Method and system for screening steady-state operation condition time period of thermal power generating unit

Abstract

The invention belongs to the technical field of power data analysis, and relates to a method and system for screening steady-state operation condition periods of a thermal power generating unit. The method comprises the following steps: acquiring a load measuring point, and acquiring an analog measuring point meeting a unit load condition; selecting analog measurement points meeting set conditions from the analog measurement points, and taking the analog measurement points meeting the set conditions and the corresponding load measurement points as feature measurement points; selecting a set number of feature measurement points as a sliding window according to the time sequence, and obtaining the slope of a fitting straight line of the feature measurement points in three continuous sliding window intervals; judging the trend of the feature measurement points in each sliding window according to the slope of the fitting straight line; obtaining all upper inflection points and lower inflection points of the feature measurement points according to the trend of the feature measurement points; according to the upper inflection point and the lower inflection point, obtaining all stable time periods of the feature measurement point, obtaining an intersection of the stable time periods, and obtaining a stable working condition time period of the unit. And the stable operation time period of the unit can be accurately calculated.

Description

Technical Field

[0001] This invention belongs to the field of power data analysis technology, and relates to a method and system for screening the steady-state operating conditions of thermal power units. Background Technology

[0002] In thermal power generation, deviations often exist between the actual operating parameters of the unit, the ideal design values, and the target values ​​for operation and control. Optimization of the thermal power production process has always been a hot research topic for technicians. However, the load-driven production mode of thermal power units means that the production process is frequently in a state of adjustment and dynamic change, leading to instability in real-time production data. This significantly reduces the value of analyzing and using this data, making it difficult to directly guide production. Therefore, it is necessary to perform unit stability calculations to obtain stable operating periods, filter production data according to stable periods, and then optimize the production process through data analysis to achieve green environmental protection, energy conservation, and emission reduction, thereby obtaining higher socio-economic benefits.

[0003] Due to the complexity of the production process of thermal power units and the large number of monitoring points during operation, the matching degree between most monitoring points and the unit's operating status is not high, making it difficult to scientifically select characteristic monitoring points to represent the stability of unit operation. The data generated by the unit's long-term operation is large in volume and has complex and volatile trends. The trends of multiple monitoring points within the same time period may be opposite, making it difficult to identify the stability of monitoring points. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for screening the steady-state operating conditions of thermal power units, so as to solve the technical problems of difficulty in scientifically selecting characteristic measurement points that characterize the stable operation of the unit and difficulty in identifying the stability of the measurement points during the operation of thermal power units.

[0005] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, the present invention provides a method for screening the steady-state operating period of a thermal power unit, comprising the following steps: Obtain load measurement points and simulated measurement points that meet the unit load conditions; Select analog measurement points that meet the set conditions from the analog measurement points, and use the analog measurement points that meet the set conditions and the corresponding load measurement points as feature measurement points. A set number of feature measurement points are selected as a sliding window according to the time series, and the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals is obtained. The trend of the feature measurement points within each sliding window is determined based on the slope of the fitted straight line. Based on the trend of the feature measurement points, obtain all the upper and lower inflection points of the feature measurement points; Based on the upper and lower inflection points, all stable time periods of the characteristic measurement points are obtained, and the intersection of the stable time periods is obtained to obtain the stable operating time period of the unit.

[0006] Furthermore, the acquisition of analog measurement points that meet the unit load conditions includes: Select several analog measurement points from the operating parameter measurement points of the DCS system based on the unit load conditions; The unit load condition is: within the selected time range, the unit load is greater than 30%.

[0007] Further, selecting analog measurement points that meet the set conditions from the analog measurement points includes: Obtain the Pearson correlation coefficient between the simulated measurement points and the load; Select analog measurement points with a Pearson correlation greater than the set Pearson correlation value.

[0008] Further, the step of selecting a set number of feature measurement points as a sliding window according to the time series, and obtaining the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals, includes: The feature measurement points are standardized using the z-score standardization method to obtain standardized feature measurement points. Select a set number of standardized feature measurement points according to the time series; The slope of the fitted line for feature measurement points within three consecutive sliding window intervals is obtained using the least squares method.

[0009] Furthermore, the step of determining the trend of feature measurement points within each sliding window based on the slope of the fitted straight line includes: The trend of feature points within each sliding window is determined by combining the slope of the fitted straight line with the set range of the stability slope.

[0010] Furthermore, the trend of the feature measurement points within each sliding window includes stable, rising, and falling trends.

