Gas turbine remote monitoring and diagnosis system based on operation big data

Abstract

The invention discloses a gas turbine remote monitoring and diagnosis system based on operation big data, and relates to the field of gas turbines, a data acquisition end is used for acquiring information data from a plurality of position nodes of a gas turbine, and the information data comprises vibration frequency data, internal temperature data and internal pressure data; the data processing end is used for calculating the normal operation interval of each position node, the normal operation interval comprises a vibration frequency interval, an internal temperature interval and an internal pressure interval, the information parameters of a plurality of node positions are monitored in real time, and the normal operation interval of each position node is obtained. Then comparison analysis is carried out according to the data monitored in real time and the corresponding information parameter intervals, the danger value of each position node in the monitoring process is analyzed, timely maintenance reminding is carried out according to the danger values analyzed in real time, faults of the gas turbine can be found in advance, the fault rate of the gas turbine is reduced, and the service life of the gas turbine is prolonged. And meanwhile, the maintenance frequency of the gas turbine is also reduced.

Description

Technical Field

[0001] The present invention belongs to the field of gas turbines, and in particular relates to a gas turbine remote monitoring and diagnosis system based on operation big data. Background Art

[0002] As a widely used energy conversion device, gas turbines offer rapid start-up and shutdown, flexible operation, and numerous advantages, including energy conservation and emission reduction, improved power supply security, peak-shaving and valley-shifting in electricity and gas supply, and the promotion of a circular economy. In the power generation sector, gas turbines are playing an increasingly important role, and their reliable, stable, and economical operation is crucial to both production and daily life.

[0003] In actual production, gas turbines operate under demanding conditions, and any failure can have serious consequences. Although gas turbine control systems feature fault alarms and a certain degree of fault-tolerant control, these alarms only confirm that current operating conditions have not exceeded operating limits and lack predictive or diagnostic capabilities. In conditions where the gas turbine control system does not issue an alarm, the gas turbine may already be operating in a dangerous zone. This operating state can at best result in performance degradation, impacting reliability and safety, or at worst, trigger a safety incident, causing significant losses to the power plant.

[0004] In the field of gas turbine operation and maintenance, a "planned maintenance" approach, implemented according to pre-specified cycles, is commonly employed. Although planned maintenance is a preventive maintenance method, it is difficult to prevent catastrophic failures of gas turbines and often results in insufficient and excessive maintenance. Therefore, for gas turbines, if the health status of the gas turbine system can be accurately predicted based on operational big data, the probability of system failure can be predicted based on its health status, and early predictions of the propagation and development of failures can be made. By gradually transitioning from "planned maintenance" to "condition-based maintenance," the losses caused by catastrophic failures can be prevented and significantly reduced, improving gas turbine operational safety and minimizing operation and maintenance costs. However, this approach cannot promptly identify the associated nodes affected by the failure point, resulting in some related nodes not receiving timely maintenance during the maintenance process. This can cause maintenance to be required shortly after the failure point, increasing maintenance costs.

[0005] In order to solve the above problems, the present invention proposes a solution. Summary of the Invention

[0006] The present invention aims to solve the problems raised in the above background technology; to this end, the present invention proposes a gas turbine remote monitoring and diagnosis system based on operation big data, comprising:

[0007] Data collection terminal: used to collect information data from several location nodes of the gas turbine, including vibration frequency data, internal temperature data and internal pressure data, and obtain information data of the normal operating range in historical data;

[0008] Data processing end: used to calculate the normal operating range of each location node, including the vibration frequency range, internal temperature range, and internal pressure range. After eliminating discrete data through standard deviation analysis, the minimum and maximum values are determined as the interval boundaries.

[0009] Data monitoring end: Based on the data acquisition end, the information data of the operation of each position node of the gas turbine is monitored in real time, and the monitored data is transmitted to the diagnosis and analysis end in real time. The diagnosis and analysis end combines the interval boundaries obtained by the data processing end to perform diagnostic analysis and processing on the real-time monitoring data.

[0010] Preferably, the data collection terminal collects the information data of the normal operation of the gas turbine in the following specific manner:

[0011] A plurality of position nodes are selected on the gas turbine, information data of the plurality of gas turbine nodes is determined based on historical data, and information data in the historical data of normal operation is obtained, wherein the information data includes vibration frequency data, internal temperature data and internal pressure data at the same time interval.

