Safety risk monitoring system for long-distance heat distribution pipeline

Abstract

The invention provides a long-distance heat distribution pipeline safety risk monitoring system, and relates to the technical field of pipeline monitoring, and the system comprises a pipeline abnormity monitoring module which is used for confirming an abnormal pipeline; the associated pipeline data acquisition module is used for generating a to-be-concerned multi-pipeline state monitoring data set; the associated pipeline classification module is used for classifying all the associated pipeline state monitoring data to generate a plurality of groups of hazard degree grade-associated pipeline state monitoring databases; the associated pipeline hazard degree determination module is used for determining the associated pipeline hazard degree corresponding to each group of hazard degree-pipeline state monitoring database; and the safety risk early warning analysis module is used for carrying out safety risk early warning prompt based on the damage degree of the associated pipeline corresponding to each group of damage degree-pipeline state monitoring database. The abnormal pipeline can be recognized in time, the safety of the system is improved, potential safety hazards are predicted in advance by monitoring the associated pipeline, and the accident risk is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of pipeline monitoring, and particularly relates to a safety risk monitoring system for long-distance heat pipelines. Background Art

[0002] As a key facility for energy production, the steam pipeline system in a power plant plays an irreplaceable role in energy conversion. However, due to the extreme operating conditions and the large scale of the system, the steam pipeline system in the power plant faces a series of safety challenges, including high-temperature and high-pressure working conditions, pipeline corrosion, abnormal temperature, pressure fluctuations, and other problems;

[0003] At present, the existing technology can only monitor and alarm abnormal pipelines in real time through data collection. For long-distance heat pipelines, since the pipelines are interconnected, if an abnormal pipeline appears, its corresponding associated pipelines will surely be affected. Therefore, there are great potential safety hazards, and the existing technology lacks the judgment of the harm degree of the associated pipelines corresponding to the abnormal pipelines and cannot give early warning of safety risks for the associated pipelines. Summary of the Invention

[0004] The present invention provides a safety risk monitoring system for long-distance heat pipelines to solve at least one of the above-mentioned technical problems.

[0005] To solve the above technical problems, the present invention discloses a safety risk monitoring system for long-distance heat pipelines, including:

[0006] A pipeline abnormality monitoring module, configured to collect status monitoring data of the long-distance heat pipeline, confirm abnormal pipelines based on the status monitoring data of the long-distance heat pipeline, and give an alarm prompt for the abnormal pipelines;

[0007] An associated pipeline data acquisition module, configured to determine the associated pipelines corresponding to the abnormal pipelines based on the abnormal pipelines, acquire the status monitoring data of all associated pipelines, and generate a multi-pipeline status monitoring data set to be concerned;

[0008] An associated pipeline classification module, configured to classify the status monitoring data of all associated pipelines based on the multi-pipeline status monitoring data set to be concerned, and generate several groups of harm degree level-associated pipeline status monitoring databases;

[0009] An associated pipeline harm degree determination module, calculating the similarity between each group of harm degree level-associated pipeline status monitoring databases and the corresponding harm degree level-associated pipeline preset standard status monitoring databases, and determining the harm degree of the associated pipelines corresponding to each group of harm degree-pipeline status monitoring databases based on the similarity between each group of harm degree level-associated pipeline status monitoring databases and the corresponding harm degree level-associated pipeline preset standard status monitoring databases;

[0010] The safety risk early warning analysis module is used to perform safety risk early warning prompts based on the associated pipeline hazard levels corresponding to each group of hazard levels - pipeline status monitoring databases.

[0011] Preferably, the pipeline anomaly monitoring module includes:

[0012] The pipeline data acquisition sub-module is used to acquire the temperature, pressure, and pipe wall thickness of several pipelines in the long-distance heating pipeline at each specified monitoring moment within the monitoring period.

[0013] The pipeline performance evaluation value acquisition sub-module is used to input the temperature, pressure, and pipe wall thickness of several pipelines in the long-distance heating pipeline at each specified monitoring moment within the monitoring period into the trained pipeline heat preservation performance evaluation model, pipeline sealing performance evaluation model, and pipeline corrosion resistance performance evaluation model respectively, to obtain the heat preservation performance evaluation value, sealing performance evaluation value, and corrosion resistance performance evaluation value of the corresponding pipeline at each specified monitoring moment within the monitoring period.

[0014] The abnormal pipeline judgment matrix construction sub-module is used to construct an abnormal pipeline judgment matrix based on the temperature, pressure, and pipe wall thickness of several pipelines in the long-distance heating pipeline at each specified monitoring moment within the monitoring period, their corresponding reference temperature, reference pressure, and reference pipe wall thickness, and the heat preservation performance evaluation value, sealing performance evaluation value, and corrosion resistance performance evaluation value of the corresponding pipeline at each specified monitoring moment within the monitoring period.