[0011] Furthermore, the set stability slope range is -0.01 to 0.01; When the slope of the fitted line is greater than -0.01 and less than 0.01, the trend of the feature measurement points within the sliding window is stable. When the slope of the fitted line is greater than or equal to 0.01, the trend of the feature measurement points within the sliding window is upward. When the slope of the fitted line is less than or equal to -0.01, the trend of the feature measurement points within the sliding window is decreasing.

[0012] Furthermore, the step of obtaining all upper and lower inflection points of the feature measurement points based on their trends includes: When three consecutive stable trends appear, the trend of the previous sliding window is used to determine whether it is an upward or downward inflection point. The time of the first data in the third sliding window of the three consecutive stable trends is recorded as the starting point of the stable period. Advance one sliding window until the three sliding windows show a stable, stable, and rising trend or a stable, stable, and falling trend. Based on the trend of the third sliding window, determine whether it is an upward or downward inflection point, and record the time of the first data in the third sliding window as the end of the stable period. After processing all the characteristic measurement points in sequence, find all the upper and lower inflection points.

[0013] Furthermore, the step of obtaining all stable time periods of the feature measurement points based on the upper and lower inflection points, and obtaining the intersection of these stable time periods to obtain the stable operating condition time periods of the unit, includes: Based on the principle of pairing upper and lower inflection points, all stable time periods of the feature measurement points are obtained; After obtaining the intersection of all stable time periods and deleting time periods shorter than the set time, the stable operating time periods of the unit are obtained.

[0014] Secondly, the present invention provides a screening system for steady-state operation periods of thermal power units, comprising: The data acquisition module is used to acquire load measurement points and analog measurement points that meet the unit load conditions; The feature measurement point acquisition module is used to select analog measurement points that meet the set conditions from the analog measurement points, and use the analog measurement points that meet the set conditions and the corresponding load measurement points as feature measurement points. The slope acquisition module is used to select a set number of feature measurement points as a sliding window according to the time series, and obtain the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals. The trend acquisition module is used to determine the trend of feature measurement points within each sliding window based on the slope of the fitted line. The inflection point acquisition module is used to acquire all upper and lower inflection points of the feature measurement points based on their trends. The stable operating condition period acquisition module is used to obtain all stable operating periods of feature measurement points based on the upper and lower inflection points, and to obtain the intersection of stable operating periods to obtain the stable operating period of the unit.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention acquires load measurement points to obtain simulated measurement points that meet the unit's load conditions. By filtering load measurement points, simulated measurement points irrelevant to the unit's load are excluded, reducing invalid data interference and providing a data foundation strongly correlated with core operating conditions for subsequent stability analysis. Simulated measurement points meeting set conditions are selected from these points, and these, along with the corresponding load measurement points, are used as feature measurement points, which helps improve the accuracy of stability judgment. A set number of feature measurement points are selected as a sliding window according to the time series, and the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals is obtained. The time series data is divided into local segments by the sliding window, and the increase or decrease trend of data within each window is quantified by fitting a straight line and calculating the slope. The trend of the feature measurement points within each sliding window is determined based on the slope of the fitted line, providing a prerequisite for subsequent inflection point detection. All upper and lower inflection points of the feature measurement points are obtained based on their trends. All stable periods of the feature measurement points are obtained based on the upper and lower inflection points, and the intersection of these stable periods is obtained to obtain the stable operating conditions of the unit. By filtering data during stable operating periods, excluding data from adjustment and dynamic change phases, and retaining high-quality data reflecting stable unit operation, this invention significantly enhances the guiding value of data analysis. Through progressive analysis involving measurement point selection, local trend quantification, inflection point identification, and multi-measurement point collaboration, this invention systematically solves problems such as unstable data, low measurement point matching, and complex trends in thermal power units. Ultimately, it outputs highly reliable stable operating periods for the units, providing a solid data foundation for production optimization.

