Pipeline flange monitoring system and method

Abstract

The invention discloses a pipeline flange monitoring system and method, relates to the technical field of pipeline flange monitoring, and can solve the problem of how to accurately and efficiently monitor leakage of a pipeline flange under the condition that manual monitoring is not needed and an active sensor is not adopted. The system comprises an acquisition module used for acquiring a first target flow velocity of a first pipeline and a second target flow velocity of a second pipeline; the judgment module is used for determining whether leakage exists in the flange monitoring point based on the first target flow velocity and the second target flow velocity. And under the condition that leakage exists at the flange monitoring points, the analysis module is used for inputting the number of the leakage points, the position of each leakage point and the gas leakage amount into the random forest model to obtain the predicted leakage type of each leakage point. And the processing module is used for determining the damage type of each leakage point, deleting the leakage points of which the damage types are irrelevant to the pipeline structure damage, and counting the number of the damage characteristics of the residual leakage points. The early warning module is used for giving out early warning of the corresponding level according to the number of the damage characteristics.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline flange monitoring, and in particular, to a pipeline flange monitoring system and method. Background Art

[0002] With the wide application of facilities such as industrial pipelines and natural gas pipelines, the problem of pipeline leakage has gradually become a major hidden danger affecting production safety, resource utilization, and environmental protection. As an important component for pipeline connection, there may be pipeline leakage at the flange connection. Therefore, it is of great significance to monitor the leakage of pipeline flanges in real time and accurately to ensure pipeline safety and operation efficiency.

[0003] However, traditional leakage monitoring systems generally have deficiencies. On the one hand, traditional pipeline monitoring systems rely on people to regularly check and find problems with flanges. The manual monitoring method relies on manual experience and is inefficient, time-consuming and laborious, and it is difficult to ensure that every link is monitored in a timely manner. In addition, manual monitoring cannot be continuously monitored, which is prone to missed inspections or delays. On the other hand, in order to improve the monitoring efficiency of pipeline flanges, many pipeline monitoring systems use active sensors for real-time data acquisition. However, active sensors require external power supply, which brings difficulties to the layout and maintenance of sensors in pipelines in some harsh environments. In addition, existing pipeline monitoring systems have problems with insufficient monitoring accuracy and cannot guarantee accurate monitoring results.

[0004] In summary, the existing pipeline flange monitoring technologies have deficiencies in terms of real-time performance, accuracy, cost, and maintenance convenience, and cannot meet the requirements of modern industries for the safe and efficient operation of pipeline systems. Therefore, how to improve the accuracy and monitoring efficiency of pipeline flange monitoring systems is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] The present invention provides a pipeline flange monitoring system and method, aiming to solve the problem of how to accurately and efficiently monitor the leakage of pipeline flanges without manual monitoring and without using active sensors.

[0006] In a first aspect, the present invention provides a pipeline flange monitoring system, which includes: a collection module, a judgment module, an analysis module, a processing module, and an early warning module.

[0007] The collection module is used to obtain the first target flow rate of the first pipeline and the second target flow rate of the second pipeline; the first pipeline and the second pipeline are connected by a flange.

[0008] The judgment module is used to determine whether there is a leak at the flange monitoring point based on the first target flow rate and the second target flow rate, and to determine the number of leak points, the location of each leak point, and the gas leakage volume of each leak point in the case of a leak at the flange monitoring point; the flange monitoring point refers to the position set at the pipeline flange connection for leak monitoring.

[0009] The analysis module is used to input the number of leak points, the location of each leak point, and the gas leakage volume of each leak point into a trained random forest model to obtain the predicted leak type of each leak point; for each leak point, based on historical leak data, determine the leak similarity of the leak point; based on the leak similarity, verify whether the predicted leak type of the leak point is accurate, and in the case of inaccurate predicted leak type, re-determine the leak type of the leak point using a clustering algorithm according to historical leak data.

[0010] The processing module is used to extract the leak type characteristics of each leak point; determine the damage type of each leak point according to the leak type characteristics of each leak point and the feature threshold; delete the leak points whose damage type has nothing to do with the pipeline structure damage, and count the number of damage characteristics of the remaining leak points.

[0011] The warning module is used to issue a warning of the corresponding level according to the number of damage characteristics and generate a visual warning report, and the visual warning report includes the location and damage type of the remaining leak points.

[0012] Based on the above technical solutions, the acquisition module can acquire the first target flow rate of the first pipeline connected by the flange and the flow rate of the second pipeline connected by the second pipeline, providing data support for subsequent monitoring of whether there is a leak at the flange monitoring point. The judgment module can judge whether there is a leak at the flange monitoring point by analyzing the difference between the first target flow rate and the second target flow rate, improving the monitoring accuracy and efficiency of the leak problem of the pipeline flange.

[0013] In the case of confirmed leakage, the analysis module can use the random forest model to predict the leakage type of the leakage point according to the number of leakage points, the location of each leakage point, and the gas leakage volume, thus avoiding the judgment of human experience and improving the automation degree of the system. The processing module can count the number of damage characteristics of the remaining leak points, extract the leak type characteristics and eliminate the leak points with irrelevant characteristics, avoiding the problem of focusing on the leak points with smaller weights, thus further improving the accuracy of pipeline monitoring. The warning module can issue a warning of the corresponding level based on the number of damage characteristics and generate a warning report, providing data support for subsequent pipeline repair and maintenance, and improving the utilization rate and scientificity of system resources.

[0014] In some embodiments, the acquisition module includes a first flow sensor, and the first flow sensor is a wireless passive sensor; specifically, the acquisition module is configured to use the first flow sensor to obtain the first flow rate of the first pipeline and the second flow rate of the second pipeline, and then determine the first target flow velocity of the first pipeline based on the first flow rate and the diameter of the first pipeline, and determine the second target flow velocity of the second pipeline based on the second flow rate and the diameter of the second pipeline.

[0015] In some embodiments, the first target flow velocity and the second target flow velocity are obtained by the following formulas:

[0016]

[0017] Wherein, V1 represents the first target flow velocity, V2 represents the second target flow velocity, Q1 represents the first flow rate of the first pipeline, Q2 represents the second flow rate of the second pipeline, D represents the diameters of the first pipeline and the second pipeline, and the diameters of the second pipeline and the second pipeline are equal.

[0018] In some embodiments, the acquisition module further includes a second flow sensor and an ultrasonic sensor, and the second flow sensor and the ultrasonic sensor are wireless passive sensors; specifically, the judgment module is configured to determine that there is no leakage at the flange monitoring point and not activate the second flow sensor and the ultrasonic sensor when the first target flow velocity and the second target flow velocity are equal; and determine that there is leakage at the flange monitoring point and activate the second flow sensor and the ultrasonic sensor when the first target flow velocity and the second target flow velocity are not equal.

[0019] In some embodiments, in the case of determining that there is leakage at the flange monitoring point, the judgment module is further specifically configured to use the ultrasonic sensor to determine the number of leakage points, and determine the position of each leakage point based on the position coordinates of the ultrasonic sensor, the ultrasonic propagation speed, and the time difference between the ultrasonic signals sent by two adjacent ultrasonic sensors reaching each leakage point; and use the second flow sensor to obtain the gas at each leakage point.

