Intelligent pipeline leakage monitoring system based on positioning fitting technology

Abstract

The present invention relates to the technical field of pipeline leakage detection, and in particular to an intelligent pipeline leakage monitoring system based on positioning and fitting technology, including a sensor configuration and signal preprocessing module, a signal interference processing module, a real-time monitoring and abnormality identification module, and a positioning and fitting and leakage assessment module; by deploying a sensor network, determining and optimizing the sensor position, and preprocessing the sensor signal at the same time, it is beneficial to improve the monitoring efficiency of the sensor; by anti-interference processing of the sensor signal, the reliability and integrity of data transmission are guaranteed; by monitoring and analyzing the pipeline state, the possible leakage point is preliminarily identified to provide data support for subsequent data analysis; by using the positioning and fitting technology to obtain the precise position of the suspected leakage point, and conducting leakage assessment analysis, it is beneficial to take measures and provide a basis for subsequent decision-making. The present invention is used to solve the technical problem that the efficiency of current pipeline leakage monitoring is low.

Description

Technical Field

[0001] The invention relates to the technical field of pipeline leakage detection, and in particular to an intelligent pipeline leakage monitoring system based on positioning fitting technology. Background Art

[0002] Pipeline leakage detection technology refers to a series of technical means used to find and locate leakage points in pipelines. Through specific methods and equipment, pipelines are inspected and tested to find and determine whether there are leakage points and their specific locations. Positioning fitting technology refers to the technology of approximating or describing a set of data points through mathematical models or functions, and determining the location of a specific target or phenomenon based on this.

[0003] In the current pipeline system leakage detection, there are still the following problems: low monitoring efficiency. The existing pipeline leakage detection technology may have deficiencies in monitoring efficiency and cannot timely and accurately find the leakage points in the pipeline, which may lead to the leakage problem not being handled in time, thereby causing greater safety hazards and economic losses; insufficient signal interference and data processing. The signals collected by the current sensors may be subject to various interferences during the transmission process, such as electromagnetic interference, environmental noise, etc., which will affect the accuracy and reliability of the signal. At the same time, a large amount of raw data needs to be effectively processed and analyzed to extract useful information and identify the leakage points. The current technology may have deficiencies in signal anti-interference processing and data processing, resulting in false alarms and missed alarms; insufficient positioning accuracy. Although some technologies can detect the presence of leakage in the pipeline, there may be difficulties in determining the exact location of the leakage point, which may make it difficult to accurately implement subsequent maintenance work and increase the cost and time of repair. Therefore, a series of targeted methods are urgently needed to deal with these problems in order to improve the monitoring and optimization management level of pipeline leakage. Summary of the invention

[0004] The purpose of the present invention is to solve the problems in the background technology and to propose an intelligent pipeline leakage monitoring system based on positioning fitting technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The pipeline leakage intelligent monitoring system based on positioning fitting technology includes: sensor configuration and signal preprocessing module, signal interference processing module, real-time monitoring and abnormality recognition module, and positioning fitting and leakage assessment module;

[0007] Sensor configuration and signal preprocessing module: deploy sensor networks, determine sensor locations, and optimize sensor locations; preprocess the raw signals of sensors through built-in signal conditioning circuits;

[0008] Signal interference processing module: responsible for the anti-interference work of the sensor signal after pre-processing and obtaining the optimal estimated value of the useful signal;

[0009] Real-time monitoring and abnormality identification module: monitors and analyzes the collected pipeline status data, preliminarily identifies possible leakage points, and marks abnormalities;

[0010] Positioning fitting and leakage assessment module: Determine suspected leakage points based on abnormally marked data, use positioning fitting technology to obtain the precise location of the suspected leakage point, and evaluate and analyze whether the location has generated a leakage event.

[0011] It should be noted that the application object of the pipeline leakage intelligent monitoring system based on positioning and fitting technology in the embodiment of the present invention can be pipeline system management in the field of industry or urban infrastructure. Specifically, it can be for comprehensive analysis and data processing of pipeline status data through big data analysis technology, and intelligent monitoring of pipeline leakage through multiple core links such as sensor configuration and signal preprocessing, signal interference processing, real-time monitoring and abnormality identification, positioning fitting and leakage assessment, so as to achieve accurate positioning of pipeline leakage points. At the same time, the system also promotes scientific decision-making for pipeline maintenance and reduces maintenance costs.

