Method, device, equipment, storage medium and program product for determining parameter delay

By conducting time-shift changes and statistical analysis on the historical data of thermal power units, the parameter delay range is automatically determined, which solves the problems of inefficiency and relying on manual experts in the existing technology, and realizes efficient and general parameter delay analysis.

CN114527665BActive Publication Date: 2025-02-18INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210186973.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-28
Publication Date
2025-02-18
Estimated Expiration
2042-02-28

AI Technical Summary

Technical Problem

The efficiency of obtaining the delay range of thermal power units in the prior art is inefficient, and it depends on artificial experts to conduct timing control curve analysis and prior knowledge correlation, which lacks universality and efficiency.

Method used

By obtaining the historical data of the thermal power unit, the control parameters are shifted in time according to multiple preset delay conditions, the target control parameters are obtained, and then correlation analysis and one-way variance analysis are performed to determine the range of parameter delay.

Benefits of technology

This method can automatically and efficiently determine the parameter delay range, reduce dependence on manual experts, improve efficiency, and be versatile, and is suitable for parameter delay analysis of different control processes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114527665B_ABST
    Figure CN114527665B_ABST
Patent Text Reader

Abstract

The present application relates to a method, device, equipment, storage medium and program product for determining parameter delay, which obtains historical data of thermal power units, performs time displacement changes on control parameters at each moment according to multiple preset delay conditions, obtains target control parameters at each moment under each delay condition, obtains correlation analysis results and one-way variance analysis results under each delay condition according to the target control parameters at each moment under each delay condition and the corresponding control parameters, and determines the range of parameter delay according to the correlation analysis results and one-way variance analysis results under each delay condition. The method only needs to perform statistical operations on historical data to determine the range of parameter delay, which overcomes the problem of the original method's strong reliance on the prior knowledge of experts in the field, can be used for parameter delay analysis of different control processes, has certain versatility, and does not require manual participation, thereby improving the efficiency of determining parameter delay.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a method, device, equipment, storage medium and program product for determining parameter delay. Background Art

[0002] Prediction and control related to thermal power unit systems is an important research field. When predicting and controlling each control process, multiple controlled parameters are usually used as model inputs to predict and control the control parameters. Among them, the parameter delay of the controlled parameters is a model hyperparameter, which is directly related to the control unit where the data comes from. It is a key factor in control data modeling and is directly related to the effect of modeling analysis. Therefore, it is necessary to determine the specific value or range as accurately as possible.

[0003] At present, the parameter delay in each control process is calculated by experts in the control field by comparing the time series control curves of each controlled parameter and the control parameter in the historical control process data, and then performing correlation analysis based on the prior knowledge of the changes of each parameter in the field, and finally obtaining the estimated delay range. However, the existing method of manually obtaining the parameter delay value or range is inefficient. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, equipment, storage medium and program product for determining parameter delay that can improve the efficiency of obtaining parameter delay range in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for determining a parameter delay, the method comprising:

[0006] Acquire historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0007] Performing a time displacement change on the control parameters at each moment according to a plurality of preset delay conditions to obtain a target control parameter at each moment under each delay condition;

[0008] According to the target control parameter and the corresponding control parameter at each moment under each delay condition, obtaining the correlation analysis result and the one-way variance analysis result under each delay condition;

[0009] The range of the parameter delay is determined according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions.

[0010] In one embodiment, the method further comprises:

[0011] Performing time-series superposition transformation on the control parameters at each of the moments to obtain candidate control parameters at each of the moments;

[0012] The step of performing a time shift change on the control parameters at each moment according to the preset multiple delay conditions to obtain the target control parameters at each moment under the delay conditions includes:

[0013] According to the multiple delay conditions, the candidate control parameters at each moment are respectively shifted in time to obtain the target control parameters at each moment under the delay conditions.

[0014] In one embodiment, obtaining the correlation analysis results and the one-way variance analysis results under each of the delay conditions according to the target control parameters and the corresponding control parameters at each moment under each of the delay conditions includes:

[0015] Determine a data group corresponding to each of the delay conditions according to the target control parameters at each of the delay conditions and the controlled parameters corresponding to each of the delay conditions; the data group includes the target control parameters at each of the delay conditions and the corresponding controlled parameters;

[0016] Performing correlation analysis on the data group corresponding to each of the delay conditions to obtain a correlation analysis result corresponding to each of the delay conditions;

[0017] A one-way ANOVA is performed on the data group corresponding to each of the delay conditions to obtain a one-way ANOVA result corresponding to each of the delay conditions.

[0018] In one embodiment, determining the range of the parameter delay according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions includes:

[0019] Performing linear fitting on the correlation analysis results under each of the delay conditions to obtain a correlation data curve;

[0020] Performing linear fitting on the one-way ANOVA results under each of the time-delay conditions to obtain a one-way data curve;

[0021] The range of the parameter delay is determined according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve.

[0022] In one embodiment, determining the range of the parameter delay according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve includes:

[0023] Obtaining a time difference between the first inflection point moment and the second inflection point moment;

[0024] The range of the parameter delay is determined according to the time difference and a preset threshold.