[0020] In some embodiments, the position of each leakage point is obtained by the following formulas:

[0021]

[0022] Wherein, c represents the ultrasonic propagation speed of the ultrasonic sensor, Δt i represents the time difference between the ultrasonic signals sent by two adjacent ultrasonic sensors reaching the leakage point, x and y represent the position coordinates of the leakage point, x i and y i represent the position coordinates of the i-th ultrasonic sensor, x1 and y1 represent the position coordinates of the first ultrasonic sensor, and the first ultrasonic sensor and the i-th ultrasonic sensor are adjacent in position; represents the distance from the i-th ultrasonic sensor to the leakage point, represents the distance from the first ultrasonic sensor to the leakage point.

[0023] In some embodiments, the analysis module is specifically configured to obtain historical leakage data, where the historical leakage data includes the number of historical leakage points, the location of each historical leakage point, the historical gas leakage volume, and the historical leakage type; use the historical leakage data as a leakage training set, and adopt cross-validation and grid search to search for the model parameters of the random forest model and establish a random forest model; use the leakage training set to fit the random forest model to obtain a trained random forest model, and the trained random forest model is used to predict the leakage type of the leakage point; input the number of leakage points, the location of each leakage point, and the gas leakage volume of each leakage point into the trained random forest model to obtain the predicted leakage type of each leakage point.

[0024] In some embodiments, the analysis module is specifically configured to, for each leakage point, screen out historical leakage points from the historical leakage data that have the same predicted leakage type as the leakage point; based on the gas leakage volume, leakage flow rate, and ultrasonic signals sent by the historical leakage point, as well as the gas leakage volume, leakage flow rate, and ultrasonic signals sent by the leakage point, determine the leakage similarity between the leakage point and the historical leakage point, and the leakage flow rate of the leakage point is obtained through the acquisition module; based on the magnitude relationship between the leakage similarity and the leakage similarity threshold, verify whether the predicted leakage type of the leakage point is accurate.

[0025] In some embodiments, the leakage similarity is obtained by the following formula:

[0026]

[0027] where L represents the leakage similarity, U1 represents the gas leakage volume of the leakage point, W1 represents the leakage flow rate of the leakage point, K1 represents the ultrasonic signal sent by the leakage point, U2 represents the gas leakage volume of the historical leakage point, W2 represents the leakage flow rate of the historical leakage point, and K2 represents the ultrasonic signal sent by the historical leakage point.

[0028] In some embodiments, the analysis module is specifically configured to determine that the predicted leakage type of the leakage point is accurate when 80% < L ≤ 100%; determine that the predicted leakage type of the leakage point is inaccurate when L ≤ 80% or L > 100%.

[0029] In some embodiments, the clustering algorithm includes a Gaussian mixture model. Based on this, in the case where the predicted leakage type of the leakage point is inaccurate, the analysis module is specifically configured to extract the signature data of each leakage type from the historical leakage data, and the signature data is used to characterize the features of the leakage type; determine the signature data in the historical leakage data and the signature data of the leakage point to be re-determined as the aggregation data set; for each signature data in the aggregation data set, use the Gaussian mixture model to determine the responsibility value of the signature data for each Gaussian distribution, and determine the cluster corresponding to the Gaussian distribution with the largest responsibility value as the leakage type of the leakage point to be re-determined. Among them, the responsibility value is used to characterize the probability that the signature data belongs to each Gaussian distribution; each cluster represents a leakage type.

[0030] In some embodiments, the processing module includes a displacement sensor, and the displacement sensor is used to collect the leakage type length feature of each leakage point. The displacement sensor is a wireless passive sensor; the processing module is specifically configured to use the displacement sensor to obtain the leakage type length feature of each leakage point; for each leakage point, when the leakage type length feature is greater than the first length feature threshold, determine that the leakage point is a pipeline structure breakage leakage point; when the leakage type length feature is less than or equal to the first length feature threshold and greater than the second length feature threshold, determine that the leakage point is a secondary pipeline structure breakage leakage point; when the leakage type length feature is less than or equal to the second length feature threshold, determine that the leakage point is a non-pipeline structure breakage leakage point.

[0031] In some embodiments, the processing module is specifically configured to count the number of pipeline structure breakage leakage points and record it as the breakage number, count the number of secondary pipeline structure breakage leakage points and record it as the secondary breakage number, and delete the non-pipeline structure breakage leakage points; determine the ratio G of the breakage number to the secondary breakage number; when 1.5 < G, rate the leakage level of the flange monitoring point as a first-level leakage; when 1 < G ≤ 1.5, rate the leakage level of the flange monitoring point as a second-level leakage; when G ≤ 1, rate the leakage level of the flange monitoring point as a third-level leakage.

[0032] In some embodiments, the early warning module is specifically configured to issue a first-level early warning to the flange monitoring point rated as a first-level leakage; issue a second-level early warning to the flange monitoring point rated as a second-level leakage; issue a third-level early warning to the flange monitoring point rated as a third-level leakage; store the positions of the pipeline structure breakage leakage points and the secondary pipeline structure breakage leakage points in a coordinate chart, store the gas leakage amounts of the pipeline structure breakage leakage points and the secondary pipeline structure breakage leakage points in a bar chart, and generate a visual early warning report based on the coordinate chart and the bar chart.

[0033] In a second aspect, the present application provides a pipeline flange monitoring method, and the method includes:

[0034] Obtain the first target flow rate of the first pipeline and the second target flow rate of the second pipeline. The first pipeline and the second pipeline are connected by a flange.

[0035] Based on the first target flow rate and the second target flow rate, determine whether there is a leak at the flange monitoring point. When there is a leak at the flange monitoring point, determine the number of leak points, the location of each leak point, and the gas leakage amount of each leak point. The flange monitoring point refers to the location set at the pipeline flange connection for monitoring leaks. Input the number of leak points, the location of each leak point, and the gas leakage amount of each leak point into the trained random forest model to obtain the predicted leak type of each leak point. For each leak point, based on the historical leak data, determine the leak similarity of the leak point. Based on the leak similarity, verify whether the predicted leak type of the leak point is accurate. When the predicted leak type is inaccurate, based on the historical leak data, use the clustering algorithm to re-determine the leak type of the leak point.

[0036] Extract the leak type features of each leak point, and based on the leak type features of each leak point and the feature threshold, determine the damage type of each leak point. Delete the leak points whose damage type has nothing to do with the pipeline structure damage, and count the number of damage features of the remaining leak points.

[0037] Send a warning of the corresponding level according to the number of damage features, and generate a visual warning report. The visual warning report includes the location and damage type of the remaining leak points.

[0038] In a third aspect, the present application provides a pipeline flange monitoring device, which includes: a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a computer program or instruction to implement the pipeline flange monitoring method described in any one of the second aspect and any possible implementation manner of the second aspect.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are run on a terminal, the terminal is caused to execute the pipeline flange monitoring method described in any one of the second aspect and any possible implementation manner of the second aspect.

[0040] In a fifth aspect, the present application provides a computer program product. The computer program product includes computer instructions. When the computer instructions are run on a computer, the computer is caused to execute the pipeline flange monitoring method described in any one of the second aspect and any possible implementation manner of the second aspect.

[0041] Therefore, the above technical features of the present invention have the following beneficial effects:

[0042] (1) The use of wireless passive sensors eliminates the dependence on external power sources, reduces the complexity of power supply arrangements, and thus lowers the maintenance costs of traditional active sensors. At the same time, wireless passive sensors have a good service life and reliability, are suitable for long-term monitoring of pipeline flanges, reduce the input of manpower and material resources, and improve the overall monitoring efficiency.

