Method and device for screening steady-state data of thermal power generating unit

Abstract

The invention discloses a steady-state data screening method and device of a thermal power generating unit, and relates to the field of thermal power generating unit control. The method comprises the steps of obtaining unit operation data of a thermal power generating unit, wherein the unit operation data comprises multiple pieces of data information; each piece of data information comprises corresponding unit load, main steam flow, main steam temperature and main steam pressure at the same moment; based on the unit load, deleting data information with the unit load smaller than the target load in the unit operation data to obtain first screening data; the first screening data represents the data after screening out the data information of the abnormal load during the unit operation in the unit operation data; in the first screening data, each piece of data information is judged based on the main steam flow, the main steam temperature and the main steam pressure on the basis of a preset algorithm, the data information meeting the steady state condition is screened out, second screening data is obtained, and the next piece of data information in the time sequence is judged. The method is used for achieving the steady-state data screening function of the thermal power generating unit.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of thermal power unit control, in particular to a steady-state data screening method and device for thermal power units. BACKGROUND

[0002] In the process of power system operation, the stable operation of thermal power units plays a crucial role in the safety and economy of the power grid. With the continuous increase in the installed capacity of new energy, the operation mode of coal-fired power units gradually changes to deep peak shaving operation. This operation mode leads to a significant increase in coal consumption and a decrease in unit reliability. In order to improve the safety and economy of thermal power units, it is necessary to accurately understand the operating state of the units and timely diagnose and optimize. In the process of operation of thermal power units, a large amount of monitoring data is generated, which truly records the operating state, operating information and characteristics of the units. However, due to the influence of various internal and external factors on the operation of the units, the unit load and state parameters are always changing, and the control system has a regulation lag, which causes the operating parameters to be unable to reflect the true operating state of the units in real time. Only the data collected under steady-state operating conditions are effective, and have important reference value for carrying out energy efficiency evaluation, energy consumption diagnosis and analyzing the economy of the units.

[0003] At present, the traditional steady-state data screening method for thermal power units mainly relies on manual operation, that is, manual analysis of the collected monitoring data is required to determine which data belongs to the steady-state data under the stable operation of the thermal power units. However, in actual application, the existing steady-state data screening method is not only time-consuming and laborious, but also difficult to meet the real-time requirement, and some steady-state identification methods exist in the prior art, but these methods are mostly for specific types of units (such as supercritical units) and lack universality, making it difficult to adapt to the steady-state data screening needs of different types of thermal power units. Therefore, how to realize a steady-state data screening method that is fast, convenient and suitable for different types of thermal power units has become a problem to be solved in the field. SUMMARY

[0004] The embodiments of the present application provide a steady-state data screening method and device for thermal power units, and the main purpose is to realize a steady-state data screening method for thermal power units, which can realize a steady-state data screening method that is fast, convenient and suitable for different types of thermal power units.

[0005] To solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0006] In a first aspect, the present application provides a steady-state data screening method for thermal power units, which comprises:

[0007] Obtain unit, for obtaining the unit operation data of the thermal power generating unit, wherein the unit operation data includes a plurality of data information, wherein each data information includes the unit load, the main steam flow, the main steam temperature and the main steam pressure corresponding to the same time point;

[0008] The data information with the unit load less than the target load is deleted in the unit operation data based on the unit load, to obtain first screening data, wherein the first screening data is used to represent the data after the data information with abnormal load during the unit operation is screened out in the unit operation data;

[0009] In the first screening data, each data information is judged based on the main steam flow, the main steam temperature and the main steam pressure based on a preset algorithm, and the data information meeting the steady state condition is screened out to obtain second screening data, wherein the preset algorithm at least includes the front point value method, and the front point value method is used to represent that when the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady state condition in the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged.

[0010] Secondly, the present application also provides a steady state data screening device for a thermal power generating unit, comprising:

[0011] Obtain unit, for obtaining the unit operation data of the thermal power generating unit, wherein the unit operation data includes a plurality of data information, wherein each data information includes the unit load, the main steam flow, the main steam temperature and the main steam pressure corresponding to the same time point;

[0012] The data information with the unit load less than the target load is deleted in the unit operation data based on the unit load, to obtain first screening data, wherein the first screening data is used to represent the data after the data information with abnormal load during the unit operation is screened out in the unit operation data;

[0013] In the first screening data, each data information is judged based on the main steam flow, the main steam temperature and the main steam pressure based on a preset algorithm, and the data information meeting the steady state condition is screened out to obtain second screening data, wherein the preset algorithm at least includes the front point value method, and the front point value method is used to represent that when the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady state condition in the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged.

[0014] Thirdly, the embodiments of the present application provide a storage medium, which includes a stored program, wherein when the program runs, the device where the storage medium is located executes the steady state data screening method of the terminal device for the thermal power generating unit of the first aspect.

[0015] In a fourth aspect, embodiments of the present application provide a device for screening steady-state data of a thermal power generating unit, the device comprising a storage medium; and one or more processors, the storage medium being coupled to the processors, the processors being configured to execute program instructions stored in the storage medium; the program instructions, when executed, implementing the method for screening steady-state data of a thermal power generating unit of the terminal device according to the first aspect.

[0016] In a fifth aspect, embodiments of the present application further provide a computer program product comprising a computer program, the computer program, when executed by a processor, implementing the steps of the method for screening steady-state data of a thermal power generating unit according to any one of the first aspect.