[0015] The abnormal pipeline determination sub-module is used to confirm the abnormal pipeline based on the abnormal pipeline judgment matrix.

[0016] Preferably, constructing the abnormal pipeline judgment matrix:

[0017] Among them, represents the abnormal pipeline judgment matrix corresponding to the i-th pipeline within the monitoring period, and a i1 is the pipeline temperature of the i-th pipeline at the first specified monitoring moment within the monitoring period, and a i2 is the pipeline temperature of the i-th pipeline at the second specified monitoring moment within the monitoring period, and a in is the pipeline temperature of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, and a i is the reference temperature of the i-th pipeline, and b i1 is the pipeline pressure of the i-th pipeline at the first specified monitoring moment within the monitoring period, and b i2 is the pipeline pressure of the i-th pipeline at the second specified monitoring moment within the monitoring period, and b in is the pipeline pressure of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, and b i is the reference pressure of the i-th pipeline, and c i1The wall thickness of the i-th pipeline at the first specified monitoring moment within the monitoring period, c i2 The wall thickness of the i-th pipeline at the second specified monitoring moment within the monitoring period, c in The wall thickness of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, c i The reference wall thickness of the i-th pipeline, A i1 The pipeline heat insulation performance evaluation value of the i-th pipeline at the first specified monitoring moment within the monitoring period, A i2 The pipeline heat insulation performance evaluation value of the i-th pipeline at the second specified monitoring moment within the monitoring period, A in The pipeline heat insulation performance evaluation value of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, B i1 The pipeline sealing performance evaluation value of the i-th pipeline at the first specified monitoring moment within the monitoring period, B i2 The pipeline sealing performance evaluation value of the i-th pipeline at the second specified monitoring moment within the monitoring period, B in The pipeline sealing performance evaluation value of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, C i1 The pipeline corrosion resistance performance evaluation value of the i-th pipeline at the first specified monitoring moment within the monitoring period, C i2 The pipeline corrosion resistance performance evaluation value of the i-th pipeline at the second specified monitoring moment within the monitoring period, C in The pipeline corrosion resistance performance evaluation value of the i-th pipeline at the n-th specified monitoring moment within the monitoring period.

[0018] Preferably, the abnormal pipeline determination sub-module includes:

[0019] A comprehensive performance coefficient determination unit, configured to obtain the rank of the abnormal pipeline judgment matrix of each pipeline within each monitoring period, and use it as the comprehensive performance coefficient of the corresponding pipeline in the corresponding monitoring period;

[0020] A judgment comprehensive performance coefficient acquisition unit, configured to calculate the average value of the comprehensive performance coefficients of the pipeline in the corresponding monitoring period and its adjacent monitoring periods, and use it as the judgment comprehensive performance coefficient of the corresponding pipeline;

[0021] An abnormal pipeline determination unit, when the judgment comprehensive performance coefficient of the pipeline is less than the preset comprehensive performance coefficient of the corresponding pipeline, uses the pipeline as an abnormal pipeline.

[0022] Preferably, the associated pipeline data acquisition module includes:

[0023] An abnormal pipeline association recognition sub-module, configured to screen out the pipelines related to the abnormal pipeline according to the physical location, connection relationship and historical data of the pipeline, and form an associated pipeline list;

[0024] The multi-pipeline status monitoring dataset generation sub-module to be concerned about is used to generate a multi-pipeline status monitoring dataset to be concerned about based on the associated pipeline list and the status monitoring data of long-distance thermal pipelines.

[0025] Preferably, the associated pipeline classification module includes:

[0026] The first hazard degree calculation unit is used to calculate the first hazard degree corresponding to each associated pipeline based on the multi-pipeline status monitoring dataset to be concerned about;

[0027] The hazard degree level determination unit is used to determine the hazard degree level of each associated pipeline based on the first hazard degree corresponding to each associated pipeline and the reference hazard degree interval;

[0028] The database generation unit is used to generate several groups of hazard degree level-associated pipeline status monitoring databases based on the multi-pipeline status monitoring dataset to be concerned about and the hazard degree level of each associated pipeline.

[0029] Preferably, based on the multi-pipeline status monitoring dataset to be concerned about, calculate the first hazard degree corresponding to each associated pipeline:

[0030] Among them, represents the first hazard degree corresponding to the j-th associated pipeline, γ1 is the weight corresponding to the pipeline temperature deviation degree, a jmax is the maximum pipeline temperature of the j-th associated pipeline during the monitoring period, a j is the reference temperature of the j-th associated pipeline, γ2 is the weight corresponding to the pipeline pressure deviation degree, b jmax is the maximum pipeline pressure of the j-th associated pipeline during the monitoring period, b j is the reference pressure of the j-th associated pipeline, γ3 is the weight corresponding to the pipe wall thickness deviation degree, c jmin is the minimum pipe wall thickness of the j-th associated pipeline during the monitoring period, c j is the reference pipe wall thickness of the j-th associated pipeline.