[0043] (2) By obtaining the target flow rates of the first pipeline and the second pipeline in real time, it is determined whether there is a leakage at the flange monitoring point, thereby quickly triggering an alarm, which has good real-time performance and effectively reduces the problems of missed detection and missed reporting.

[0044] (3) The random forest model is used to predict the leakage type, which can accurately classify the leakage points. Through the training of historical leakage data, the accuracy of model prediction is improved. The intelligent adaptive processing of the clustering algorithm enables the system to dynamically optimize its monitoring accuracy when facing different environments and complex situations, improves the overall monitoring ability and adaptability, and avoids the interference of irrelevant data by screening out the leakage points whose damage types are irrelevant to the pipeline structure damage, ensuring the accuracy of the pipeline flange monitoring system.

[0045] (4) An alarm of the corresponding level is issued according to the number of damage characteristics, and a visual report is generated. The visual data display is conducive to quickly identifying potential risks, improving the transparency of pipeline operation management, enhancing the emergency response and decision-making efficiency, thereby reducing potential safety hazards and providing a strong safety guarantee for pipeline operation. Description of the Drawings

[0046] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0047] Figure 1 It is an architecture diagram of a pipeline flange monitoring system provided by an embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram of a collection module provided by an embodiment of the present invention;

[0049] Figure 3 It is another schematic diagram of a collection module provided by an embodiment of the present invention;

[0050] Figure 4 It is a schematic diagram of a processing module provided by an embodiment of the present invention;

[0051] Figure 5 It is an interaction flowchart of a pipeline flange monitoring method provided by an embodiment of the present invention;

[0052] Figure 6 This is a schematic structural diagram of a pipeline flange monitoring device provided by an embodiment of the present invention. Specific embodiments

[0053] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0054] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0055] To facilitate a clear description of the technical solutions in the embodiments of the present application, in the embodiments of the present application, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and roles. Those skilled in the art can understand that the terms "first" and "second" do not limit the quantity and execution order.

[0056] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes other steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0057] With the rapid development of modern industry, facilities such as industrial pipelines and natural gas pipelines have been widely used in various industrial productions and daily lives. The safety and stability of these pipeline systems play a crucial role in ensuring production safety, efficiently utilizing resources, and environmental protection. As an important component for pipeline connection, the sealing performance of the flange is directly related to the overall safety of the pipeline system. Once a leak occurs at the flange connection, it will not only cause resource waste but also may trigger safety accidents and pollute the environment. Therefore, it is of great significance to monitor the leakage of pipeline flanges in real time and accurately for preventing leakage accidents and ensuring pipeline safety and operation efficiency.

[0058] However, traditional pipeline flange leakage monitoring systems have many deficiencies. On the one hand, manual detection methods rely on manual experience, with low efficiency and difficulty in achieving continuous monitoring, which easily leads to missed detections or delays and cannot ensure the safe and stable operation of the pipeline system. On the other hand, although some systems use active sensors for real-time data collection to improve monitoring efficiency, these sensors require external power supply, which brings great difficulties to the layout and maintenance of the sensors, especially in pipeline systems with harsh environments where it is difficult to provide stable power. In addition, existing pipeline monitoring systems also have problems with insufficient monitoring accuracy. Due to various reasons such as sensor performance, data processing algorithms, and environmental factors, existing monitoring systems cannot guarantee accurate monitoring results, posing potential risks to the safe operation of the pipeline system.

[0059] In summary, existing pipeline flange monitoring technologies have deficiencies in terms of real-time performance, accuracy, cost, and maintenance convenience, and cannot meet the requirements of modern industry for the safe and efficient operation of pipeline systems. Therefore, how to improve the accuracy and monitoring efficiency of pipeline flange monitoring systems is a technical problem that needs to be urgently solved by those skilled in the art.

[0060] To solve the above technical problems, an embodiment of the present invention provides a pipeline flange detection system, which includes: a collection module, a judgment module, an analysis module, a processing module, and an early warning module. The collection module can collect the first target flow rate of the first pipeline connected by the flange and the flow rate of the second pipeline connected by the second pipeline, providing data support for subsequent monitoring of whether the flange monitoring point leaks. The judgment module can judge whether there is a leakage situation at the flange monitoring point by analyzing the difference between the first target flow rate and the second target flow rate, improving the monitoring accuracy and efficiency of the leakage problem of the pipeline flange.

[0061] In the case of confirming leakage, the analysis module can use a random forest model to predict the leakage type of the leakage point according to the number of leakage points, the location of each leakage point, and the gas leakage amount, thus avoiding the judgment of human experience and improving the automation degree of the system. The processing module can count the number of damage characteristics of the remaining leakage points, extract the leakage type characteristics and eliminate the leakage points with irrelevant characteristics, avoiding the problem of focusing on leakage points with smaller weights in monitoring, thereby further improving the accuracy of pipeline monitoring. The early warning module can issue corresponding-level early warnings based on the number of damage characteristics and generate an early warning report, providing data support for subsequent pipeline repair and maintenance, and improving the utilization rate and scientific nature of system resources.

[0062] Next, the implementation mode of the embodiment of the present application will be described in detail in conjunction with the accompanying drawings of the specification.

[0063] Figure 1The architecture diagram of a pipeline flange monitoring system provided by an embodiment of the present application is as follows Figure 1 As shown, the system includes: a collection module 101, a judgment module 102, an analysis module 103, a processing module 104, and an early warning module 105.

[0064] Among them, the collection module 101 can be used to obtain the first target flow rate of the first pipeline and the second target flow rate of the second pipeline.

[0065] In the embodiment of the present application, the pipelines at the connection are divided into the first pipeline and the second pipeline according to the conveying direction with the flange as the boundary. For example, if the transportation direction is from west to east, the pipeline on the west side of the flange is defined as the first pipeline, and the pipeline on the east side of the flange is defined as the second pipeline.

[0066] The judgment module 102 can be used to determine whether there is a leak at the flange monitoring point based on the first target flow rate and the second target flow rate, and determine the number of leak points, the location of each leak point, and the gas leakage amount of each leak point in the case of a leak at the flange monitoring point.

[0067] The analysis module 103 is used to input the number of leak points, the location of each leak point, and the gas leakage amount of each leak point into a random forest model to obtain the predicted leak type of each leak point. Then, for each leak point, based on historical leak data, the leak similarity of the leak point is determined, and whether the predicted leak type is accurate is verified based on the leak similarity. In the case where the predicted leak type is inaccurate, the leak type of the leak point is re-determined using a clustering algorithm according to historical leak data.

[0068] The processing module 104 is used to extract the leak type characteristics of each leak point, determine the damage type of each leak point according to the leak type characteristics of each leak point and the characteristic threshold, delete the leak points whose damage type has nothing to do with the pipeline structure, and count the number of damage characteristics of the remaining leak points.

[0069] The early warning module 105 is used to issue an early warning of the corresponding level according to the number of damage characteristics and generate a visual early warning report.

[0070] Optionally, the collection module 101 is the basic module of the system, as Figure 2 shown, the collection module 101 may include wireless passive sensors. The collection module 101 can obtain the first target flow rate of the first pipeline and the second target flow rate of the second pipeline at the flange connection in real time through wireless passive sensors deployed at the flange monitoring point, so as to analyze the pipeline state.

