Condenser leakage real-time grading diagnosis method and device

Abstract

The invention provides a condenser leakage real-time grading diagnosis method and device, and the method comprises the steps: building a unit load-based conductivity reference value dynamic model, and generating an expected value range of the positive conductivity of a condensate pump outlet under different load intervals; collecting and processing positive conductivity data of a condensate pump outlet, an economizer inlet and main steam in real time, and respectively calculating average values of a sliding window in 5 minutes and 1 minute; according to the conductivity reference value dynamic model and the processed conductivity average value, multi-condition logic combination judgment is carried out in combination with alarm duration and vibration parameters, and the leakage level is determined; and outputting low-pressure cylinder blade breakage risk early warning according to the triggered corresponding leakage level alarm signal. According to the method, real-time grading diagnosis of condenser leakage can be realized, the diagnosis accuracy is improved, the response time is shortened, accident expansion is effectively prevented, and the unit operation risk and economic loss are reduced.

Description

Technical Field

[0001] This invention belongs to the field of condenser leakage detection and classification diagnosis technology, specifically relating to a real-time classification diagnosis method for condenser leakage. Background Technology

[0002] As a critical piece of equipment in thermal power plants, the condenser's titanium tube leakage detection technology is a core element in ensuring the safe operation of the unit. With the increasing demand for intelligent upgrades of thermal power equipment, the existing technology system mainly relies on manual monitoring of single parameters such as condensate hydrogen conductivity and main reheat steam hydrogen conductivity for leakage judgment. Specifically, this technology covers the entire process from data acquisition to decision control, including key aspects such as conductivity monitoring, load parameter correlation, and alarm threshold setting. Supporting technologies such as hydrogen exchange column status monitoring (resin color depth ≥50mm) and fine treatment system indicators (Na<5μg / L, SiO2<15μg / L) jointly construct the basic detection framework, but overall it still remains at the level of manual experience-based judgment. However, existing technical methods directly use static thresholds for parameter comparison without establishing a load-related dynamic benchmark model, which may lead to a misjudgment rate of over 30% (refer to the "2023 Reliability Report of Thermal Power Equipment from China Electric Power Research Institute"). Summary of the Invention

[0003] The present invention aims to at least partially solve one of the technical problems in the related art.

[0004] Therefore, the first objective of this invention is to propose a real-time graded diagnosis method for condenser leakage.

[0005] The second objective of this invention is to provide a real-time graded diagnostic device for condenser leaks.

[0006] The third objective of this invention is to provide a computer device.

[0007] A fourth objective of this invention is to provide a non-transitory computer-readable storage medium.

[0008] To achieve the above objectives, a first aspect of the present invention provides a real-time graded diagnosis method for condenser leakage, comprising: S1. Establish a dynamic model of conductivity benchmark value based on unit load to generate the expected range of positive conductivity at condensate pump outlet under different load ranges. S2 collects and processes the positive conductivity data of the condensate pump outlet, economizer inlet and main steam in real time, and calculates the average value of each data point within a 5-minute or 1-minute sliding window. S3, based on the dynamic model and the average conductivity after processing, combined with the alarm duration and vibration parameters, a multi-condition logical combination judgment is made to determine the leakage level; S4 triggers the corresponding leakage level alarm signal and outputs a low-pressure cylinder blade breakage risk warning.

[0009] In one embodiment of the present invention, S1 includes: S11, when the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: ; S12, when the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: .

[0010] In one embodiment of the present invention, S2 includes: S21, the average value of the positive conductivity data at the condensate pump outlet is calculated using a 5-minute sliding window; S22, the average value of the economizer inlet and main steam conductivity data is calculated using a 1-minute sliding window.

[0011] In one embodiment of the present invention, S3 further includes: S31, when a minor leak alarm persists for 72 hours without disappearing, a significant leak determination is triggered; S32, when the obvious leakage alarm persists for 24 hours without disappearing and any measuring point of the turbine's #3, #4, or #5 watts vibrates. Expected value of corresponding load vibration At that time, a low-pressure cylinder blade breakage risk warning was triggered.