[0025] In one embodiment, determining the range of the parameter delay according to the time difference and a preset threshold value includes:

[0026] If the time difference is less than or equal to a preset threshold, the range between the first inflection point moment and the second inflection point moment is determined as the range of the parameter delay.

[0027] In one embodiment, the method further comprises:

[0028] If the time difference is greater than the preset threshold, the method returns to the step of obtaining the historical data of the thermal power unit, or executes the step of updating the delay condition and adopting the new delay condition to perform a time displacement change on the control parameters at each moment.

[0029] If the time difference is smaller than a preset threshold, the range between the first inflection point moment and the second inflection point moment is determined as the range of the parameter delay.

[0030] In a second aspect, the present application further provides a device for determining a parameter delay, the device comprising:

[0031] A first acquisition module is used to acquire historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0032] A first determination module is used to perform a time displacement change on the control parameters at each moment according to a plurality of preset delay conditions to obtain a target control parameter at each moment under each delay condition;

[0033] A second acquisition module is used to acquire the correlation analysis results and the one-way variance analysis results under each of the delay conditions according to the target control parameters and the corresponding control parameters at each moment under each of the delay conditions;

[0034] The second determination module is used to determine the range of the parameter delay according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions.

[0035] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0036] Acquire historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0037] Performing a time displacement change on the control parameters at each moment according to a plurality of preset delay conditions to obtain a target control parameter at each moment under each delay condition;

[0038] According to the target control parameter and the corresponding control parameter at each moment under each delay condition, obtaining the correlation analysis result and the one-way variance analysis result under each delay condition;

[0039] The range of the parameter delay is determined according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0041] Acquire historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0042] Performing a time displacement change on the control parameters at each moment according to a plurality of preset delay conditions to obtain a target control parameter at each moment under each delay condition;

[0043] According to the target control parameter and the corresponding control parameter at each moment under each delay condition, obtaining the correlation analysis result and the one-way variance analysis result under each delay condition;

[0044] The range of the parameter delay is determined according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions.

[0045] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which implements the following steps when executed by a processor:

[0046] Acquire historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0047] Performing a time displacement change on the control parameters at each moment according to a plurality of preset delay conditions to obtain a target control parameter at each moment under each delay condition;

[0048] According to the target control parameter and the corresponding control parameter at each moment under each delay condition, obtaining the correlation analysis result and the one-way variance analysis result under each delay condition;

[0049] The range of the parameter delay is determined according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions.

[0050] The above-mentioned parameter delay determination method, device, equipment, storage medium and program product obtain the historical data of the thermal power unit, the historical data includes the controlled parameters and control parameters corresponding to multiple moments, and the control parameters at each moment are shifted according to the preset multiple delay conditions to obtain the target control parameters at each moment under each delay condition. According to the target control parameters at each moment under each delay condition and the corresponding control parameters, the correlation analysis results and the one-way variance analysis results under each delay condition are obtained, and the range of the parameter delay is determined according to the correlation analysis results and the one-way variance analysis results under each delay condition. This method only needs to perform statistical operations on the historical data to determine the range of the parameter delay, which overcomes the problem that the original method strongly relies on the prior knowledge of domain experts, has a certain degree of versatility, can be used for parameter delay analysis of different control processes, solves the versatility problem of the delay estimation process, and does not require human participation, which improves the efficiency of determining the parameter delay. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 An application environment diagram of a method for determining parameter delay in an embodiment;

[0052] Figure 2 Schematic diagram of a flow chart of a method for determining parameter delay in one embodiment;

[0053] Figure 3 is a flow chart of a method for determining parameter delay in another embodiment;

[0054] Figure 4 is a flow chart of a method for determining parameter delay in another embodiment;

[0055] Figure 5 is a flow chart of a method for determining parameter delay in another embodiment;

[0056] Figure 6 is a flow chart of a method for determining parameter delay in another embodiment;

[0057] Figure 7 is a flow chart of a method for determining parameter delay in another embodiment;

[0058] Figure 8 is a structural block diagram of a device for determining parameter delay in one embodiment;

[0059] Fig. 9 is a structural block diagram of a device for determining parameter delay in another embodiment;

[0060] Fig.10 is a structural block diagram of a device for determining parameter delay in another embodiment;

[0061] Fig.11 is a structural block diagram of a device for determining parameter delay in another embodiment;

[0062] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0064] The method for determining the parameter delay provided in the embodiment of the present application can be applied to the following examples: Figure 1 In the application environment shown in FIG. 1 , the application environment may include a computer device, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 1 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data of the thermal power unit. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining a parameter delay is implemented.

[0065] In the actual production control process, modern control systems with distributed control systems (DCS) as the mainstream not only realize load regulation and basic safe operation, but also record a large amount of production history data. These control data contain rich unit operation status information and valuable control adjustment rules, which provide good data support for various optimization analyses of unit operation control. However, since industrial control processes often have complex and multi-factor characteristics, the analysis of control data in various fields has high uncertainty. In order to model and analyze control data more efficiently, it is necessary to continuously improve modeling methods from various angles and improve comprehensive efficiency. One of the key points is to obtain the parameter delay of the controlled parameters involved in each control process. Taking the coal-adding temperature control process of thermal power units as an example, after controlling the coal-adding, the superheater temperature will not rise immediately, and it will also go through a series of operations such as coal grinding and powder blowing. There is a control time difference between the historical data of the two. The parameter delay is directly related to the control unit of the data source, which is a key factor in control data modeling and directly related to the effect of modeling analysis.