[0031] Preferably, calculate the similarity between each group of hazard degree level-associated pipeline status monitoring databases and the corresponding hazard degree level-associated pipeline preset standard status monitoring databases:

[0032] Among them, δ k is the similarity between the k-th group of hazard degree level-associated pipeline status monitoring databases and the corresponding hazard degree level-associated pipeline preset standard status monitoring databases, ε 1xy represents the y-th data value in the associated pipeline status monitoring data of the x-th associated pipeline in the k-th group of hazard degree level-associated pipeline status monitoring databases, ε2xy It represents the preset standard value of the y-th data in the associated pipeline status monitoring data of the x-th associated pipeline in the hazard level - associated pipeline preset standard status monitoring database corresponding to the hazard level of the k-th group, where m is the total number of associated pipelines included in the hazard level - associated pipeline status monitoring database of the k-th group, and n is the total number of status monitoring data corresponding to each associated pipeline in the hazard level - associated pipeline status monitoring database of the k-th group;

[0033] Based on the similarity between each group of hazard level - associated pipeline status monitoring databases and the corresponding hazard level - associated pipeline preset standard status monitoring databases, determine the hazard level of the associated pipelines corresponding to each group of hazard level - pipeline status monitoring databases:

[0034] Among them, is the hazard level of the associated pipelines in the hazard level - associated pipeline status monitoring database of the k-th group, and ln is the natural logarithm with base e.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention can timely identify abnormal pipelines, improve the safety of the system, and through the monitoring of associated pipelines, predict potential safety hazards in advance, reduce the accident risk. Based on data analysis, it can provide a scientific basis for pipeline management, optimize maintenance strategies, and through systematic monitoring and early warning, it can reduce the workload of manual inspections and improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0038] <unk> Figure 1 is a schematic diagram of the long - distance thermal pipeline safety risk monitoring system of the present invention. <unk> DETAILED DESCRIPTION OF THE EMBODIMENTS <unk> <unk>

[0039] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention. <unk> <unk>

[0040] In addition, in the present invention, descriptions such as "first" and "second" are only for descriptive purposes, and do not particularly refer to the order or sequence, nor are they used to limit the present invention. They are merely used to distinguish components or operations described with the same technical terms, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions and technical features between various embodiments may be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0041] The present invention provides the following embodiments

[0042] Embodiment 1

[0043] The embodiment of the present invention provides a long-distance heat pipeline safety risk monitoring system, as Figure 1 shown, including:

[0044] A pipeline anomaly monitoring module, configured to collect status monitoring data of a long-distance heat pipeline, confirm an abnormal pipeline based on the status monitoring data of the long-distance heat pipeline, and give an alarm prompt for the abnormal pipeline;

[0045] An associated pipeline data acquisition module, configured to determine the associated pipelines corresponding to the abnormal pipeline based on the abnormal pipeline, acquire the status monitoring data of all associated pipelines, and generate a multi-pipeline status monitoring data set that needs attention;

[0046] An associated pipeline classification module, configured to classify the status monitoring data of all associated pipelines based on the multi-pipeline status monitoring data set that needs attention, and generate several groups of hazard degree level-associated pipeline status monitoring databases;

[0047] An associated pipeline hazard degree determination module, calculating the similarity between each group of hazard degree level-associated pipeline status monitoring databases and the corresponding hazard degree level-associated pipeline preset standard status monitoring databases, and determining the associated pipeline hazard degree corresponding to each group of hazard degree-pipeline status monitoring databases based on the similarity between each group of hazard degree level-associated pipeline status monitoring databases and the corresponding hazard degree level-associated pipeline preset standard status monitoring databases;

[0048] A safety risk early warning analysis module, configured to give a safety risk early warning prompt based on the associated pipeline hazard degree corresponding to each group of hazard degree-pipeline status monitoring databases.

[0049] In this embodiment, the status monitoring data of the long-distance heating pipeline includes the position of each section of the pipeline, the temperature, pressure, and wall thickness of each section of the pipeline at each specified monitoring moment within the monitoring period.

[0050] In this embodiment, the associated pipelines are determined based on the physical location of the pipelines (the physical distance from the abnormal pipeline is less than the preset distance), the connection relationship (directly connected to the abnormal pipeline), and historical data (other pipelines that showed abnormalities simultaneously when the abnormal pipeline had an abnormality in the historical data).