[0071] The embodiment of the present application does not limit the number of sensors included in the collection module 101. For example, the number of sensors can be 7, 8, or 9, and can be specifically adjusted according to actual needs.

[0072] In some embodiments, as Figure 3 shown, the acquisition module 101 may include a first flow sensor, wherein the first flow sensor is a wireless passive sensor. On this basis, the acquisition module 101 may specifically be configured to use the first flow sensor to obtain the first flow rate of the first pipeline and the second flow rate of the second pipeline, and preprocess the first flow rate and the second flow rate. After that, the acquisition module 101 may calculate a first target flow velocity based on the preprocessed first flow rate and the diameter of the first pipeline, and calculate a second target flow velocity based on the preprocessed second flow rate and the diameter of the second pipeline.

[0073] It can be understood that the wireless passive sensor does not require an external power supply, reduces the maintenance cost and has good adaptability, and can effectively work continuously in various complex environments, providing guarantee for the stability and reliability of the system.

[0074] Exemplarily, the first target flow velocity and the second target flow velocity are respectively obtained by the following formulas 1 and 2:

[0075]

[0076] Wherein, V1 represents the first target flow velocity, V2 represents the second target flow velocity, Q1 represents the first flow rate of the first pipeline, Q2 represents the second flow rate of the second pipeline, and D represents the diameters of the first pipeline and the second pipeline.

[0077] Specifically, the sensors in the acquisition module 101 may include 7 sensors, including 2 first flow sensors. The 2 first flow sensors are evenly distributed on both sides of the flange monitoring point and are deployed on the first pipeline and the second pipeline. Preprocessing is performed on the first flow data and the second flow data, and the preprocessing is to remove the noise of the first flow data and the second flow data to avoid the noise affecting the accuracy of the subsequent calculation of the first target flow velocity and the second target flow velocity.

[0078] In some embodiments, referring further to Figure 3 , the acquisition module 101 may further include a second flow sensor and an ultrasonic sensor, and the second flow sensor and the ultrasonic sensor are wireless passive sensors. On this basis, the determination module 102 may specifically be configured to, when the first target flow velocity and the second target flow velocity are equal, determine that there is no leakage at the flange monitoring point and do not activate the second flow sensor and the ultrasonic sensor of the acquisition module 101. When the first target flow velocity and the second target flow velocity are not equal, determine that there is leakage at the flange monitoring point and activate the second flow sensor and the ultrasonic sensor of the acquisition module 101.

[0079] In some embodiments, when it is determined that there is a leak at the flange monitoring point, the determination module 102 is further specifically configured to use an ultrasonic sensor to determine the number of leak points, and based on the position coordinates of the ultrasonic sensor, the ultrasonic propagation speed, and the time difference between the ultrasonic signals sent by two adjacent ultrasonic sensors reaching each leak point, determine the position of each leak point; use a second flow sensor to obtain the gas at each leak point.

[0080] Exemplarily, the position of each leak point is obtained by the following formula 3:

[0081]

[0082] where c represents the ultrasonic propagation speed of the ultrasonic sensor, Δt i represents the time difference between the ultrasonic signals sent by two adjacent ultrasonic sensors reaching the leak point, x and y represent the position coordinates of the leak point, x i and y i represent the position coordinates of the i-th ultrasonic sensor, represents the distance from the i-th ultrasonic sensor to the leak point, represents the distance from the first ultrasonic sensor to the leak point.

[0083] It can be understood that the first target flow rate and the second target flow rate represent the flow rate states of the first pipeline and the second pipeline. When the first target flow rate and the second target flow rate are not equal, it indicates that there is a leak at the flange monitoring point, and then the second flow sensor and the ultrasonic sensor of the acquisition module 101 are turned on. The 7 sensors in the acquisition module 101 include 2 second flow sensors and 3 ultrasonic sensors. The 2 second flow sensors and 3 ultrasonic sensors are evenly deployed at the flange monitoring point to comprehensively cover the connection of the pipeline flange. The 3 ultrasonic sensors use triangulation and emit ultrasonic signals after being turned on to determine the number of leak points and the positions of the leak points at the flange monitoring point. The first flow sensor collects the first flow data and the second flow data, and preprocesses them to obtain the first target flow rate and the second target flow rate, and analyzes in real time whether there is a leak at the flange monitoring point, improving the response speed and automation degree of the system. When a leak is found, the second flow sensor and the ultrasonic sensor are turned on, effectively utilizing resources and accurately positioning the leak point through the ultrasonic sensor, improving the resource utilization rate and timeliness of the system.

[0084] In some embodiments, the analysis module 103 is specifically configured to obtain historical leakage data, and then use the historical leakage feature data as a leakage training set. By adopting cross-validation and combining it with grid search, the model parameters of the random forest model are searched for, and a random forest model is established. After that, the analysis module 103 can use the leakage training set to fit the random forest model to obtain a trained random forest model. Finally, the analysis module 103 can input the number of leakage points, the location of each leakage point, and the gas leakage volume into the trained random forest model to obtain the predicted leakage type of each leakage point.

[0085] Among them, the historical leakage data includes the number of historical leakage points, the location of each historical leakage point, the historical gas leakage volume, and the historical leakage type.

[0086] It should be noted that the historical leakage data records the actual conditions of the connections of pipeline flanges at different time periods. Using the historical leakage data as a leakage training set ensures the generalization ability of the random forest model. Cross-validation and grid search are used to search for the model parameters of the random forest model. Cross-validation divides the data into several parts and trains the model multiple times to verify its stability and performance. Grid search exhaustively searches for the combination of model parameters of the random forest model, such as the branches of the tree, in the large data. Using the leakage training set to fit the random forest model reduces the risk of overfitting of the random forest model and improves the accuracy and stability of the random forest model. Using the historical leakage data to train the random forest model can make full use of the actual conditions of the connections of pipeline flanges at different time periods, thereby improving the prediction ability of the random forest model. Cross-validation and grid search ensure the optimization of the random forest model parameters and enhance the stability and reliability of the random forest model.

[0087] It can be understood that during the training process of the random forest model, by continuously adjusting the parameters, a random forest model is finally trained. The historical leakage type feature in the historical leakage data represents the initially set leakage point type. Usually, a circular hole with a diameter greater than 5 mm is defined as a hole, and a crack with a length greater than 1 cm and a depth exceeding 10% of the pipe wall thickness is defined as a crack. By inputting the number of leakage points, the location of each leakage point, and the gas leakage volume into the trained random forest model, the predicted leakage type of each leakage point can be obtained, which improves the efficient and accurate prediction ability of the system and enhances the scientific nature of pipeline safety management.

[0088] In some embodiments, the analysis module 103 is specifically configured to, for each leakage point, screen out historical leakage points with the same leakage type as the leakage point from the historical leakage data. Then, the analysis module 103 can determine the leakage similarity between the leakage point and the historical leakage point based on the gas leakage volume, leakage volume flow rate, and ultrasonic signal sent by the historical leakage point, as well as the gas leakage volume, leakage volume flow rate, and ultrasonic signal sent by the leakage point. The leakage volume flow rate of the leakage point is obtained by the acquisition module 101. Finally, the analysis module 103 can verify whether the predicted leakage type of the leakage point is accurate based on the magnitude of the leakage similarity and the leakage similarity threshold.