[0012] In one embodiment of the present invention, it further includes: S5, monitors the state parameters of the hydrogen exchange column, including resin color depth. High-speed mixed bed effluent indicators , Differential pressure of resin trap Cyclic water production 10,000 tons, and the hydrogen conductivity of the condensate replenishment tank .

[0013] To achieve the above objectives, a second aspect of the present invention provides a real-time graded diagnostic device for condenser leakage, comprising: The dynamic model building module is used to build a dynamic model of conductivity benchmark value based on unit load, and generate the expected value range of positive conductivity of condensate pump outlet under different load ranges; The data acquisition and processing module is used to collect and process the positive conductivity data of the condensate pump outlet, economizer inlet and main steam in real time, and calculate the average value of each data point within a 5-minute or 1-minute sliding window. The multi-condition logic judgment module is used to determine the leakage level by combining the dynamic model and the processed average conductivity, along with the alarm duration and vibration parameters, to make a multi-condition logic combination judgment. The alarm signal triggering module is used to trigger the corresponding leakage level alarm signal and output a low-pressure cylinder blade breakage risk warning.

[0014] The present invention discloses a real-time graded diagnosis method and apparatus for condenser leakage, which can realize real-time graded diagnosis of condenser leakage, improve the accuracy of diagnosis and shorten the response time, effectively prevent the expansion of accidents, and reduce the risk of unit operation and economic losses.

[0015] To achieve the above objectives, a third aspect of this application provides a computer device, including a processor and a memory; wherein the processor reads executable program code stored in the memory to run a program corresponding to the executable program code, for implementing a real-time graded diagnosis method for condenser leakage as described in the first aspect embodiment.

[0016] To achieve the above objectives, a fourth aspect of this application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a real-time graded diagnosis method for condenser leakage as described in the first aspect embodiment.

[0017] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0018] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a real-time graded diagnosis method for condenser leakage according to an embodiment of the present invention; Figure 2 This is a structural diagram of a real-time graded diagnostic device for condenser leakage according to an embodiment of the present invention; Figure 3 It is a computer device according to an embodiment of the present invention. Detailed Implementation

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] The following describes a real-time graded diagnosis method and apparatus for condenser leakage according to an embodiment of the present invention, with reference to the accompanying drawings.

[0022] Example 1 Figure 1 This is a flowchart of a real-time graded diagnosis method for condenser leakage according to an embodiment of the present invention, such as... Figure 1 As shown, it includes: S1. Establish a dynamic model of conductivity benchmark value based on unit load to generate the expected range of positive conductivity at the condensate pump outlet under different load ranges.

[0023] In some implementations, this step first involves collecting real-time measurements of unit load data and condensate pump outlet anode conductivity. Statistical analysis of historical operating data is then performed to extract typical variation patterns of anode conductivity across different load ranges (e.g., 280MW to 750MW, and above 750MW). Based on this, a mathematical model of the relationship between conductivity and load is established using piecewise linear regression or nonlinear fitting methods. The model output is the expected range of condensate pump outlet anode conductivity within a specific load range; for example, within the 280MW to 750MW range, the expected range is... When the load is greater than 750MW, the expected value range is: .in, This represents the 5-minute average of the positive conductivity at the condensate pump outlet.

[0024] Specifically, the model's inputs include unit load. (Unit: MW) and condensate pump outlet positive conductivity (unit: The output is the expected conductivity range for that load interval. During model construction, it is necessary to ensure a data sampling frequency of no less than 1 minute per sampling to meet real-time monitoring requirements. Simultaneously, the model must consider system operational stability and set reasonable error tolerances, for example... This is to avoid misjudgment due to instantaneous fluctuations.

[0025] Furthermore, S1 includes: S11, when the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: .

