pressure abnormality threshold; constructing a first edge monitoring node based on the first flow abnormality threshold, the first pressure abnormality threshold and the first collaborative abnormality threshold; and so on, configuring the K edge monitoring nodes at the K pipeline network monitoring sites.

[0009] In a possible implementation, the remote monitoring method of the ultrasonic control and measurement device further performs the following processing: the first ultrasonic control and measurement device collects the first real-time flow and the first real-time pressure of the first pipe network monitoring site in real time, and transmits the first real-time flow and the first real-time pressure to the first edge monitoring node; in the first edge monitoring node, when either the first real-time flow and the first real-time pressure does not meet the first flow abnormality threshold and the first pressure abnormality threshold, or the first real-time flow and the first real-time pressure do not meet the first collaborative abnormality threshold, the first edge monitoring node generates the control and measurement risk warning, wherein the control and measurement risk warning includes the first edge monitoring node and the node pipe network measured data, and the node pipe network measured data includes the first real-time flow and the first real-time pressure; after receiving the control and measurement risk warning, the remote monitoring cloud locates the edge node by parsing the control and measurement risk warning, and outputs the first pipe network monitoring site as the real-time risk node; the real-time risk node is used to traverse the pipe network backtracking judgment network to obtain the real-time associated node combination, wherein the real-time associated node combination is composed of M edge monitoring nodes, and M is a positive integer less than K.

[0010] In a possible implementation, the remote monitoring method of the ultrasonic detection device further performs the following processing: The remote monitoring cloud generates a pipeline network data traceback instruction according to the M edge monitoring nodes, where the pipeline network data traceback instruction includes M data traceback authorities; the M edge monitoring nodes receive and transmit M node pipeline network traceback data to the remote monitoring cloud according to the M data traceback authorities; the remote monitoring cloud activates a real-time deviation calculation unit from the K transport deviation calculation units of the transport deviation calculation network according to the real-time risk node; inputs the M node pipeline network traceback data into the real-time deviation calculation unit, and calculates to obtain the node pipeline network verification data, where the node pipeline network verification data includes node flow verification data and node pressure verification data.

[0011] In a possible implementation, the remote monitoring method of the ultrasonic detection device further performs the following processing: Calculate the Euclidean distance between the node pipeline network verification data and the node pipeline network measured data to obtain a first verification deviation; perform a one-dimensional deviation calculation on the first real-time flow and the node flow verification data to obtain a second verification deviation; perform a one-dimensional deviation calculation on the first real-time pressure and the node pressure verification data to obtain a third verification deviation; perform a weighted calculation on the first verification deviation, the second verification deviation, and the third verification deviation based on a preset deviation weight to obtain a comprehensive verification deviation; if the comprehensive verification deviation meets a preset verification deviation threshold, the remote risk type is a pipeline network failure; if the comprehensive verification deviation does not meet the preset verification deviation threshold, the remote risk type is a detection device failure.

[0012] The present application also provides a remote monitoring system for an ultrasonic detection device, including: a detection device layout module for laying out detection devices according to the historical failure records of a fluid transportation pipeline network to obtain K ultrasonic detection devices laid at K pipeline network monitoring sites; a pipeline network anomaly analysis module for performing pipeline network anomaly analysis according to the historical failure records and configuring K edge monitoring nodes at the K pipeline network monitoring sites according to the analysis results, where the K edge monitoring nodes are in bidirectional communication connection with a remote monitoring cloud, and the K edge monitoring nodes are in unidirectional communication connection with the K ultrasonic detection devices; an edge node positioning module for, after the remote monitoring cloud receives a detection risk warning, performing edge node positioning by parsing the detection risk warning and outputting a real-time risk node and a real-time associated node combination; a data traceback analysis module for the remote monitoring cloud performing data traceback analysis on the real-time associated node combination and outputting node pipeline network verification data; a remote risk type output module for extracting node pipeline network measured data from the detection risk warning and outputting the remote risk type of the real-time risk node by comparing the node pipeline network verification data and the node pipeline network measured data.

[0013] The remote monitoring method and system for ultrasonic detection equipment proposed in this application layout detection equipment according to the historical fault records of the fluid transportation pipeline network, and obtain K ultrasonic detection equipment deployed at K pipe network monitoring sites; configure K edge monitoring nodes; perform edge node positioning, and output a combination of real-time risk nodes and real-time associated nodes; perform data backtracking analysis, and output node pipe network verification data; by comparing the node pipe network verification data with the measured data of the node pipe network, output the remote risk type of the real-time risk node. It solves the technical problems in the prior art that it is difficult to distinguish the early warnings triggered by pipe network faults or ultrasonic detection equipment faults, which leads to low reliability of pipe network monitoring, low efficiency of risk monitoring, and poor accuracy of fault early warnings, and achieves the technical effects of realizing two-way monitoring of equipment and pipe networks, and improving the efficiency, reliability and early warning accuracy of pipe network risk monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the application. It should be understood that the operations described above or below do not necessarily need to be executed precisely in sequence. On the contrary, as needed, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0015] Figure 1 Schematic diagram of the process of the remote monitoring method for ultrasonic detection equipment provided by the embodiment of the present application; Figure 2 Schematic diagram of the structure of the remote monitoring system for ultrasonic detection equipment provided by the embodiment of the present application.

[0016] Description of the reference numerals: Detection equipment layout module 10, pipe network anomaly analysis module 20, edge node positioning module 30, data backtracking analysis module 40, remote risk type output module 50. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the detailed implementation manners of this application.