[0017] By means of the above technical solutions, the technical solutions provided by the present application have at least the following advantages:

[0018] The application provides a steady-state data screening method and device for a thermal power generating unit. The application can first acquire unit operation data of the thermal power generating unit, wherein the unit operation data comprises a plurality of data information; wherein each piece of data information comprises unit load, main steam flow, main steam temperature and main steam pressure corresponding to the same time point; then, based on the unit load, data information with unit load less than target load is deleted from the unit operation data to obtain first screening data; wherein the first screening data is used to represent data after data information with abnormal load during unit operation is screened out from the unit operation data; finally, in the first screening data, each piece of data information is judged based on main steam flow, main steam temperature and main steam pressure based on a preset algorithm, and data information meeting steady-state conditions is screened out to obtain second screening data; wherein the preset algorithm at least comprises a front point value method, and the front point value method is used to represent that when the main steam flow, main steam temperature and main steam pressure of the current data information meet the steady-state condition in the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged, thereby realizing the steady-state data screening function of the thermal power generating unit. Compared with the prior art, the method of the application can quickly identify and eliminate data information when the unit load is abnormal, reduce the workload of manual screening, improve the data screening efficiency, and realize the effect of faster steady-state data screening. At the same time, by combining the front point value method, the steady-state data can be further screened out more efficiently, avoiding the tediousness and time-consuming of manual point-by-point screening in the prior art. Moreover, the method of the application can more accurately identify the steady-state operation data of the unit through comprehensive judgment of multiple conditions (including the relative deviation of the unit load, the main steam flow, the main steam temperature and the main steam pressure), compared with the prior art which only screens data according to a single parameter or a simple method, the method can effectively avoid misjudgment caused by fluctuation of a single parameter, improve the accuracy and reliability of the screened data, and provide more accurate data support for subsequent energy efficiency evaluation and energy consumption diagnosis. Moreover, since the method can screen the steady-state data of the thermal power generating unit based on the unit load, the main steam flow, the main steam temperature and the main steam pressure during implementation, it can be adapted to any unit, and has better universality compared with the prior art. In addition, the application can automatically run based on the machine during execution, which can not only save the manpower problem caused by manual screening, but also improve the reliability of the screening process, and can realize real-time online screening of the steady-state data of the thermal power generating unit during execution, helping the power plant staff to timely understand the real operation state of the unit, and through real-time monitoring of the unit operation data and quick screening of the steady-state data, the staff can timely find problems and take measures, thereby improving the stability and reliability of the unit operation.

[0019] The above description is only a summary of the technical solutions of the present application. In order to enable one skilled in the art to better understand the technical means of the present application, the present application can be implemented according to the content of the description, and in order to enable the above and other purposes, characteristics and advantages of the present application to be more apparent and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0020] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when read in conjunction with the accompanying drawings, in which several embodiments of the present application are shown by way of example. In the drawings, the same or corresponding parts are referred to by the same or corresponding reference numerals, and in which:

[0021] Figure 1 A flow chart of a steady-state data screening method for a thermal power generating unit is shown according to an embodiment of the present application;

[0022] Figure 2 A block diagram of a steady-state data screening device for a thermal power generating unit is shown according to an embodiment of the present application;

[0023] Figure 3 A block diagram of another steady-state data screening device for a thermal power generating unit is shown according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] The exemplary embodiments of the present application will be described more fully hereinafter with reference to the accompanying drawings, in which several embodiments of the present application are shown. It should be understood that the present application can be embodied in many forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0025] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in the present application should be understood as their usual meanings understood by those skilled in the art to which the present application belongs.

[0026] An embodiment of the present application provides a steady-state data screening method for a thermal power generating unit, specifically as shown in the figure, the method comprises: Figure 1

[0027] 101, obtaining unit operation data of a thermal power generating unit.

[0028] The unit operation data comprises a plurality of data information, and each data information comprises unit load, main steam flow, main steam temperature and main steam pressure corresponding to the same time point.

[0029] ​In this embodiment, unit operating data can be obtained from the thermal power unit's data acquisition system. This data covers the unit's operating status at different points in time, including key parameters such as unit load, main steam flow rate, main steam temperature, and main steam pressure. The main steam flow rate refers to the mass flow rate of high-temperature, high-pressure steam entering the turbine through the main steam valve, measured in tons per hour (t / h). It is a core parameter reflecting the turbine's operating status and directly affects the unit's output efficiency. Measurement methods include direct instrument detection or indirect calculation through condensate flow rate and thermodynamic relationships, with the need for comprehensive correction by adding high-pressure bypass flow rate. The main steam temperature can be understood as the temperature of the main steam at the turbine inlet (unit: °C). As a key parameter of steam state, its stability determines the unit's safety and economy: excessively high temperatures damage equipment, while excessively low temperatures reduce thermal efficiency. The control objective is to maintain the temperature within the allowable range, protect the superheater tube walls, and reduce heat loss. The main steam pressure refers to the steam pressure before the automatic main steam valve at the turbine inlet (unit: MPa). For multiple pipelines, the arithmetic mean is taken. This parameter is a core indicator for the coordinated operation of the boiler and turbine: excessive pressure increases the stress risk on pressure-bearing components, while excessively low pressure affects power generation efficiency. The fuel control system regulates and maintains a balance between load demand and safe operation. Specifically, multiple sensors installed on the thermal power unit can collect data on these parameters in real time and store it in a database for subsequent processing.

[0030] 102. Based on the unit load, delete data information where the unit load is less than the target load from the unit operation data to obtain the first filtered data.

[0031] The first screening data is used to characterize the data after filtering out data information on abnormal load during unit operation from the unit operation data.

[0032] After acquiring the unit operation data, since not all of this data meets the requirements, this step requires preliminary screening of the collected unit operation data. Specifically, data where the unit load is less than the target load (e.g., 1MW) can be removed. This is because when the unit load is too low, the unit may be in startup, shutdown, or other abnormal operating states, and data in these states is meaningless for steady-state analysis. For example, the data processing system will read the unit load value in each data entry; if the value is less than 1MW, this data entry will be deleted from the dataset, resulting in the first filtered data.

[0033] 103. In the first filtered data, each piece of data is judged based on the main steam flow rate, main steam temperature and main steam pressure according to the preset algorithm, and the data that meets the steady-state conditions is filtered out to obtain the second filtered data.

[0034] The preset algorithm at least comprises a previous point value method, and the previous point value method is used to represent that when the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady state condition in the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged.