[0051] In this embodiment, the multi-pipeline status monitoring data set that needs attention is the set of status monitoring data of all associated pipelines.

[0052] In this embodiment, the hazard level - associated pipeline status monitoring database includes the first-level hazard level - associated pipeline status monitoring database, the second-level hazard level - associated pipeline status monitoring database, the third-level hazard level - associated pipeline status monitoring database, the fourth-level hazard level - associated pipeline status monitoring database, the fifth-level hazard level - associated pipeline status monitoring database, the sixth-level hazard level - associated pipeline status monitoring database, and the seventh-level hazard level - associated pipeline status monitoring database.

[0053] In this embodiment, each group of hazard level - associated pipeline status monitoring databases and the corresponding hazard level - associated pipeline preset standard status monitoring databases are databases composed of the preset standard critical values of each monitoring data when the corresponding associated pipelines in each group of hazard level - associated pipeline status monitoring databases are at the same hazard level.

[0054] The working principle and beneficial effects of the above technical solution are as follows: The present invention collects the status monitoring data of the pipeline through the pipeline abnormality monitoring module, identifies the abnormal pipeline and issues an alarm. Then, the associated pipeline data acquisition module determines the pipelines related to the abnormal pipeline and acquires their status monitoring data to form a multi-pipeline monitoring data set that needs attention. Next, the associated pipeline classification module classifies these data to generate a database of hazard levels and associated pipeline status monitoring. Then, the associated pipeline hazard level determination module calculates the hazard levels of each associated pipeline. Finally, the safety risk early warning analysis module conducts safety risk early warning based on the hazard levels;

[0055] The present invention can promptly identify abnormal pipelines, improve the safety of the system, and through the monitoring of associated pipelines, predict potential safety hazards in advance, reduce the accident risk. The data-based analysis can provide a scientific basis for pipeline management, optimize maintenance strategies, and through systematic monitoring and early warning, reduce the workload of manual inspections and improve work efficiency.

[0056] Embodiment 2

[0057] Based on Embodiment 1, the pipeline anomaly monitoring module includes:

[0058] A pipeline data acquisition sub-module, which is used to collect the temperature, pressure, and pipe wall thickness of several pipelines in the long-distance thermal pipeline at each specified monitoring moment within the monitoring period;

[0059] A pipeline performance evaluation value acquisition sub-module, which is used to input the temperature, pressure, and pipe wall thickness of several pipelines in the long-distance thermal pipeline at each specified monitoring moment within the monitoring period into the trained pipeline heat preservation performance evaluation model, pipeline sealing performance evaluation model, and pipeline corrosion resistance performance evaluation model respectively, to obtain the heat preservation performance evaluation value, sealing performance evaluation value, and corrosion resistance performance evaluation value of the corresponding pipeline at each specified monitoring moment within the monitoring period;

[0060] An abnormal pipeline judgment matrix construction sub-module, which is used to construct an abnormal pipeline judgment matrix based on the temperature, pressure, and pipe wall thickness of several pipelines in the long-distance thermal pipeline at each specified monitoring moment within the monitoring period, their corresponding reference temperature, reference pressure, and reference pipe wall thickness, and the heat preservation performance evaluation value, sealing performance evaluation value, and corrosion resistance performance evaluation value of the corresponding pipeline at each specified monitoring moment within the monitoring period;

[0061] An abnormal pipeline determination sub-module, which is used to confirm the abnormal pipeline based on the abnormal pipeline judgment matrix.

[0062] In this embodiment, the pipeline heat preservation performance evaluation model is a model obtained by training a neural network model with a large number of pipeline temperature values as training input samples and the heat preservation performance evaluation value of the pipeline as the output quantity.

[0063] In this embodiment, the pipeline sealing performance evaluation model is a model obtained by training a neural network model with a large number of pipeline pressure values as training input samples and the sealing performance evaluation value of the pipeline as the output quantity.

[0064] In this embodiment, the pipeline corrosion resistance performance evaluation model is a model obtained by training a neural network model with a large number of pipeline wall thicknesses as training input samples and the corrosion resistance performance evaluation value of the pipeline as the output quantity.

[0065] The working principle and beneficial effects of the above technical solution are as follows: The pipeline data acquisition sub-module is responsible for regularly collecting the temperature, pressure, and pipe wall thickness data of the pipeline. The pipeline performance evaluation value acquisition sub-module inputs these data into multiple evaluation models to obtain the heat preservation, sealing, and corrosion resistance performance evaluation values of the pipeline. The abnormal pipeline judgment matrix construction sub-module constructs a judgment matrix based on these evaluation values and reference values. Finally, the abnormal pipeline determination sub-module uses the judgment matrix to confirm the abnormal pipeline;

[0066] By comprehensively considering multiple factors such as temperature, pressure, and pipe wall thickness, the accuracy of abnormal pipe judgment is improved, and data from different sources are fused to enhance the overall reliability and effectiveness of the system.

