Water-turbine generator set working condition early warning method and device and storage medium

By screening the health history data of the water turbine generator set and dividing the working condition grid, and combining real-time data to make early warning judgments, the problem of insufficient accuracy of fixed value early warning methods in the existing technology is solved, and the accuracy and accuracy of early warning are improved .

CN119089015APending Publication Date: 2024-12-06CHINA YANGTZE POWER
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411016638.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing stability warning method for water turbine generator sets cannot accurately reflect the real status of different units using fixed values, resulting in more false alarms and missed reports, low warning accuracy, and failure to consider the stability parameters differences under different working conditions. .

Method used

By reading unit health history data, screening and working condition grid division, calculate the median stability measurement points of each working condition grid as a reference, combine real-time data to make early warning and judgment, and eliminate non-stable working conditions and empty values , improve the accuracy of early warning.

Benefits of technology

Early warning benchmarks under different working conditions have been established, the accuracy and accuracy of early warning are improved, false alarms and missed reports are reduced, and the real status of the unit is more accurately reflected.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089015A_ABST
    Figure CN119089015A_ABST
Patent Text Reader

Abstract

The invention discloses a working condition early warning method and device for a water-turbine generator set and a storage medium. The method comprises the following steps: reading health historical data of the set; screening the historical data; performing working condition grid division on the screened historical data: performing division according to active power and water head according to unit operation interval distribution characteristics, uniformly dividing an operation water head into # imgabs 0 # interval ranges, uniformly dividing active power into # imgabs 1 # interval ranges, and finally obtaining # imgabs 2 # working condition grids; the screened historical data are classified into the divided working condition grids in sequence, the median # imgabs3 # of all stability measuring points of the historical data of each working condition grid is calculated and serves as the reference of all the stability measuring points of the working condition grids, # imgabs4 # represents the # imgabs5 water head interval, # imgabs6 # represents the # imgabs7 active interval, and # imgabs8 # represents the # imgabs9 stability measuring point; reading real-time data of the latest one month, and screening the real-time data; and carrying out early warning judgment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to hydroelectric power generation equipment technology, and in particular to a method, a device and a storage medium for early warning of the working condition of a hydroelectric generator set. Background Art

[0002] The stability parameters of hydro-turbine generator sets are key indicators that affect the safe operation of the units, and stability evaluation can guide the safe operation of the units. At present, the stability warnings of hydro-turbine generator sets in the industry mostly use the fixed values ​​recommended by the industry, but there are very large individual differences in hydro-turbine generator sets, and the performance characteristics of different power station units are quite different. All unit stability parameters use the same fixed value for warning, which cannot well reflect the true status of different units, and do not consider that the stability parameters themselves are very different under different working conditions, resulting in large false alarms and missed alarms, and the accuracy of warnings is not high. It is necessary to define warning values ​​according to the status of different units. Summary of the invention

[0003] The invention provides a method, a device and a storage medium for early warning of the working condition of a hydro-generator set.

[0004] In a first aspect, the present invention provides a method for early warning of a hydro-generator operating condition, the method comprising: Read the unit health history data; the time interval of the historical data is six months after the last overhaul, including: active power, head, and stability parameters; Filter historical data; Divide the filtered historical data into working condition grids: according to the distribution characteristics of the unit operation interval, divide it according to active power and water head, and divide the operating water head into The active power is divided into The range of the interval is finally obtained A working condition grid; The filtered historical data are classified into the divided working condition grids in turn, and the median of each stability measurement point of the historical data of each working condition grid is calculated. , as the benchmark for each stability measurement point of the working condition grid, where Indicates Head interval, Indicates Active interval, Indicates Stability measurement points; Read the real-time data of the last month and filter it; Make early warning judgments.

[0005] Furthermore, the screening of historical data includes: Eliminate the data for 2 hours after the unit is started; According to the unit operation characteristic curve, eliminate the data of the unit operating in the unstable operating area; Screening steady-state conditions; Perform null value processing on the filtered data set.

[0006] Furthermore, the data for 2 hours after the unit is started is specifically excluded as follows: Set the power threshold for power-on judgment, filter the entire time series data set according to active power, and filter out data with active power greater than the power threshold. The filtered data set is divided into multiple time intervals, and the data in the first two hours of each time interval is removed.

[0007] Furthermore, the data of the unit operating in the unstable operating area is eliminated according to the unit operating characteristic curve, specifically: According to the active power and water head, the unit operation characteristic curve is queried to determine whether the corresponding operating condition belongs to the stable operating condition. If it does not belong to the stable operating condition, the corresponding data is eliminated.

[0008] Furthermore, the screening steady-state working condition is specifically: Set the steady-state fluctuation threshold and read each time point The corresponding active power values ​​10 minutes before and after it are used to determine whether the difference between the maximum and minimum active power values ​​in this time interval is greater than the set steady-state fluctuation threshold; if it is greater than the set steady-state fluctuation threshold, then the corresponding time point is a non-steady-state operating point; otherwise is the steady-state operating point; traverse the entire interval time in turn, eliminate all non-steady-state operating conditions, and obtain the screened steady-state operating condition.