[0012] Furthermore, the process of deploying the sensor network, determining the sensor location, and optimizing the sensor location in the data collection and preprocessing module includes:

[0013] In pipeline monitoring, a linear topology is chosen to deploy the sensor network;

[0014] Based on the linear arrangement of sensors along the pipeline, using the diagram represents a sensor network; each sensor corresponds to a node in the sensor network, is a node set, representing the set of all sensors, is a set of edges, representing the connection relationship between sensors, then , , where Represents a node, represents the edge, Indicates the number of nodes; in a linear topology, each node All nodes are connected to each other by edges or Connected, Represents the node index;

[0015] After completing the sensor network deployment, obtain the total length of the pipeline , installed along the pipeline Sensors;

[0016] It can be understood that by deploying highly sensitive leakage detection sensors (such as pressure sensors, humidity sensors, acoustic sensors, etc.) at key locations along the pipeline, a comprehensive monitoring network is formed;

[0017] Get the location of the sensor , where represents the number of sensor locations; where ;

[0018] Set the sensor's detection range to a fixed value Each sensor covers the left and right sides of its position If the distance between adjacent sensors is less than twice the detection range, then there is a constraint: the distance between adjacent sensors does not exceed twice the detection range, that is , where Indicates the sensor location index;

[0019] Maximize sensor coverage using the formula: , where Indicates the area not covered by the sensor; Indicates the distance between adjacent sensors; Indicates the actual covered portion within the distance and does not exceed the detection range of the sensor ;

[0020] It is understood that in order to maximize the coverage and accuracy of the sensor monitoring network, the location of the sensors is optimized to ensure that the spacing between the sensors is as small as possible so as to reduce any portion of the pipeline not covered by the sensors so that the entire pipeline is effectively monitored;

[0021] Each sensor in the sensor network will continuously collect pipeline status data near its location, including pressure, humidity, sound, etc.; the pipeline status data will be recorded and stored in the form of time series.

[0022] Furthermore, the data collection and preprocessing module preprocesses the original signal of the sensor through the built-in signal conditioning circuit, including:

[0023] Get the original signal and use the formula The original signal is initially filtered and amplified, where: Represents the input signal, that is, the change of the original signal collected by the sensor over time. represents the output signal, that is, the change of the signal after being processed by the filter and amplifier over time. Represents the impulse response function of the filter, which is used to describe the frequency response characteristics of the filter to the input signal. Determines how the signal is transformed by the filter, is the gain of the amplifier, which represents the input signal With output signal The proportional relationship between Determines the degree to which the signal is amplified. The gain of the amplifier is set according to the output range of the sensor. Indicates the moment when the signal is acquired, and is used to describe the change of the signal over time. is an integral variable, representing the time from a certain moment in the past to the current moment The delay is used to calculate the integral of the product of the input signal and the impulse response function during the filtering process;

[0024] It is understandable that in a sensor network, the sensor is responsible for collecting data about the surrounding environment. These data are usually raw, unprocessed signals when collected. These raw signals may contain noise, interference or a format that is not suitable for direct transmission and processing. Therefore, the sensor must be equipped with a signal conditioning circuit. The main function of this circuit is to perform preliminary processing on these raw signals to improve the accuracy, reliability and readability of the data. Among them, signal conditioning may include operations such as amplification and filtering to convert the raw signal into a form suitable for transmission and processing, and to enhance the strength of the signal so that it can be more easily recognized and processed by subsequent circuits. In the present invention, the built-in signal conditioning circuit of the sensor will perform preliminary filtering and amplification on the collected raw signal. The purpose of filtering is to remove environmental noise interference, and the purpose of amplification is to improve the signal-to-noise ratio of the signal.

[0025] Furthermore, the signal interference processing module is responsible for the anti-interference work of the sensor signal after preprocessing, and the process of obtaining the optimal estimated value of the useful signal includes:

[0026] Receive pre-processed sensor signal set , where represents the received signal samples, represents the sampling time point of the corresponding signal sample, Indicates the number of sampling time points;

[0027] Get signal ruleset ;in, The representation consists of a set of rules that describe the generation, propagation, and reception of wanted and interfering signals;

[0028] According to the established set of received signals and signal rules, the optimal estimate of the useful signal is solved by calculating and maximizing the posterior probability:

[0029] , where Indicates that given a set of received signals , Signal Rule Set And the signal impact factor Under the condition of The best estimate of ; Represents the posterior probability, which is used to reflect the useful signal given the observed data and information. Credibility; Represents the posterior probability Reaching the maximum ; Indicates signal influencing factors, including signal frequency, phase, amplitude, power spectrum density of noise, channel gain and phase response, etc.;

[0030] The pipeline status data after signal interference processing is transmitted to the real-time monitoring and abnormality identification module through the network.