[0067] Example 3

[0068] Based on Example 2, construct an abnormal pipe judgment matrix:

[0069] Among them, represents the abnormal pipe judgment matrix corresponding to the i-th pipe within the monitoring period, and a i1 is the pipe temperature of the i-th pipe at the first specified monitoring moment within the monitoring period, and a i2 is the pipe temperature of the i-th pipe at the second specified monitoring moment within the monitoring period, and a in is the pipe temperature of the i-th pipe at the n-th specified monitoring moment within the monitoring period, and a i is the reference temperature of the i-th pipe, and b i1 is the pipe pressure of the i-th pipe at the first specified monitoring moment within the monitoring period, and b i2 is the pipe pressure of the i-th pipe at the second specified monitoring moment within the monitoring period, and b in is the pipe pressure of the i-th pipe at the n-th specified monitoring moment within the monitoring period, and b i is the reference pressure of the i-th pipe, and c i1 is the pipe wall thickness of the i-th pipe at the first specified monitoring moment within the monitoring period, and c i2 is the pipe wall thickness of the i-th pipe at the second specified monitoring moment within the monitoring period, and c in is the pipe wall thickness of the i-th pipe at the n-th specified monitoring moment within the monitoring period, and c i is the reference pipe wall thickness of the i-th pipe, and A i1 is the pipe heat insulation performance evaluation value of the i-th pipe at the first specified monitoring moment within the monitoring period, and A i2 is the pipe heat insulation performance evaluation value of the i-th pipe at the second specified monitoring moment within the monitoring period, and A in is the pipe heat insulation performance evaluation value of the i-th pipe at the n-th specified monitoring moment within the monitoring period, and B i1 is the pipe sealing performance evaluation value of the i-th pipe at the first specified monitoring moment within the monitoring period, and B i2 is the pipe sealing performance evaluation value of the i-th pipe at the second specified monitoring moment within the monitoring period, and B in is the pipe sealing performance evaluation value of the i-th pipe at the n-th specified monitoring moment within the monitoring period, and C i1 is the pipe corrosion resistance performance evaluation value of the i-th pipe at the first specified monitoring moment within the monitoring period, and Ci2 The evaluation value of the corrosion resistance of the i-th pipeline at the 2nd specified monitoring moment during the monitoring period, C in is the evaluation value of the corrosion resistance of the i-th pipeline at the n-th specified monitoring moment during the monitoring period.

[0070] The working principle and beneficial effects of the above technical solution are as follows: By constructing an abnormal pipeline judgment matrix, the systematic analysis of the pipeline state is realized, the comprehensiveness of monitoring is enhanced, abnormal pipelines can be identified more accurately, the possibility of false alarms and missed reports is reduced, and the construction of the abnormal pipeline judgment matrix provides a basis for the visual analysis of data, which is convenient for subsequent processing and decision-making.

[0071] Embodiment 4

[0072] Based on Embodiment 3, the abnormal pipeline determination sub-module includes:

[0073] The comprehensive performance coefficient determination unit is used to obtain the rank of the abnormal pipeline judgment matrix of each pipeline in each monitoring period and use it as the comprehensive performance coefficient of the corresponding pipeline in the corresponding monitoring period;

[0074] The judgment comprehensive performance coefficient acquisition unit is used to calculate the average value of the comprehensive performance coefficients of the pipeline in the corresponding monitoring period and its adjacent monitoring period and use it as the judgment comprehensive performance coefficient of the corresponding pipeline;

[0075] The abnormal pipeline determination unit, when the judgment comprehensive performance coefficient of the pipeline is less than the preset comprehensive performance coefficient of the corresponding pipeline, takes this pipeline as an abnormal pipeline.

[0076] The working principle and beneficial effects of the above technical solution: By calculating the average value of the comprehensive performance coefficients of the pipeline in the corresponding monitoring period and its adjacent monitoring period and using it as the judgment comprehensive performance coefficient of the corresponding pipeline, the abnormal pipeline is confirmed, the accuracy of abnormal pipeline judgment is improved, and the probability of misjudgment is reduced.

[0077] Embodiment 5

[0078] Based on Embodiment 1, the associated pipeline data acquisition module includes:

[0079] The abnormal pipeline association recognition sub-module is used to screen out the pipelines related to the abnormal pipeline according to the physical location, connection relationship and historical data of the pipeline to form an associated pipeline list;

[0080] The multi-pipeline status monitoring data set generation sub-module to be concerned is used to generate a multi-pipeline status monitoring data set to be concerned based on the associated pipeline list and the status monitoring data of the long-distance thermal pipeline.