[0018] In order to make the purpose, technical solutions and advantages of this application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first" and "second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0020] The embodiments of this application provide a remote monitoring method for ultrasonic detection devices, as Figure 1 shown, the method includes: Step S100, arranging detection devices according to the historical failure records of the fluid transportation pipeline network, and obtaining K ultrasonic detection devices arranged at K pipeline network monitoring sites.

[0021] Preferably, the historical failure data of the fluid transportation pipeline network is used to arrange the pipeline network monitoring devices. Specifically, according to the historical failure records of the fluid transportation pipeline network (i.e., various failure event data during the historical operation of the pipeline network, such as pipeline rupture, leakage, blockage, pressure abnormality, etc.), the positions of the ultrasonic detection devices are reasonably planned and arranged to ensure that the ultrasonic detection devices are arranged in the middle section of the pipeline in the high-failure area to achieve the best monitoring effect; by analyzing the historical failure records of the pipeline network, identify which parts of the pipeline network are most prone to failure, and then arrange the ultrasonic detection devices accordingly, including identifying the K pipeline network monitoring sites (areas with special pipeline structures, materials or working environments) that are most prone to failure in the pipeline network, and arranging one ultrasonic detection device at each monitoring site. Among them, K is a positive integer representing the total number of pipeline network monitoring points. The ultrasonic detection device uses ultrasonic technology to monitor parameters such as fluid flow, pressure, and vibration in the pipeline, and has high precision and non-contact characteristics, which is suitable for high-precision monitoring and early warning of the pipeline network. Through the data-driven arrangement of monitoring devices, the operation status of the fluid pipeline can be monitored more effectively, early warning can be given in advance, and the monitoring efficiency and accuracy of the pipeline network can be improved.

[0022] Step S200: Analyze the anomalies in the pipeline network based on the historical fault records, and configure K edge monitoring nodes at the K pipeline network monitoring sites according to the analysis results. Among them, the K edge monitoring nodes are connected to the remote monitoring cloud in a two-way communication manner, and the K edge monitoring nodes are connected to K ultrasonic detection devices in a one-way communication manner.

[0023] Preferably, analyzing the anomalies in the pipeline network based on the historical fault records means analyzing the operating status of the pipeline network using the historical fault records, specifically including high-risk area identification (analyzing which pipeline positions have had multiple failures and belong to key monitoring objects), fault mode induction (summarizing the fault types and their triggering conditions, such as leaks being more likely to occur within a specific pressure range), and potential anomaly prediction (predicting the areas or time periods where problems may occur in the future based on the regularity of historical data). Then, determine the K pipeline network monitoring sites that most need to be monitored (which may be points with frequent historical faults, high-risk areas, or core pipeline network nodes) and configure K edge monitoring nodes according to the analysis results. The edge monitoring node refers to the intelligent monitoring device at each pipeline network monitoring site, which can perform real-time data collection, data preprocessing (preliminary analysis and processing of the collected data, such as filtering noise data, calculating anomaly indicators), etc., so as to improve the monitoring coverage and real-time performance.

[0024] Preferably, the edge monitoring nodes are connected to the remote monitoring cloud in a two-way communication manner, including the edge nodes transmitting the collected data to the cloud in real time for remote analysis and storage, and the cloud can send the processed analysis results or adjustment strategies to the edge nodes. For example, after the cloud determines that the pressure of a certain node is abnormal, it can instruct the edge node to increase the collection frequency or trigger an alarm. The remote monitoring cloud can comprehensively analyze the data of all edge nodes to support the monitoring of the operating status of the pipeline network across regions; the edge monitoring nodes are connected to the ultrasonic detection devices in a one-way communication manner, that is, the ultrasonic detection devices monitor the state of fluid transportation and send data to the edge nodes, and the edge nodes receive and process it, avoiding the resource consumption caused by two-way communication to the ultrasonic devices, while improving security, ensuring the real-time performance, flexibility, and efficiency of pipeline network monitoring.

[0025] Further, step S200 also includes step S210, obtaining the first historical fault monitoring data of the first pipeline network monitoring node by calling the historical fault record; step S220, obtaining multiple first historical fault flows and multiple first historical fault pressures by disassembling the first historical fault monitoring data; step S230, using IQR to perform univariate analysis on the multiple first historical fault flows and multiple first historical fault pressures respectively, to obtain a first flow abnormality threshold and a first pressure abnormality threshold; step S240, constructing a first pipeline network heat map according to the time series characteristics of the multiple first historical fault flows and multiple first historical fault pressures; step S250, performing a joint regional analysis on the first pipeline network heat map through K-means clustering, and outputting a first collaborative abnormality threshold, wherein the first collaborative abnormality threshold includes a second flow abnormality threshold and a second pressure abnormality threshold; step S260, constructing a first edge monitoring node based on the first flow abnormality threshold, the first pressure abnormality threshold and the first collaborative abnormality threshold; step S270, and so on, configuring the K edge monitoring nodes at the K pipeline network monitoring sites.

[0026] Preferably, a pipeline monitoring node is randomly selected from the historical fault records as the first pipeline monitoring node and the corresponding first historical fault monitoring data is called, including fault data such as flow and pressure, and then the first historical fault monitoring data is disassembled to obtain more detailed fault data, that is, multiple first historical fault flows and multiple first historical fault pressures are obtained respectively; then IQR is used to perform univariate analysis on the multiple first historical fault flows and multiple first historical fault pressures respectively, that is, by calculating the interquartile range of the fault flow and the fault pressure and defining the normal range, specifically including, according to the IQR analysis of the flow data, obtaining the abnormal value threshold (first flow abnormal threshold) outside the normal range of the flow, similarly, according to the IQR analysis of the pressure data, obtaining the abnormal threshold (first pressure abnormal threshold) of the pressure, wherein IQR, i.e., interquartile range, is a commonly used statistical method that can identify abnormal values ​​in data.