[0089] Exemplarily, the leakage similarity can be obtained by the following formula 4:

[0090]

[0091] Wherein, L represents the leakage similarity, U1 represents the gas leakage volume of the leakage point, W1 represents the leakage volume flow rate of the leakage point, K1 represents the ultrasonic signal sent by the leakage point, U2 represents the gas leakage volume of the historical leakage point, W2 represents the leakage volume flow rate of the historical leakage point, and K2 represents the ultrasonic signal sent by the historical leakage point.

[0092] Exemplarily, when 80% < L ≤ 100%, the analysis module 103 can determine that the predicted leakage type of the leakage point is accurate. When L ≤ 80% or L > 100%, the analysis module 103 can determine that the predicted leakage type of the leakage point is inaccurate.

[0093] In some embodiments, when the predicted leakage type of the leakage point is inaccurate, the analysis module 103 can extract the flag data of each leakage type from the historical leakage data, and then combine the flag data of the historical leakage data and the flag data of the leakage point to be re-determined to establish an aggregated data set. After that, the analysis module 103 can extract the flag vectors of each flag data in the aggregated data set, determine that the number of expected clusters is 3, and initialize the parameters of the Gaussian distribution. Finally, the analysis module 103 can calculate the responsibility value of each flag data in the aggregated data set belonging to each Gaussian distribution, that is, the probability of belonging to each Gaussian distribution, and use the cluster corresponding to the Gaussian distribution with the largest responsibility value as the leakage type of the leakage point to be re-determined.

[0094] It can be understood that by comparing with historical leakage data, the system can accurately identify whether the leakage type of the leakage point is accurate, avoiding the error of the random forest model prediction and affecting subsequent analysis, calculating the leakage similarity in real time, reducing the dependence on manual experience and operations, improving the efficiency of system monitoring. When it is determined that the predicted leakage type of the leakage point is inaccurate, the leakage type of the leakage point is re-determined through the clustering algorithm, avoiding the accidental error caused by the random forest model and improving the accuracy of system classification. The Gaussian mixture model allows the system to automatically adjust the classification parameters according to the natural distribution of the data, so as to adapt to different leakage types of the leakage point and avoid the risk of classification error.

[0095] In some embodiments, such as Figure 4 shown, the processing module 104 includes a displacement sensor, and the displacement sensor is used to collect the leakage type length feature of each leakage point. The displacement sensor is a wireless passive sensor. On this basis, the processing module 104 can use the displacement sensor to obtain the leakage type length feature of each leakage point. Then, for each leakage point, when the leakage type length feature of the leakage point is greater than the first length feature threshold, the processing module 104 can determine the leakage point as a pipeline structure breakage leakage point; when the leakage type length feature of the leakage point is less than or equal to the first length feature threshold and greater than the second length feature threshold, the processing module 104 can determine the leakage point as a secondary pipeline structure breakage leakage point; when the leakage type length feature of the leakage point is less than or equal to the second length feature threshold, the processing module 104 can determine the leakage point as a non-pipeline structure breakage leakage point.

[0096] It should be noted that the first length feature threshold and the second length feature threshold are preset.

[0097] In some embodiments, the processing module 104 can specifically also be used to count the number of pipeline structure breakage leakage points and record it as the breakage number, count the number of secondary pipeline structure breakage leakage points and record it as the secondary breakage number, and delete the non-pipeline structure breakage leakage points. Then, the processing module 104 can determine the ratio of the breakage number to the secondary breakage number and determine the leakage level of the flange monitoring point based on the ratio.

[0098] Exemplarily, assuming that the ratio of the breakage number to the secondary breakage number is G. On this basis, when 1.5 < G, the processing module 104 can rate the leakage level of the flange monitoring point as a first-level leakage; when 1 < G ≤ 1.5, the processing module 104 can rate the leakage level of the flange monitoring point as a second-level leakage; when G ≤ 1, the processing module 104 can rate the leakage level of the flange monitoring point as a third-level leakage.

[0099] It can be understood that the processing module 104 adopts a wireless passive displacement sensor. The processing module 104 includes two displacement sensors, which are evenly distributed at the flange monitoring points, comprehensively covering the entire flange monitoring points. The first length feature threshold is greater than the second length feature threshold, and the first length feature threshold and the second length feature threshold can be numerically adjusted according to actual requirements. Through the length features of the leakage types of each leakage point collected by the displacement sensor, the system can further distinguish the leakage points and determine whether the leakage points belong to the pipeline structure breakage leakage points, secondary pipeline structure breakage leakage points, and non-pipeline structure breakage leakage points, avoiding missed detections and misjudgments, and effectively improving the accuracy and precision of pipeline flange monitoring. For holes and cracks with a length feature less than or equal to the second length feature threshold, the system determines them as non-pipeline structure breakage leakage points, which can be ignored within a reasonable range, and sets the more serious holes and cracks as the objects that need to be processed first, improving the efficiency of system monitoring. The ratio G of pipeline structure breakage and secondary pipeline structure breakage is statistically calculated, providing a quantitative standard for the leakage level assessment of the flange monitoring points. The leakage levels of first-level leakage, second-level leakage, and third-level leakage decrease in sequence. Through hierarchical and precise judgment and evaluation, not only can the hidden dangers of pipeline flange leakage be reduced, but also the efficiency of subsequent maintenance can be improved, reducing resource waste, thus ensuring the safety and stability of pipeline operation.

[0100] In some embodiments, after determining the number of breakages and the number of secondary breakages, the warning module 105 can issue a first-level warning to the flange monitoring points rated as first-level leakage, issue a second-level warning to the flange monitoring points rated as second-level leakage, and issue a third-level warning to the flange monitoring points rated as third-level leakage. Then, the warning module 105 can record the positions of the pipeline structure breakage leakage points and the secondary pipeline structure breakage leakage points and establish a coordinate chart, and then establish a bar chart based on the gas leakage amounts of the pipeline structure breakage leakage points and the secondary pipeline structure breakage leakage points. Finally, a visual warning report is generated according to the coordinate chart and the bar chart.

[0101] It can be understood that the early warning module 105 issues corresponding-level early warnings according to the leakage levels of the flange monitoring points, which helps to ensure that the system can respond in a timely manner according to the leakage degree. The urgency levels of the first-level early warning, second-level early warning, and third-level early warning decrease in sequence, and the mechanism of hierarchical early warning effectively determines the processing priorities and reasonably allocates resources. By generating a bar chart of the gas leakage amounts at the pipeline structure breakage leakage points and secondary pipeline structure breakage leakage points, and establishing a coordinate chart of the positions of the pipeline structure breakage leakage points and secondary pipeline structure breakage leakage points, the gas leakage amounts and the distribution of the leakage points can be visually displayed. The visual report form improves the efficiency and transparency of information transmission, reduces the communication and processing time of personnel, thereby improving the response speed of system monitoring and ensuring the long-term stable operation of the pipeline.

[0102] The following will introduce the pipeline flange monitoring method provided by the present invention by taking the interaction between the acquisition module, judgment module, analysis module, processing module, and early warning module as an example in combination with the above content. Figure 5 It is an interaction flowchart of a pipeline flange monitoring method provided by an embodiment of the present invention. This method is executed by an acquisition module, a judgment module, an analysis module, a processing module, and an early warning module. As Figure 5 shown, this method includes:

[0103] S501. The acquisition module obtains the first target flow rate of the first pipeline and the second target flow rate of the second pipeline.