[0009] Furthermore, the filtered data set is subjected to null value processing, specifically: When a null value appears, delete the corresponding entire data record; Alternatively, when a null value occurs, a fitting value is calculated using the data before and after the null value to replace the null value, and the fitting calculation includes: replacing the fitting calculation value with the previous value, replacing the fitting calculation value with the next value, and replacing the fitting calculation value with linear interpolation of the previous and next values.

[0010] Furthermore, the early warning judgment is specifically: The filtered real-time data are classified into the working condition grids in turn, and the median of each stability measurement point in each working condition grid is calculated. ,in Indicates Head interval, Indicates Active interval, Indicates stability measurement points, and the median of each stability measurement point of the working condition grid corresponding to the historical data For comparison, if , then the grid is judged to be the early warning grid of the corresponding measuring point; Calculate the number of warning grids at each measuring point and record it as , further judge: If , an early warning is issued for the measuring point.

[0011] Furthermore, the real-time data of the latest month is read and filtered, specifically: Eliminate the data for 2 hours after the unit is started; According to the unit operation characteristic curve, eliminate the data of the unit operating in the unstable operating area; Screening steady-state conditions; Perform null value processing on the filtered data set.

[0012] In a second aspect, the present invention provides a hydraulic generator operating condition early warning device, the device comprising: Memory, used to store programs; The processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above method.

[0013] In a third aspect, the present invention provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, causes the one or more processors to execute the above method.

[0014] Compared with the prior art, the present invention has the following advantages: An early warning benchmark under different working conditions grids has been established to improve the early warning precision and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a method for early warning of a hydro-generator operating condition provided by an embodiment of the present invention; Figure 2 A schematic diagram of the composition of a hydro-generator operating condition warning device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] Figure 1 A schematic diagram of a method for early warning of a hydro-generator operating condition provided by an embodiment of the present invention, the method comprising: Read the unit health history data; the time interval of the historical data is six months after the last overhaul, including: active power, head, and stability parameters; Filter historical data; Divide the filtered historical data into working condition grids: according to the distribution characteristics of the unit operation interval, divide it according to active power and water head, and divide the operating water head into The active power is divided into The range of the interval is finally obtained A working condition grid; The filtered historical data are classified into the divided working condition grids in turn, and the median of each stability measurement point of the historical data of each working condition grid is calculated. , as the benchmark for each stability measurement point of the working condition grid, where Indicates Head interval, Indicates Active interval, Indicates Stability measurement points; Read the real-time data of the last month and filter it; Make early warning judgments.

[0018] In one embodiment, the filtering of historical data includes: Eliminate the data for 2 hours after the unit is started; According to the unit operation characteristic curve, eliminate the data of the unit operating in the unstable operating area; Screening steady-state conditions; Perform null value processing on the filtered data set.

[0019] In one embodiment, the data of the rejection unit 2 hours after startup is specifically: Set the power threshold for power-on judgment. Generally, the power threshold is set to 10% of the rated power. The entire time series data set is filtered according to the active power, and the data with active power greater than the power threshold is filtered out. The filtered data set is divided into multiple time intervals, and the data in the first 2 hours of each time interval is removed.

[0020] In one embodiment, the data of the unit operating in the unstable operating area is eliminated according to the unit operating characteristic curve, specifically: According to the active power and water head, the unit operation characteristic curve is queried to determine whether the corresponding operating condition belongs to the stable operating condition. If it does not belong to the stable operating condition, the corresponding data is eliminated.

[0021] In one embodiment, the screening steady-state operating condition is specifically: Set the steady-state fluctuation threshold and read each time point The corresponding active power values ​​10 minutes before and after it are used to determine whether the difference between the maximum and minimum active power values ​​in this time interval is greater than the set steady-state fluctuation threshold; if it is greater than the set steady-state fluctuation threshold, then the corresponding time point is a non-steady-state operating point; otherwise is the steady-state operating point; traverse the entire interval time in turn, eliminate all non-steady-state operating conditions, and obtain the screened steady-state operating condition.

[0022] In one embodiment, the filtering data set is subjected to null value processing, specifically: When a null value appears, delete the corresponding entire data record; Alternatively, when a null value occurs, a fitting value is calculated using the data before and after the null value to replace the null value, and the fitting calculation includes: replacing the fitting calculation value with the previous value, replacing the fitting calculation value with the next value, and replacing the fitting calculation value with linear interpolation of the previous and next values.

[0023] In one embodiment, the early warning judgment is specifically: The filtered real-time data are classified into the working condition grids in turn, and the median of each stability measurement point in each working condition grid is calculated. ,in Indicates Head interval, Indicates Active interval, Indicates stability measurement points, and the median of each stability measurement point of the working condition grid corresponding to the historical data For comparison, if , then the grid is judged to be the early warning grid of the corresponding measuring point; Calculate the number of warning grids at each measuring point and record it as , further judge: If , an early warning is issued for the measuring point.