[0081] The working principle and beneficial effects of the above technical solution are as follows: The abnormal pipeline correlation identification sub-module and the multi-pipeline status monitoring data set generation sub-module to be concerned can identify the pipelines related to the abnormal pipeline through physical location, connection relationship and historical data, and can accurately identify the pipelines related to the abnormal pipeline, providing a basis for subsequent safety management.

[0082] Embodiment 6

[0083] Based on Embodiment 1, the associated pipeline classification module includes:

[0084] The first hazard degree calculation unit is used to calculate the first hazard degree corresponding to each associated pipeline based on the multi-pipeline status monitoring data set to be concerned;

[0085] The hazard degree level determination unit is used to determine the hazard degree level of each associated pipeline based on the first hazard degree corresponding to each associated pipeline and the reference hazard degree interval;

[0086] The database generation unit is used to generate several groups of hazard degree level-associated pipeline status monitoring databases based on the multi-pipeline status monitoring data set to be concerned and the hazard degree level of each associated pipeline.

[0087] The working principle and beneficial effects of the above technical solution are as follows: Through the division of the hazard degree level, hierarchical management can be realized, the pertinence of safety monitoring can be improved, and the generated hazard degree level-associated pipeline status monitoring database provides rich data support for subsequent analysis and decision-making.

[0088] Embodiment 7

[0089] Based on Embodiment 6, calculate the first hazard degree corresponding to each associated pipeline based on the multi-pipeline status monitoring data set to be concerned:

[0090] Wherein, represents the first hazard degree corresponding to the jth associated pipeline, γ1 is the weight corresponding to the pipeline temperature deviation degree, a jmax is the maximum pipeline temperature of the jth associated pipeline during the monitoring period, a j is the reference temperature of the jth associated pipeline, γ2 is the weight corresponding to the pipeline pressure deviation degree, b jmax is the maximum pipeline pressure of the jth associated pipeline during the monitoring period, b j is the reference pressure of the jth associated pipeline, γ3 is the weight corresponding to the pipe wall thickness deviation degree, c jmin is the minimum pipe wall thickness of the jth associated pipeline during the monitoring period, c j is the reference pipe wall thickness of the jth associated pipeline.

[0091] The working principle and beneficial effects of the above technical solution are as follows: By considering the deviation degree of each parameter, a more refined assessment of the hazard degree can be achieved. Considering multiple factors comprehensively improves the comprehensiveness and accuracy of the assessment, providing more scientific data support for subsequent decision-making.

[0092] Example 8

[0093] Based on Example 1, calculate the similarity between the hazard degree level-associated pipeline status monitoring database of each group and the corresponding hazard degree level-associated pipeline preset standard status monitoring database:

[0094] where δ k is the similarity between the hazard degree level-associated pipeline status monitoring database of the k-th group and the corresponding hazard degree level-associated pipeline preset standard status monitoring database, and ε 1xy represents the y-th data value in the associated pipeline status monitoring data of the x-th associated pipeline in the hazard degree level-associated pipeline status monitoring database of the k-th group, and ε 2xy represents the preset standard value of the y-th data in the associated pipeline status monitoring data of the x-th associated pipeline in the hazard degree level-associated pipeline preset standard status monitoring database corresponding to the hazard degree level-associated pipeline status monitoring database of the k-th group. m is the total number of associated pipelines included in the hazard degree level-associated pipeline status monitoring database of the k-th group, and n is the total number of status monitoring data corresponding to each associated pipeline in the hazard degree level-associated pipeline status monitoring database of the k-th group;

[0095] Based on the similarity between the hazard degree level-associated pipeline status monitoring database of each group and the corresponding hazard degree level-associated pipeline preset standard status monitoring database, determine the associated pipeline hazard degree corresponding to each group of hazard degree-pipeline status monitoring databases:

[0096] where is the associated pipeline hazard degree of the hazard degree level-associated pipeline status monitoring database of the k-th group, and ln is the natural logarithm with base e.

[0097] The working principle and beneficial effects of the above technical solution are as follows: Calculating the similarity between the hazard degree level-associated pipeline status monitoring database of each group and the corresponding hazard degree level-associated pipeline preset standard status monitoring database provides a reference framework for the assessment by comparing with the preset standard, improving the objectivity of judgment. Through quantitative similarity analysis, high-risk pipelines can be quickly identified, the decision-making efficiency can be improved, and targeted hierarchical management can be carried out based on the associated pipeline hazard degree corresponding to each group of hazard degree-pipeline status monitoring databases.