[0031] Furthermore, the real-time monitoring and anomaly identification module monitors and analyzes the collected pipeline status data, preliminarily identifies possible leakage points, and marks anomalies. The process includes:

[0032] for sensors, each with a time interval Collect pipeline status data; among them, Sensors at time The pipeline status data is represented as , and each sensor pipeline has a unique identifier ;

[0033] Arrange the pipeline status data into a time series form, that is, for each sensor, form a data sequence , where Indicates the amount of data;

[0034] Identifier Associated with the data sequence to form a data pair ;

[0035] Extract features from pipeline status data to obtain feature vectors , where represents the eigenvalue, represents the number of eigenvalues;

[0036] Random forest is used for training data. The training set contains normal pipeline status data and known abnormal pipeline status data, which are marked as , where Represents the data attributes of the training set. When , it is normal;

[0037] Extract feature vectors from newly collected pipeline status data ;

[0038] The feature vector Input the trained random forest model to get the prediction results ;like , it is marked as abnormal, and the abnormal pipeline status data and its identifier are recorded, that is, .

[0039] Furthermore, the positioning fitting and leakage assessment module determines the suspected leakage point based on the abnormally marked data, obtains the precise position of the suspected leakage point by using the positioning fitting technology, and evaluates and analyzes whether the position generates a leakage event. The process includes:

[0040] Extract all labeled abnormal pipeline status datasets , where Indicates the abnormal pipeline status data index, Indicates the number of abnormal pipeline status data;

[0041] According to the abnormal pipeline status data, the suspected leakage point set is set as , where Indicates the location of the suspected leak. Indicates the corresponding pipeline identifier, Indicates the location index of the suspected leakage point, Indicates the number of locations where leakage is suspected;

[0042] Based on the suspected leakage point identification conditions: ;

[0043] Combine suspected leakage points to obtain the corresponding sensor information set , where Indicates the sensor location, Indicates the signal time detected by the sensor. Indicates the sensor information index. Indicates the number of sensor information;

[0044] Use positioning algorithms to calculate the target location of suspected leaks :

[0045] , where Represents the error function in the positioning algorithm;

[0046] Analyze the calculated target position of the suspected leakage point and obtain the precise position of the suspected leakage point;

[0047] Based on the precise location of the suspected leak , obtain the monitoring set of leakage parameters at this location , where represents the leakage parameter, Represents the monitoring index of the leakage parameter, Indicates the number of monitoring leakage parameters;

[0048] Get the leakage rate based on the monitoring set of leakage parameters : ;

[0049] The impact of leakage is evaluated using the formula to generate leakage events:

[0050] , where Indicates the leakage impact value of the suspected leakage point; Indicates the maximum velocity allowed for pipeline leakage; represents the standard threshold value of leakage parameters; Indicates the leakage area of ​​the suspected leakage point; are respectively the preset leakage velocity, leakage parameter and proportional coefficient of leakage area;

[0051] Set a leakage detection threshold, compare and analyze the leakage impact value of the suspected leakage point with the leakage detection threshold. If the leakage impact value of the suspected leakage point is higher than the leakage detection threshold, a leakage event is generated; if the leakage impact value of the suspected leakage point is not higher than the leakage detection threshold, the suspected leakage point is further investigated.

[0052] Furthermore, the positioning fitting and leakage assessment module analyzes the calculated target position of the suspected leakage point and obtains the precise position of the suspected leakage point, including:

[0053] Identify the target location of suspected leaks , where Respectively represent the horizontal and vertical coordinates;

[0054] Get the The vector of sensor measurements , where Indicates the dimensions of the measurement, for example, if the measurement is distance and angle in two-dimensional space, then ;

[0055] Definition and The measurement matrix associated with each sensor , the measurement matrix The target location Mapping to a vector of measurements ;

[0056] Find the exact location of the suspected leakage point by using the weighted least squares formula , so that the sum of squares of weighted measurement errors of all sensors is minimized:

[0057] , where is the matrix transpose symbol, Indicates The covariance matrix of the measurement error of the sensors, and its inverse matrix is a weight matrix, which reflects the reliability and accuracy of different sensor measurements.