[0016] The system of this invention includes a data acquisition module, a feature measurement point acquisition module, a slope acquisition module, a trend acquisition module, an inflection point acquisition module, and a stable operating condition period acquisition module. The data acquisition module acquires load measurement points and simulated measurement points that meet the unit's load conditions. The feature measurement point acquisition module selects simulated measurement points that meet set conditions from the simulated measurement points, using these simulated measurement points and the corresponding load measurement points as feature measurement points. The slope acquisition module selects a set number of feature measurement points as a sliding window according to the time series and acquires the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals. The trend acquisition module determines the trend of the feature measurement points within each sliding window based on the slope of the fitted line. The inflection point acquisition module acquires all upper and lower inflection points of the feature measurement points based on their trends. The stable operating condition period acquisition module acquires all stable periods of the feature measurement points based on the upper and lower inflection points, and obtains the intersection of these stable periods to obtain the unit's stable operating condition period. The various modules work together to accurately determine the period of stable operation of the unit based on the curve trends of the unit's operating characteristic measurement points, thereby enhancing the analytical value of the unit's operating parameters and meeting the data requirements for optimized production operation. Attached Figure Description

[0017] Figure 1 This is a flowchart of a method according to an embodiment of the present invention; Figure 2 This is a system block diagram of an embodiment of the present invention; Figure 3 This is a flowchart of another embodiment of the present invention; Figure 4 This is a diagram illustrating the inflection point acquisition process in an embodiment of the present invention. Detailed Implementation

[0018] 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.

[0019] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] The present invention will now be described in further detail with reference to the accompanying drawings: See Figure 1 This invention discloses a method for screening the steady-state operating period of a thermal power unit, comprising the following steps: S1. Obtain load measurement points: Acquire simulated measurement points that meet the unit load conditions. Through load measurement point screening, eliminate simulated measurement points irrelevant to the unit load, reducing invalid data interference and improving subsequent analysis efficiency. Ensure that the selected simulated measurement points are directly related to unit load changes, providing a data foundation strongly correlated with core operating conditions for subsequent stability analysis.

[0021] In this embodiment of the invention, obtaining the simulated measurement points that meet the unit load conditions includes: From the operating parameter measurement points of the DCS system (Distributed Control System), select several analog measurement points based on the unit load conditions; The unit load condition is: within the selected time range, the unit load is greater than 30%.

[0022] S2, Selecting analog measurement points that meet the set conditions from the analog measurement points, and using the analog measurement points that meet the set conditions and the corresponding load measurement points as feature measurement points, is beneficial to improving the accuracy of stability judgment.

[0023] In this embodiment of the invention, selecting analog measurement points that meet the set conditions from the analog measurement points includes: Obtain the Pearson correlation coefficient between the simulated measurement points and the load; Select analog measurement points with a Pearson correlation greater than the set Pearson correlation value.

[0024] S3: Select a predetermined number of feature measurement points as a sliding window according to the time series, and obtain the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals. The time series data is segmented into local segments by using sliding windows. By fitting lines and calculating the slopes, the increasing or decreasing trend of data within each window is quantified. The slope calculation for three consecutive windows reflects the continuity of the trend and avoids the randomness of single-window analysis.

[0025] In this embodiment of the invention, the step of selecting a set number of feature measurement points as a sliding window according to the time series and obtaining the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals includes: The feature measurement points are standardized using the z-score standardization method to obtain standardized feature measurement points. Select a set number of standardized feature measurement points according to the time series; The slope of the fitted line for feature measurement points within three consecutive sliding window intervals is obtained using the least squares method.

[0026] S4, based on the slope of the fitted straight line, determines the trend of feature measurement points within each sliding window, providing prerequisites for subsequent inflection point detection, including: The trend of feature points within each sliding window is determined by combining the slope of the fitted straight line with the set range of the stability slope.

[0027] In this embodiment of the invention, the trend of the feature measurement points within each sliding window includes stable, rising, and falling.

[0028] In this embodiment of the invention, the set stationarity slope range is -0.01 to 0.01; When the slope of the fitted line is greater than -0.01 and less than 0.01, the trend of the feature measurement points within the sliding window is stable. When the slope of the fitted line is greater than or equal to 0.01, the trend of the feature measurement points within the sliding window is upward. When the slope of the fitted line is less than or equal to -0.01, the trend of the feature measurement points within the sliding window is decreasing.

[0029] S5, based on the trend of the feature measurement points, obtain all upper and lower inflection points of the feature measurement points, including: When three consecutive stable trends appear, the trend of the previous sliding window is used to determine whether it is an upward or downward inflection point. The time of the first data in the third sliding window of the three consecutive stable trends is recorded as the starting point of the stable period. Advance one sliding window until the three sliding windows show a stable, stable, and rising trend or a stable, stable, and falling trend. Based on the trend of the third sliding window, determine whether it is an upward or downward inflection point, and record the time of the first data in the third sliding window as the end of the stable period. After processing all the characteristic measurement points in sequence, find all the upper and lower inflection points.