[0104] Among them, the first pipeline and the second pipeline are connected by a flange.

[0105] In the embodiment of the present application, the pipelines at the connection are divided into a first pipeline and a second pipeline according to the conveying direction with the flange as the boundary. For example: if the transportation direction is from west to east, the pipeline located on the west side of the flange is defined as the first pipeline, and the pipeline located on the east side of the flange is defined as the second pipeline.

[0106] Specifically, the acquisition module may include a first flow sensor, and the first flow sensor is a wireless passive sensor. The acquisition module can obtain the first flow rate of the first pipeline and the second flow rate of the second pipeline by using the first flow sensor, and preprocess the first flow rate and the second flow rate. Then, the acquisition module can determine the first target flow rate of the first pipeline based on the first flow rate and the diameter of the first pipeline, and determine the second target flow rate of the second pipeline based on the second flow rate and the diameter of the second pipeline. The calculation formulas for the first target flow rate and the second target flow rate can respectively refer to the above formulas 1 and 2, which will not be elaborated here.

[0107] S502. The acquisition module sends the first target flow rate of the first pipeline and the second target flow rate of the second pipeline to the judgment module.

[0108] S503. The determination module determines whether there is a leak at the flange monitoring point based on the first target flow rate and the second target flow rate.

[0109] Specifically, when the first target flow rate is equal to the second target flow rate, the determination module can determine that there is no leak at the flange monitoring point. When the first target flow rate is not equal to the second target flow rate, the determination module can determine that there is a leak at the flange monitoring point.

[0110] S504. In the case where there is a leak at the flange monitoring point, the determination module determines the number of leak points, the location of each leak point, and the gas leakage amount.

[0111] Among them, the flange monitoring point refers to the position set at the pipe flange connection for monitoring leaks. The gas leakage amount refers to the gas leakage amount of the leak point per unit time.

[0112] Specifically, the acquisition module may further include a second flow sensor and an ultrasonic sensor, and the second flow sensor and the ultrasonic sensor are wireless passive sensors. On this basis, in the case where it is determined that there is a leak at the flange monitoring point, the determination module can activate the second flow sensor and the ultrasonic sensor of the acquisition module. Then, the determination module can use the ultrasonic sensor to determine the number of leak points, and based on the position coordinates of the ultrasonic sensor, the ultrasonic propagation speed, and the time difference between the ultrasonic signals sent by two adjacent ultrasonic sensors reaching each leak point, determine the location of each leak point. In addition, the determination module can also use the second flow sensor to obtain the gas of each leak point. Among them, the calculation formula for the location of each leak point can refer to the above formula 3 and will not be elaborated here.

[0113] It can be understood that by using wireless passive sensors to collect, process, analyze, and intelligently predict data, and sending corresponding early warnings in a timely manner, the monitoring accuracy and response speed of the pipeline flange are improved, the occurrence of pipeline leakage accidents is effectively reduced, and the maintenance cost is reduced, thus ensuring the safety of pipeline facilities.

[0114] S505. The determination module sends the number of leak points, the location of each leak point, and the gas leakage amount to the analysis module.

[0115] S506. The analysis module inputs the number of leak points, the location of each leak point, and the gas leakage amount into the trained random forest model to obtain the predicted leak type of each leak point.

[0116] Specifically, the analysis module can use the historical leakage feature data as the leakage training set, adopt cross-validation and combine it with grid search to search for the model parameters of the random forest model, establish the random forest model, and use the leakage training set to fit the random forest model to obtain the trained random forest model. Finally, the analysis module can input the number of leakage points, the location of each leakage point, and the gas leakage volume into the trained random forest model to obtain the predicted leakage type of each leakage point.

[0117] S507. For each leakage point, the analysis module determines the leakage similarity of the leakage point based on the historical leakage data, and verifies whether the predicted leakage type of the leakage point is accurate based on the leakage similarity.

[0118] For each leakage point, the analysis module can screen out the historical leakage points with the same leakage type as the leakage point from the historical leakage data. Then, the analysis module can determine the leakage similarity between the leakage point and the historical leakage points based on the gas leakage volume, leakage volume flow rate, and ultrasonic signals sent by the historical leakage points, as well as the gas leakage volume, leakage volume flow rate, and ultrasonic signals sent by the leakage point. Finally, the analysis module can verify whether the predicted leakage type of the leakage point is accurate based on the magnitude of the leakage similarity and the leakage similarity threshold.

[0119] Among them, the leakage volume flow rate of the leakage point is obtained by the acquisition module.

[0120] Exemplarily, assume that the leakage similarity of the leakage point is L. When 80% < L ≤ 100%, the analysis module can determine that the predicted leakage type of the leakage point is accurate. When L ≤ 80% or L > 100%, the analysis module can determine that the predicted leakage type of the leakage point is inaccurate. The calculation formula of the leakage similarity L can refer to the above formula 4 and will not be elaborated here.

[0121] S508. In the case where the predicted leakage type of the leakage point is inaccurate, the analysis module re-determines the leakage type of the leakage point according to the historical leakage data using the clustering algorithm.

[0122] Specifically, in the case where the predicted leakage type of the leakage point is inaccurate, the analysis module can extract the flag data of each leakage type from the historical leakage data, and then combine the flag data of the historical leakage data and the flag data of the leakage point to be re-determined to establish an aggregated data set. After that, for each flag data in the aggregated data set, the analysis module can use the Gaussian mixture model to determine the responsibility value of the flag data for each Gaussian distribution, and determine the cluster corresponding to the Gaussian distribution with the largest responsibility value as the leakage type of the leakage point to be re-determined.

[0123] Among them, the responsibility value is used to characterize the probability that the flag data belongs to each Gaussian distribution. Each cluster represents a leakage type.

[0124] S509. The analysis module sends the leakage type of each leakage point to the processing module.

[0125] S510. The processing module extracts the leakage type characteristics of each leakage point, and determines the breakage type of each leakage point according to the leakage type characteristics and the characteristic threshold of each leakage point.

[0126] Specifically, the processing module can use a displacement sensor to obtain the leakage type length characteristics of each leakage point. Then, for each leakage point, when the leakage type length characteristic is greater than the first length characteristic threshold, the processing module can determine that the leakage point is a pipeline structure breakage leakage point; when the leakage type length characteristic is less than or equal to the first length characteristic threshold and greater than the second length characteristic threshold, the processing module can determine that the leakage point is judged as a secondary pipeline structure breakage leakage point; when the leakage type length characteristic is less than or equal to the second length characteristic threshold, the processing module can determine that the leakage point is a non-pipeline structure breakage leakage point.

[0127] S511. The processing module deletes the leakage points whose breakage types have nothing to do with the pipeline structure breakage, and counts the number of breakage characteristics of the remaining leakage points.

[0128] Specifically, the processing module can count the number of pipeline structure breakage leakage points and record it as the breakage quantity, count the number of secondary pipeline structure breakage leakage points and record it as the secondary breakage quantity, and determine the ratio of the breakage quantity to the secondary breakage quantity. At the same time, the processing module can delete the non-pipeline structure breakage leakage points.

[0129] Exemplarily, assume that the ratio of the breakage quantity to the secondary breakage quantity is G. When 1.5 < G, the processing module can rate the leakage level of the flange monitoring point as a first-level leakage. When 1 < G ≤ 1.5, the processing module can rate the leakage level of the flange monitoring point as a second-level leakage. When G ≤ 1, the processing module can rate the leakage level of the flange monitoring point as a third-level leakage.

