A pipeline health analysis system for high-condensate oil transportation

Abstract

The present invention relates to the technical field of pipeline detection and analysis, and specifically discloses a pipeline health analysis system for high-condensate oil transportation. The present invention deploys several parameter monitoring areas in the pipeline, obtains the initial state parameters of the high-condensate oil in each parameter monitoring area as a first state parameter, and obtains the second state parameters and flow rate parameters during the high-condensate oil transportation in real time, and analyzes the pipeline health status based on factors such as preset temperature and pressure thresholds. Through multi-segment, dynamic monitoring and dual-model health assessment, temperature, pressure and flow rate anomalies can be immediately detected before wax deposition has formed a layer, thereby avoiding the risk of major blockage caused by accumulation of deposits.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline detection and analysis, and more particularly to a pipeline health analysis system for high-condensate oil transportation. Background Art

[0002] During the transportation of high pour point oil, the oil contains a high proportion of wax components, which are prone to crystallization and deposition below a certain temperature. The existing literature (Sun Qizhi. Research on wax deposition rate model of insulated crude oil pipeline [D]. Liaoning Petrochemical University, 2019. DOI: 10.27023 / d.cnki.gfssc.2019.000201.) obtained a series of data from the wax deposition loop experimental device in the laboratory, and used SPSS software to obtain a stepwise regression wax deposition rate model. Then, using MATLAB software, a support vector machine model was obtained, and the following was given: Figure 2 The relationship between the amount of wax precipitation per degree Celsius and the temperature is shown in the figure and Figure 3 The experimental viscosity-temperature curve shown in the figure below shows rapid and drastic changes in oil velocity and pressure during startup and shutdown of the pump station. This can lead to localized low-velocity areas, thickened boundary layers, and sudden temperature drops within the pipeline. These transient effects prolong the residence time of the oil near the pipeline wall, deteriorating heat exchange conditions and creating favorable conditions for the rapid precipitation and adhesion of wax. After repeated startups and shutdowns, these brief deposition processes accumulate, gradually thickening the localized deposition layer. This not only compromises pipeline transport health but can also cause localized blockages, equipment wear, and increased energy consumption, negatively impacting the safe operation and economic efficiency of the entire transportation system.

[0003] At the initial start-up of the pump station, since it takes a certain amount of acceleration time for the oil to change from a stagnant state to a flowing state, the overall flow rate in the pipeline is significantly lower than the design value. At this stage, due to insufficient shear force, the oil forms a thicker boundary layer near the pipe wall, and the local heat transfer efficiency is reduced, causing the temperature of the pipe wall area to drop rapidly, and wax crystals to precipitate rapidly on the pipe wall. During the shutdown process, the pump station quickly reduces the operating pressure and flow rate, and the oil quickly switches from a dynamic equilibrium state to a low-speed or partially static state. At this time, due to a significant drop in convective heat transfer, the local temperature of the pipeline drops rapidly, and the deposition conditions suddenly improve. The wax that was originally in suspension in the oil precipitates in large quantities in a short period of time. At the same time, due to the temperature drop effect and pressure fluctuation caused by the local pressure drop, the oil state undergoes a sudden change, and the wax that was not originally deposited is concentrated and attached to the pipe wall in a short period of time. In order to solve the above problems, a technical solution is now provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a pipeline health analysis system for high-condensate oil transportation. Through multi-segment, dynamic monitoring and dual-model health assessment, it is used to solve the problem that transient start / shutdown during high-condensate oil transportation prolongs the oil residence time near the pipeline wall, deteriorates heat exchange conditions, and promotes the rapid precipitation and adhesion of wax, affecting the health of pipeline transportation. It can immediately detect temperature, pressure and flow rate anomalies before wax deposition forms a layer, avoid the risk of major blockage caused by accumulation of sediment, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A pipeline health analysis system for high-condensate oil transportation includes a parameter acquisition module, a data communication storage center, a parameter classification processing module, a pipeline health status analysis module, and an intelligent feedback adjustment module. The parameter acquisition module is used to deploy several parameter monitoring areas within the pipeline, obtain the initial state parameters of the high-condensate oil in each parameter monitoring area as a first state parameter, and obtain in real time a second state parameter and a flow rate parameter during the transportation of the high-condensate oil. The state parameters include temperature parameters and pressure parameters.