[0012] Preferably, the data processing end performs discrete degree analysis based on the acquired vibration frequency data, internal temperature data and internal pressure data, and obtains the corresponding minimum and maximum values of each vibration frequency data, internal temperature data and internal pressure data from the analyzed and processed data, and calibrates the range from the minimum value to the maximum value as the data interval for normal operation.

[0013] Preferably, the data monitoring terminal monitors the information data of each node position during the operation of the gas turbine in real time based on the data acquisition terminal, and transmits the monitored data to the diagnosis and analysis terminal in real time for diagnosis and processing.

[0014] Preferably, the diagnostic analysis end determines the fault point of the gas turbine based on the real-time data monitored by the data monitoring end and the normal operation data interval of each location node processed by the data processing end, specifically in the following manner:

[0015] The real-time information data monitored by each location node is compared with the interval corresponding to each information data. When any data in the information data exceeds the interval, the node location is marked as a fault point.

[0016] Preferably, it also includes a deep analysis end, which collects data for j consecutive monitoring cycles of information data of each position node selected in the gas turbine through the data monitoring end, j = 1, 2, ..., m, m represents the number of monitoring cycles, and analyzes and processes the information data collected from each node position in each cycle, specifically in the following way: establish an information data and time change curve for each monitoring cycle, use the middle value of the parameter interval as the standard value B, calculate the proportion Zj of the time when the data value is greater than B in the monitoring cycle, and when Marked as a period with high loss.

[0017] Preferably, according to the monitored change curve, the vertical coordinate in the change curve is obtained to take the jump point Yjsmax in the range greater than BQ and less than BM, s = 1, 2...b, b is the number of impact data obtained, BQ is a preset value, and BQ>B, BM is the maximum value of the information parameter interval, and the data difference CZ between the jump point and the previous time point Δt is calculated. When CZ>F, F is the preset value and is marked as the impact point. Then, the number of impact points L in the monitoring period is counted. When L>Q, the period is marked as the impact point period.

[0018] Preferably, the operating status indicator of each location node during j monitoring cycles is obtained:

[0019] Vibration frequency: loss cycle number A1 G1 and impact cycle number A1 G2;

[0020] Internal temperature: loss cycle number A2G1 and shock cycle number A2G2;

[0021] Internal pressure: loss cycle number A3G1 and impact cycle number A3G2;

[0022] Calculate the comprehensive risk value of each parameter as follows:

[0023] Vibration frequency danger value: W1=β1×A1 G1+β2×A1 G2;

[0024] Internal temperature danger value: W2 = β3 × A2G1 + β4 × A2G2;

[0025] Internal pressure danger value: W3 = β5 × A3G1 + β6 × A3G2;

[0026] β1, β2, β3, β4, β5 and β6 are weight coefficients. The danger standard values of the vibration frequency parameter, internal temperature parameter and internal pressure parameter are set as ɑ1, ɑ2 and ɑ3 respectively. ɑ1, ɑ2 and ɑ3 are preset values. When any danger value exceeds the corresponding preset standard value, an abnormal signal is generated.

[0027] Update the monitoring data using a sliding window mechanism: Delete the data of the earliest monitoring period and supplement new data, and calculate the latest hazard value in a loop.

[0028] Preferably, obtain the moment HT of the impact point in each monitoring period within j monitoring periods at the position of the node to be maintained and repaired, and then calculate the slope of the impact point: Subsequently, obtain the moment HT with a duration of θt before the moment HT

[0032] , of the parameter value, where θt is a preset value, and mark the node position corresponding to the moment HT θt as other node position QT. Subsequently, obtain the parameter value corresponding to the previous interval time Δt before the moment HT θt and then calculate the slope Kh of the other node position QT in the same way as the slope Kj above;

[0029] When Kh satisfies Kh > Kj or 0.7Kj < Kh < Kj, at this time, mark the monitoring point corresponding to the moment HT of the other node position QT θt as the associated impact point of the maintenance and repair node position, and count the number F of associated impact points within one monitoring period of the other node position QT, The value range is At this time, mark this monitoring period as an associated period of the maintenance and repair node position, and count the number Fg of associated periods within j monitoring periods 总 , when Fg 总 > C, where C is a preset value, at this time, mark the monitoring node position QT as the associated position of the maintenance and repair node position and display the associated position.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows: By dividing the gas turbine into several position nodes, obtaining the vibration frequency parameter range, internal temperature parameter range and internal pressure parameter range of each position node by calculating the historical data monitored during normal operation, and then comparing the real-time monitored data with the corresponding ranges according to the real-time monitoring of the data of several position nodes, and correcting the monitored data, the accurate judgment of the fault point position is realized, and the accuracy of diagnosing the fault point position is further improved.