[0027] Preferably, by analyzing the temporal characteristics of historical fault data (multiple first historical fault flows and multiple first historical fault pressures), a first pipe network heat map is generated to display the distribution density of the data or the changes of certain variables (such as flow rate, pressure, etc.) at different time periods or spatial positions. Among them, the highlighted areas of the pipe network heat map may represent high-risk and fault-prone areas in the pipe network. Through the heat map, it is possible to quickly identify which areas in the pipe network show abnormal flow rate or pressure changes during certain periods; then, use K-means clustering to analyze the change data of flow rate and pressure, and divide these data into several regions (i.e., clusters) according to similarity. Each cluster represents a certain abnormal pattern or high-risk area in the pipe network, which can reveal the possible co-abnormal phenomena between multiple positions during the same period. Specifically, take the flow rate and pressure data in the pipe network heat map as features, divide these data through K-means clustering, find the abnormal areas in the data, and then output the first co-abnormal threshold to judge which areas or nodes show synchronous abnormalities in terms of the changes of flow rate and pressure. For example, if the flow rate exceeds a certain upper limit and the pressure is lower than a certain lower limit, this combination may represent a pipe network fault. The first co-abnormal threshold includes the second flow rate abnormal threshold and the second pressure abnormal threshold. Finally, based on the obtained first flow rate abnormal threshold, first pressure abnormal threshold, and first co-abnormal threshold, a first edge monitoring node is constructed. This node monitors the flow rate, pressure, and their associated abnormalities of the pipe network nodes based on these thresholds; according to the historical data and abnormal analysis of each pipe network monitoring node, the corresponding edge monitoring nodes are configured respectively, and K edge monitoring nodes are obtained to ensure that potential faults and abnormalities can be effectively monitored in each region.

[0028] Further, step S200 further includes step A, performing operation correlation analysis on the historical transportation data of the fluid transportation pipeline network to obtain K groups of associated monitoring nodes; step B, calling the K groups of associated operation data of the K groups of associated monitoring nodes from the historical transportation data; step C, generating a transportation deviation calculation network by performing multiple regression analysis on the K groups of associated operation data; step D, associatively storing the K edge monitoring nodes and the K groups of associated monitoring nodes based on a knowledge graph to generate a pipe network backtracking judgment network; step E, loading the transportation deviation calculation network and the pipe network backtracking judgment network to the remote monitoring cloud to complete the function configuration of the remote monitoring cloud.

[0029] Preferably, historical transportation data of the fluid transportation pipeline network is obtained, which may include flow rate, pressure, transportation volume, etc. Operational correlation analysis is performed based on the historical transportation data, that is, statistical analysis, pattern recognition, etc. are carried out on these historical data to identify which monitoring points in the pipeline network have strong correlation relationships. For example, when there are fluctuations in the flow rate at certain pipeline positions, it may cause pressure changes at other positions, and then K groups of associated monitoring nodes are identified. Each group of associated monitoring nodes is a pipeline network position that is correlated in the operating state; then, K groups of associated operation data of the K groups of associated monitoring nodes are retrieved from the historical transportation data, that is, the detailed transportation data of each group of associated nodes in the past period of time is retrieved, such as flow rate, pressure, etc.; then, multiple regression analysis is performed on these K groups of associated operation data, that is, to explore how multiple factors (such as flow rate, pressure, etc. at different pipeline network positions) jointly affect the output of the pipeline network (such as the transportation efficiency of the pipeline network) to identify the transportation deviation between different monitoring points. As the result of the regression analysis, a calculation network is constructed based on the analysis result to predict possible transportation deviations in the pipeline network. For example, if there is an abnormal fluctuation in the flow rate of a node, the regression can predict whether it will affect other pipeline network nodes. Then, the K edge monitoring nodes and the K groups of associated monitoring nodes are stored in the knowledge graph to generate a pipeline network backtracking judgment network to trace the source of the problem. For example, if an abnormality occurs at a certain node, through backtracking analysis, it is judged whether it is related to the transportation deviation of other nodes to find the root cause of the failure. Finally, the calculated transportation deviation calculation network and the pipeline network backtracking judgment network are loaded into the remote monitoring cloud to complete the function configuration of the remote monitoring cloud, enabling the remote monitoring cloud to realize dynamic monitoring and fault warning of the pipeline network operation data, and further realizing intelligent and automated monitoring and management of the pipeline network.

[0030] Further, step C further includes step C1, performing multiple regression analysis on the K groups of associated operation data to obtain K flow rate correlation functions and K pressure correlation functions; step C2, constructing K flow rate correlation analysis channels and K pressure correlation analysis channels based on the K flow rate correlation functions and the K pressure correlation functions; step C3, mapping and paralleling the K flow rate correlation analysis channels and the K pressure correlation analysis channels to complete the construction of K transportation deviation calculation units; step C4, paralleling the K transportation deviation calculation units to generate the transportation deviation calculation network.

[0031] Preferably, perform multiple regression analysis on K groups of associated operation data (historical operation data of K pipe network monitoring nodes, including flow rate, pressure, etc.) to determine the relationships between nodes. Specifically, by analyzing the flow rate data of a certain monitoring node and the flow rate data of other relevant nodes, establish a flow rate association function to predict or describe the flow rate fluctuation pattern of this node. Similarly, through regression analysis of the pressure data, obtain the association function of the pressure between nodes to predict the performance of each node under different pressures, and then obtain K flow rate association functions and K pressure association functions; then construct K flow rate association analysis channels and K pressure association analysis channels according to the K flow rate association functions and K pressure association functions respectively. Each flow rate association analysis channel corresponds to a flow rate association function, indicating the flow rate association relationship between a specific node and other relevant nodes. The flow rate association analysis channel inputs real-time data and uses the flow rate association function for analysis to predict the current flow rate data; each pressure association analysis channel corresponds to a pressure association function, reflecting the correlation and change of node pressure. Through the pressure association analysis channel, the real-time data of node pressure can be monitored and the pressure data of the node can be predicted.