[0007] The data communication storage center is used to store state parameters and flow rate parameters in real time;

[0008] The parameter classification processing module is used to classify the state parameters according to the parameter detection section;

[0009] The pipeline health status analysis module is configured to perform multi-layer pipeline health status detection based on the classification results and flow rate parameters; the pipeline health status analysis module includes a first health status analysis unit; the first health status analysis unit is configured to construct a first pipeline status detection model based on the first detection factor and the second detection factor output by the parameter classification processing module to obtain a first health coefficient of the pipeline, and determine whether the pipeline is healthy based on the first health coefficient;

[0010] The intelligent feedback adjustment module is used to provide feedback when an abnormality occurs in the pipeline.

[0011] Furthermore, the pipeline health status analysis module also includes a second health status analysis unit; the second health status analysis unit is used to analyze the second health coefficient of the pipeline by obtaining the flow change rate of the high-viscosity oil in the pipeline; the second health status analysis unit includes a change rate calculation subunit and a second health status detection subunit; the change rate calculation subunit is used to obtain the total kinetic energy of the high-viscosity oil in the i-th parameter detection section in the pipeline according to the flow rate parameter. According to the principle of conservation of energy, the instantaneous change rate of the kinetic energy in each parameter detection section is obtained by the difference between the local time change and the kinetic energy flux of the high-viscosity oil through the boundary.

[0012] Furthermore, the second health status detection subunit is used to calculate the second health coefficient based on the average of the instantaneous change rate of kinetic energy in each parameter detection section, and compare the instantaneous change rate of kinetic energy in each parameter detection section with the second health coefficient. If the instantaneous change rate of kinetic energy in the parameter detection section is greater than or equal to the second health coefficient threshold, then there is an abnormality in the parameter detection section; if the instantaneous change rate of kinetic energy in the parameter detection section is less than the second health coefficient threshold, then the parameter detection section is healthy.

[0013] Furthermore, the parameter classification processing module includes a target state parameter determination unit, a first classification clustering unit, and a second classification clustering unit; the target state parameter determination unit is used to obtain pre-processed state parameters according to the parameter detection section to form a target state parameter set for each parameter monitoring area;

[0014] The first classification and clustering unit is used to classify the target state parameter set into a third state parameter and a fourth state parameter according to a preset state parameter threshold, and extract the third state parameter and the fourth state parameter based on each parameter monitoring area to construct a first state set and a second state set;

[0015] The second classification and clustering unit is used to obtain a first detection factor and a second detection factor according to the first state set and the second state set respectively.

[0016] Furthermore, the first classification clustering unit is used to classify the target state parameter set into a third state parameter and a fourth state parameter according to a preset state parameter threshold, and to divide the state parameters at the same moment in the target state parameter set according to a preset temperature parameter and a pressure parameter. If any state parameter at the same moment is greater than or equal to the preset temperature parameter or pressure parameter, the state parameter is divided into the third state parameter; if any state parameter at the same moment is less than the preset temperature parameter or pressure parameter, the state parameter is divided into the fourth state parameter.

[0017] Furthermore, the second classification and clustering unit is used to obtain the first detection factor and the second detection factor according to the first state set and the second state set respectively, and the specific steps are:

[0018] In the first state set, two third state parameters are randomly selected as the first cluster center and the second cluster center respectively, and the first average value is obtained by taking the weighted average of the cluster cluster where the first cluster center is located in the first state set according to the weight. The second average value is obtained by taking the weighted average of the cluster cluster where the second cluster center is located in the second state set according to the weight, and the first average value and the second average value are used as the first detection factor.

[0019] Furthermore, two fourth state parameters are randomly selected in the second state set as the third cluster center and the fourth cluster center respectively, and the cluster cluster where the third cluster center is located in the second state set is calculated by taking the weighted average according to the weight to obtain the third average value, and the cluster cluster where the fourth cluster center is located in the second state set is calculated by taking the weighted average according to the weight to obtain the fourth average value, and the third average value and the fourth average value are used as the second detection factor.