[0030] S6 obtains all stable time periods of the feature measurement points based on the upper and lower inflection points, and obtains the intersection of these stable time periods to obtain the stable operating conditions of the unit. By filtering the stable operating conditions, data from adjustment and dynamic change phases are excluded, retaining high-quality data on stable unit operation, significantly improving the guiding value of data analysis.

[0031] In this embodiment of the invention, the step of obtaining all stable time periods of the feature measurement points based on the upper and lower inflection points, and obtaining the intersection of the stable time periods to obtain the stable operating condition time period of the unit, includes: Based on the principle of pairing upper and lower inflection points, all stable time periods of the feature measurement points are obtained; After obtaining the intersection of all stable time periods and deleting time periods shorter than the set time, the stable operating time periods of the unit are obtained.

[0032] This invention systematically solves problems such as unstable data, low measurement point matching, and complex trends in thermal power units through progressive analysis of measurement point screening, local trend quantification, inflection point identification, and multi-measurement point collaboration. Ultimately, it outputs highly reliable stable operating periods of the units, providing a solid data foundation for production optimization.

[0033] See Figure 2 Based on the above method, the present invention also discloses a screening system for steady-state operation periods of thermal power units, comprising: The data acquisition module is used to acquire load measurement points and analog measurement points that meet the unit load conditions; The feature measurement point acquisition module is used to select analog measurement points that meet the set conditions from the analog measurement points, and use the analog measurement points that meet the set conditions and the corresponding load measurement points as feature measurement points. The slope acquisition module is used to select a set number of feature measurement points as a sliding window according to the time series, and obtain the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals. The trend acquisition module is used to determine the trend of feature measurement points within each sliding window based on the slope of the fitted line. The inflection point acquisition module is used to acquire all upper and lower inflection points of the feature measurement points based on their trends. The stable operating condition period acquisition module is used to obtain all stable operating periods of feature measurement points based on the upper and lower inflection points, and to obtain the intersection of stable operating periods to obtain the stable operating period of the unit.

[0034] The various modules of this invention work together to accurately determine the time period of stable operation of the unit based on the curve trend of the unit's operating characteristic measurement points, thereby enhancing the analytical value of the unit's operating parameters and meeting the data requirements for optimized production operation.

[0035] Example 2: To address the technical challenges faced by power generation companies in production optimization analysis, this invention proposes a method for screening steady-state operating periods of thermal power units. This method identifies characteristic measurement points that characterize the unit's operating state. By judging the data trends of each characteristic measurement point, calculating the upper and lower inflection points and their times, and then taking the intersection of the stable periods of each characteristic, the steady-state operating period of the unit is obtained. (See also...) Figure 3 This includes the following steps: S10. From the operating parameter measurement points that can be monitored at the top of all operation monitoring screens in the DCS system, initially determine m analog measurement points that affect the operation of thermal power units. According to the selected time range, filter the downtime based on the unit load being greater than 30%, calculate the Pearson correlation coefficient between the m measurement points and the load, and select the n measurement points with the highest Pearson correlation coefficient as characteristic measurement points representing the unit's operating conditions, including load measurement points. S20. For the historical data of selected n feature measurement points, the z-score standardization method is used for standardization. The i data points are selected as a sliding window according to the time series. The slope k of the fitted line in the three sliding intervals is calculated using the least squares method. The trend of the data in each sliding window is judged according to the set stationarity slope interval range [-a, a]. It is divided into three types, as shown in the table below.

[0036] Table 1. Criteria for Determining the Trend of Feature Measurement Points:

[0037] Based on the permutation and combination of the data trends in the three sliding windows, there are 27 possible combinations. When three consecutive stable trends appear, the trend of the previous sliding window is used to determine whether it is an upward or downward inflection point. The time of the first data in the third sliding window is recorded as the starting point of the stable period. The process is repeated until the three sliding windows show a stable, stable, and rising trend or a stable, stable, and falling trend. The trend in the third sliding window is then used to determine whether it is an upward or downward inflection point. The time of the first data in the third sliding window is recorded as the ending point of the stable period. All data from the measurement points are processed in sequence to find all the upward and downward inflection points. S30, following the principle of pairing upper and lower inflection points, calculate all stable time periods of the measuring points, calculate the intersection of stable time periods of n operating condition characteristic measuring points, and after deleting time periods that are too short, obtain the stable operating time periods of the unit.