[0026] In some implementations, when the unit load is at When operating within the specified range, this invention sets the desired range for the positive conductivity of the condensate pump outlet as follows: This step is based on the impact of condenser titanium tube leakage on water quality parameters. Combined with the unit's operating conditions, it achieves preliminary identification of condenser leakage status by setting a reasonable conductivity threshold range.

[0027] This step involves real-time acquisition of the positive conductivity signal at the condensate pump outlet and performing a 5-minute moving average to eliminate the interference of instantaneous fluctuations on the judgment result. This signal is typically acquired by an online conductivity meter, with a sampling frequency of generally 1 time / second. The data is transmitted to the monitoring platform via a DCS system or PLC acquisition module. In the software modeling, this parameter is compared with a preset expected value range. If the actual value falls within... If the leak occurs within the specified range, it is determined that there is a slight leak in the condenser titanium tube, and the system will trigger the corresponding alarm logic.

[0028] Specifically, the set range of the positive conductivity at the condensate pump outlet is based on long-term operational data statistics and analysis of typical leakage characteristics. Among these, This is the lower limit threshold for minor leakage, while This is the upper limit threshold; exceeding this range may indicate an increased degree of leakage. The setting of this parameter needs to consider factors such as the condenser titanium tube material, cooling water quality, and the operating status of the hydrogen exchange column to ensure good adaptability and sensitivity under different load conditions.

[0029] S12, when the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: .

[0030] In some implementations, this step involves collecting the 5-minute moving average of the condensate pump outlet conductivity in real time and making conditional judgments based on the unit's current operating load. Specifically, when the unit load exceeds 750MW, the system automatically switches to the high-load condition condensate conductivity threshold judgment logic to accommodate potential leakage characteristics of the condenser titanium tubes under different operating conditions. This logic is implemented through conditional statements in the PLC or DCS system, such as using an "IF-THEN" structure or a state machine model, to evaluate the collected conductivity data in real time.

[0031] Specifically, the expected range of anode conductivity set in this step is: The value is determined based on the typical water quality change trend of the condenser under high load operation. This range reflects the reasonable fluctuation range of the positive conductivity in the condensate system when the unit is operating at full load. If it exceeds this range, it may indicate a slight leak in the condenser titanium tubes. In addition, this step also requires ensuring that the pretreatment equipment such as the hydrogen exchange column, the fine treatment system, and the condensate makeup water tank are in normal operating condition to eliminate the influence of non-leakage factors on the conductivity.

[0032] S2 collects and processes the positive conductivity data of the condensate pump outlet, economizer inlet, and main steam in real time, and calculates the average value of each data point within a 5-minute or 1-minute sliding window.

[0033] Specifically, this step involves real-time acquisition of anode conductivity sensor output signals from the condensate pump outlet, economizer inlet, and main steam pipeline via a distributed control system (DCS) or independent monitoring software platform. The acquisition frequency is typically once per second or higher to ensure real-time data accuracy. The acquired raw data is then input to a data processing module, which uses a sliding window algorithm to smooth the data. Specifically, a 5-minute sliding window is used for the condensate pump outlet anode conductivity, while a 1-minute sliding window is used for the main steam and economizer inlet anode conductivity.

[0034] Furthermore, the 5-minute moving average of the condensate pump outlet conductivity needs to meet threshold conditions within different load ranges. For example, within the load range of 280MW to 750MW, if the average value... If the leakage is not significant, it is considered a minor leak. For the main steam and economizer inlet anode conductivity, a 1-minute sliding window is used, with a threshold value of [value missing]. It is used to identify obvious leaks.

[0035] Furthermore, S2 includes: S21, the average value of the positive conductivity data at the condensate pump outlet is calculated using a 5-minute sliding window.

[0036] In some implementations, this step uses a sliding window algorithm to process the real-time acquired cation conductivity signal at the condensate pump outlet. Specifically, the system acquires cation conductivity data at fixed time intervals (e.g., 1 minute), then slides the window across the time axis with a window length of 5 minutes, calculating the arithmetic mean of all data points within the window. For example, if the current time is... The sliding window covers a time interval of [t - 4, t], with a total of 5 data points. This algorithm can be implemented in a PLC or DCS system through programming, or it can be processed offline or online using tools such as Python and MATLAB in a host computer monitoring system.