[0032] Preferably, map and connect in parallel the flow rate association analysis channel and the pressure association analysis channel (connect one-to-one) to construct a transportation deviation calculation unit, and then complete the construction of K transportation deviation calculation units to ensure that each monitoring node has both flow rate analysis ability and pressure analysis ability. Among them, each unit includes flow rate deviation calculation (real-time analysis of whether the flow rate data of the node is abnormal) and pressure deviation calculation (simultaneously analyzing the deviation of the node pressure data), that is, the transportation deviation calculation unit can comprehensively analyze the flow rate and pressure data of a single monitoring node to identify abnormal deviations; finally, connect the K transportation deviation calculation units in parallel to generate a transportation deviation calculation network. Each calculation unit is responsible for the data analysis of a monitoring node, and the transportation deviation calculation network as a whole is responsible for the global monitoring of the entire pipe network, used to monitor and calculate the flow rate and pressure deviations of the entire pipe network system, can process the real-time data of multiple nodes simultaneously, identify abnormal phenomena within the global scope, and achieve real-time monitoring and early warning of large-scale complex pipe networks.

[0033] Step S300, after receiving the detection risk warning, the remote monitoring cloud locates the edge node by parsing the detection risk warning and outputs a combination of real-time risk nodes and real-time associated nodes.

[0034] Preferably, after the remote monitoring cloud receives the detection risk warning (an alarm signal sent from the edge monitoring node, including detailed fault data, such as specific location, time, flow rate fluctuation, or pressure anomaly), it analyzes the detection risk warning, identifies the anomaly, and extracts key information, including the abnormal monitoring node (i.e., the location where the warning occurs), the type and degree of the anomaly (such as the flow rate exceeding the threshold by 30%, the pressure being lower than the set value, etc.), and locates the specific edge monitoring node where the anomaly occurs through this key information, that is, the key nodes arranged in the pipe network through historical data analysis and the monitoring network, which are responsible for real-time monitoring of flow rate, pressure, etc., and then determines the real-time risk node (the specific monitoring node in the pipe network where the anomaly is detected) and the real-time associated node combination. Among them, the real-time associated node is another monitoring node that is associated with the risk node in the operating state and may interact with each other through flow rate, pressure, or physical connection. The real-time associated node combination is a set of nodes representing all the monitoring nodes currently associated with the risk node, thereby realizing the real-time and accurate risk assessment and warning functions for the pipe network.

[0035] Further, step S300 further includes step S310, where the first ultrasonic detection device continuously collects the first real-time flow rate and the first real-time pressure of the first pipe network monitoring site and transmits the first real-time flow rate and the first real-time pressure to the first edge monitoring node; step S320, in the first edge monitoring node, when any one of the first real-time flow rate and the first real-time pressure does not meet the first flow anomaly threshold and the first pressure anomaly threshold, or both the first real-time flow rate and the first real-time pressure do not meet the first collaborative anomaly threshold, the first edge monitoring node generates the detection risk warning, where the detection risk warning includes the first edge monitoring node and the measured data of the node pipe network, and the measured data of the node pipe network includes the first real-time flow rate and the first real-time pressure; step S330, after the remote monitoring cloud receives the detection risk warning, it performs edge node positioning by analyzing the detection risk warning and outputs the first pipe network monitoring site as the real-time risk node; step S340, uses the real-time risk node to traverse the pipe network backtracking judgment network to obtain the real-time associated node combination, where the real-time associated node combination is composed of M edge monitoring nodes, and M is a positive integer less than K.

[0036] Preferably, the first ultrasonic detection device is used to collect the first real-time flow rate and the first real-time pressure of the first pipe network monitoring site in real time, and transmit them to the first edge monitoring node to determine whether there is an abnormality and generate a risk warning. Specifically, in the first edge monitoring node, if the first real-time flow rate or the first real-time pressure does not meet the first flow rate abnormality threshold or the first pressure abnormality threshold, or both the first real-time flow rate and the first real-time pressure do not meet the first collaborative abnormality threshold, a detection risk warning is generated, including the location of the first edge monitoring node (i.e., the monitoring point) and the measured data of the node pipe network (i.e., the current first real-time flow rate and the first real-time pressure); after receiving the detection risk warning, the remote monitoring cloud performs warning analysis, that is, analyzes the location of the warning node (the first pipe network monitoring site) and the current measured data, determines the location of the edge monitoring node that issues the warning, and determines it as the real-time risk node and outputs it; then, the determined real-time risk node is used to traverse the pipe network to backtrack and judge the network, and other monitoring nodes associated with this node are judged through the pipe network backtracking and judging network, and M real-time associated nodes are obtained to form a real-time associated node combination, where M is a positive integer representing the number of associated nodes, and M is less than K, so as to conduct comprehensive fault warning and management, and more effectively ensure the safe operation of the pipe network.

[0037] Step S400, the remote monitoring cloud outputs the node pipe network verification data by performing data backtracking analysis on the real-time associated node combination.