[0031] By monitoring the information parameters of several node positions in real time, and then comparing and analyzing the real-time monitored data with the corresponding information parameter ranges, the hazard value of each position node during the monitoring process is analyzed. According to the real-time analyzed hazard value, timely maintenance reminders are given, which is convenient for early detection of gas turbine faults, reduces the failure rate of gas turbines, and also reduces the maintenance times of gas turbines.

[0032] The time of the impact point in each monitoring cycle of the node position requiring maintenance and overhaul is obtained, and then the parameters of several position nodes at the time node are obtained, and the slope of the point is calculated to determine whether the point is an associated point, and whether it is an associated cycle based on the number of associated points in the cycle, and then whether it is an associated position node of the maintenance node based on the number of associated cycles, so that the associated position nodes affected by the maintenance position node during operation are marked, so that maintenance personnel can find the corresponding associated position nodes in time during maintenance and maintain the associated position nodes, thereby realizing comprehensive maintenance and overhaul of the gas turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the principle framework of the present invention. DETAILED DESCRIPTION

[0034] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0035] Example 1

[0036] See also Figure 1 , this application provides a gas turbine remote monitoring and diagnosis system based on operation big data, including:

[0037] Data collection end: Select several location nodes on the gas turbine and determine information data of several nodes of the gas turbine based on historical data. The information data specifically includes vibration frequency data, internal temperature data, and internal pressure data of the gas turbine;

[0038] The historical data of normal operation is obtained by obtaining all information data of the gas turbine within 3 hours after starting stable operation and before shutting down. All information data include vibration frequency data, internal temperature data and internal pressure data at the same time interval.

[0039] Data processing end: Based on the acquired information data, the vibration frequency range, internal temperature range, and internal pressure range during the normal operation of the gas turbine are calculated. The specific method is as follows:

[0040] Analyze and process the obtained vibration frequency data, internal temperature data, and internal pressure data to determine the degree of dispersion, and from the analyzed data, find the minimum and maximum values corresponding to each vibration frequency data, internal temperature data, and internal pressure data, and determine the range from the minimum to the maximum value as the data interval for normal operation;

[0041] For example, take the internal temperature of a location node as an example. This location node is marked as D. Several temperature data Ti of location node D within 3 hours are obtained from historical data. i = 1, 2...n, where n represents the number of temperature data obtained within 3 hours. The average value Tp of the obtained temperature data values is calculated.

[0042] Then calculate the standard deviation based on the obtained temperature data:

[0043]

[0044] Compare the standard deviation σ with the preset value y1, which is set by the administrator. When σ < y1, the minimum and maximum values are selected from the temperature data and calibrated as the temperature range for normal operation of the location node D.

[0045] When σ>y1, it means that the discrete degree of this group of data is large. i =|T i -T p |Calculate the absolute value TC of the difference between each temperature data i ; and delete the TC with the largest corresponding value in order from large to small. i , then calculate the undeleted TC i The standard deviation of , until σ<y1,

[0046] Then the TC that has not been deleted is obtained i Corresponding T i And select the minimum and maximum values from the remaining temperature data and mark them as the temperature range when the location node D is operating normally;

[0047] Thus, the stable temperature range of the position node D during normal operation is obtained, and the same method as above is used to calculate the stable vibration frequency range and internal pressure range of the position node D during normal operation.

[0048] According to the above method, the temperature range, vibration frequency range and internal pressure range within each node position selected by the gas turbine are obtained.