[0035] Based on the foregoing steps, first screening data can be obtained, which is data when the unit load is abnormal. On this basis, each piece of data information can be further analyzed by using a preset algorithm. The core of the preset algorithm is a previous point value method, which judges whether the current data information meets the steady state condition according to the relative deviation of the main steam flow, the main steam temperature and the main steam pressure. Specifically, if the change amplitudes of the main steam flow, the main steam temperature and the main steam pressure of the current data information are all small, it can be considered that the data information meets the steady state condition, should be retained, and the next data information in the time sequence is continued to be judged. For example, based on the method of the embodiment, each piece of data information is checked in the time sequence, and the data information meeting the steady state condition is added to the second screening data, so that the second screening data meeting the steady state condition is finally obtained.

[0036] The application provides a steady-state data screening method for a thermal power generating unit. The method can first acquire unit operation data of the thermal power generating unit, wherein the unit operation data comprises a plurality of data information; each piece of data information comprises unit load, main steam flow, main steam temperature and main steam pressure corresponding to the same time point; then, based on the unit load, data information with unit load less than a target load is deleted from the unit operation data to obtain first screening data; the first screening data is used to represent data after data information with abnormal unit load during unit operation is screened out; finally, based on a preset algorithm, the main steam flow, the main steam temperature and the main steam pressure of each piece of data information in the first screening data are judged, and data information meeting steady-state conditions is screened out to obtain second screening data; the preset algorithm at least comprises a front point value method, which is used to represent that when the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady-state conditions in the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged, so as to realize the steady-state data screening function of the thermal power generating unit. Compared with the prior art, the method of the application embodiment can quickly identify and eliminate data information when the unit load is abnormal, reduce the workload of manual screening, improve the data screening efficiency, and realize the effect of faster steady-state data screening. At the same time, by combining the front point value method, the steady-state data can be further screened out more efficiently, avoiding the tediousness and time-consuming of manual point-by-point screening in the prior art. Moreover, the method of the application embodiment can more accurately identify the steady-state operation data of the unit by comprehensive judgment of multiple conditions (including the relative deviations of the unit load, the main steam flow, the main steam temperature and the main steam pressure), compared with the prior art which only screens data according to a single parameter or a simple method, the method can effectively avoid misjudgment caused by fluctuations of a single parameter, improve the accuracy and reliability of the screened data, and provide more accurate data support for subsequent energy efficiency evaluation and energy consumption diagnosis. Moreover, since the method can screen the steady-state data of the thermal power generating unit based on the unit load, the main steam flow, the main steam temperature and the main steam pressure during implementation, it can be adapted to any unit, and has better universality compared with the prior art. In addition, the application embodiment can automatically run based on the machine during execution, which can not only save the manpower problem caused by manual screening, but also improve the reliability of the screening process, and can realize real-time online screening of the steady-state data of the thermal power generating unit during execution, helping the power plant staff to timely understand the real operation state of the unit, and through real-time monitoring of the unit operation data and quick screening of the steady-state data, the staff can timely find problems and take measures, improving the stability and reliability of the unit operation.

[0037] As a further description and refinement of the above embodiments, in some embodiments, the aforementioned embodiment step "103, judging each piece of data information based on the preset algorithm based on the main steam flow, the main steam temperature, and the main steam pressure, and screening out the data information meeting the steady state condition to obtain the second screening data" comprises:

[0038] S31, obtaining the running time length of the thermal power generating unit, and determining whether the running time length exceeds a steady state time length, wherein the steady state time length is used to represent a time threshold value of the thermal power generating unit being in a preliminary stable state; and the steady state time length is determined based on a unit rated load, a unit service life, an operating environment temperature, and an operating pressure of the thermal power generating unit;

[0039] S32, when it is determined that the running time length exceeds the steady state time length, judging each piece of data information based on the main steam flow, the main steam temperature, and the main steam pressure based on a forward point value method, and when the main steam flow, the main steam temperature, and the main steam pressure of the current data information meet the steady state condition, retaining the current data information, and judging the next data information in time sequence to obtain the second screening data.

[0040] In step S1, first, the running time length x of the thermal power generating unit needs to be obtained. Specifically, this can be achieved by monitoring the operating state of the unit, and recording the time length from the start of the unit to the current time, so as to obtain the running time length x. Then, it is determined whether the running time length exceeds a steady state time length. Specifically, the obtained running time length x can be compared with a preset steady state time length (for example, 10 minutes). This steady state time length is determined according to the rated load, service life, operating environment temperature, and operating pressure of the thermal power generating unit, and is used to represent the time required for the thermal power generating unit to reach a preliminary stable state.

[0041] In step S32, based on the judgment result of step S31, if it is determined that the running time length exceeds the steady state time length, that is, the running time length x exceeds 10 minutes, it is considered that the thermal power generating unit has sufficient time to reach a stable operating state. Then, the steady state data can be screened based on the forward point value method, that is, in the case where the running time length exceeds the steady state time length, the forward point value method is used to judge each piece of data information.

[0042] Specifically, it is determined whether the current data information meets the steady state condition, which can be checking whether the main steam flow, the main steam temperature, and the main steam pressure of the current data information meet the steady state condition. That is, it is analyzed whether the changes of the three parameters meet the steady state condition. If the current data information meets the steady state condition, it is retained and added to the second screening data, and then the same judgment is continued for the next data information in time sequence, until all data information is processed, and finally the second screening data, that is, the data set meeting the steady state condition, is obtained.

[0043] By considering the running time length of the thermal power generating unit and comparing it with the steady state time length, it can be more accurately judged whether the unit has reached a stable running state. Only when the running time length exceeds the steady state time length, it is considered that the unit is likely to enter the steady state, so that data screening is carried out on this basis, which can reduce the misjudgment caused by the unit not reaching the stable state, and improve the accuracy of the screened steady state data. At the same time, the introduction of the judgment of the steady state time length makes the data screening process more targeted. For the data information whose running time length exceeds the steady state time length, the front point value method is used for screening, which can more effectively identify the data of the unit in the stable running stage. These data can more truly reflect the performance and state of the unit in normal operation, and provide a more valuable data basis for subsequent analysis and evaluation. In this way, through the method of the embodiment, it can analyze the parameters of the unit in the steady state running for subsequent analysis, find out the key factors affecting the energy efficiency, provide the basis for taking targeted energy-saving measures, help to improve the energy utilization efficiency of the thermal power generating unit, reduce energy consumption and production cost, and improve the economy and market competitiveness of the thermal power generating unit.