[0038] This invention filters downtime data from analog measurement points affecting thermal power unit operation within a selected time range, calculates the Pearson correlation coefficient between the measurement points and the load, and selects the measurement points with the highest correlation coefficients as characteristic measurement points representing the unit's operating condition. Then, the selected characteristic measurement point data is standardized, and the slope of the fitted straight line within three sliding intervals is calculated using the least squares method. Based on the stability slope range, the upper and lower inflection points of the characteristic measurement point curves are calculated, and the stable operating period is calculated from the time difference between the upper and lower inflection points. By calculating the intersection of the stable operating periods of each characteristic measurement point and removing excessively short periods, the stable operating condition period is obtained. This method can accurately calculate the stable operating period of the unit based on the curve trend of the unit's characteristic measurement points, improving the analytical value of unit operating parameters and meeting the data requirements for optimized production operation.

[0039] This invention is widely applicable to stability calculations under different load conditions of thermal power units.

[0040] The selection of measurement points in this invention can be based on primary measurement points acquired in real time, or on secondary measurement points calculated in real time.

[0041] This invention can quickly screen out characteristic measurement points that characterize the unit's operating status, and smooth out minor data fluctuations in the characteristic measurement points by adjusting the size of the sliding window, thereby quickly calculating the period of stable unit operation and providing steady-state data for production optimization and operation analysis.

[0042] Example 3: like Figure 3As shown, a method for calculating the steady-state operation period of a thermal power unit is illustrated using a 600MW ultra-supercritical coal-fired unit as an example. Measurement points are selected from the DCS system's operation monitoring screen, and historical operation data of the unit is extracted from the DCS system's real-time database. The steady-state operation period of the unit is calculated according to the following steps: S10. From the operating parameter measurement points that can be monitored at the top of all operation monitoring screens in the DCS system, 20 analog measurement points that affect the operation of thermal power units are initially identified, including unit load, main steam temperature, main steam pressure, feedwater flow rate, total fuel quantity, reheat steam temperature, reheat steam pressure, condenser vacuum, boiler negative pressure, etc. According to the selected time range, the downtime is filtered based on the unit load being greater than 30%. The Pearson correlation coefficient between the 20 measurement points and the load is calculated. The 5 measurement points with the highest Pearson correlation coefficient are selected as characteristic measurement points to characterize the unit's operating conditions, including unit load, feedwater flow rate, total fuel quantity, main steam pressure, and condenser vacuum. S20. For the historical data of the selected 5 feature measurement points, the z-score standardization method is used for standardization. Five data points are selected as a sliding window according to the time series. The slope k of the fitted line within the 3 sliding intervals is calculated using the least squares method. The trend of the data in each sliding window is judged according to the set stationarity slope interval range [-0.01, 0.01], which is divided into three types, as shown in Table 1.

[0043] There are 27 possible occurrences of three sliding windows, as shown in the table below. When three consecutive stable trends appear, the trend of the preceding sliding window is used to determine whether it is an upward or downward inflection point. The time of the first data point in the third sliding window is recorded as the starting point of the stable period. This process is repeated one sliding window until three sliding windows show a pattern of stable, stable, and rising, or stable, stable, and falling. Then, the trend in the third sliding window is used to determine whether it is an upward or downward inflection point. The time of the first data point in the third sliding window is recorded as the ending point of the stable period. Figure 4 As shown, after processing all the data from the measuring points in sequence, all the upper and lower inflection points were identified, as shown in Table 2: Table 2. Correspondence between data trends and inflection point judgments for the three sliding windows:

[0044] S30, following the principle of pairing upper and lower inflection points, calculate all stable time periods of the measuring points, calculate the intersection of stable time periods of the 5 operating condition characteristic measuring points, and delete time periods of no more than 5 minutes to obtain the stable operating time periods of the unit.

[0045] The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made to the technical solution based on the technical concept proposed in this invention shall fall within the scope of protection of this invention.

Claims

1. A method for screening steady-state operating periods of thermal power units, characterized in that, Includes the following steps: Obtain load measurement points and simulated measurement points that meet the unit load conditions; Select analog measurement points that meet the set conditions from the analog measurement points, and use the analog measurement points that meet the set conditions and the corresponding load measurement points as feature measurement points. A set number of feature measurement points are selected as a sliding window according to the time series, and the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals is obtained. The trend of the feature measurement points within each sliding window is determined based on the slope of the fitted straight line. Based on the trend of the feature measurement points, obtain all the upper and lower inflection points of the feature measurement points; Based on the upper and lower inflection points, all stable time periods of the characteristic measurement points are obtained, and the intersection of the stable time periods is obtained to obtain the stable operating time period of the unit.