[0049] Data monitoring terminal: monitors the operating information data of each node of the gas turbine in real time, and transmits the monitored data to the diagnosis and analysis terminal for diagnosis and processing;

[0050] Diagnostic analysis end: Based on the calibration of the vibration frequency range, internal temperature range, and internal pressure range of several position nodes during normal operation, combined with the real-time data monitored by the data monitoring end, the fault diagnosis of several position nodes of the gas turbine is carried out in the following ways:

[0051] The real-time information data monitored by each location node is compared with the corresponding interval of each information data. When any data in the information data exceeds the interval, the node position is marked as a fault point, so that the location of the fault point can be accurately determined, which facilitates maintenance personnel to carry out timely repairs.

[0052] Example 2

[0053] Compared with the first embodiment and the above embodiment, this embodiment mainly focuses on determining the maintenance time during the operation of the gas turbine, and its specific execution ends are the data processing end, the data monitoring end, and the deep analysis end;

[0054] The data monitoring terminal collects information data from each node selected in the gas turbine for j consecutive monitoring cycles, where j = 1, 2, ..., m, and m represents the number of monitoring cycles. The information data collected from each node position in each cycle is analyzed and processed in the following manner:

[0055] Based on the information data obtained from each monitoring cycle, a curve of the change of each information data value and time is established. The monitoring timeline is used as the horizontal axis, and the information data value corresponding to the monitoring time is used as the vertical axis. The information data values corresponding to each time point are connected to obtain a change curve, and the middle value of the corresponding information parameter interval is used as the standard value B, y in the monitoring process. b =B, generate standard line BL;

[0056] Then calculate the duration Xj1 of the point where the y value in the change curve is greater than B during the monitoring period, and then The proportion value Zj is calculated; X is the total duration of a monitoring cycle;

[0057] when When , it means that the information data of the location node during operation is in a relatively high operating data range for a long time within the normal range during the monitoring period. At this time, the monitoring period is marked as a period with large loss.

[0058] Obtain coordinate points in the change curve whose ordinate values are greater than BQ and less than BM, mark these coordinate points as jump points, and mark the ordinate of the jump point as Yjsmax, s = 1, 2...b, b is the number of impact data obtained, BQ is a preset value, and BQ>B, BM is the maximum value of the information parameter interval, then obtain the ordinate Yt of the coordinate point on the change curve that is at an interval Δt before the corresponding moment of the jump point, Δt is a preset value set by the administrator, and calculate the difference CZ between Yt and Yjsmax = |Yt-Yjsmax|. When CZ>F, F is a preset value set by the administrator, which means that the information data Yjsmax jumps rapidly within the Δt time, indicating that the information data Yjsmax fluctuates greatly and has a greater impact on the equipment. The maximum value of this point is marked as the impact point, and then the number of impact points L in this period is counted. When L>Q, the period is marked as the impact point period;

[0059] According to the above method, after each location node performs j monitoring cycles, the number of cycles in which the vibration frequency data, internal temperature data, and internal pressure data of each location node have large loss and the number of impact point cycles in the entire j monitoring cycles are obtained;

[0060] The vibration frequency parameter is marked as A within the jth monitoring cycle, and the number of cycles with large loss and impact point cycles monitored in real time 1G1 and A 1G2 ;

[0061] The number of cycles with large loss and impact point detected in real time during the jth monitoring cycle of the internal temperature frequency parameter is marked as A. 2G1 and A 2G2 ;

[0062] The vibration frequency parameter is marked as A within the jth monitoring cycle, and the number of cycles with large loss and impact point cycles monitored in real time 3G1 and A 3G2 ;

[0063] Based on the data obtained above, the dangerous values of vibration frequency parameters, internal temperature parameters and internal pressure parameters are calculated:

[0064] Danger value of vibration frequency parameter: W1=β1xA 1G1 +β1xA 1G2 ,β1 and β2 are weight coefficients;

[0065] Danger value of internal temperature parameter: W2=β3xA 2G1 +β4xA 2G2 ,β1 and β2 are weight coefficients;

[0066] Dangerous value of internal pressure parameter: W3=β5xA3G1 +β6xA 3G2 , where β1 and β2 are weighting coefficients;

[0067] Set the respective dangerous standard values of the vibration frequency parameter, internal temperature parameter, and internal pressure parameter as ɑ1, ɑ2, and ɑ3. ɑ1, ɑ2, and ɑ3 are preset values set by the administrator;

[0068] After running in the jth cycle, calculate each dangerous value. When each dangerous value exceeds the corresponding dangerous standard value, an abnormal signal is generated at this time; otherwise, no processing is performed;

[0069] According to the real-time monitoring of the information parameters of each position node, when each dangerous value exceeds the corresponding dangerous standard value within the jth monitoring cycle, an abnormal signal is generated at this time, realizing the real-time monitoring of the gas turbine;

[0070] During the monitoring process, if the danger of any monitored parameter at each position node is greater than the corresponding dangerous standard value, a pre-detection signal is generated at this time to remind the staff to perform timely maintenance and repair, realizing the reminder of timely maintenance according to the real-time monitoring data, facilitating the early discovery of faults in the gas turbine and reducing the failure rate of the gas turbine.