[0037] Specifically, the sliding window length is set to 5 minutes, based on a comprehensive consideration of the condenser system's operating characteristics and the response time to changes in anode conductivity. The 5-minute time window effectively filters out abnormal fluctuations caused by instantaneous water quality disturbances or sensor noise, while retaining characteristic trends reflecting changes in system status. This average value will serve as an important input parameter for subsequent leak level determination (minor, significant, severe), and its value range is closely related to the unit load. For example, within the 280MW to 750MW load range, if... and If this occurs, an "obvious leak" alarm will be triggered.

[0038] S22, the average value of the economizer inlet and main steam conductivity data is calculated using a 1-minute sliding window.

[0039] In some implementations, this step involves collecting real-time anode conductivity data from the unit's PLC system and dynamically averaging the anode conductivity of the economizer inlet and main steam (left and right sides) at minute intervals using a sliding window mechanism. Specifically, the sliding window length is 60 seconds, and the window step size is 1 second, meaning the dataset within the window is updated every second, and the arithmetic mean of all data points within the current window is calculated. This average value is used in subsequent leakage level judgment logic; for example, in determining obvious and severe leaks in the condenser titanium tubes, the 1-minute average value is used as the key threshold.

[0040] Specifically, the unit of positive conductivity is... Its numerical range has clearly defined thresholds for different leakage levels. For example, when the 1-minute average of the economizer inlet anode conductivity is greater than... and less than or equal to When the value exceeds a certain threshold, the system determines it as a significant leak; if the value exceeds a certain threshold... If this occurs, a serious leak alarm will be triggered. This parameter setting complies with industry standards for water quality monitoring in power systems and can effectively reflect abnormal water quality changes caused by leaks in the condenser titanium tubes.

[0041] S3 determines the leakage level by combining multiple conditions and logic based on the dynamic model and the average conductivity after processing, along with the alarm duration and vibration parameters.

[0042] In some implementations, this step first establishes a dynamic expectation model of condenser vibration parameters based on the unit load, specifically including the expected values ​​of vibration for condensers #3, #4, and #5. Through historical data training or empirical modeling, the system can set corresponding vibration expectation values ​​for different load ranges (e.g., 280MW to 750MW, or greater than 750MW). Subsequently, the system collects key parameters such as the 5-minute average of the condensate pump outlet conductivity, the 1-minute average of the economizer inlet conductivity, and the 1-minute average of the main steam (left and right sides) conductivity, and standardizes these parameters to ensure that their units are consistent. This facilitates subsequent logical judgments.

[0043] Specifically, the system sets multiple threshold ranges to determine the leakage level. For example, when the unit load is between 280MW and 750MW, if the 5-minute average value of the condensate pump outlet conductivity meets the following criteria... If so, a "minor leak" alarm will be triggered; if If the alarm duration is not cleared within 72 hours, it will be classified as a "serious leak". In addition, the system also introduces the alarm duration as a criterion. If the "minor leak" alarm is not cleared within 72 hours, it will be upgraded to "significant leak"; if the "significant leak" alarm is not cleared within 24 hours, it will be further classified as a "serious leak".

[0044] Furthermore, S3 includes: S31, when a minor leak alarm persists for 72 hours without disappearing, a significant leak determination is triggered.

[0045] In some implementations, this step relies on continuous monitoring of the minor leak alarm status of the condenser titanium tubes. Specifically, the system collects the 5-minute average of the condensate pump outlet conductivity in real time and combines it with the current unit load range (280MW≤load≤750MW or load>750MW) to determine whether the triggering conditions for a minor leak are met. Once a minor leak alarm is triggered, the system starts a 72-hour timer to continuously monitor whether the alarm status is cleared. If the alarm is not reset or returns to normal within 72 hours, the system will automatically enter the significant leak determination process. This process further combines the 1-minute average of the economizer inlet conductivity of Unit #2 (… ) and the average 1-minute conductivity of the main steam (left and right sides) A comprehensive assessment will be conducted to determine whether the leak has escalated to a significant level.