[0098] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. Long-distance thermal pipeline safety risk monitoring system, characterized in that: Including: A pipeline anomaly monitoring module, which is used to collect the status monitoring data of a long-distance heat pipeline, confirm the abnormal pipeline based on the status monitoring data of the long-distance heat pipeline, and give an alarm prompt for the abnormal pipeline; An associated pipeline data acquisition module, which is used to determine the associated pipelines corresponding to the abnormal pipeline based on the abnormal pipeline, acquire the status monitoring data of all associated pipelines, and generate a multi-pipeline status monitoring data set that needs attention; An associated pipeline classification module, which is used to classify the status monitoring data of all associated pipelines based on the multi-pipeline status monitoring data set that needs attention, and generate several sets of hazard level-associated pipeline status monitoring databases; An associated pipeline hazard level determination module, which calculates the similarity between each set of hazard level-associated pipeline status monitoring databases and the corresponding hazard level-associated pipeline preset standard status monitoring databases, and determines the associated pipeline hazard level corresponding to each set of hazard level-pipeline status monitoring databases based on the similarity between each set of hazard level-associated pipeline status monitoring databases and the corresponding hazard level-associated pipeline preset standard status monitoring databases; A safety risk early warning analysis module, which is used to give a safety risk early warning prompt based on the associated pipeline hazard level corresponding to each set of hazard level-pipeline status monitoring databases.

2. The long-distance thermal pipeline safety risk monitoring system according to claim 1, wherein: The pipeline anomaly monitoring module includes: A pipeline data acquisition sub-module, which is used to collect the temperature, pressure and pipe wall thickness of several pipelines in the long-distance heat pipeline at each specified monitoring moment within a monitoring period; A pipeline performance evaluation value acquisition sub-module, which is used to input the temperature, pressure and pipe wall thickness of several pipelines in the long-distance heat pipeline at each specified monitoring moment within a monitoring period into the trained pipeline heat insulation performance evaluation model, pipeline sealing performance evaluation model and pipeline corrosion resistance performance evaluation model respectively, and obtain the heat insulation performance evaluation value, sealing performance evaluation value and corrosion resistance performance evaluation value of the corresponding pipeline at each specified monitoring moment within the monitoring period; An abnormal pipeline judgment matrix construction sub-module, which is used to construct an abnormal pipeline judgment matrix based on the temperature, pressure and pipe wall thickness of several pipelines in the long-distance heat pipeline at each specified monitoring moment within a monitoring period, their corresponding reference temperature, reference pressure and reference pipe wall thickness, and the heat insulation performance evaluation value, sealing performance evaluation value and corrosion resistance performance evaluation value of the corresponding pipeline at each specified monitoring moment within the monitoring period; An abnormal pipeline determination sub-module, which is used to confirm the abnormal pipeline based on the abnormal pipeline judgment matrix.

3. The long-distance thermal pipeline safety risk monitoring system according to claim 2, characterized in that: Constructing an abnormal pipeline judgment matrix: Among them, represents the abnormal pipeline judgment matrix corresponding to the i-th pipeline within the monitoring period, a i1 is the pipeline temperature of the i-th pipeline at the first specified monitoring moment within the monitoring period, a i2 is the pipeline temperature of the i-th pipeline at the second specified monitoring moment within the monitoring period, a in is the pipeline temperature of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, a i is the reference temperature of the i-th pipeline, b i1 is the pipeline pressure of the i-th pipeline at the first specified monitoring moment within the monitoring period, b i2 is the pipeline pressure of the i-th pipeline at the second specified monitoring moment within the monitoring period, b in is the pipeline pressure of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, b i is the reference pressure of the i-th pipeline, c i1 is the wall thickness of the i-th pipeline at the first specified monitoring moment within the monitoring period, c i2 is the wall thickness of the i-th pipeline at the second specified monitoring moment within the monitoring period, c in is the wall thickness of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, c i is the reference wall thickness of the i-th pipeline, A i1 is the pipeline heat insulation performance evaluation value of the i-th pipeline at the first specified monitoring moment within the monitoring period, A i2 is the pipeline heat insulation performance evaluation value of the i-th pipeline at the second specified monitoring moment within the monitoring period, A in is the pipeline heat insulation performance evaluation value of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, B i1 is the pipeline sealing performance evaluation value of the i-th pipeline at the first specified monitoring moment within the monitoring period, B i2 is the pipeline sealing performance evaluation value of the i-th pipeline at the second specified monitoring moment within the monitoring period, B in is the pipeline sealing performance evaluation value of the i-th pipeline at the n-th specified monitoring moment within the monitoring period, C i1 is the pipeline corrosion resistance performance evaluation value of the i-th pipeline at the first specified monitoring moment within the monitoring period, C i2 is the pipeline corrosion resistance performance evaluation value of the i-th pipeline at the second specified monitoring moment within the monitoring period, C in is the pipeline corrosion resistance performance evaluation value of the i-th pipeline at the n-th specified monitoring moment within the monitoring period.