[0071] After the jth monitoring cycle, when no dangerous value is greater than the standard value, the data of the first monitoring within the jth monitoring cycle is deleted at this time, and continuous monitoring is carried out to supplement the data of the (j + 1)th time. Subsequently, the dangerous value is calculated, and so on, continuously updating the monitored data, so as to accurately judge the maintenance time of the gas turbine at a specific moment.

[0072] Embodiment III

[0073] Please refer to Figure 1 As shown, based on Embodiment II, this embodiment is obtained. Obtain the moment HT of the impact point within each monitoring cycle of the j monitoring cycles of the node positions that need maintenance and repair. At the same time, according to the obtained Yjsmax and Yt, then calculate the slope of the impact point: Subsequently, obtain the moment HT at an interval of θt from the moment HT θt of the parameter value. θt is set according to the distance between the maintenance and repair node and other position nodes, and is set by the administrator. Mark the node position corresponding to the moment HT θt as the other node position QT. Subsequently, obtain the parameter value corresponding to the previous interval Δt of the moment HT θt . Then, calculate the slope Kh of the other position node QT in the same way as the slope Kj above;

[0074] If Kh > Kj or 0.7Kj < Kh < Kj, then at the moment HT corresponding to the other node position QTθt The monitoring points are marked as the associated impact points of the maintenance and inspection node locations;

[0075] When the number of associated impact points F in one monitoring cycle of other node positions QT, The value range is At this time, the monitoring period is marked as an associated period of the maintenance node position, and the number of associated periods in j monitoring periods is counted. 总 , when Fg 总 >C, (C is the number of times, which is a preset value), at this time, other node positions QT are marked as associated positions of the maintenance and overhaul node positions, and the associated positions are displayed, so that maintenance personnel can find the corresponding associated position nodes in time when maintaining the maintenance and overhaul nodes, and maintain the associated position nodes, thereby realizing comprehensive maintenance and overhaul of the gas turbine.

[0076] Some of the data in the above formulas are dimensionless for numerical calculations, and any content not described in detail in this specification belongs to the prior art known to those skilled in the art. The above embodiments are intended only to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A gas turbine remote monitoring and diagnosis system based on operational big data, characterized in that: include: Data collection terminal: used to collect information data from several location nodes of the gas turbine, including vibration frequency data, internal temperature data and internal pressure data, and obtain information data of the normal operating range in historical data; Data processing end: used to calculate the normal operating range of each location node, including the vibration frequency range, internal temperature range, and internal pressure range. After eliminating discrete data through standard deviation analysis, the minimum and maximum values are determined as the interval boundaries. Data monitoring end: Based on the data acquisition end, the information data of the operation of each position node of the gas turbine is monitored in real time, and the monitored data is transmitted to the diagnosis and analysis end in real time. The diagnosis and analysis end combines the interval boundaries obtained by the data processing end to perform diagnostic analysis and processing on the real-time monitoring data.

2. The gas turbine remote monitoring and diagnosis system based on operation big data according to claim 1 is characterized in that: The data collection end collects information data on the normal operation of the gas turbine in the following specific ways: A plurality of position nodes are selected on the gas turbine, information data of the plurality of gas turbine nodes is determined based on historical data, and information data in the historical data of normal operation is obtained, wherein the information data includes vibration frequency data, internal temperature data and internal pressure data at the same time interval.

3. The gas turbine remote monitoring and diagnosis system based on operation big data according to claim 2 is characterized in that: The data processing end performs discrete degree analysis based on the acquired vibration frequency data, internal temperature data and internal pressure data, and obtains the corresponding minimum and maximum values of each vibration frequency data, internal temperature data and internal pressure data from the analyzed and processed data, and calibrates the range from the minimum value to the maximum value as the data interval for normal operation.