[0058] Compared with the existing technology, the advantages of the pipeline leakage intelligent monitoring system and method provided by the present invention based on positioning fitting technology are:

[0059] 1. The present invention deploys a sensor network, determines the sensor location, and optimizes the sensor location to form a comprehensive monitoring network to ensure comprehensive perception of the pipeline status; the original signal of the sensor is pre-processed by the built-in signal conditioning circuit, which is conducive to improving the signal-to-noise ratio of the signal and providing high-quality input for subsequent data processing;

[0060] 2. The present invention calculates and maximizes the posterior probability to solve the optimal estimate of the useful signal, effectively resists external interference, ensures the accuracy of the data, further purifies the sensor signal, reduces false alarms and missed alarms, and improves the stability and reliability of the monitoring system; by monitoring and analyzing the collected pipeline status data, the possible leakage points are preliminarily identified, and abnormal marking is performed, thereby improving the intelligent level of monitoring and providing strong support for subsequent precise positioning and leakage assessment;

[0061] 3. The present invention determines the suspected leakage point according to the abnormally marked data, obtains the precise position of the suspected leakage point by using the positioning fitting technology, and evaluates and analyzes whether the position generates a leakage event, which helps to take timely response measures and reduce losses. It can provide a scientific basis for pipeline maintenance and management, optimize maintenance strategies, and reduce maintenance costs.

[0062] In summary, the present invention realizes intelligent monitoring and efficient management of pipeline leakage through the steps of comprehensive monitoring of pipeline status, abnormality identification, precise positioning and leakage assessment, ensuring the efficient and stable operation of the subsequent pipeline leakage intelligent monitoring system based on positioning fitting technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a module diagram of the pipeline leakage intelligent monitoring system based on positioning fitting technology proposed by the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the implementation regulations described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] Reference Figure 1 , an intelligent pipeline leakage monitoring system based on positioning fitting technology, the system includes a sensor configuration and signal preprocessing module, a signal interference processing module, a real-time monitoring and abnormality recognition module, and a positioning fitting and leakage assessment module;

[0066] Sensor configuration and signal preprocessing module: deploy sensor networks, determine sensor locations, and optimize sensor locations; preprocess the raw signals of sensors through built-in signal conditioning circuits;

[0067] Signal interference processing module: responsible for the anti-interference work of the sensor signal after pre-processing and obtaining the optimal estimated value of the useful signal;

[0068] Real-time monitoring and abnormality identification module: monitors and analyzes the collected pipeline status data, preliminarily identifies possible leakage points, and marks abnormalities;

[0069] Positioning fitting and leakage assessment module: Determine suspected leakage points based on abnormally marked data, use positioning fitting technology to obtain the precise location of the suspected leakage point, and evaluate and analyze whether the location has generated a leakage event.

[0070] It should be noted that the application object of the pipeline leakage intelligent monitoring system based on positioning and fitting technology in the embodiment of the present invention can be pipeline system management in the field of industry or urban infrastructure. Specifically, it can be for comprehensive analysis and data processing of pipeline status data through big data analysis technology, and intelligent monitoring of pipeline leakage through multiple core links such as sensor configuration and signal preprocessing, signal interference processing, real-time monitoring and abnormality identification, positioning fitting and leakage assessment, so as to achieve accurate positioning of pipeline leakage points. At the same time, the system also promotes scientific decision-making for pipeline maintenance and reduces maintenance costs.

[0071] The sensor configuration and signal preprocessing module deploys the sensor network, determines the sensor location, and optimizes the sensor location. The steps of preprocessing the raw signal of the sensor through the built-in signal conditioning circuit include:

[0072] Step 101: In pipeline monitoring, a linear topology is selected to deploy a sensor network;

[0073] Step 102, based on the linear arrangement of sensors along the pipeline, using the diagram represents a sensor network;

[0074] In step 102, each sensor corresponds to a node in the sensor network. is a node set, representing the set of all sensors, is a set of edges, representing the connection relationship between sensors, then , , where Represents a node, represents the edge, Indicates the number of nodes, corresponding to the number of sensors; in a linear topology, each node All nodes are connected to each other by edges or Connected, Represents the node index, corresponding to the sensor index;

[0075] Step 103: After the sensor network deployment is completed, the total length of the pipeline is obtained. , installed along the pipeline Sensors;

[0076] In steps 101-103, a comprehensive monitoring network is formed by deploying highly sensitive leakage detection sensors (such as pressure sensors, humidity sensors, acoustic sensors, etc.) at key locations along the pipeline;

[0077] Step 104: Get the location of the sensor , where represents the number of sensor locations; where ;

[0078] Step 105: Set the sensor's detection range to a fixed value Each sensor covers the left and right sides of its position If the distance between adjacent sensors is less than twice the detection range, then there is a constraint: the distance between adjacent sensors does not exceed twice the detection range, that is , where Indicates the sensor location index;