[0046] Specifically, the key thresholds for this step include the 72-hour alarm duration window, the 5-minute average of the positive conductivity at the condensate pump outlet, and the 1-minute average of the positive conductivity at the economizer inlet and main steam. These parameters are all set based on actual operating data and historical experience, and have clear physical meaning and engineering basis, ensuring the accuracy and reliability of the judgment.

[0047] S32, when the obvious leakage alarm persists for 24 hours without disappearing and any measuring point of the turbine's #3, #4, or #5 watts vibrates. Expected value of corresponding load vibration At that time, a low-pressure cylinder blade breakage risk warning was triggered.

[0048] In some implementations, this step is based on time-series analysis and logical judgment of multi-source parameters. First, the system continuously collects the 5-minute average of the positive conductivity at the condensate pump outlet and performs dynamic threshold comparison in conjunction with the current unit load status. Second, the system monitors the 1-minute average of the positive conductivity at the economizer inlet and the positive conductivity of the main steam (left and right sides) of Unit #2 to detect rapid water quality deterioration caused by condenser leakage. Simultaneously, the system acquires real-time vibration data of turbine #3, #4, and #5 watts through a vibration monitoring module and compares it with the expected vibration values ​​obtained based on load modeling. If the vibration value at any measuring point meets the requirements... The condition indicates that the turbine may have been subjected to mechanical disturbance caused by a condenser leak.

[0049] Specifically, the key parameters involved in this step include: condensate pump outlet anolyte conductivity (unit: ...). Economizer inlet anode conductivity, main steam anode conductivity (both averaged over 1 minute), and turbine bearing vibration value (unit: ...). The vibration threshold is set to the desired value. This value is derived from historical operational data modeling and has high engineering applicability.

[0050] S4 triggers the corresponding leakage level alarm signal and outputs a low-pressure cylinder blade breakage risk warning.

[0051] In some implementations, the system first collects the 5-minute average of the positive conductivity at the condensate pump outlet and the 1-minute average of the positive conductivity at the economizer inlet and main steam (left and right sides) via a PLC or DCS system. These parameters reflect whether and to what extent leakage has occurred in the condenser titanium tubes. When the 5-minute average of the positive conductivity at the condensate pump outlet exceeds a set threshold and matches the current unit load range, the system will trigger a leakage alarm of the corresponding level. For example, if the value is greater than 0.4 μs / cm when the unit load is greater than 750MW, it is considered a serious leak. Simultaneously, the system also needs to monitor the real-time vibration values ​​of the #3, #4, and #5 turbines of the main unit and compare them with the expected vibration values ​​under the corresponding load. If the vibration value at any measuring point is greater than the expected value plus 2 mm / s, a low-pressure cylinder blade breakage risk warning is triggered.

[0052] Specifically, the criteria for determining the positive conductivity at the condensate pump outlet are as follows: In the load range of 280MW to 750MW, its 5-minute average value should be less than or equal to 0.3μs / cm; if it is greater than 0.3μs / cm but less than or equal to 0.5μs / cm, it is considered a significant leak; if it is greater than or equal to 0.5μs / cm, it is considered a serious leak. When the load is greater than 750MW, the thresholds are adjusted accordingly to 0.2μs / cm, 0.4μs / cm, and 0.4μs / cm. Furthermore, the 1-minute average value of the positive conductivity at the economizer inlet and main steam must both be greater than 0.15μs / cm to trigger a serious leak alarm.

[0053] S5, monitors the state parameters of the hydrogen exchange column, including resin color depth. High-speed mixed bed effluent indicators , Differential pressure of resin trap Cyclic water production 10,000 tons, and the hydrogen conductivity of the condensate replenishment tank .