[0038] Preferably, the remote monitoring cloud uses the data of the real-time associated node combination to generate the node pipe network verification data through backtracking analysis, that is, analyzes the operation data (flow rate data and pressure data) of the real-time associated node combination, and calculates the pipe network verification data of the monitoring node, including flow rate data and pressure data. Specifically, according to the monitoring data of the associated nodes (such as time series data of flow rate, pressure, etc.), the real-time deviation calculation unit in the deviation calculation network is used to calculate the flow rate data and pressure data of the node, and then the node pipe network verification data is generated to verify the operation state and abnormal conditions of the pipe network. For example, it verifies whether the flow rate and pressure of the current node are consistent with the measured data, and evaluates whether the real-time associated nodes are abnormal due to the influence of the risk node, ensuring the intelligence and accuracy of the pipe network monitoring, and at the same time improving the efficiency of risk management.

[0039] Further, step S400 further includes step S410, where the remote monitoring cloud generates a pipeline network data traceback instruction according to the M edge monitoring nodes. Among them, the pipeline network data traceback instruction includes M data traceback authorities; step S420, the M edge monitoring nodes receive and transmit M node pipeline network traceback data to the remote monitoring cloud according to the M data traceback authorities; step S430, the remote monitoring cloud activates a real-time deviation calculation unit from the K delivery deviation calculation units of the delivery deviation calculation network according to the real-time risk node; step S440, input the M node pipeline network traceback data into the real-time deviation calculation unit, and calculate and obtain the node pipeline network verification data. Among them, the node pipeline network verification data includes node flow verification data and node pressure verification data.

[0040] Preferably, the remote monitoring cloud generates a pipeline network data traceback instruction according to the M edge monitoring nodes, that is, an instruction requiring these nodes to transmit historical data related to abnormal flow and pressure to the cloud. When each edge monitoring node receives the instruction, it is given a specific data traceback authority, which determines the types of historical data (such as flow, pressure, etc.) that the node needs to transmit back, as well as the time range of the data; the M node pipeline network traceback data (including node historical flow data and node historical pressure data) refers to the historical operation data transmitted back by the M edge monitoring nodes according to the data traceback authority. Specifically, after receiving the traceback instruction, the edge monitoring node retrieves the stored pipeline network historical data according to the specified authority and transmits the pipeline network data that meets the requirements back to the remote monitoring cloud; when the remote monitoring cloud locates the real-time risk node, it calls and activates the real-time deviation calculation unit related to this node among the K delivery deviation calculation units of the delivery deviation calculation network, which is used to analyze the deviation situation of the current abnormal node; finally, the pipeline network traceback data collected from the M edge monitoring nodes is input into the activated real-time deviation calculation unit, and the deviation calculation unit uses the correlation functions (such as flow correlation function, pressure correlation function) in the delivery deviation calculation network to perform data analysis, and calculates and obtains the node pipeline network verification data, which is used to verify whether the current pipeline network operation state meets the expectations, including node flow verification data (the deviation degree of the flow, for example, whether the actual flow exceeds the normal range) and node pressure verification data (the abnormal degree of the pressure, for example, whether there is overpressure or too low pressure), so as to ensure accurate fault location and improve the pipeline network management efficiency.

[0041] Step S500, extract the node pipeline network measured data from the detection risk warning, and output the remote risk type of the real-time risk node by comparing the node pipeline network verification data and the node pipeline network measured data.

[0042] Preferably, the measured data of the node pipe network (including real-time flow and real-time pressure) is extracted from the risk warning extraction, and then the verification data of the node pipe network is compared with the measured data of the node pipe network, that is, the measured data of the node pipe network (current state) is compared item by item with the verification data of the node pipe network (expected state), including single-index deviation analysis and collaborative abnormal deviation analysis, calculating the deviation value between the measured data and the verification data, and analyzing whether the deviation exists for a long time or occurs suddenly in the short term, so as to judge the type of failure (such as pipe network failures such as pipe blockage and leakage or ultrasonic detection equipment failures), and finally classifying the failures or abnormal states of the risk nodes, and outputting the remote risk types of the real-time risk nodes, which may include pipe network failures (pipe leakage, pipe blockage), detection equipment failures or abnormal operating parameters (overpressure or low pressure). For example, if the flow rate decreases significantly and the pressure increases, it may be a pipe blockage; if the flow rate and pressure both decrease, it may be a pipe leakage; if there is no deviation in the flow rate and pressure, it may be a detection equipment failure. By combining the comparison of the verification data and the measured data, the failure can be more accurately located and classified, the time from failure detection to response can be shortened, and the efficiency of pipe network management can be improved.

[0043] Further, step S500 further includes step S510 of calculating the Euclidean distance between the verification data of the node pipe network and the measured data of the node pipe network to obtain a first verification deviation; step S520 of performing one-dimensional deviation calculation on the first real-time flow rate and the node flow rate verification data to obtain a second verification deviation; step S530 of performing one-dimensional deviation calculation on the first real-time pressure and the node pressure verification data to obtain a third verification deviation; step S540 of performing weighted calculation on the first verification deviation, the second verification deviation and the third verification deviation based on a preset deviation weight to obtain a comprehensive verification deviation; step S550, if the comprehensive verification deviation meets the preset verification deviation threshold, the remote risk type is a pipe network failure; step S560, if the comprehensive verification deviation does not meet the preset verification deviation threshold, the remote risk type is a detection equipment failure.