[0020] Furthermore, the first health status analysis unit determines whether the pipeline is healthy based on the first health coefficient: a first deviation value is calculated based on the difference between the normalized first average value and the second average value, a second deviation value is calculated based on the difference between the normalized third average value and the fourth average value, half of the sum of the first average value and the second average value, and half of the sum of the third average value and the fourth average value are multiplied by the inhibition factor, and then 1 is added as the denominator, and the first deviation value and the second deviation value are multiplied by their respective weight coefficients are added as the numerator to calculate the first health coefficient.

[0021] Furthermore, whether the pipeline is healthy is determined based on the first health coefficient: the first health coefficient is compared with a preset health coefficient. If the first health coefficient is greater than or equal to the preset health coefficient, the pipeline is abnormal; if the first health coefficient is less than the preset health coefficient, the pipeline is healthy.

[0022] The technical effects and advantages of the pipeline health analysis system for high-condensate oil transportation of the present invention are as follows: the present invention deploys several parameter monitoring areas in the pipeline, obtains the initial state parameters of the high-condensate oil in each parameter monitoring area as the first state parameters, and obtains the second state parameters and flow rate parameters during the transportation of the high-condensate oil in real time. Based on the preset temperature and pressure thresholds, the target set is divided into a third state parameter and a fourth state parameter, which respectively constitute the first state set and the second state set to obtain the first detection factor and the second detection factor, and obtain the first health coefficient to judge the health status of the pipeline; through multi-segment, dynamic monitoring and dual-model health assessment, temperature, pressure and flow rate anomalies can be immediately detected before wax deposition has formed a layer, avoiding the risk of large blockage caused by accumulation of deposition; the present invention statically utilizes temperature and pressure deviation and coupling strength to evaluate pipeline health, and dynamically adds a flow rate kinetic energy change rate model to achieve all-round health monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 The monitoring section status distribution diagram provided by the present invention;

[0024] Figure 2 A graph showing the relationship between the amount of wax precipitation per degree Celsius and temperature in the prior art provided by the present invention;

[0025] Figure 3 The viscosity-temperature curve diagram obtained by the prior art experiment provided by the present invention;

[0026] Figure 4 The health coefficient distribution diagram of the monitoring section provided by the present invention;

[0027] Figure 5 This is a structural schematic diagram of a pipeline health analysis system for high-condensate oil transportation provided by the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the accompanying drawings. Obviously, the technical solutions described are only part of the present invention, not the entire invention. Based on the technical solutions of the present invention, all other technical solutions obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0029] Example 1

[0030] Figure 5 The present invention provides a structural schematic diagram of a pipeline health analysis system for high-condensate oil transportation. As shown in the figure, a pipeline health analysis system for high-condensate oil transportation includes a parameter acquisition module, a data communication storage center, a parameter classification processing module, a pipeline health status analysis module, and an intelligent feedback adjustment module; the parameter acquisition module is connected to the data communication storage center, the parameter classification processing module, and the pipeline health status analysis module; the parameter classification processing module is connected to the pipeline health status analysis module; and the pipeline health status analysis module is connected to the intelligent feedback adjustment module;

[0031] The parameter acquisition module is used to deploy several parameter monitoring areas in the pipeline, obtain the initial state parameters of the high pour point oil in each parameter monitoring area as the first state parameter, and obtain the second state parameters and flow rate parameters of the high pour point oil during transportation in real time; the state parameters include temperature parameters and pressure parameters;

[0032] The data communication storage center is used to store state parameters and flow rate parameters in real time;

[0033] The parameter classification processing module is used to classify the state parameters according to the parameter detection section;

[0034] The pipeline health status analysis module is used to perform multi-layer pipeline health status detection based on classification results and flow rate parameters;

[0035] The intelligent feedback adjustment module is used to provide feedback when there is an abnormality in the pipeline.