[0079] Step 106: Maximize the sensor coverage area using the formula:

[0080] , where Indicates the area not covered by the sensor; Indicates the distance between adjacent sensors; Indicates the actual covered portion within the distance and does not exceed the detection range of the sensor ;

[0081] In step 106, in order to maximize the coverage and accuracy of the sensor monitoring network, the positions of the sensors are optimized to ensure that the spacing between the sensors is as small as possible, so as to reduce any portion of the pipeline not covered by the sensors, so that the entire pipeline can be effectively monitored;

[0082] Step 107: Each sensor in the sensor network will continuously collect pipeline status data near its location, including pressure, humidity, sound, etc.; wherein the pipeline status data is recorded and stored in the form of a time series;

[0083] Step 108: Get the original signal and use the formula The original signal is initially filtered and amplified, where: Represents the input signal, that is, the change of the original signal collected by the sensor over time. represents the output signal, that is, the change of the signal after being processed by the filter and amplifier over time. Represents the impulse response function of the filter, which is used to describe the frequency response characteristics of the filter to the input signal. Determines how the signal is transformed by the filter, is the gain of the amplifier, which represents the input signal With output signal The proportional relationship between Determines the degree to which the signal is amplified. The gain of the amplifier is set according to the output range of the sensor. Indicates the moment when the signal is acquired, and is used to describe the change of the signal over time. is an integral variable, representing the time from a certain moment in the past to the current moment The delay is used to calculate the integral of the product of the input signal and the impulse response function during the filtering process;

[0084] In step 108, in the sensor network, the sensor is responsible for collecting data about the surrounding environment. These data are usually raw, unprocessed signals when collected. These raw signals may contain noise, interference or the format is not suitable for direct transmission and processing. Therefore, the sensor must be equipped with a signal conditioning circuit. The main function of this circuit is to perform preliminary processing on these raw signals to improve the accuracy, reliability and readability of the data. Among them, signal conditioning may include operations such as amplification and filtering to convert the raw signal into a form suitable for transmission and processing, and to enhance the strength of the signal so that it is easier to be recognized and processed by subsequent circuits. In the present invention, the built-in signal conditioning circuit of the sensor will perform preliminary filtering and amplification on the collected raw signal. The purpose of filtering is to remove environmental noise interference, and the purpose of amplification is to improve the signal-to-noise ratio of the signal.

[0085] The signal interference processing module is responsible for the anti-interference work of the sensor signal after preprocessing, and the steps of obtaining the optimal estimated value of the useful signal include:

[0086] Step 201: Receive a set of pre-processed sensor signals , where represents the received signal samples, represents the sampling time point of the corresponding signal sample, Indicates the number of sampling time points;

[0087] Step 202: Obtain signal rule set ;in, The representation consists of a set of rules that describe the generation, propagation, and reception of wanted and interfering signals;

[0088] Step 203: According to the predetermined set of received signals and signal rule set, the optimal estimate of the useful signal is obtained by calculating and maximizing the posterior probability:

[0089] , where Indicates that given a set of received signals , Signal Rule Set And the signal impact factor Under the condition of The best estimate of ; Represents the posterior probability, which is used to reflect the useful signal given the observed data and information. Credibility; Represents the posterior probability Reaching the maximum ; Indicates signal influencing factors, including signal frequency, phase, amplitude, power spectrum density of noise, channel gain and phase response, etc.;

[0090] Step 204: Transmit the pipeline status data after signal interference processing to the real-time monitoring and abnormality identification module through the network.

[0091] The real-time monitoring and anomaly identification module monitors and analyzes the collected pipeline status data, preliminarily identifies possible leakage points, and marks anomalies in the following steps:

[0092] Step 301: sensors, each with a time interval Collect pipeline status data; among them, Sensors at time The pipeline status data is represented as , and each sensor pipeline has a unique identifier ;

[0093] Step 302: Arrange the pipeline status data into a time series form, that is, for each sensor, form a data series , where Indicates the amount of data;

[0094] Step 303: The identifier Associated with the data sequence to form a data pair ;

[0095] Step 304: Extract features from pipeline status data to obtain feature vectors , where represents the eigenvalue, represents the number of eigenvalues;

[0096] Step 305: Use random forest to train data. The training set includes normal pipeline status data and known abnormal pipeline status data, and is marked as , where Represents the data attributes of the training set. When , it is normal;

[0097] Step 306: Extract feature vectors from the newly collected pipeline status data ;

[0098] Step 307: transform the feature vector Input the trained random forest model to get the prediction results ;like , it is marked as abnormal, and the abnormal pipeline status data and its identifier are recorded, that is, .