[0044] As a further description and refinement of the above-mentioned embodiments, in some embodiments, the preset algorithm in the foregoing embodiments further includes a rear point value method. Based on this, after the step "S31, the running time length of the thermal power generating unit is obtained, and it is determined whether the running time length exceeds the steady state time length" in the foregoing embodiments, the method further includes:

[0045] S33, when it is determined that the running time length does not exceed the steady state time length, each data information is judged based on the main steam flow, the main steam temperature and the main steam pressure based on the rear point value method, and in the first data, if it is determined that the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady state condition, the current data information and all data information within the same running time length thereafter are retained, and the data information after the running time length is directly jumped to continue to be judged, so as to obtain the second screened data.

[0046] Based on the description of the foregoing embodiments, after the step S31 is judged, there is another case that the running time length does not exceed the steady state time length, that is, after obtaining the running time length x of the thermal power generating unit and determining that x does not exceed the steady state time length (10 minutes), it is considered that the thermal power generating unit has not reached the preliminary stable state. In this case, the running of the unit may still be in the fluctuation or adjustment stage, and the front point value method may not be able to accurately screen out the steady state data at this time, because the front point value method focuses on point-by-point judgment, and the current running time length is short, so a method that can take into account the stability of subsequent data is needed.

[0047] In the embodiment, the data is screened based on the post-point value method. That is, the post-point value method is used to judge each piece of data information, wherein the core of the post-point value method is that when it is found that a piece of data information meets the steady state condition, not only the data information is retained, but also all data information after the data information is retained, which is equal to the running time x. For example, if the current running time x is 5 minutes, when it is judged that a piece of data meets the steady state condition, the data and all data within 5 minutes after the data are retained, and then the data after the 5 minutes is directly jumped to continue to be judged. The specific steps are as follows:

[0048] (1) It is judged whether the current data meets the steady state condition. It is checked whether the main steam flow, temperature and pressure of the current data information meet the steady state condition (that is, whether the variation amplitudes of the three parameters meet the requirements of the steady state condition).

[0049] (2) If it meets, the current data and all data within x time length after the current data are retained. For example, the running time is 8 minutes, the current data meets the steady state condition, and then the data and all data within 8 minutes after the data are retained.

[0050] (3) The subsequent data is jumped to be judged. At this time, since it is determined in step (2) that all data within x time length after the data meets the steady state condition, the data after x time length is directly jumped to continue to be judged, so that repeated judgment on the data within the retained data range is avoided, and the screening efficiency is improved.

[0051] (4) Through the above post-point value method, the data meeting the steady state condition and the subsequent related data are integrated as the second screening data, which is used for subsequent analysis.

[0052] Based on the method of the embodiment, when the running time is short, the post-point value method can effectively avoid misjudgment caused by insufficient data, and adapt to the characteristics of short-time running data. The method can effectively screen the steady state data of the unit within a short running time, and avoid inaccurate judgment caused by incomplete data. In addition, the post-point value method of the embodiment can reduce repeated judgment, improve the screening efficiency, especially in the case of short running time and relatively small amount of data, the steady state data section can be quickly determined, unnecessary data processing steps are reduced, and the overall screening efficiency is improved.

[0053] As a further description and refinement of the above embodiment, in some embodiments, in the foregoing embodiment, the steady state condition includes a first condition, a second condition, and a third condition, wherein the first condition is used to represent that the variation of the main steam flow is less than a preset flow variation threshold; the second condition is used to represent that the variation of the main steam temperature is less than a preset temperature threshold; and the third condition is used to represent that the variation of the main steam pressure is less than a preset pressure variation threshold.

[0054] In the embodiment, the steady state condition is specifically refined into three different conditions, namely a first condition, a second condition and a third condition. Specifically as follows:

[0055] The first condition (main steam flow) is mainly to determine the preset flow variation threshold of the main steam flow, for example, set to be less than 10% of the relative deviation of the main steam flow. The calculation formula of the relative deviation is relative deviation = actual value - expected value x 100%. The expected value can be determined according to the design parameters or historical operation data of the thermal power unit.

[0056] The second condition (main steam temperature) is used to set the preset temperature variation threshold of the main steam temperature.

[0057] The third condition (main steam pressure) is used to set the preset pressure variation threshold of the main steam pressure.

[0058] Data acquisition and preprocessing: real-time acquisition of main steam flow, main steam temperature and main steam pressure data of the thermal power unit through sensors, and transmission to the data processing system.

[0059] After determining the three conditions, the process of judging the steady state condition is actually to analyze each data information collected to determine whether it meets the three steady state conditions.

[0060] For example, to judge the main steam flow, calculate the relative deviation of the main steam flow of the current data information, if it is less than 10%, it meets the first condition, and so on to determine whether the data information meets the second condition and the third condition.

[0061] When the above three conditions are met at the same time, it is determined that the data information meets the steady state condition, indicating that the thermal power unit is in a steady state running state at that moment. Otherwise, it is determined as non-steady state data.

[0062] Further, in the embodiment, data screening and recording can also be performed. For retaining steady state data, data information meeting the steady state condition is screened out to form second screening data for subsequent analysis and processing. Data information not meeting the steady state condition is marked or excluded so that subsequent analysis can focus on steady state running data.

[0063] It should be noted that in the embodiment, the types of thresholds involved in the first condition, the second condition and the third condition can be selected based on actual conditions, for example, as shown in the example, it can be a relative deviation threshold, so in this case, the current data information meets the steady state condition under the three conditions. The comparison process is also a comparison between the relative deviation value and the relative deviation threshold. Of course, in actual application, other ways can also be used as the threshold, for example, the average value or the variance value can also be used. In the embodiment, it is not limited, and can be selected as needed.