[0036] Specifically, the parameter classification processing module includes a target state parameter determination unit, a first classification clustering unit and a second classification clustering unit; the target state parameter determination unit is connected to the first classification clustering unit, and the first classification clustering unit is connected to the second classification clustering unit.

[0037] The target state parameter determination unit is used to obtain the pre-processed state parameters according to the parameter detection section to form a target state parameter set for each parameter monitoring area;

[0038] The first classification and clustering unit is used to classify the target state parameter set into a third state parameter and a fourth state parameter according to a preset state parameter threshold, and extract the third state parameter and the fourth state parameter based on each parameter monitoring area to construct a first state set and a second state set;

[0039] The second classification and clustering unit is used to obtain a first detection factor and a second detection factor according to the first state set and the second state set respectively.

[0040] Specifically, the first classification clustering unit is used to classify the target state parameter set into a third state parameter and a fourth state parameter according to a preset state parameter threshold, and to divide the state parameters at the same moment in the target state parameter set according to a preset temperature parameter and pressure parameter. If any state parameter at the same moment is greater than or equal to the preset temperature parameter or pressure parameter, the state parameter is divided into the third state parameter; if any state parameter at the same moment is less than the preset temperature parameter or pressure parameter, the state parameter is divided into the fourth state parameter.

[0041] Specifically, the second classification and clustering unit is used to obtain the first detection factor and the second detection factor according to the first state set and the second state set, respectively, and the specific steps are:

[0042] Randomly selecting two third-state parameters in the first state set as the first cluster center and the second cluster center, respectively, calculating the weighted average of the clusters where the first cluster center is located in the first state set according to the weight to obtain a first average value, calculating the weighted average of the clusters where the second cluster center is located in the second state set according to the weight to obtain a second average value, and using the first average value and the second average value as the first detection factor;

[0043] Randomly selecting two fourth-state parameters in the second state set as the third cluster center and the fourth cluster center, respectively, calculating the weighted average of the clusters where the third cluster center is located in the second state set according to the weight to obtain a third average value, calculating the weighted average of the clusters where the fourth cluster center is located in the second state set according to the weight to obtain a fourth average value, and using the third average value and the fourth average value as the second detection factor;

[0044] It should be noted that the number of clusters is set to 2.

[0045] The target state parameter determination unit uses preprocessing such as filtering, noise removal, and normalization to eliminate faulty readings and random disturbances, unify the dimensions, and then summarize them. This ensures that the "target parameters" used in subsequent analysis are of high quality and reasonable dimensions, laying a solid foundation for clustering and model calculations. The first classification clustering unit first performs segmentation based on preset temperature / pressure thresholds, quickly distinguishing between obviously out-of-limit and normal parameters, avoiding the participation of all data in subsequent calculations, saving computing resources and immediately intercepting large-scale anomalies. Each unit has clear responsibilities and low coupling, facilitating the subsequent replacement of more advanced preprocessing algorithms, more complex binning strategies, or more sophisticated clustering algorithms without affecting the overall architecture. This "three-stage → two-level clustering" process not only ensures data quality and detection accuracy, but also takes into account computing efficiency and system scalability, and is an indispensable "bridge" link in the pipeline health analysis system.

[0046] Specifically, the pipeline health status analysis module includes a first health status analysis unit and a second health status analysis unit; the first health status analysis unit is connected to the second health status analysis unit;

[0047] The first health status analysis unit is used to construct a first pipeline status detection model based on the first detection factor and the second detection factor to obtain a first health coefficient of the pipeline, and judge whether the pipeline is healthy based on the first health coefficient: a first deviation value is calculated based on the difference between the normalized first average value and the second average value, a second deviation value is calculated based on the difference between the normalized third average value and the fourth average value, half of the sum of the first average value and the second average value, and half of the sum of the third average value and the fourth average value are multiplied by the inhibition factor, and then 1 is added as the denominator, and the first deviation value and the second deviation value multiplied by their respective weight coefficients are added as the numerator to calculate the first health coefficient.

[0048] The specific formula is:

[0049] ;

[0050] Where: is the first health coefficient, is the first average value, is the second average value, is the weight coefficient of the first deviation value, is the weight coefficient of the second deviation value, is the third average value, is the fourth average value, For the inhibitory factor.