4. The long-distance thermal pipeline safety risk monitoring system according to claim 3, wherein: The abnormal pipeline determination sub-module includes: A comprehensive performance coefficient determination unit, which is used to obtain the rank of the abnormal pipeline judgment matrix of each pipeline within each monitoring period, and use it as the comprehensive performance coefficient of the corresponding pipeline in the corresponding monitoring period; A judgment comprehensive performance coefficient acquisition unit, which is used to calculate the average value of the comprehensive performance coefficients of the pipelines in the corresponding monitoring period and its adjacent monitoring periods, and use it as the judgment comprehensive performance coefficient of the corresponding pipeline; An abnormal pipeline determination unit, when the judgment comprehensive performance coefficient of the pipeline is less than the preset comprehensive performance coefficient of the corresponding pipeline, takes the pipeline as an abnormal pipeline.

5. The long-distance thermal pipeline safety risk monitoring system according to claim 1, wherein: The associated pipeline data acquisition module includes: An abnormal pipeline association recognition sub-module, which is used to screen out pipelines related to the abnormal pipeline according to the physical location, connection relationship and historical data of the pipeline, and form an associated pipeline list; A multi-pipeline status monitoring data set generation sub-module that needs attention, which is used to generate a multi-pipeline status monitoring data set that needs attention based on the associated pipeline list and the status monitoring data of the long-distance heat pipeline.

6. The long-distance thermal pipeline safety risk monitoring system according to claim 1, characterized in that; The associated pipeline classification module includes: A first hazard degree calculation unit, which is used to calculate the first hazard degree corresponding to each associated pipeline based on the multi-pipeline status monitoring data set that needs attention; A hazard degree level determination unit, which is used to determine the hazard degree level of each associated pipeline based on the first hazard degree corresponding to each associated pipeline and the reference hazard degree interval; A database generation unit, which is used to generate several groups of hazard degree level-associated pipeline status monitoring databases based on the multi-pipeline status monitoring data set that needs attention and the hazard degree level of each associated pipeline.

7. The long-distance thermal pipeline safety risk monitoring system according to claim 6, characterized in that: Based on the multi-pipeline status monitoring data set that needs attention, calculate the first hazard degree corresponding to each associated pipeline: Among them, represents the first hazard level corresponding to the j-th associated pipeline, γ1 is the weight corresponding to the pipeline temperature deviation degree, a jmax is the maximum pipeline temperature of the j-th associated pipeline during the monitoring period, a j is the reference temperature of the j-th associated pipeline, γ2 is the weight corresponding to the pipeline pressure deviation degree, b jmax is the maximum pipeline pressure of the j-th associated pipeline during the monitoring period, b j is the reference pressure of the j-th associated pipeline, γ3 is the weight corresponding to the pipe wall thickness deviation degree, c jmin is the minimum pipe wall thickness of the j-th associated pipeline during the monitoring period, c j is the reference pipe wall thickness of the j-th associated pipeline.

8. The long-distance heat pipeline safety risk monitoring system according to claim 1, wherein: Calculate the similarity between each group of hazard degree level-associated pipeline status monitoring databases and the corresponding hazard degree level-associated pipeline preset standard status monitoring databases; Among them, δ k is the similarity between the k-th group of hazard level-associated pipeline status monitoring database and the corresponding hazard level-associated pipeline preset standard status monitoring database, and ε 1xy represents the y-th data value in the associated pipeline status monitoring data of the x-th associated pipeline in the k-th group of hazard level-associated pipeline status monitoring database, and ε 2xy represents the preset standard value of the y-th data in the associated pipeline status monitoring data of the x-th associated pipeline in the hazard level-associated pipeline preset standard status monitoring database corresponding to the k-th group of hazard level-associated pipeline status monitoring database. m is the total number of associated pipelines included in the k-th group of hazard level-associated pipeline status monitoring database, and n is the total number of status monitoring data corresponding to each associated pipeline in the k-th group of hazard level-associated pipeline status monitoring database; Based on the similarity between each group of hazard degree level-associated pipeline status monitoring databases and the corresponding hazard degree level-associated pipeline preset standard status monitoring databases, determine the hazard degree of the associated pipeline corresponding to each group of hazard degree-pipeline status monitoring databases; Among them, is the associated pipeline hazard degree of the k-th group of hazard degree level - associated pipeline status monitoring database, and ln is the natural logarithm with base e.

Images