[0064] By setting three steady-state conditions, the steady-state operation data of the thermal power generating unit can be comprehensively and accurately identified, thereby providing reliable data support for subsequent energy efficiency evaluation, fault diagnosis, etc.

[0065] As further description and refinement of the above embodiments, in some embodiments, in the aforementioned embodiments, the first condition comprises a relative deviation of the main steam flow being less than 1%; the second condition comprises a relative deviation of the main steam temperature being less than 5℃; and the third condition comprises a relative deviation of the main steam pressure being less than 1%.

[0066] In the present embodiment, data collection is first performed on the above three parameters:

[0067] (1) Main steam flow data collection: A flow sensor is installed on the main steam pipe of the thermal power generating unit to monitor the main steam flow in real time and transmit the data to the unit's data acquisition and monitoring system (SCADA). The system records the main steam flow data at a preset time interval (e.g., 1 second).

[0068] (2) Main steam temperature data collection: A temperature sensor is installed on the main steam pipe to measure the main steam temperature in real time. The sensor converts the temperature signal into an electrical signal and transmits it to the data acquisition system. The system records the temperature data at the same time interval.

[0069] (3) Main steam pressure data collection: A pressure sensor is installed on the main steam pipe to measure the main steam pressure in real time. The sensor converts the pressure value into an electrical signal, and the data acquisition system records the pressure data at a set interval.

[0070] Then, relative deviation calculation is performed based on the collection results:

[0071] (1) Main steam flow relative deviation calculation: The data processing system obtains the actual value and the expected value (the expected value can be determined according to the unit design parameters, operating conditions, or historical operation data) of the main steam flow at the current time from the database. Calculate the relative deviation, if the relative deviation is less than 1%, then the first condition is met. The formula for calculating the relative deviation is:

[0072]

[0073] (2) Main steam temperature relative deviation calculation: Obtain the actual value and the expected value (the expected value is usually determined based on the unit design standard or operating experience) of the main steam temperature at the current time. Calculate the relative deviation, if the absolute value of the relative deviation is less than 5%, then the second condition is met.

[0074] (3) Main steam pressure relative deviation calculation: obtain the actual value and the expected value (the expected value is determined according to the design pressure of the unit or the operation requirement) of the main steam pressure at the current time. Calculate the relative deviation. If the relative deviation is less than 1%, the third condition is met.

[0075] After determining the relative deviations of the three parameters and analyzing whether the corresponding conditions are met, a comprehensive judgment is made. That is, the main steam flow, temperature and pressure relative deviations of each data information are comprehensively judged. Only when the three relative deviations simultaneously meet the respective conditions, it is considered that the data information meets the steady state condition.

[0076] Finally, data marking and screening are performed. In this embodiment, the data information meeting the steady state condition can be marked as steady state data and screened out to form the second screening data. These data will be used for subsequent analysis and processing, such as energy efficiency evaluation, fault diagnosis, etc.

[0077] Specific examples are as follows:

[0078] Suppose the data information A of a certain thermal power unit at a certain time is as follows:

[0079] Among them, the expected value: main steam flow: 1000 cubic meters / hour; main steam temperature: 550℃; main steam pressure: 20 megapascals.

[0080] In data information A, the main steam flow is 1005 cubic meters / hour; the main steam temperature is 548℃; and the main steam pressure is 20.2 megapascals. Next, the relative deviation formula is calculated as follows:

[0081] Among them, the main steam flow relative deviation is:

[0082]

[0083] Since 0.5% is less than 1%, the first condition is met. In this way, the main steam temperature relative deviation is determined to be -0.36%, the absolute value of which is less than 5%, meeting the second condition. The main steam pressure relative deviation is 1%, which is equal to 1% and within the allowable range, meeting the third condition. Since the three conditions are met, the data information A at this time meets the steady state condition and is retained in the second screening data.

[0084] As a further description and refinement of the above embodiment, in some embodiments, before the step "101, obtaining the unit operation data of the thermal power unit" in the foregoing embodiment, the method further comprises:

[0085] According to a target time step, at each time corresponding to the target time step, main steam flow, main steam temperature, main steam pressure and unit load of the thermal power unit are collected from preset sensors respectively to obtain data information corresponding to each time, and statistics are performed to obtain unit operation data formed by the data information of multiple continuous times.

[0086] In the embodiment, the specific implementation process is as follows:

[0087] First, data collection preparation is performed. Specifically, according to the operation characteristics and monitoring requirements of the thermal power unit, a suitable target time step is set, for example, data is collected once every 10 seconds. Then, sensor calibration and arrangement are performed, in which it is necessary to ensure that various sensors (such as main steam flow, temperature, pressure sensors and load sensors) installed on the thermal power unit are accurately calibrated and work normally.

[0088] Then, data collection execution is performed. Specifically, data collection can be started according to the target time step, that is, the data collection system triggers the collection cycle once every 10 seconds according to the preset target time step. In addition, at each collection time, the instantaneous values of main steam flow, temperature, pressure and unit load are synchronously obtained from the sensors.

[0089] Finally, the collected data needs to be stored and preliminarily processed. The collected data is first temporarily stored in a cache storage area to ensure data integrity. At the same time, preliminary anomaly detection can be performed on the temporarily stored data to eliminate obviously incorrect or missing data points. After that, the preliminarily processed data is stored in a database, and each record contains a time stamp and parameter values.

[0090] In addition, the collected data also needs to be statistically processed and integrated.

[0091] (1) Data statistics: the collected data is statistically processed, such as calculating the average value, maximum value and minimum value of each parameter in a specific time interval, to reflect the change trend of the unit operation state.

[0092] (2) Data integration: the parameter data in the same time step is integrated into a complete operation data record, which contains time stamp, main steam flow, temperature, pressure and load information.