[0044] Preferably, based on the Euclidean distance, calculate the Euclidean distance between the node pipe network verification data and the node pipe network measured data, that is, the first verification deviation, which represents the overall deviation between the node measured data and the verification data. Then, perform a one-dimensional deviation calculation on the first real-time flow rate and the node flow rate verification data, that is, separately calculate the difference between the first real-time flow rate (measured flow rate) and the node flow rate verification data (expected flow rate) as the second verification deviation, which represents the deviation degree (abnormality) of the pipe network flow rate. Similarly, perform a one-dimensional deviation calculation on the first real-time pressure and the node pressure verification data, that is, calculate the difference between the first real-time pressure (measured pressure) and the node pressure verification data (expected pressure), which represents the deviation degree (abnormality) of the pipe network pressure. Assign different weights to different deviations (for example, the importance of flow rate and pressure to the operation of the pipe network is different) to comprehensively consider the deviations of flow rate and pressure. Through the preset deviation weights, perform a weighted sum of the first verification deviation (overall deviation), the second verification deviation (flow rate deviation), and the third verification deviation (pressure deviation) to obtain the comprehensive verification deviation. Finally, judge the remote risk type of the pipe network according to the comprehensive verification deviation. If the comprehensive verification deviation exceeds the preset verification deviation threshold, it is determined that there is a pipe network failure. If the comprehensive verification deviation does not exceed the preset verification deviation threshold, it may be that there is a failure in the monitoring equipment itself (such as sensor failure, equipment error, etc.). Among them, the preset verification deviation threshold is a standard value set according to historical data and experience. By comparing the comprehensive verification deviation with the threshold, quickly and accurately determine whether the pipe network state is due to a pipe network failure or an equipment failure, so as to achieve precise fault diagnosis and rapid response, and then improve the efficiency and quality of the risk monitoring of the fluid transportation pipeline network.

[0045] In the above, with reference to Figure 1 a remote monitoring method for an ultrasonic detection device according to an embodiment of the present invention was described in detail. Next, with reference to Figure 2 a remote monitoring system for an ultrasonic detection device according to an embodiment of the present invention will be described.

[0046] The remote monitoring system for an ultrasonic detection device according to an embodiment of the present invention is used to solve the technical problems in the prior art that it is difficult to distinguish the early warning triggered by a pipe network failure or an ultrasonic detection device failure, which leads to low reliability of pipe network monitoring, low efficiency of risk monitoring, and poor accuracy of fault early warning, and achieves the technical effect of realizing two-way monitoring of the device and the pipe network, improving the efficiency, reliability, and early warning accuracy of pipe network risk monitoring. As Figure 2 shown, the remote monitoring system for an ultrasonic detection device includes: a detection device layout module 10, a pipe network anomaly analysis module 20, an edge node positioning module 30, a data backtracking analysis module 40, and a remote risk type output module 50.

[0047] The detection device deployment module 10 is used to deploy detection devices according to the historical fault records of the fluid transportation pipeline network, and obtain K ultrasonic detection devices deployed at K pipeline network monitoring sites. The pipeline network anomaly analysis module 20 is used to analyze the pipeline network anomalies according to the historical fault records, and configure K edge monitoring nodes at the K pipeline network monitoring sites according to the analysis results, wherein the K edge monitoring nodes are bidirectionally communicatively connected to the remote monitoring cloud, and the K edge monitoring nodes are unidirectionally communicatively connected to the K ultrasonic detection devices. The edge node positioning module 30 is used to perform edge node positioning by parsing the detection risk warning after the remote monitoring cloud receives the detection risk warning, and output a combination of real-time risk nodes and real-time associated nodes. The data traceback analysis module 40 is used for the remote monitoring cloud to perform data traceback analysis on the real-time associated node combination and output node pipeline network verification data. The remote risk type output module 50 is used to extract the measured data of the node pipeline network from the detection risk warning, and output the remote risk type of the real-time risk node by comparing the node pipeline network verification data and the measured data of the node pipeline network.

[0048] Next, the specific configuration of the pipeline network anomaly analysis module 20 will be described in detail. The pipeline network anomaly analysis module 20 further includes: performing operation correlation analysis on the historical transportation data of the fluid transportation pipeline network to obtain K groups of associated monitoring nodes; calling the K groups of associated operation data of the K groups of associated monitoring nodes from the historical transportation data; generating a transportation deviation calculation network by performing multiple regression analysis on the K groups of associated operation data; associatively storing the K edge monitoring nodes and the K groups of associated monitoring nodes based on a knowledge graph to generate a pipeline network traceback judgment network; loading the transportation deviation calculation network and the pipeline network traceback judgment network into the remote monitoring cloud to complete the function configuration of the remote monitoring cloud.

[0049] Next, the specific configuration of the pipeline network anomaly analysis module 20 will be further described in detail. The pipeline network anomaly analysis module 20 further includes: performing multiple regression analysis on the K groups of associated operation data to obtain K flow correlation functions and K pressure correlation functions; constructing K flow correlation analysis channels and K pressure correlation analysis channels based on the K flow correlation functions and the K pressure correlation functions; mapping and paralleling the K flow correlation analysis channels and the K pressure correlation analysis channels to complete the construction of K transportation deviation calculation units; paralleling the K transportation deviation calculation units to generate the transportation deviation calculation network.

[0050] Next, the specific configuration of the pipeline network anomaly analysis module 20 will be further described in detail. The pipeline network anomaly analysis module 20 further includes: obtaining the first historical fault monitoring data of the first pipeline network monitoring node by calling from the historical fault records; obtaining a plurality of first historical fault flows and a plurality of first historical fault pressures by disassembling the first historical fault monitoring data; using IQR to perform univariate analysis on the plurality of first historical fault flows and the plurality of first historical fault pressures respectively to obtain a first flow anomaly threshold and a first pressure anomaly threshold; constructing a first pipeline network heat map according to the temporal characteristics of the plurality of first historical fault flows and the plurality of first historical fault pressures; performing joint region analysis on the first pipeline network heat map through K-means clustering to output a first collaborative anomaly threshold, where the first collaborative anomaly threshold includes a second flow anomaly threshold and a second pressure anomaly threshold; constructing a first edge monitoring node based on the first flow anomaly threshold, the first pressure anomaly threshold, and the first collaborative anomaly threshold; and so on, configuring the K edge monitoring nodes at the K pipeline network monitoring sites.