[0130] S512. The processing module sends the number of breakage characteristics of the remaining leakage points to the warning module.

[0131] S513. The warning module issues a warning of the corresponding level according to the number of breakage characteristics of the remaining leakage points, and generates a visual warning report.

[0132] Among them, the visual warning report includes the positions and breakage types of the remaining leakage points.

[0133] Specifically, the warning module can issue a first-level warning for the flange monitoring point rated as a first-level leakage, issue a second-level warning for the flange monitoring point rated as a second-level leakage, and issue a third-level warning for the flange monitoring point rated as a third-level leakage.

[0134] In addition, the early warning module can also store the positions of the pipeline structure breakage and leakage points and the positions of the secondary pipeline structure breakage and leakage points in a coordinate chart, store the gas leakage amounts of the pipeline structure breakage and leakage points and the gas leakage amounts of the secondary pipeline structure breakage and leakage points in a bar chart, and generate a visual early warning report based on the coordinate chart and the bar chart.

[0135] Based on the above technical solutions, the beneficial effects of the present invention are as follows: The use of wireless passive sensors eliminates the dependence on external power sources, reduces the complexity of power supply arrangement, and thus reduces the maintenance cost of traditional active sensors. At the same time, wireless passive sensors have good service life and reliability, are suitable for long-term monitoring of pipeline flanges, reduce the input of manpower and material resources, and improve the overall monitoring efficiency. By obtaining the first target flow rate of the first pipeline and the second target flow rate of the second pipeline in real time, it is judged whether there is a leakage at the flange monitoring point, so as to quickly trigger an early warning, which has good real-time performance and effectively reduces the problems of missed detection and missed reporting. The use of a random forest model to predict the leakage type can accurately classify the leakage points. Through the training of historical leakage data, the accuracy of model prediction is improved. The intelligent adaptive processing of the clustering algorithm enables the system to dynamically optimize its monitoring accuracy when facing different environments and complex situations, improve the overall monitoring ability and adaptability, and avoid the interference of irrelevant data by screening the breakage features and eliminating the irrelevant features, ensuring the accuracy of the pipeline flange monitoring system. At the same time, corresponding-level early warnings are issued according to the number of breakage features, and a visual report is generated. The visual data display is conducive to quickly identifying potential risks, improving the transparency of pipeline operation management, enhancing the emergency response and decision-making efficiency, thus reducing potential safety hazards and providing a strong safety guarantee for pipeline operation.

[0136] Figure 6 Fig. shows another possible structural schematic diagram of the pipeline flange monitoring device involved in the above embodiments. The pipeline flange monitoring device includes: a processor 601 and a communication interface 602. The processor 601 is used to control and manage the actions of the pipeline flange monitoring device, and the communication interface 602 is used to support the communication between the pipeline flange monitoring device and other network entities. The pipeline flange monitoring device may further include a memory 603 and a bus 604, and the memory 603 is used to store the program code and data of the pipeline flange monitoring device.

[0137] Among them, the memory 603 may be a memory in the pipeline flange monitoring device, etc. This memory may include volatile memory, such as random access memory; this memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk or solid-state drive; this memory may also include a combination of the above types of memory.

[0138] The above-mentioned processor 601 may implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present application. The processor may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0139] The bus 604 may be an extended industry standard architecture (EISA) bus or the like. The bus 604 may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 6 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0140] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used for illustration. In actual applications, the above functions may be allocated to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working processes of the systems, devices, and units described above may refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0141] The embodiment of the present application provides a computer program product including instructions. When the computer program product runs on a computer, it causes the computer to execute the pipeline flange monitoring method in the foregoing method embodiment.

[0142] The embodiment of the present application also provides a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, they cause the computer to execute the pipeline flange monitoring method in the method flow shown in the foregoing method embodiment.

[0143] Among them, a computer-readable storage medium may be, for example, but not limited to, a system, apparatus, or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer-readable storage medium well-known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in an application specific integrated circuit (ASIC). In the embodiments of the present application, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0144] An embodiment of the present invention provides a computer program product including instructions. When the instructions run on a computer, the computer is caused to execute the pipeline flange monitoring method described in the embodiments of the present application.

[0145] Since the pipeline flange monitoring device, computer-readable storage medium, and computer program product in the embodiments of the present invention can be applied to the above method, the technical effects that can be obtained thereby can also refer to the method embodiments above, and the embodiments of the present invention will not be elaborated herein.

[0146] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0147] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, each functional unit in various embodiments of the present application may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit.

[0149] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A pipeline flange monitoring system, characterized in that: The system includes: a collection module, a judgment module, an analysis module, a processing module and an early warning module; The acquisition module is used to obtain a first target flow rate of a first pipeline and a second target flow rate of a second pipeline; the first pipeline and the second pipeline are connected by a flange; The judgment module is used to determine whether there is a leak at the flange monitoring point based on the first target flow rate and the second target flow rate, and if there is a leak at the flange monitoring point, determine the number of leak points, the position of each leak point and the gas leakage amount of each leak point; the flange monitoring point refers to a position set at the pipeline flange connection for monitoring leaks; The analysis module is used to input the number of the leakage points, the location of each leakage point and the gas leakage amount of each leakage point into the trained random forest model to obtain the predicted leakage type of each leakage point; for each leakage point, based on the historical leakage data, determine the leakage similarity of the leakage point; based on the leakage similarity, verify whether the predicted leakage type of the leakage point is accurate, and if the predicted leakage type is inaccurate, use the clustering algorithm to re-determine the leakage type of the leakage point based on the historical leakage data; The processing module is used to extract the leakage type feature of each leakage point; determine the damage type of each leakage point according to the leakage type feature and feature threshold of each leakage point; delete the leakage points whose damage type is not related to the damage of the pipeline structure, and count the number of damage features of the remaining leakage points; The warning module is used to issue a warning of a corresponding level according to the number of damage features and generate a visual warning report; the visual warning report includes the location and damage type of the remaining leakage points.

2. The system according to claim 1, characterized in that The acquisition module includes a first flow sensor, which is a wireless passive sensor; the acquisition module is specifically used for: Using the first flow sensor to obtain a first flow of the first pipeline and a second flow of the second pipeline; The first target flow rate of the first pipe is determined based on the first flow rate and the diameter of the first pipe, and the second target flow rate of the second pipe is determined based on the second flow rate and the diameter of the second pipe.

3. The system according to claim 2, characterized in that The first target flow rate and the second target flow rate are obtained by the following formula: Among them, V1 represents the first target flow rate, V2 represents the second target flow rate, Q1 represents the first flow rate of the first pipeline, Q2 represents the second flow rate of the second pipeline, and D represents the diameter of the first pipeline and the diameter of the second pipeline; the diameter of the second pipeline and the diameter of the second pipeline are equal.

4. The system according to claim 1, characterized in that The acquisition module also includes a second flow sensor and an ultrasonic sensor, wherein the second flow sensor and the ultrasonic sensor are wireless passive sensors; the judgment module is specifically used to: When the first target flow rate is equal to the second target flow rate, it is determined that there is no leakage at the flange monitoring point, and the second flow sensor and the ultrasonic sensor are not turned on; When the first target flow rate is not equal to the second target flow rate, it is determined that there is a leak at the flange monitoring point, and the second flow sensor and the ultrasonic sensor are turned on.