[0093] (3) Data storage update: the integrated operation data is appended to the historical database to form a continuously updated unit operation data set, which provides a basis for subsequent screening and analysis.

[0094] Based on the method of the embodiment, the above-mentioned data collection method can ensure that the collected data accurately reflects the operation state of the thermal power unit, lays a good foundation for subsequent analysis, and improves the operation efficiency and economy.

[0095] Further, as the implementation of the method shown in the above embodiments Figure 1 and the method shown in the above embodiments, another embodiment of the present application further provides a steady-state data screening device of a thermal power generating unit. The steady-state data screening device embodiment of the thermal power generating unit corresponds to the foregoing method embodiment, for the sake of reading, the steady-state data screening device embodiment of the thermal power generating unit will not repeat the details of the foregoing method embodiment one by one, but it should be clear that the device in the present embodiment can correspond to the implementation of all the contents in the foregoing method embodiment. Specifically, as shown in the Figure 2 , the steady-state data screening device of the thermal power generating unit comprises:

[0096] The acquisition unit 21 can be used to acquire unit operation data of the thermal power generating unit, wherein the unit operation data comprises a plurality of data information; wherein each data information comprises unit load, main steam flow, main steam temperature and main steam pressure corresponding to the same time point;

[0097] The elimination unit 22 can be used to delete data information with unit load less than the target load in the unit operation data based on the unit load acquired by the acquisition unit 21, to obtain first screening data; wherein the first screening data can be used to represent data after data information with abnormal load during unit operation is screened out in the unit operation data;

[0098] The screening unit 23 can be used to judge the main steam flow, the main steam temperature and the main steam pressure of each data information based on a preset algorithm in the first screening data obtained by the elimination unit 22, and screen out data information meeting the steady-state condition to obtain second screening data; wherein the preset algorithm at least comprises a front point value method, the front point value method can be used to represent that when the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady-state condition in the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged.

[0099] Further, as shown in the Figure 3 , the screening unit 23 comprises:

[0100] The acquisition module 231 can be used to acquire the running time of the thermal power generating unit, and determine whether the running time exceeds the steady-state time, wherein the steady-state time can be used to represent a time threshold value when the thermal power generating unit is preliminarily stable; the steady-state time is determined based on the unit rated load, the service life of the unit, the operating environment temperature and the operating pressure of the thermal power generating unit;

[0101] The first screening module 232 can be used to determine the runtime length obtained by the acquisition module 231 exceeds the steady state length, and then judge each piece of data information based on the main steam flow, the main steam temperature and the main steam pressure based on the forward point taking method. When the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady state condition, the current data information is retained, and the next data information in time sequence is judged to obtain the second screening data.

[0102] Further, as shown in Figure 3 The preset algorithm further includes a backward point taking method.

[0103] The screening unit 23 further includes:

[0104] The second screening module 233 can be used to determine the runtime length obtained by the acquisition module 231 does not exceed the steady state length, and then judge each piece of data information based on the main steam flow, the main steam temperature and the main steam pressure based on the backward point taking method. In the first data, if it is determined that the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady state condition, the current data information and all data information within the same runtime length thereafter are retained, and the data information after the runtime length is directly jumped to continue to be judged, so as to obtain the second screening data.

[0105] Further, as shown in Figure 3 The steady state condition includes a first condition, a second condition and a third condition. The first condition can be used to represent that the change of the main steam flow is less than a preset flow change threshold value. The second condition can be used to represent that the change of the main steam temperature is less than a preset temperature threshold value. The third condition can be used to represent that the change of the main steam pressure is less than a preset pressure change threshold value.

[0106] Further, as shown in Figure 3 The first condition includes that the relative deviation of the main steam flow is less than 1%. The second condition includes that the relative deviation of the main steam temperature is less than 5℃. The third condition includes that the relative deviation of the main steam pressure is less than 1%.

[0107] Further, as shown in Figure 3 The device further includes:

[0108] The acquisition unit 24 can be used to collect the main steam flow, the main steam temperature, the main steam pressure and the unit load of the thermal power generating unit from the preset sensor at each target time step, obtain the data information corresponding to each time, and count to obtain the unit operation data formed by the data information of multiple continuous time points, so that the acquisition unit 21 acquires.

[0109] The embodiment of the present application provides a kind of steady-state data screening method and device of thermal power generating unit, the embodiment of the present application can first obtain the unit operation data of thermal power generating unit, wherein the unit operation data includes multiple data information;Wherein each data information includes the unit load corresponding to the same time, main steam flow, main steam temperature and main steam pressure;Then, based on the unit load, the data information of unit load less than target load is deleted in unit operation data, and first screening data is obtained;Wherein the first screening data is used to represent the data after the data information of abnormal load during unit operation is screened out in unit operation data;Finally, in the first screening data, each data information is judged based on main steam flow, main steam temperature, main steam pressure based on pre-set algorithm, and the data information meeting steady-state condition is screened out, and second screening data is obtained;Wherein the pre-set algorithm at least includes front point value method, and the front point value method is used to represent that when the main steam flow, main steam temperature and main steam pressure of current data information meet steady-state condition according to the time sequence of data information, the current data information is retained, and the next data information in time sequence is judged, so as to realize the steady-state data screening function of thermal power generating unit.Compared with prior art, the method of the embodiment of the present application can quickly identify and reject data information when unit load is abnormal, reduce the workload of manual screening, can improve the data screening efficiency, realize the effect of faster steady-state data screening.At the same time, by combining the front point value method, the steady-state data can be more efficiently screened out by further screening the data information, which avoids the tediousness and time-consuming of manual point-by-point screening in prior art.And, the method of the embodiment of the present application can more accurately identify the steady-state operation data of unit by comprehensive judgment of multiple conditions (which includes the relative deviation of unit load, main steam flow, main steam temperature and main steam pressure), compared with prior art, which only depends on single parameter or simple method to screen data, the method can effectively avoid the misjudgment caused by single parameter fluctuation, improve the accuracy and reliability of screening data, and provide more accurate data support for subsequent energy efficiency evaluation and energy consumption diagnosis.And, since the method can screen the steady-state data of thermal power generating unit based on unit load, main steam flow, main steam temperature and main steam pressure during implementation, it can adapt to any unit, and has better universality compared with prior art.In addition, the embodiment of the present application can run automatically based on machine during execution, which can not only save the manpower problem caused by manual screening, but also improve the reliability in screening process, and can realize real-time online screening of steady-state data of thermal power generating unit during execution, help power plant staff to understand the real operation state of unit in time, through real-time monitoring of unit operation data and quickly screening out steady-state data, staff can find problems in time and take measures, improve the stability and reliability of unit operation.