[0099] The positioning fitting and leakage assessment module determines the suspected leakage point based on the abnormally marked data, obtains the precise position of the suspected leakage point by using the positioning fitting technology, and evaluates and analyzes whether the position generates a leakage event. The steps include:

[0100] Step 401: Extract all marked abnormal pipeline status data sets , where Indicates the abnormal pipeline status data index, Indicates the number of abnormal pipeline status data;

[0101] Step 402: Set the suspected leakage point set according to the abnormal pipeline status data as , where Indicates the location of the suspected leak. Indicates the corresponding pipeline identifier, Indicates the location index of the suspected leakage point, Indicates the number of locations where leakage is suspected;

[0102] Step 403: Determine based on the suspected leakage point identification condition:

[0103] ;

[0104] Step 404: Acquire the corresponding sensor information set in combination with the suspected leakage point , where Indicates the sensor location, Indicates the signal time detected by the sensor. Indicates the sensor information index. Indicates the number of sensor information;

[0105] Step 405: Calculate the target position of the suspected leakage point using a positioning algorithm :

[0106] , where Represents the error function in the positioning algorithm;

[0107] Step 406: Analyze the calculated target position of the suspected leakage point and obtain the precise position of the suspected leakage point. The specific steps are as follows:

[0108] U1. Determine the target location of the suspected leakage point , where Respectively represent the horizontal and vertical coordinates;

[0109] U2. Get the The vector of sensor measurements , where Indicates the dimensions of the measurement, for example, if the measurement is distance and angle in two-dimensional space, then ;

[0110] U3. Definition and The measurement matrix associated with each sensor , the measurement matrix The target location Mapping to a vector of measurements ;

[0111] U4. Find the exact location of the suspected leakage point through the weighted least squares formula , so that the sum of squares of weighted measurement errors of all sensors is minimized:

[0112] , where is the matrix transpose symbol, Indicates The covariance matrix of the measurement error of the sensors, and its inverse matrix is the weight matrix, which reflects the reliability and accuracy of the measurements of different sensors;

[0113] Step 407: Based on the precise location of the suspected leakage point , obtain the monitoring set of leakage parameters at this location , where represents the leakage parameter, Represents the monitoring index of the leakage parameter, Indicates the number of monitoring leakage parameters;

[0114] Step 408: Obtain leakage velocity based on the monitoring set of leakage parameters : ;

[0115] Step 409: Use the formula to evaluate the impact of leakage and generate a leakage event:

[0116] , where Indicates the leakage impact value of the suspected leakage point; Indicates the maximum velocity allowed for pipeline leakage; represents the standard threshold value of leakage parameters; Indicates the leakage area of ​​the suspected leakage point; are respectively the preset leakage velocity, leakage parameter and proportional coefficient of leakage area;

[0117] Step 410, set a leakage detection threshold, compare and analyze the leakage impact value of the suspected leakage point with the leakage detection threshold, if the leakage impact value of the suspected leakage point is higher than the leakage detection threshold, a leakage event is generated; if the leakage impact value of the suspected leakage point is not higher than the leakage detection threshold, the suspected leakage point is further checked.

[0118] In the embodiment of the present invention, by deploying highly sensitive leakage detection sensors at key positions along the pipeline, a comprehensive monitoring network can be formed to ensure that there are no blind spots in monitoring. By using a formula to maximize the sensor coverage area, the spacing between sensors is ensured to be as small as possible, the pipeline portion not covered by the sensor is reduced, and the monitoring efficiency is improved. The original signal is preliminarily filtered and amplified by the built-in signal conditioning circuit of the sensor to remove environmental noise interference, improve the signal-to-noise ratio of the signal, and provide an accurate and reliable data basis for subsequent data processing. By calculating and maximizing the posterior probability, the optimal estimate of the useful signal is solved, the quality of the signal is improved, and accurate data support is provided for subsequent data analysis. By using an algorithm, the monitoring data is analyzed in real time, abnormal data can be accurately identified, and possible leakage points can be marked, thereby improving the accuracy and efficiency of monitoring. By using positioning fitting technology, the suspected leakage point is located with high precision to ensure the accuracy of positioning. By calculating the leakage impact value of the suspected leakage point, the severity of the leakage event can be comprehensively evaluated to provide a basis for subsequent decision-making. By setting a leakage detection threshold, when the leakage impact value of the suspected leakage point is higher than the threshold, a leakage event can be automatically generated to improve the emergency response speed. In summary, the example of the present invention solves the problem of low efficiency of current pipeline leakage monitoring. In actual situations, more data and context information may be needed to make specific decisions and optimize solutions.