[0054] In some implementations, this step involves real-time data acquisition and logical judgment of the hydrogen exchange column's operating status through a distributed control system (DCS) or a separate monitoring module. Specific monitoring parameters include: resin color depth. Used to determine whether the resin's color has changed due to contamination or failure; sodium ion concentration in the effluent of high-speed mixed bed. and silica concentration These two indicators reflect the purity of the mixed bed effluent; exceeding the standard may affect the accuracy of subsequent conductivity measurements. (The text also mentions the resin trap differential pressure.) Used to determine if resin blockage is causing abnormal pressure differences; cycle water production. 10,000 tons, used to assess whether the resin regeneration cycle is normal; hydrogen conductivity of the condensate tank. This serves as the final verification indicator for water quality compliance.

[0055] Specifically, all the above parameters are set according to the power industry standard "Water and Steam Quality Standard for Thermal Power Plants" (GB / T12145-2017) to ensure that the water quality and equipment operating conditions meet the requirements for safe operation of the unit. For example, the threshold for hydrogen conductivity is set as follows: It is a statistical analysis result based on the water quality test data of the condensate replenishment tank, which can effectively reflect the overall performance of the water treatment system.

[0056] The present invention provides a real-time graded diagnosis method for condenser leakage, which can realize real-time graded diagnosis of condenser leakage, improve the accuracy of diagnosis and shorten the response time, effectively prevent the expansion of accidents, and reduce the risk of unit operation and economic losses.

[0057] Example 2 The following describes in detail, with reference to the accompanying drawings, a real-time graded diagnosis method for condenser leakage according to an embodiment of the present invention.

[0058] Software modeling was used to realize the expected vibration values ​​of #3, #4, and #5 watts under different loads. The following functions were implemented using code: 5-minute average positive conductivity of condensate pump outlet, 1-minute average positive conductivity of economizer inlet, 1-minute average positive conductivity of main steam (left and right sides), and conditional logic judgment, thereby realizing condenser leakage analysis and judgment. As shown in Table 1.

[0059] Table 1

[0060] Prerequisites: No failure of hydrogen exchange column, no failure of fine treatment, and qualified water quality test results in condensate / makeup tank (since the above parameters cannot be obtained from the PLC, the following text descriptions are provided on the alarm screen: 1. Dark-colored resin in hydrogen exchange column is not less than 50mm; 2. High-speed mixed bed effluent indicators: Na < 5μg / L, SiO2 < 15μg / L, resin trap differential pressure < 0.1MPa, cycle water production < 300,000 tons; 3. Hydrogen conductivity in condensate / makeup tank < 0.4μs / cm).

[0061] 1. Minor leakage in condenser titanium tubes (criteria for judgment, or): For units with a load between 280MW and 750MW, the average 5-minute anodic conductivity at the condensate pump outlet should be ≤0.3μs / cm (0.2μs / cm < 0.3μs / cm); for units with a load >750MW, the average 5-minute anodic conductivity at the condensate pump outlet should be ≤0.2μs / cm (0.15μs / cm < 0.2μs / cm).

[0062] The above conditions are met to trigger an alarm: minor leak in the condenser titanium tube.

[0063] 2. Obvious leakage in condenser titanium tubes (criteria for judgment, or): ① Condensate pump outlet positive conductivity (or): 280MW≤unit load≤750MW, 0.3μs / cm<condensate pump outlet positive conductivity 5-minute average ≤0.5μs / cm; unit load>750MW, 0.2μs / cm<condensate pump outlet positive conductivity 5-minute average ≤0.4μs / cm.

[0064] ② 0.1μs / cm < Average value of the anode conductivity at the economizer inlet of Unit #2 over 1 minute ≤ 0.15μs / cm.

[0065] ③ The average conductivity of the main steam (left and right sides) of Unit #2 for 1 minute is ≤0.15μs / cm.

[0066] The alarm for a minor leak in the condenser titanium tubes has not disappeared after 72 hours.