[0051] Determine whether the pipeline is healthy based on the first health coefficient: compare the first health coefficient with the preset health coefficient. If the first health coefficient is greater than or equal to the preset health coefficient, the pipeline is abnormal; if the first health coefficient is less than the preset health coefficient, the pipeline is healthy.

[0052] The second health status analysis unit is used to analyze the second health coefficient of the pipeline by obtaining the flow change rate of the high pour point oil in the pipeline;

[0053] Specifically, the second health status analysis unit includes a change rate calculation subunit and a second health status detection subunit;

[0054] The rate of change calculation subunit is used to obtain the total kinetic energy of the high pour point oil in the i-th parameter detection section in the pipeline according to the flow rate parameter. , High condensate density, is the mean value of the flow velocity parameter of the pipe section in the i-th parameter detection section at time t, is the cross-sectional area of the pipe, is the microelement length of the parameter detection section along the pipeline axis. According to the principle of conservation of energy, the instantaneous rate of change of kinetic energy in each parameter detection section is obtained by the difference between the local time change and the kinetic energy flux of high pour point oil passing through the boundary. The calculation formula for the instantaneous rate of change of kinetic energy in the i-th parameter detection section is:

[0055] ;

[0056] The second health status detection subunit is used to calculate a second health coefficient based on the average of the instantaneous change rate of kinetic energy in each parameter detection section, and compare the instantaneous change rate of kinetic energy in each parameter detection section with the second health coefficient. If the instantaneous change rate of kinetic energy in the parameter detection section is greater than or equal to the second health coefficient threshold, the parameter detection section is abnormal; if the instantaneous change rate of kinetic energy in the parameter detection section is less than the second health coefficient threshold, the parameter detection section is healthy. The calculation formula of the second health coefficient is:

[0057] ;

[0058] Where: is the second health coefficient, is the total kinetic energy of the high pour point oil in the i-th parameter detection section in the pipeline, is the instantaneous rate of change of kinetic energy in the i-th parameter detection section, The number of parameter detection segments.

[0059] Figure 1The distribution diagram of the monitoring section status provided by the present invention; the horizontal axis is the five pipeline monitoring sections (area 1-area 5), and the vertical axis is the percentage of the total samples in the section. The green part represents the proportion of "normal" state samples, and the red part represents the proportion of "abnormal" state samples. Figure 1 As can be seen, the anomaly rate in area 3 is the highest (≈12%), followed by area 5 (≈10%) and area 2 (≈8%); the anomaly rates in areas 1 and 4 are relatively low, approximately 5% and 3% respectively.

[0060] Figure 4 This is the distribution diagram of the health coefficient of the monitoring section provided by the present invention; the horizontal axis is the five monitoring sections of the pipeline, and the vertical axis is the first health coefficient obtained by corresponding calculation (after normalization, between 0 and 1, the larger the value, the better the health status). Figure 4 As can be seen, the health coefficient of area 3 is the highest (≈0.95), indicating that the temperature-pressure synergy deviation is the smallest; the health coefficient of area 2 is the lowest (≈0.87), which requires special attention. Figure 1 Although region 3 has a high abnormality ratio, its “health factor” is still relatively high, which may be due to the small amplitude of abnormal fluctuation. Although region 2 has the second highest abnormality rate, its health score is the lowest after combining the deviation amplitude and coupling effect.

[0061] The first health factor quantitatively measures the coordinated deviation of temperature and pressure, reflecting the risk of "waxing" of oil on the pipe wall; the second health factor is based on the instantaneous rate of change of flow velocity kinetic energy, and provides insight into flow instability and stagnation effects under operating conditions such as startup / shutdown. The dual models are linked to simultaneously capture "waxing precursors" and "flow anomalies", avoiding the blind spots of a single indicator; the numerator uses weighted deviation value aggregation to highlight the most sensitive temperature and pressure fluctuation signals, and the denominator is added with the coupling product term × suppression factor to effectively suppress the false amplification caused by large-scale mean drift and improve anti-interference ability; all average values are normalized before calculating the deviation and coupling term to eliminate sensor dimension and section differences, making the health factors of different pipe sections and different operating conditions comparable.