[0024] In one embodiment, the real-time data of the most recent month is read and filtered, specifically: Eliminate the data for 2 hours after the unit is started; According to the unit operation characteristic curve, eliminate the data of the unit operating in the unstable operating area; Screening steady-state conditions; Perform null value processing on the filtered data set.

[0025] It should be noted that the method of this process is the same as the method of processing historical data.

[0026] Figure 2A schematic diagram of a hydro-generator operating condition early warning device provided in an embodiment of the present invention; the device comprises: Memory, used to store programs; The processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above method.

[0027] In addition, an embodiment of the present invention provides a storage medium storing computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the above method.

[0028] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for early warning of the working condition of a hydro-generator set, characterized in that: The method comprises: Read the unit health history data; the time interval of the historical data is six months after the last overhaul, including: active power, head, and stability parameters; Filter historical data; Divide the filtered historical data into working condition grids: according to the distribution characteristics of the unit operation interval, divide it according to active power and water head, and divide the operating water head into The active power is divided into The range of the interval is finally obtained A working condition grid; The filtered historical data are classified into the divided working condition grids in turn, and the median of each stability measurement point of the historical data of each working condition grid is calculated. , as the benchmark for each stability measurement point of the working condition grid, where Indicates Head interval, Indicates Active interval, Indicates Stability measurement points; Read the real-time data of the last month and filter it; Make early warning judgments.

2. The method for early warning of the operating condition of a hydro-generator set according to claim 1, characterized in that: The screening of historical data includes: Eliminate the data for 2 hours after the unit is started; According to the unit operation characteristic curve, eliminate the data of the unit operating in the unstable operating area; Screening steady-state conditions; Perform null value processing on the filtered data set.

3. The method for early warning of the operating condition of a hydro-generator set according to claim 2, characterized in that: The data of the rejection unit 2 hours after startup is specifically: Set the power threshold for power-on judgment, filter the entire time series data set according to active power, and filter out data with active power greater than the power threshold. The filtered data set is divided into multiple time intervals, and the data in the first two hours of each time interval is removed.

4. The method for early warning of the operating condition of a hydro-generator set according to claim 2, characterized in that: According to the unit operation characteristic curve, the data of the unit operating in the unstable operating area is eliminated, specifically: According to the active power and water head, the unit operation characteristic curve is queried to determine whether the corresponding operating condition belongs to the stable operating condition. If it does not belong to the stable operating condition, the corresponding data is eliminated.

5. The method for early warning of the operating condition of a hydro-generator set according to claim 2, characterized in that: The screening steady-state working condition is specifically: Set the steady-state fluctuation threshold and read each time point The corresponding active power values ​​10 minutes before and after it are used to determine whether the difference between the maximum and minimum active power values ​​in this time interval is greater than the set steady-state fluctuation threshold; if it is greater than the set steady-state fluctuation threshold, then the corresponding time point is a non-steady-state operating point; otherwise is the steady-state operating point; traverse the entire interval time in turn, eliminate all non-steady-state operating conditions, and obtain the screened steady-state operating condition.

6. The method for early warning of the operating condition of a hydro-generator set according to claim 2, characterized in that: The null value processing of the filtered data set is specifically as follows: When a null value appears, delete the corresponding entire data record; Alternatively, when a null value occurs, a fitting value is calculated using the data before and after the null value to replace the null value, and the fitting calculation includes: replacing the fitting calculation value with the previous value, replacing the fitting calculation value with the next value, and replacing the fitting calculation value with linear interpolation of the previous and next values.

7. The method for early warning of the operating condition of a hydro-generator set according to claim 1, characterized in that: The aforementioned early warning judgment is specifically as follows: The filtered real-time data are classified into the working condition grids in turn, and the median of each stability measurement point in each working condition grid is calculated. ,in Indicates Head interval, Indicates Active interval, Indicates stability measurement points, and the median of each stability measurement point of the working condition grid corresponding to the historical data For comparison, if , then the grid is judged to be the early warning grid of the corresponding measuring point; Calculate the number of warning grids at each measuring point and record it as , further judge: If , an early warning is issued for the measuring point.

8. The method for early warning of the operating condition of a hydro-generator set according to claim 1, characterized in that: The real-time data of the latest month is read and filtered, specifically: Eliminate the data for 2 hours after the unit is started; According to the unit operation characteristic curve, eliminate the data of the unit operating in the unstable operating area; Screening steady-state conditions; Perform null value processing on the filtered data set.

9. A hydro-generator operating condition early warning device, characterized in that: The device comprises: Memory, used to store programs; A processor, configured to execute the program stored in the memory; when the program stored in the memory is executed, the processor is configured to execute the steps of the method as claimed in any one of claims 1 to 8.

10. A storage medium storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the steps of the method according to any one of claims 1 to 8.