[0110] The embodiment of the present application provides a storage medium, the storage medium comprises a stored program, wherein the device where the storage medium is located executes the steady-state data screening method of the thermal power generating unit when the program runs. The storage medium can include a non-permanent memory in a computer readable medium, a random access memory (RAM) and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM), and the memory includes at least one memory chip.

[0111] The embodiment of the present application also provides a steady-state data screening device of a thermal power generating unit, the device comprises a storage medium; and one or more processors, the storage medium is coupled with the processor, and the processor is configured to execute program instructions stored in the storage medium; the program instructions execute the steady-state data screening method of the thermal power generating unit as described above.

[0112] The embodiment of the present application provides a device, the device comprises a processor, a memory and a program stored in the memory and executable on the processor, and the processor executes the program to implement the following steps: obtaining unit operation data of a thermal power generating unit, wherein the unit operation data comprises a plurality of data information; wherein each data information comprises unit load, main steam flow, main steam temperature and main steam pressure corresponding to the same time point; based on the unit load, deleting data information with unit load less than a target load in the unit operation data to obtain first screening data; wherein the first screening data is used to represent data after data information with abnormal load during unit operation is screened out in the unit operation data; in the first screening data, judging each data information based on the main steam flow, the main steam temperature and the main steam pressure based on a preset algorithm, and screening out data information meeting a steady-state condition to obtain second screening data; wherein the preset algorithm at least comprises a previous point value method, and the previous point value method is used to represent that when the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady-state condition in the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged.

[0113] Further, the judging each data information based on the main steam flow, the main steam temperature and the main steam pressure based on the preset algorithm, and screening out data information meeting a steady-state condition to obtain second screening data comprises:

[0114] obtaining a running duration of the thermal power generating unit, and determining whether the running duration exceeds a steady-state duration, wherein the steady-state duration is used to represent a time threshold value when the thermal power generating unit is preliminarily stable; and the steady-state duration is determined based on a unit rated load of the thermal power generating unit, a service life of the unit, an operating environment temperature and an operating pressure.

[0115] When it is determined that the running time length exceeds the steady state time length, each piece of data information is judged based on the main steam flow, the main steam temperature and the main steam pressure based on the forward point taking method, and when the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady state condition, the current data information is retained, and the next data information in time sequence is judged to obtain second screening data.

[0116] Further, the preset algorithm further includes a backward point taking method.

[0117] After the running time length of the thermal power generating unit is acquired and it is determined whether the running time length exceeds the steady state time length, the method further includes:

[0118] When it is determined that the running time length does not exceed the steady state time length, each piece of data information is judged based on the main steam flow, the main steam temperature and the main steam pressure based on the backward point taking method, and in the first data, when it is determined that the main steam flow, the main steam temperature and the main steam pressure of the current data information meet the steady state condition, the current data information and all data information in the same running time length thereafter are retained, and the data information after the running time length is directly jumped to continue to be judged to obtain second screening data.

[0119] Further, the steady state condition includes a first condition, a second condition and a third condition, wherein the first condition is used to represent that the change of the main steam flow is less than a preset flow change threshold value; the second condition is used to represent that the change of the main steam temperature is less than a preset temperature threshold value; and the third condition is used to represent that the change of the main steam pressure is less than a preset pressure change threshold value.

[0120] Further, the first condition includes that the relative deviation of the main steam flow is less than 1%; the second condition includes that the relative deviation of the main steam temperature is less than 5℃; and the third condition includes that the relative deviation of the main steam pressure is less than 1%.

[0121] Further, before the unit operation data of the thermal power generating unit is acquired, the method further includes:

[0122] According to the target time step, the main steam flow, the main steam temperature, the main steam pressure and the unit load of the thermal power generating unit are respectively collected from the preset sensor at the time corresponding to each target time step to obtain data information corresponding to each time, and the data information of multiple continuous times is counted to obtain the unit operation data formed by the data information of multiple continuous times.

[0123] The embodiment of the present application further provides a computer program product, which is suitable for executing program codes for initializing the method steps when executed on a data processing device: obtaining unit operation data of a thermal power generating unit, wherein the unit operation data comprises a plurality of data information, wherein each data information comprises unit load, main steam flow, main steam temperature and main steam pressure corresponding to the same time point; deleting, based on the unit load, data information with unit load less than a target load in the unit operation data to obtain first screening data, wherein the first screening data is used for representing data after data information with abnormal unit load during unit operation is screened out in the unit operation data; and in the first screening data, judging, based on a preset algorithm, each data information based on the main steam flow, the main steam temperature and the main steam pressure, and screening out data information meeting steady state conditions to obtain second screening data, wherein the preset algorithm at least comprises a previous point value method, and the previous point value method is used for representing that when the main steam flow, the main steam temperature and the main steam pressure of current data information meet the steady state conditions in the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged.

[0124] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the embodiments of the present application can adopt a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present application can adopt a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0125] The embodiments of the present application are described with reference to flowcharts and / or block diagrams according to the methods, devices (systems) and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device implemented in the flowcharts and / or block diagrams. Figure 1 The device for implementing the functions specified in one flow or multiple flows and / or one block or multiple blocks. Figure 1 The device for implementing the functions specified in one flow or multiple flows and / or one block or multiple blocks.