[0062] Example 2

[0063] Based on a 30km long high-condensate oil pipeline, a real application example of the system is given according to three parameter detection sections (Section 1: 0–10km, Section 2: 10km–20km, Section 3: 20km–30km), and a key data table is attached.

[0064] Pipeline Overview: Transporting high-condensate oil, total length 30km, diameter DN500, oil density ρ=900kg / m³.

[0065] Deployment of monitoring sections: a set of sensors is deployed at 0km, 10km, and 20km to collect temperature (°C), pressure (MPa), and flow velocity (m / s) respectively.

[0066] Threshold settings: temperature threshold 60°C, pressure threshold 5MPa; preset health factor threshold is 0.05;

[0067] Clustering parameters: number of clusters k = 2; bias weights w1 = w2 = 0.5, suppression factor λ = 0.1.

[0068] Table 1 shows the original and real-time data and status classification table:

[0069] Table 1: Raw and real-time data and status classification

[0070]

[0071] Construct the first state set and the second state set: First state set (third state parameter): ; Second state set (fourth state parameter): ;

[0072] Detection factor calculation: First detection factor , randomly select cluster centers: points (58, 5.1) and (61, 5.4), and take the weighted average of the weights within each cluster, that is, take its own value: , ;

[0073] Second detection factor , randomly select cluster centers: points (55, 4.9) and (50, 4.8), and take the weighted average within the cluster, that is, take the value of itself: , ;

[0074] Based on the above, the first health coefficient is obtained:

[0075] ,

[0076] Health judgment: 0.05, therefore, the pipeline is healthy in terms of temperature and pressure.

[0077] According to the second health coefficient of the velocity parameter: the three-stage instantaneous kinetic energy change rate (J / s) are: ; , Health judgment: The first parameter detection section: , so the first parameter detection section is healthy; the second parameter detection section: , so the second parameter detection section is healthy; the third parameter detection section: , so the third section parameter detection section is healthy.

[0078] The embodiment of the present invention deploys several parameter monitoring areas in the pipeline, obtains the initial state parameters of the high-condensation oil in each parameter monitoring area as the first state parameters, and obtains the second state parameters and flow rate parameters of the high-condensation oil during transportation in real time. Based on preset temperature and pressure thresholds, the target set is divided into a third state parameter and a fourth state parameter, which respectively constitute a first state set and a second state set to obtain a first detection factor and a second detection factor, and obtain a first health coefficient to judge the health status of the pipeline; through multi-segment, dynamic monitoring and dual-model health assessment, temperature, pressure and flow rate anomalies can be immediately detected before wax deposition has formed a layer, avoiding the risk of large blockage caused by accumulation of deposition; the present invention statically uses temperature and pressure deviation and coupling strength to evaluate pipeline health, and dynamically adds a flow rate kinetic energy change rate model to achieve all-round health monitoring.