[0119] In addition, the formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The proportional coefficient in the formula and the various preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the proportional coefficient depends on the amount of sample data and the preliminary setting of the corresponding processing coefficient for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0120] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically based on the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0121] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0122] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0124] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0126] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0127] Finally: The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field within the technical scope disclosed by the present invention, who makes equivalent replacement or change according to the technical scheme and inventive concept of the present invention, should be covered by the protection scope of the present invention.

Claims

1. Pipeline leakage intelligent monitoring system based on positioning fitting technology, characterized by: It includes sensor configuration and signal preprocessing module, signal interference processing module, real-time monitoring and anomaly identification module, and positioning fitting and leakage assessment module; Sensor configuration and signal preprocessing module: deploy sensor network, determine sensor location, and optimize sensor location; preprocess the original signal of the sensor through the built-in signal conditioning circuit; the sensor location optimization process is to deploy the sensor network based on the linear topology structure and the linear arrangement of sensors along the pipeline, and use graph theory and the method of maximizing sensor coverage area to optimize the sensor layout; Signal interference processing module: responsible for the anti-interference work of the pre-processed sensor signal and obtaining the optimal estimated value of the useful signal; the process of obtaining the optimal estimated value is to solve the optimal estimated value of the useful signal from the pre-processed sensor signal by calculating and maximizing the posterior probability; Real-time monitoring and abnormality identification module: monitors and analyzes the collected pipeline status data, preliminarily identifies possible leakage points, and marks abnormalities; Positioning fitting and leakage assessment module: Determine the suspected leakage point based on the abnormally marked data, use the positioning fitting technology to obtain the precise location of the suspected leakage point, and evaluate and analyze whether the location generates a leakage event; The process of obtaining the precise location of the suspected leakage point is to use the weighted least squares formula to calculate and obtain the precise location of the suspected leakage point; The positioning fitting and leakage assessment module determines the suspected leakage point based on the abnormally marked data, obtains the precise position of the suspected leakage point by using the positioning fitting technology, and evaluates and analyzes whether the position generates a leakage event. The process includes: Extract all labeled abnormal pipeline status datasets , where Indicates the abnormal pipeline status data index, Indicates the number of abnormal pipeline status data; According to the abnormal pipeline status data, the suspected leakage point set is set as , where Indicates the location of the suspected leak. Indicates the corresponding pipeline identifier, Indicates the location index of the suspected leakage point, Indicates the number of locations where leakage is suspected; Based on the suspected leakage point identification conditions: ; Combine suspected leakage points to obtain the corresponding sensor information set , where Indicates the sensor location, Indicates the signal time detected by the sensor. Indicates the sensor information index. Indicates the number of sensor information; Use positioning algorithms to calculate the target location of suspected leaks : , where Represents the error function in the positioning algorithm; Analyze the calculated target position of the suspected leakage point and obtain the precise position of the suspected leakage point; Based on the precise location of the suspected leak , obtain the monitoring set of leakage parameters at this location , where represents the leakage parameter, Represents the monitoring index of the leakage parameter, Indicates the number of monitoring leakage parameters; Get the leakage rate based on the monitoring set of leakage parameters : ; The impact of leakage is evaluated using the formula to generate leakage events: , where Indicates the leakage impact value of the suspected leakage point; Indicates the maximum velocity allowed for pipeline leakage; represents the standard threshold value of leakage parameters; Indicates the leakage area of ​​the suspected leakage point; are respectively the preset leakage velocity, leakage parameter and proportional coefficient of leakage area; Set a leakage detection threshold, compare and analyze the leakage impact value of the suspected leakage point with the leakage detection threshold. If the leakage impact value of the suspected leakage point is higher than the leakage detection threshold, a leakage event is generated; if the leakage impact value of the suspected leakage point is not higher than the leakage detection threshold, the suspected leakage point is further investigated.