[0067] The above conditions are met to trigger an alarm: There is a significant leak in the titanium tubes of the condenser.

[0068] 3. Severe leakage in condenser titanium tubes (criteria for judgment, or): ① Condensate pump outlet positive conductivity (or): For units with a load of 280MW ≤ 750MW, the average positive conductivity of the condensate pump outlet over 5 minutes is ≥ 0.5μs / cm; For units with a load > 750MW, the average positive conductivity of the condensate pump outlet over 5 minutes is ≥ 0.4μs / cm.

[0069] ② The average conductivity of the economizer inlet of Unit #2 over 1 minute is >0.15μs / cm.

[0070] ③ The average conductivity of the main steam (left and right sides) of Unit #2 over 1 minute is >0.15μs / cm.

[0071] The alarm for obvious leakage in the titanium tubes of the condenser has not disappeared after 24 hours.

[0072] The above conditions are met to trigger an alarm: serious leakage in the condenser titanium tube.

[0073] 4. Broken blades in the low-pressure cylinder (judgment criteria, and): Condensate pump outlet positive conductivity (or): 280MW≤unit load≤750MW, 5-minute average condensate pump outlet positive conductivity ≥0.5μs / cm; unit load>750MW, 5-minute average condensate pump outlet positive conductivity ≥0.4μs / cm.

[0074] The average conductivity of the economizer inlet of Unit #2 is >0.15 μs / cm over 1 minute.

[0075] The average conductivity of the main steam (left and right sides) of Unit #2 over 1 minute is >0.15 μs / cm.

[0076] The vibration at any measuring point of the #2 unit's main unit #3, 4, and 5 watts is greater than or equal to the expected value of the corresponding load vibration plus 2 mm / s.

[0077] The above conditions are met to trigger an alarm: Low-pressure cylinder blade breakage.

[0078] Example 3 To achieve the above embodiments, such as Figure 2 As shown, this embodiment also provides a real-time graded diagnostic device 10 for condenser leakage. The device 10 includes a dynamic model establishment module 100, a data acquisition and processing module 200, a multi-condition logic judgment module 300, and an alarm signal triggering module 400.

[0079] The dynamic model building module 100 is used to build a dynamic model of conductivity benchmark value based on unit load and generate the expected value range of positive conductivity of condensate pump outlet under different load ranges. The data acquisition and processing module 200 is used to collect and process the positive conductivity data of the condensate pump outlet, economizer inlet and main steam in real time, and calculate the average value of each data point within a 5-minute or 1-minute sliding window. The multi-condition logic judgment module 300 is used to determine the leakage level by combining the dynamic model and the processed average conductivity, along with the alarm duration and vibration parameters, to make a multi-condition logic combination judgment. The alarm signal triggering module 400 is used to trigger the corresponding leakage level alarm signal and output a low-pressure cylinder blade breakage risk warning.

[0080] Furthermore, the aforementioned dynamic model building module 100 is also used for: When the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: ; When the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: .

[0081] Furthermore, the aforementioned data acquisition and processing module 200 is also used for: The average value of the positive conductivity data at the condensate pump outlet was calculated using a 5-minute sliding window. The average value of the economizer inlet and main steam conductivity data was calculated using a 1-minute sliding window.

[0082] Furthermore, the aforementioned multi-condition logic judgment module 300 is also used for: If a minor leak alarm persists for 72 hours without disappearing, a significant leak determination is triggered. When the obvious leakage alarm persists for 24 hours and vibration occurs at any measuring point of turbine #3, #4, or #5 watts, Expected value of corresponding load vibration At that time, a low-pressure cylinder blade breakage risk warning was triggered.

[0083] Furthermore, device 10 also includes: The monitoring module is used to monitor the status parameters of the hydrogen exchange column, including resin color depth. High-speed mixed bed effluent indicators , Differential pressure of resin trap Cyclic water production 10,000 tons, and the hydrogen conductivity of the condensate replenishment tank .