2. The method for screening steady-state operating conditions of thermal power units according to claim 1, characterized in that, The acquisition of analog measurement points that meet the unit load conditions includes: Select several analog measurement points from the operating parameter measurement points of the DCS system based on the unit load conditions; The unit load condition is: within the selected time range, the unit load is greater than 30%.

3. The method for screening steady-state operating conditions of thermal power units according to claim 1, characterized in that, Selecting simulated measurement points that meet the set conditions from the simulated measurement points includes: Obtain the Pearson correlation coefficient between the simulated measurement points and the load; Select analog measurement points with a Pearson correlation greater than the set Pearson correlation value.

4. The method for screening steady-state operating conditions of thermal power units according to claim 1, characterized in that, The step of selecting a predetermined number of feature measurement points as a sliding window according to the time series, and obtaining the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals, includes: The feature measurement points are standardized using the z-score standardization method to obtain standardized feature measurement points. Select a set number of standardized feature measurement points according to the time series; The slope of the fitted line for feature measurement points within three consecutive sliding window intervals is obtained using the least squares method.

5. The method for screening steady-state operating conditions of thermal power units according to claim 1, characterized in that, The step of determining the trend of feature measurement points within each sliding window based on the slope of the fitted straight line includes: The trend of feature points within each sliding window is determined by combining the slope of the fitted straight line with the set range of the stability slope.

6. The method for screening steady-state operating conditions of thermal power units according to claim 5, characterized in that, The trends of the feature measurement points within each sliding window include stable, rising, and falling.

7. The method for screening steady-state operating conditions of thermal power units according to claim 6, characterized in that, The set stability slope range is -0.01 to 0.01; When the slope of the fitted line is greater than -0.01 and less than 0.01, the trend of the feature measurement points within the sliding window is stable. When the slope of the fitted line is greater than or equal to 0.01, the trend of the feature measurement points within the sliding window is upward. When the slope of the fitted line is less than or equal to -0.01, the trend of the feature measurement points within the sliding window is decreasing.

8. The method for screening steady-state operating conditions of thermal power units according to claim 6, characterized in that, The step of obtaining all upper and lower inflection points of the feature measurement points based on their trends includes: When three consecutive stable trends appear, the trend of the previous sliding window is used to determine whether it is an upward or downward inflection point. The time of the first data in the third sliding window of the three consecutive stable trends is recorded as the starting point of the stable period. Advance one sliding window until the three sliding windows show a stable, stable, and rising trend or a stable, stable, and falling trend. Based on the trend of the third sliding window, determine whether it is an upward or downward inflection point, and record the time of the first data in the third sliding window as the end of the stable period. After processing all the characteristic measurement points in sequence, find all the upper and lower inflection points.

9. The method for screening steady-state operating conditions of thermal power units according to claim 1, characterized in that, The process of obtaining all stable time periods of characteristic measurement points based on the upper and lower inflection points, and obtaining the intersection of these stable time periods to obtain the stable operating conditions of the unit, includes: Based on the principle of pairing upper and lower inflection points, all stable time periods of the feature measurement points are obtained; After obtaining the intersection of all stable time periods and deleting time periods shorter than the set time, the stable operating time periods of the unit are obtained.

10. A screening system for steady-state operating conditions of thermal power units, characterized in that, include: The data acquisition module is used to acquire load measurement points and analog measurement points that meet the unit load conditions; The feature measurement point acquisition module is used to select analog measurement points that meet the set conditions from the analog measurement points, and use the analog measurement points that meet the set conditions and the corresponding load measurement points as feature measurement points. The slope acquisition module is used to select a set number of feature measurement points as a sliding window according to the time series, and obtain the slope of the fitted line of the feature measurement points within three consecutive sliding window intervals. The trend acquisition module is used to determine the trend of feature measurement points within each sliding window based on the slope of the fitted line. The inflection point acquisition module is used to acquire all upper and lower inflection points of the feature measurement points based on their trends. The stable operating condition period acquisition module is used to obtain all stable operating periods of feature measurement points based on the upper and lower inflection points, and to obtain the intersection of stable operating periods to obtain the stable operating period of the unit.

Images