2. The pipeline leakage intelligent monitoring system based on positioning fitting technology according to claim 1 is characterized by: The process of deploying the sensor network, determining the sensor location, and optimizing the sensor location in the data collection and preprocessing module includes: In pipeline monitoring, a linear topology is chosen to deploy the sensor network; Based on the linear arrangement of sensors along the pipeline, using the diagram represents a sensor network; each sensor corresponds to a node in the sensor network, is a node set, representing the set of all sensors, is a set of edges, representing the connection relationship between sensors, then , , where Represents a node, represents the edge, Indicates the number of nodes; in a linear topology, each node All nodes are connected to each other by edges or Connected, Represents the node index; After completing the sensor network deployment, obtain the total length of the pipeline , installed along the pipeline Sensors; Get the location of the sensor , where represents the number of sensor locations; where ; Set the sensor's detection range to a fixed value Each sensor covers the left and right sides of its position If the distance between adjacent sensors is less than twice the detection range, then there is a constraint: the distance between adjacent sensors does not exceed twice the detection range, that is , where Indicates the sensor location index; Maximize sensor coverage using the formula: , where Indicates the area not covered by the sensor; Indicates the distance between adjacent sensors; Indicates the actual covered portion within the distance and does not exceed the detection range of the sensor ; Each sensor in the sensor network will continuously collect pipeline status data near its location; the pipeline status data will be recorded and stored in the form of time series.

3. The pipeline leakage intelligent monitoring system based on positioning fitting technology according to claim 1 is characterized by: The data collection and preprocessing module preprocesses the original signal of the sensor through the built-in signal conditioning circuit. The process includes: Get the original signal and use the formula The original signal is initially filtered and amplified, where: Represents the input signal, that is, the change of the original signal collected by the sensor over time. represents the output signal, that is, the change of the signal after being processed by the filter and amplifier over time. Represents the impulse response function of the filter, which is used to describe the frequency response characteristics of the filter to the input signal. is the gain of the amplifier, which represents the input signal With output signal The proportional relationship between Indicates the moment when the signal is acquired, and is used to describe the change of the signal over time. is the integral variable used to calculate the integral of the product of the input signal and the impulse response function during the filtering process.

4. The pipeline leakage intelligent monitoring system based on positioning fitting technology according to claim 1 is characterized by: The signal interference processing module is responsible for the anti-interference work of the sensor signal after preprocessing, and the process of obtaining the optimal estimated value of the useful signal includes: Receive pre-processed sensor signal set , where represents the received signal samples, represents the sampling time point of the corresponding signal sample, Indicates the number of sampling time points; Get signal ruleset ; According to the established set of received signals and signal rules, the optimal estimate of the useful signal is solved by calculating and maximizing the posterior probability: , where Indicates that given a set of received signals , Signal Rule Set And the signal impact factor Under the condition of The best estimate of ; represents the posterior probability; Represents the posterior probability Reaching the maximum ; represents the signal impact factor; The pipeline status data after signal interference processing is transmitted to the real-time monitoring and abnormality identification module through the network.

5. The pipeline leakage intelligent monitoring system based on positioning fitting technology according to claim 1 is characterized by: The real-time monitoring and anomaly identification module monitors and analyzes the collected pipeline status data, preliminarily identifies possible leakage points, and marks anomalies. The process includes: for sensors, each with a time interval Collect pipeline status data; among them, Sensors at time The pipeline status data is represented as , and each sensor pipeline has a unique identifier ; Arrange the pipeline status data into a time series form, that is, for each sensor, form a data sequence , where Indicates the amount of data; Identifier Associated with the data sequence to form a data pair ; Extract features from pipeline status data to obtain feature vectors , where represents the eigenvalue, represents the number of eigenvalues; Random forest is used for training data. The training set contains normal pipeline status data and known abnormal pipeline status data, which are marked as , where Represents the data attributes of the training set. When , it is normal; Extract feature vectors from newly collected pipeline status data ; The feature vector Input the trained random forest model to get the prediction results ;like , it is marked as abnormal, and the abnormal pipeline status data and its identifier are recorded, that is, .

6. The pipeline leakage intelligent monitoring system based on positioning fitting technology according to claim 1 is characterized by: The positioning fitting and leakage assessment module analyzes the calculated target position of the suspected leakage point and obtains the precise position of the suspected leakage point. The process includes: Target suspected leaks , where Respectively represent the horizontal and vertical coordinates; Get the The vector of sensor measurements , where Represents the dimension of the measurement value; Definition and The measurement matrix associated with each sensor , the measurement matrix The target location Mapping to a vector of measurements ; Find the exact location of the suspected leakage point by using the weighted least squares formula , so that the sum of squares of weighted measurement errors of all sensors is minimized: , where is the matrix transpose symbol, Indicates The covariance matrix of the measurement error of the sensors, and its inverse matrix is the weight matrix.

Images