[0079] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0080] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A pipeline health analysis system for high pour point oil transportation, comprising a parameter acquisition module, a data communication storage center, a parameter classification processing module, a pipeline health status analysis module, and an intelligent feedback adjustment module; characterized in that: The parameter acquisition module is used to deploy several parameter monitoring areas in the pipeline, obtain the initial state parameters of the high pour point oil in each parameter monitoring area as the first state parameter, and obtain the second state parameters and flow rate parameters of the high pour point oil during transportation in real time; the state parameters include temperature parameters and pressure parameters; The data communication storage center is used to store state parameters and flow rate parameters in real time; The parameter classification processing module is used to classify the state parameters according to the parameter detection section; The pipeline health status analysis module is configured to perform multi-layer pipeline health status detection based on the classification results and flow rate parameters; the pipeline health status analysis module includes a first health status analysis unit; the first health status analysis unit is configured to construct a first pipeline status detection model based on the first detection factor and the second detection factor output by the parameter classification processing module to obtain a first health coefficient of the pipeline, and determine whether the pipeline is healthy based on the first health coefficient; The intelligent feedback adjustment module is used to provide feedback when an abnormality occurs in the pipeline; The parameter classification processing module includes a target state parameter determination unit, a first classification clustering unit and a second classification clustering unit; The target state parameter determination unit is used to obtain the pre-processed state parameters according to the parameter detection section to form a target state parameter set for each parameter monitoring area; The first classification and clustering unit is used to classify the target state parameter set into a third state parameter and a fourth state parameter according to a preset state parameter threshold, and extract the third state parameter and the fourth state parameter based on each parameter monitoring area to construct a first state set and a second state set; The second classification and clustering unit is used to obtain a first detection factor and a second detection factor according to the first state set and the second state set respectively; The first classification and clustering unit is used to classify the target state parameter set into a third state parameter and a fourth state parameter according to a preset state parameter threshold, and divide the state parameters at the same moment in the target state parameter set according to a preset temperature parameter and a pressure parameter. If any state parameter at the same moment is greater than or equal to the preset temperature parameter or pressure parameter, the state parameter is divided into the third state parameter; if any state parameter at the same moment is less than the preset temperature parameter or pressure parameter, the state parameter is divided into the fourth state parameter; The second classification and clustering unit is used to obtain the first detection factor and the second detection factor according to the first state set and the second state set respectively, and the specific steps are as follows: Randomly selecting two third-state parameters in the first state set as the first cluster center and the second cluster center, respectively, calculating the weighted average of the clusters where the first cluster center is located in the first state set according to the weight to obtain a first average value, calculating the weighted average of the clusters where the second cluster center is located in the second state set according to the weight to obtain a second average value, and using the first average value and the second average value as the first detection factor; Randomly selecting two fourth-state parameters in the second state set as the third cluster center and the fourth cluster center, respectively, calculating the weighted average of the clusters where the third cluster center is located in the second state set according to the weight to obtain a third average value, calculating the weighted average of the clusters where the fourth cluster center is located in the second state set according to the weight to obtain a fourth average value, and using the third average value and the fourth average value as the second detection factor; The first deviation value is calculated based on the difference between the normalized first average value and the second average value, and the second deviation value is calculated based on the difference between the normalized third average value and the fourth average value. The first health coefficient is calculated by multiplying half of the sum of the first average value and the second average value and half of the sum of the third average value and the fourth average value by the inhibition factor, and then adding 1 as the denominator. The first deviation value and the second deviation value multiplied by their respective weight coefficients are added as the numerator.

2. A pipeline health analysis system for high pour point oil transportation according to claim 1, characterized in that: The pipeline health status analysis module also includes a second health status analysis unit; the second health status analysis unit is used to analyze the second health coefficient of the pipeline by obtaining the flow change rate of the high-viscosity oil in the pipeline; the second health status analysis unit includes a change rate calculation subunit and a second health status detection subunit; the change rate calculation subunit is used to obtain the total kinetic energy of the high-viscosity oil in the i-th parameter detection section in the pipeline according to the flow rate parameter. According to the principle of conservation of energy, the instantaneous change rate of the kinetic energy in each parameter detection section is obtained by the difference between the local time change and the kinetic energy flux of the high-viscosity oil passing through the boundary.

3. A pipeline health analysis system for high pour point oil transportation according to claim 2, characterized in that: The second health status detection subunit is configured to calculate a second health coefficient based on an average of the instantaneous change rates of kinetic energy within each parameter detection section, compare the instantaneous change rates of kinetic energy within each parameter detection section with the second health coefficient, and determine that an abnormality exists in the parameter detection section if the instantaneous change rates of kinetic energy within the parameter detection section are greater than or equal to a second health coefficient threshold; If the instantaneous rate of change of kinetic energy in the parameter detection section is less than the second health coefficient threshold, the parameter detection section is healthy.

4. A pipeline health analysis system for high pour point oil transportation according to claim 1, characterized in that: Determine whether the pipeline is healthy based on the first health coefficient: compare the first health coefficient with the preset health coefficient. If the first health coefficient is greater than or equal to the preset health coefficient, the pipeline is abnormal. If the first health coefficient is less than the preset health coefficient, the pipeline is healthy.

Images