[0126] These computer program instructions can also be stored in a computer readable storage medium capable of guiding the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufactured product including instruction devices, which implement the flowcharts and / or block diagrams. Figure 1one or more processes and / or blocks Figure 1 the function(s) specified in the block or blocks.

[0127] These computer program instructions can also be loaded into computer or other programmable data processing devices to cause a series of operational steps to be performed on the computer or other programmable devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable devices provide steps for implementing the functions of the flow Figure 1 one or more processes and / or blocks Figure 1 Figure 1 the function(s) specified in the block or blocks.

[0128] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0129] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the computer stores information such as computer program instructions. Memory is an example of computer readable media.

[0130] Computer readable media includes permanent and non-permanent, moveable and non-moveable media that can be implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile discs (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that is accessible to a computing device. According to the definition provided herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0131] It is also important to note that the terms "comprises", "comprising", or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0132] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems or computer program products. Accordingly, embodiments of the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code thereon for use by or in connection with an instruction execution system.

[0133] The above merely provides embodiments of the present application and is not intended to limit the present application. The present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for screening steady-state data of thermal power units, characterized in that, include: Acquire unit operation data of thermal power units, wherein the unit operation data includes multiple data information; wherein each data information includes the unit load, main steam flow, main steam temperature and main steam pressure at the same time; Based on the unit load, data information where the unit load is less than the target load is deleted from the unit operation data to obtain the first filtered data; wherein, the first filtered data is used to characterize the data after filtering out data information where the unit load is abnormal during operation from the unit operation data; In the first filtered data, each piece of data is judged based on the main steam flow rate, main steam temperature, and main steam pressure according to a preset algorithm, and the data that meets the steady-state conditions is filtered out to obtain the second filtered data; wherein, the preset algorithm includes at least the previous point value method, which is used to characterize that when the main steam flow rate, main steam temperature, and main steam pressure of the current data meet the steady-state conditions according to the time sequence of the data information, the current data information is retained, and the next data information in the time sequence is judged.

2. The method according to claim 1, characterized in that, The method involves using a preset algorithm to evaluate each piece of data based on main steam flow rate, main steam temperature, and main steam pressure, and then filtering out data that meets steady-state conditions to obtain the second set of filtered data, including: The operating time of the thermal power unit is obtained, and it is determined whether the operating time exceeds the steady-state duration, wherein the steady-state duration is used to characterize the time threshold for the thermal power unit to reach initial stability; the steady-state duration is determined based on the rated load of the thermal power unit, the service life of the unit, the ambient temperature and the operating pressure. When it is determined that the running time exceeds the steady-state time, the main steam flow, main steam temperature and main steam pressure of each data information are judged based on the previous point value method. When the main steam flow, main steam temperature and main steam pressure of the current data information meet the steady-state conditions, the current data information is retained, and the next data information in the time sequence is judged to obtain the second filtered data.

3. The method according to claim 2, characterized in that, The preset algorithm also includes the back-point value method; After obtaining the operating time of the thermal power unit and determining whether the operating time exceeds the steady-state duration, the method further includes: When it is determined that the running time does not exceed the steady-state time, the main steam flow, main steam temperature and main steam pressure of each data information are judged based on the back-point value method. In the first data, if it is determined that the main steam flow, main steam temperature and main steam pressure of the current data information meet the steady-state conditions, the current data information and all data information within the same running time are retained, and the judgment is directly skipped to the data information after the running time to obtain the second screened data.

4. The method according to any one of claims 1-3, characterized in that, The steady-state conditions include a first condition, a second condition, and a third condition, wherein the first condition is used to characterize that the change in main steam flow rate is less than a preset flow rate change threshold; the second condition is used to characterize that the change in main steam temperature is less than a preset temperature threshold; and the third condition is used to characterize that the change in main steam pressure is less than a preset pressure change threshold.

5. The method according to claim 4, characterized in that, The first condition includes a relative deviation of less than 1% in the main steam flow rate; the second condition includes a relative deviation of less than 5°C in the main steam temperature; and the third condition includes a relative deviation of less than 1% in the main steam pressure.

6. The method according to claim 1, characterized in that, Before acquiring the unit operating data of the thermal power unit, the method further includes: According to the target time step, at each time step, the main steam flow, main steam temperature, main steam pressure and unit load of the thermal power unit are collected from the preset sensors to obtain the data information corresponding to each time step, and the data information of multiple consecutive time steps is statistically analyzed to obtain the unit operation data formed by the data information of multiple consecutive time steps.

7. A steady-state data screening device for thermal power units, characterized in that, include: The acquisition unit is used to acquire the unit operation data of the thermal power unit, wherein the unit operation data includes multiple data information; wherein each data information includes the unit load, main steam flow, main steam temperature and main steam pressure at the same time. The elimination unit is used to delete data information where the unit load is less than the target load from the unit operation data based on the unit load, to obtain the first filtered data; wherein, the first filtered data is used to characterize the data after filtering out data information where the unit load is abnormal during operation from the unit operation data; The filtering unit is used to, in the first filtered data, judge each piece of data information based on the main steam flow rate, main steam temperature, and main steam pressure according to a preset algorithm, and filter out the data information that meets the steady-state conditions to obtain the second filtered data; wherein, the preset algorithm includes at least the previous point value method, which is used to characterize that, according to the time sequence of the data information, when the main steam flow rate, main steam temperature, and main steam pressure of the current data information meet the steady-state conditions, the current data information is retained, and the next data information in the time sequence is judged.

8. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, it controls the device where the storage medium is located to perform the steady-state data screening method for thermal power units as described in any one of claims 1 to 6.

9. A steady-state data screening device for thermal power units, characterized in that, The device includes a storage medium; and one or more processors, the storage medium being coupled to the processors, the processors being configured to execute program instructions stored in the storage medium; the program instructions, when executed, perform the steady-state data filtering method for thermal power units as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the steady-state data screening method for thermal power units according to any one of claims 1 to 6.

Images