5. The system according to claim 4, characterized in that When it is determined that there is leakage at the flange monitoring point, the judgment module is further specifically used to: Determine the number of leakage points by using the ultrasonic sensor, and determine the position of each leakage point based on the position coordinates of the ultrasonic sensor, the ultrasonic propagation speed, and the time difference between the ultrasonic signals sent by two adjacent ultrasonic sensors reaching each leakage point; The gas at each leakage point is acquired by using the second flow sensor.

6. The system according to claim 5, characterized in that The position of each of the leak points is given by the following formula: Wherein, c represents the ultrasonic propagation velocity of the ultrasonic sensor, Δt i represents the time difference between the ultrasonic signals sent by two adjacent ultrasonic sensors reaching the leakage point, x and y represent the position coordinates of the leakage point, x i and i represents the position coordinates of the ith ultrasonic sensor, x1 and y1 represent the position coordinates of the first ultrasonic sensor, and the first ultrasonic sensor and the ith ultrasonic sensor are adjacent to each other; represents the distance from the ith ultrasonic sensor to the leakage point, Indicates the distance from the first ultrasonic sensor to the leakage point.

7. The system according to claim 1, characterized in that The analysis module is specifically used to obtain historical leakage data, wherein the historical leakage data includes the number of historical leakage points, the location of each of the historical leakage points, the historical gas leakage volume and the historical leakage type; The historical leakage data is used as a leakage training set, cross validation is used in combination with grid search, model parameters of a random forest model are searched, and a random forest model is established; The random forest model is fitted using the leakage training set to obtain a trained random forest model; the trained random forest model is used to predict the leakage type of the leakage point; The number of the leakage points, the position of each leakage point and the gas leakage amount of each leakage point are input into the trained random forest model to obtain the predicted leakage type of each leakage point.

8. The system according to claim 1, characterized in that The analysis module is specifically used for: For each of the leakage points, filtering out historical leakage points with the same leakage type as the leakage point from the historical leakage data; Based on the gas leakage amount, leakage flow rate and ultrasonic signal sent by the historical leakage point, as well as the gas leakage amount, leakage flow rate and ultrasonic signal sent by the leakage point, the leakage similarity between the leakage point and the historical leakage point is determined; the leakage flow rate of the leakage point is obtained by the acquisition module; Based on the magnitude of the leakage similarity and the leakage similarity threshold, it is verified whether the predicted leakage type of the leakage point is accurate.

9. The system according to claim 8, characterized in that The leakage similarity is obtained by the following formula: Among them, L represents the leakage similarity, U1 represents the gas leakage amount of the leakage point, W1 represents the leakage flow rate of the leakage point, K1 represents the ultrasonic signal sent by the leakage point, U2 represents the gas leakage amount of the historical leakage point, W2 represents the leakage flow rate of the historical leakage point, and K2 represents the ultrasonic signal sent by the historical leakage point.

10. The system according to claim 9, characterized in that The analysis module is specifically used for: When 80%<L≤100%, it is determined that the predicted leakage type of the leakage point is accurate; When L≤80% or L>100%, it is determined that the predicted leakage type of the leakage point is inaccurate.

11. The system according to any one of claims 8 to 10, characterized in that: The clustering algorithm includes a Gaussian mixture model; when the predicted leakage type of the leakage point is inaccurate, the analysis module is specifically used to: Extracting marker data of each leakage type from the historical leakage data; the marker data is used to characterize the characteristics of the leakage type; Determine the marker data in the historical leakage data and the marker data of the leakage point to be re-determined as an aggregated data set; For each marker data in the aggregated data set, the Gaussian mixture model is used to determine the responsibility value of the marker data for each Gaussian distribution, and the cluster corresponding to the Gaussian distribution with the largest responsibility value is determined as the leakage type of the leakage point to be re-determined; the responsibility value is used to characterize the probability that the marker data belongs to each Gaussian distribution; each cluster represents a leakage type.

12. The system according to claim 1, characterized in that The processing module includes a displacement sensor, which is used to collect the leakage type and length characteristics of each leakage point, and the displacement sensor is a wireless passive sensor; the processing module is specifically used to: Using the displacement sensor to obtain the leakage type length characteristics of each leakage point; For each leakage point, when the leakage type length feature is greater than a first length feature threshold, the leakage point is determined to be a pipeline structure damage leakage point; When the length characteristic of the leakage type is less than or equal to the first length characteristic threshold and greater than the second length characteristic threshold, the leakage point is determined to be a secondary pipeline structure damage leakage point; the second length characteristic threshold is less than the first length characteristic threshold; When the leakage type length feature is less than or equal to the second length feature threshold, it is determined that the leakage point is a non-pipeline structure damaged leakage point.

13. The system according to claim 12, characterized in that The processing module is specifically used for: Counting the number of damaged and leaking points of the pipeline structure and recording it as the damaged number, counting the number of damaged and leaking points of the secondary pipeline structure and recording it as the secondary damaged number, and deleting the non-pipeline structure damaged and leaking points; Determining a ratio G of the number of breakages to the number of secondary breakages; When 1.5<G, the leakage level of the flange monitoring point is rated as level one leakage; When 1<G≤1.5, the leakage level of the flange monitoring point is rated as secondary leakage; When G≤1, the leakage level of the flange monitoring point is rated as level 3 leakage.

14. The system according to claim 13, characterized in that The early warning module is specifically used for: A first-level warning will be issued for flange monitoring points that are assessed as first-level leakage; a second-level warning will be issued for flange monitoring points that are assessed as second-level leakage; and a third-level warning will be issued for flange monitoring points that are assessed as third-level leakage; The positions of the damaged leakage points of the pipeline structure and the positions of the damaged leakage points of the secondary pipeline structure are stored in a coordinate chart, the gas leakage amounts of the damaged leakage points of the pipeline structure and the gas leakage amounts of the damaged leakage points of the secondary pipeline structure are stored in a bar chart, and a visual early warning report is generated based on the coordinate chart and the bar chart.

15. A pipeline flange monitoring method, characterized in that: The method comprises: Obtaining a first target flow rate of a first pipeline and a second target flow rate of a second pipeline; the first pipeline and the second pipeline are connected by a flange; Determine whether there is a leak at the flange monitoring point based on the first target flow rate and the second target flow rate, and if there is a leak at the flange monitoring point, determine the number of leak points, the position of each leak point and the gas leakage amount of each leak point; the flange monitoring point refers to a position set at the pipeline flange connection for monitoring leaks; The number of leakage points, the location of each leakage point and the gas leakage amount of each leakage point are input into the trained random forest model to obtain the predicted leakage type of each leakage point; for each leakage point, the leakage similarity of the leakage point is determined based on the historical leakage data; based on the leakage similarity, whether the predicted leakage type of the leakage point is accurate is verified, and if the predicted leakage type is inaccurate, the leakage type of the leakage point is re-determined using a clustering algorithm based on the historical leakage data; Extracting the leakage type feature of each leakage point; determining the damage type of each leakage point according to the leakage type feature and feature threshold of each leakage point; deleting the leakage points whose damage type is not related to pipeline structure damage, and counting the number of damage features of the remaining leakage points; A warning of a corresponding level is issued according to the number of damage features, and a visual warning report is generated; the visual warning report includes the location and damage type of the remaining leakage points.

Images