[0051] Next, the specific configuration of the edge node positioning module 30 will be described in detail. The edge node positioning module 30 further includes: the first ultrasonic detection device real-time collects the first real-time flow and the first real-time pressure of the first pipeline network monitoring site and transmits the first real-time flow and the first real-time pressure to the first edge monitoring node; in the first edge monitoring node, when any one of the first real-time flow and the first real-time pressure does not meet the first flow anomaly threshold and the first pressure anomaly threshold, or both the first real-time flow and the first real-time pressure do not meet the first collaborative anomaly threshold, the first edge monitoring node generates the detection risk warning, where the detection risk warning includes the first edge monitoring node and the measured data of the node pipeline network, and the measured data of the node pipeline network includes the first real-time flow and the first real-time pressure; after receiving the detection risk warning, the remote monitoring cloud performs edge node positioning by parsing the detection risk warning and outputs the first pipeline network monitoring site as the real-time risk node; using the real-time risk node to traverse the pipeline network backtracking judgment network to obtain the real-time associated node combination, where the real-time associated node combination is composed of M edge monitoring nodes, and M is a positive integer less than K.

[0052] Next, the specific configuration of the data traceback analysis module 40 will be described in detail. The data traceback analysis module 40 further includes: the remote monitoring cloud generates a pipeline network data traceback instruction according to the M edge monitoring nodes, where the pipeline network data traceback instruction includes M data traceback authorities; the M edge monitoring nodes receive and transmit M node pipeline network traceback data to the remote monitoring cloud according to the M data traceback authorities; the remote monitoring cloud activates a real-time deviation calculation unit from the K delivery deviation calculation units of the delivery deviation calculation network according to the real-time risk node; input the M node pipeline network traceback data into the real-time deviation calculation unit to calculate and obtain the node pipeline network verification data, where the node pipeline network verification data includes node flow verification data and node pressure verification data.

[0053] Next, the specific configuration of the remote risk type output module 50 will be described in detail. The remote risk type output module 50 further includes: calculating the Euclidean distance between the node pipeline network verification data and the node pipeline network measured data to obtain a first verification deviation; performing a one-dimensional deviation calculation on the first real-time flow and the node flow verification data to obtain a second verification deviation; performing a one-dimensional deviation calculation on the first real-time pressure and the node pressure verification data to obtain a third verification deviation; performing a weighted calculation on the first verification deviation, the second verification deviation, and the third verification deviation based on a preset deviation weight to obtain a comprehensive verification deviation; if the comprehensive verification deviation meets the preset verification deviation threshold, the remote risk type is a pipeline network failure; if the comprehensive verification deviation does not meet the preset verification deviation threshold, the remote risk type is a detection device failure.

[0054] The remote monitoring system of the ultrasonic detection device provided by the embodiment of the present invention can execute the remote monitoring method of the ultrasonic detection device provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0055] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0056] The above specific implementation manners do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A remote monitoring method for ultrasonic control and measurement equipment, characterized in that: The method comprises: Deploy control and measurement equipment according to historical fault records of the fluid transport pipeline network, and obtain K ultrasonic control and measurement equipment deployed at K pipeline network monitoring locations; Performing pipeline network abnormality analysis according to the historical fault records, and configuring K edge monitoring nodes at the K pipeline network monitoring locations according to the analysis results, wherein the K edge monitoring nodes are bidirectionally connected to the remote monitoring cloud, and the K edge monitoring nodes are unidirectionally connected to the K ultrasonic control and measurement devices; After receiving the control and measurement risk warning, the remote monitoring cloud performs edge node positioning by analyzing the control and measurement risk warning, and outputs a real-time risk node and a real-time associated node combination; The remote monitoring cloud performs data backtracking analysis on the real-time associated node combination and outputs node network verification data; The measured data of the node network is extracted from the control and measurement risk warning, and the remote risk type of the real-time risk node is output by comparing the node network verification data with the measured data of the node network.

2. The remote monitoring method of ultrasonic control and measurement equipment according to claim 1, characterized in that: The method further comprises: Performing operation correlation analysis based on historical transportation data of the fluid transportation pipeline network to obtain K groups of associated monitoring nodes; Calling the K groups of associated operation data of the K groups of associated monitoring nodes from the historical transport data; Generate a delivery deviation calculation network by performing a multivariate regression analysis on the K groups of associated operation data; Based on the knowledge graph, the K edge monitoring nodes and the K groups of associated monitoring nodes are stored in association to generate a pipe network backtracking judgment network; The transmission deviation calculation network and the pipeline network backtracking judgment network are loaded into the remote monitoring cloud to complete the functional configuration of the remote monitoring cloud.

3. The remote monitoring method of ultrasonic control and measurement equipment according to claim 2, characterized in that: By performing a multivariate regression analysis on the K groups of associated operation data, a delivery deviation calculation network is generated, and the method includes: Performing a multivariate regression analysis on the K groups of associated operation data to obtain K flow correlation functions and K pressure correlation functions; Constructing K flow correlation analysis channels and K pressure correlation analysis channels based on the K flow correlation functions and the K pressure correlation functions; Mapping and connecting the K flow correlation analysis channels and the K pressure correlation analysis channels in parallel to complete the construction of K delivery deviation calculation units; The K conveying deviation calculation units are connected in parallel to generate the conveying deviation calculation network.