[0084] The present invention discloses a real-time graded diagnostic device for condenser leakage, which can realize real-time graded diagnosis of condenser leakage, improve diagnostic accuracy and shorten response time, effectively prevent the expansion of accidents, and reduce unit operation risks and economic losses.

[0085] To implement the methods of the above embodiments, the present invention also provides a computer device, such as... Figure 3 As shown, the computer device 600 includes a memory 601 and a processor 602; wherein, the processor 602 reads executable program code stored in the memory 601 to run a program corresponding to the executable program code, so as to implement the various steps of the method described above.

[0086] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in the foregoing embodiments.

[0087] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0088] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A real-time graded diagnostic method for condenser leakage, characterized in that, include: S1. Establish a dynamic model of conductivity benchmark value based on unit load to generate the expected range of positive conductivity at condensate pump outlet under different load ranges. S2 collects and processes the positive conductivity data of the condensate pump outlet, economizer inlet and main steam in real time, and calculates the average value of the 5-minute and 1-minute sliding windows respectively; S3. Based on the dynamic model of the conductivity benchmark value and the processed average conductivity value, and combined with the alarm duration and vibration parameters, a multi-condition logical combination judgment is performed to determine the leakage level. S4 outputs a low-pressure cylinder blade breakage risk warning based on the triggered corresponding leakage level alarm signal.

2. The method as described in claim 1, characterized in that, S1 includes: S11, when the unit load meets the requirements At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: ; S12, when the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: .

3. The method as described in claim 1, characterized in that, S2 includes: S21, the average value of the positive conductivity data at the condensate pump outlet is calculated using a 5-minute sliding window; S22, the average value of the economizer inlet and main steam conductivity data is calculated using a 1-minute sliding window.

4. The method as described in claim 1, characterized in that, The S3 further includes: S31, when a minor leak alarm persists for 72 hours without disappearing, a significant leak determination is triggered; S32, when the obvious leakage alarm persists for 24 hours without disappearing and any measuring point of the turbine's #3, #4, or #5 watts vibrates. Expected value of corresponding load vibration At that time, a low-pressure cylinder blade breakage risk warning was triggered.

5. The method as described in claim 1, characterized in that, Also includes: S5, monitors the state parameters of the hydrogen exchange column, including resin color depth. High-speed mixed bed effluent indicators , Differential pressure of resin trap Cyclic water production 10,000 tons, and the hydrogen conductivity of the condensate replenishment tank .

6. A real-time graded diagnostic device for condenser leakage, characterized in that, include: The dynamic model building module is used to build a dynamic model of conductivity benchmark value based on unit load, and generate the expected value range of positive conductivity of condensate pump outlet under different load ranges; The data acquisition and processing module is used to collect and process the positive conductivity data of the condensate pump outlet, economizer inlet and main steam in real time, and calculate their average values ​​for 5-minute and 1-minute sliding windows, respectively. The multi-condition logic judgment module is used to determine the leakage level by combining the dynamic model of the conductivity benchmark value and the processed average conductivity value with the alarm duration and vibration parameters to make a multi-condition logic combination judgment. The alarm signal triggering module outputs a low-pressure cylinder blade breakage risk warning based on the corresponding leakage level alarm signal triggered.

7. The apparatus as claimed in claim 6, characterized in that, The dynamic model building module is also used for: When the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: ; When the unit load meets At that time, the expected range of the positive conductivity at the condensate pump outlet was set as follows: .

8. The apparatus as claimed in claim 6, characterized in that, The data acquisition and processing module is also used for: The average value of the positive conductivity data at the condensate pump outlet was calculated using a 5-minute sliding window. The average value of the economizer inlet and main steam conductivity data was calculated using a 1-minute sliding window.

9. A computer device, characterized in that, Including processor and memory; The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the real-time graded diagnosis method for condenser leakage as described in any one of claims 1-5.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the real-time graded diagnosis method for condenser leakage as described in any one of claims 1-5.

Images