4. The gas turbine remote monitoring and diagnosis system based on operation big data according to claim 1, characterized in that: The data monitoring end monitors the information data of each node position during the operation of the gas turbine in real time based on the data acquisition end, and transmits the monitored data to the diagnosis and analysis end in real time for diagnosis and processing.

5. The gas turbine remote monitoring and diagnosis system based on operation big data according to claim 4 is characterized in that: The diagnostic analysis end determines the fault point of the gas turbine based on the real-time data monitored by the data monitoring end and the normal operation data interval of each location node processed by the data processing end. The specific method is as follows: The real-time information data monitored by each location node is compared with the interval corresponding to each information data. When any data in the information data exceeds the interval, the node location is marked as a fault point.

6. The gas turbine remote monitoring and diagnosis system based on operation big data according to claim 1, characterized in that: The system also includes a deep analysis terminal, which collects information data of each position node selected in the gas turbine for j consecutive monitoring cycles through the data monitoring terminal, where j = 1, 2, ..., m, and m represents the number of monitoring cycles. The information data collected from each node position in each cycle is analyzed and processed in the following manner: a curve of information data and time variation of each monitoring cycle is established, the middle value of the parameter interval is used as the standard value B, and the proportion Zj of the time period in which the data value is greater than B in the monitoring cycle is calculated. When Marked as a period with high loss.

7. The gas turbine remote monitoring and diagnosis system based on operation big data according to claim 6 is characterized in that: According to the monitored change curve, obtain the jump point Yjsmax in the change curve with the vertical coordinate in the range greater than BQ and less than BM, s = 1, 2...b, b is the number of impact data obtained, BQ is the preset value, and BQ>B, BM is the maximum value of the information parameter interval, calculate the data difference CZ between the jump point and the previous time point Δt, when CZ>F, F is the preset value, marked as the impact point, and then count the number of impact points L in the monitoring period. When L>Q, the period is marked as the impact point period.

8. The gas turbine remote monitoring and diagnosis system based on operation big data according to claim 7 is characterized in that: Get the operating status indicators of each location node during j monitoring cycles: Vibration frequency: loss cycle number A1 G1 and impact cycle number A1 G2; Internal temperature: loss cycle number A2G1 and shock cycle number A2G2; Internal pressure: loss cycle number A3G1 and impact cycle number A3G2; Calculate the comprehensive risk value of each parameter as follows: Vibration frequency danger value: W1=β1×A1 G1+β2×A1 G2; Internal temperature danger value: W2 = β3 × A2G1 + β4 × A2G2; Internal pressure danger value: W3 = β5 × A3G1 + β6 × A3G2; β1, β2, β3, β4, β5 and β6 are weight coefficients. The danger standard values of the vibration frequency parameter, internal temperature parameter and internal pressure parameter are set as ɑ1, ɑ2 and ɑ3 respectively. ɑ1, ɑ2 and ɑ3 are preset values. When any danger value exceeds the corresponding preset standard value, an abnormal signal is generated. A sliding window mechanism is used to update monitoring data: the earliest monitoring cycle data is deleted and new data is added, and the latest hazard value is calculated cyclically.

9. The gas turbine remote monitoring and diagnosis system based on operation big data according to claim 7, characterized in that: Obtain the time HT of the impact point in each monitoring cycle within j monitoring cycles of the node location requiring maintenance and inspection, and then calculate the slope of the impact point: Then obtain the time θt before the time HT The parameter value of θt is the preset value, and the moment The corresponding node position is marked as other node position QT, and then the time is obtained The parameter value corresponding to the previous interval time Δt is then used to calculate the slope Kh of other node positions QT in the same way as the above slope Kj; When Kh satisfies Kh > Kj or 0.7Kj < Kh < Kj, at this time, the monitoring points corresponding to other node positions QT at the corresponding moment are marked as the associated impact points of the maintenance and repair node positions, and the number F of associated impact points within one monitoring period of other node positions QT is counted. The value range is At this time, this monitoring period is marked as an associated period of the maintenance and repair node position, and the number Fg of associated periods within j monitoring periods is counted. 总 , when Fg 总 > C, where C is a preset value, at this time, the monitoring node position QT is marked as the associated position of the maintenance and repair node position, and the associated position is displayed.

Images