4. The remote monitoring method of ultrasonic control and measurement equipment according to claim 3, characterized in that: Performing pipeline network anomaly analysis according to the historical fault records, and configuring K edge monitoring nodes at the K pipeline network monitoring sites according to the analysis results, the method comprising: Obtaining first historical fault monitoring data of a first pipe network monitoring node from the historical fault record; By disassembling the first historical fault monitoring data, a plurality of first historical fault flows and a plurality of first historical fault pressures are obtained; Using IQR to perform univariate analysis on the plurality of first historical fault flows and the plurality of first historical fault pressures, respectively, to obtain a first flow abnormality threshold and a first pressure abnormality threshold; Constructing a first pipe network heat map according to the time series characteristics of the plurality of first historical fault flows and the plurality of first historical fault pressures; Performing joint regional analysis on the first pipe network heat map by K-means clustering, and outputting a first collaborative abnormality threshold, wherein the first collaborative abnormality threshold includes a second flow abnormality threshold and a second pressure abnormality threshold; Building a first edge monitoring node based on the first flow abnormality threshold, the first pressure abnormality threshold and the first collaborative abnormality threshold; By analogy, the K edge monitoring nodes are configured at the K pipe network monitoring sites.

5. The remote monitoring method of ultrasonic control and measurement equipment according to claim 4, characterized in that: After the remote monitoring cloud receives the control and measurement risk warning, edge nodes are located by parsing the control and measurement risk warning, and a real-time risk node and a real-time associated node combination are output. The method includes: The first ultrasonic control and measurement device collects the first real-time flow and the first real-time pressure at the first pipe network monitoring point in real time, and transmits the first real-time flow and the first real-time pressure to the first edge monitoring node; In the first edge monitoring node, when either the first real-time flow rate or the first real-time pressure does not satisfy the first flow rate abnormality threshold and the first pressure abnormality threshold, or both the first real-time flow rate and the first real-time pressure do not satisfy the first coordinated abnormality threshold, the first edge monitoring node generates the control and measurement risk warning, wherein the control and measurement risk warning includes the first edge monitoring node and the node pipe network measured data, and the node pipe network measured data includes the first real-time flow rate and the first real-time pressure; After receiving the control and measurement risk warning, the remote monitoring cloud performs edge node positioning by analyzing the control and measurement risk warning, and outputs the first pipe network monitoring site as the real-time risk node; The real-time risk node is used to traverse the pipeline network backtracking judgment network to obtain the real-time associated node combination, wherein the real-time associated node combination is composed of M edge monitoring nodes, and M is a positive integer less than K.

6. The remote monitoring method of ultrasonic control and measurement equipment according to claim 5, characterized in that: The remote monitoring cloud performs data backtracking analysis on the real-time associated node combination to output node network validation data, and the method includes: The remote monitoring cloud generates a pipe network data backtracking instruction according to the M edge monitoring nodes, wherein the pipe network data backtracking instruction includes M data backtracking permissions; The M edge monitoring nodes receive and transmit the M node network backtracking data to the remote monitoring cloud according to the M data backtracking permissions; The remote monitoring cloud activates a real-time deviation calculation unit from the K delivery deviation calculation units of the delivery deviation calculation network according to the real-time risk node; The M node pipe network traceback data are input into the real-time deviation calculation unit to calculate and obtain the node pipe network verification data, wherein the node pipe network verification data includes node flow verification data and node pressure verification data.

7. The remote monitoring method of ultrasonic control and measurement equipment according to claim 6, characterized in that: By comparing the node pipe network validation data and the node pipe network measured data, the remote risk type of the real-time risk node is output, and the method includes: Calculating the Euclidean distance between the node pipe network validation data and the node pipe network measured data to obtain a first validation deviation; Performing a one-dimensional deviation calculation on the first real-time traffic and node traffic validation data to obtain a second validation deviation; Performing a one-dimensional deviation calculation on the first real-time pressure and node pressure verification data to obtain a third verification deviation; Performing weighted calculation on the first verification deviation, the second verification deviation and the third verification deviation based on a preset deviation weight to obtain a comprehensive verification deviation; If the comprehensive validation deviation meets the preset validation deviation threshold, the remote risk type is a pipeline network failure; If the comprehensive verification deviation does not meet the preset verification deviation threshold, the remote risk type is a control and measurement equipment failure.

8. A remote monitoring system for ultrasonic control and measurement equipment, characterized in that: The system is used to implement the remote monitoring method of the ultrasonic control and measurement equipment according to any one of claims 1 to 7, and the system comprises: A control and measurement equipment deployment module is used to deploy control and measurement equipment according to the historical fault records of the fluid transmission pipeline network, and obtain K ultrasonic control and measurement equipment deployed at K pipeline network monitoring locations; A pipe network abnormality analysis module, used for performing pipe network abnormality analysis according to the historical fault records, and configuring K edge monitoring nodes at the K pipe network monitoring sites according to the analysis results, wherein the K edge monitoring nodes are bidirectionally connected to the remote monitoring cloud, and the K edge monitoring nodes are unidirectionally connected to the K ultrasonic control and measurement devices; An edge node positioning module is used for locating edge nodes by analyzing the control and measurement risk warning after the remote monitoring cloud receives the control and measurement risk warning, and outputting a real-time risk node and a real-time associated node combination; A data backtracking analysis module is used for the remote monitoring cloud to perform data backtracking analysis on the real-time associated node combination and output node network verification data; The remote risk type output module is used to extract the node network measured data from the control and measurement risk warning, and output the remote risk type of the real-time risk node by comparing the node network verification data with the node network measured data.

Images