[0066] In the related art, when predictive control modeling is performed on each control process, multiple controlled parameters are usually used as model inputs to predict and control the control parameters. The parameter delay of the controlled parameter is used as a model hyperparameter, and the specific value or range that is as accurate as possible needs to be determined. Due to the production characteristics of the thermal power control field, the control data of each control link of the thermal power unit involves many parameters and the parameter coupling is strong, which contains complex control mechanism relationships. Usually, the controlled parameter delay of each control process is calculated by the control field experts by comparing the controlled parameters in the historical control process data with the time series control curve of the control parameters, and the correlation analysis is performed in combination with the prior knowledge of the changes of each parameter in the field, and finally the estimated delay range is obtained. Due to the complexity of the control system and the different equipment conditions of different thermal power plants, the delay parameters of the same control process in different thermal power plants have no corresponding reference value. At present, the hyperparameter of parameter delay is highly dependent on the prior knowledge of field experts and has low efficiency. There is no other general method for estimating parameter delay. Based on the above problems, the present application proposes a method, apparatus, device, storage medium and program product for determining parameter delay, which can improve the efficiency of obtaining the parameter delay range.

[0067] In one embodiment, Figure 2 As shown, a method for determining parameter delay is provided, and the method is applied to Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0068] S201, obtaining historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments.

[0069] Among them, the controlled parameter can be understood as an independent variable, and the control parameter can be understood as a dependent variable. For example, the controlled parameter can be the coal quantity, and the corresponding control parameter can be the temperature; or the controlled parameter can be the first-stage cooling water flow rate of the superheater, and the corresponding control parameter can also be the temperature, etc.

[0070] In this embodiment, the computer device can obtain the historical data of the thermal power unit in real time; it can also obtain the historical data of the thermal power unit periodically, or obtain the historical data of the thermal power unit when receiving a control instruction.

[0071] S202, performing time displacement changes on the control parameters at each moment according to a plurality of preset delay conditions, to obtain target control parameters at each moment under each delay condition.

[0072] In this embodiment, according to the preset multiple delay conditions, the control parameters at each moment can be changed by forward displacement, that is, the control parameters at the later moment are moved to the position corresponding to the previous moment. For example, the control parameter corresponding to t0 is y0, the control parameter corresponding to t1 is y1, ..., the control parameter corresponding to t100 is y100, and the delay condition is to move the control parameter forward by one moment. After the displacement change, the target control parameter corresponding to t0 is y1, the target control parameter corresponding to t1 is y2, ..., and the target control parameter corresponding to t99 is y100; the control parameters at each moment can also be changed by backward displacement, that is, the control parameter at the previous moment is moved to the position corresponding to the later moment. For example, the delay condition is to move the control parameter back one time. After the displacement change, the target control parameter corresponding to t1 is y0, the target control parameter corresponding to t2 is y1, ..., and the target control parameter corresponding to t100 is y99; or the control parameters at each time are subjected to displacement changes at any time. For example, after the displacement change, the target control parameter corresponding to t0 is y20, the target control parameter corresponding to t1 is y5, ..., and the target control parameter corresponding to t100 is y50.

[0073] S203, obtaining the correlation analysis result and the one-way variance analysis result under each delay condition according to the target control parameter and the corresponding control parameter at each moment under each delay condition.

[0074] In this embodiment, after the displacement changes are performed according to the above-mentioned delay conditions, the target control parameters and the corresponding control parameters at each moment under each delay condition can be obtained, and the Pearson correlation coefficient or Spearman correlation coefficient under each delay condition can be directly calculated. The obtained Pearson correlation coefficient or Spearman correlation coefficient is the correlation analysis result under each delay condition; and the one-way analysis of variance result is obtained through one-way analysis of variance; the chart can also be analyzed by drawing a graph to obtain the correlation analysis results and one-way analysis of variance results under each delay condition.

[0075] S204, determining the range of parameter delay according to the correlation analysis results and the one-way variance analysis results under each delay condition.

[0076] In this embodiment, the first mean of the correlation analysis results under each delay condition and the second mean of the one-way variance analysis results can be calculated, and the range of the parameter delay can be determined by the first moment corresponding to the first mean and the second moment corresponding to the second mean; the first inflection point moment of the correlation analysis results under each delay condition and the second inflection point moment of the one-way variance analysis results can also be calculated, and the range of the parameter delay can be determined based on the first inflection point moment and the second inflection point moment; or the two moments of intersection of the correlation analysis results and the one-way variance analysis results can be determined as the range of the parameter delay.

[0077] In the above parameter delay determination method, by obtaining the historical data of the thermal power unit, the historical data includes the controlled parameters and control parameters corresponding to multiple moments, and the control parameters at each moment are shifted according to the preset multiple delay conditions to obtain the target control parameters at each moment under each delay condition. According to the target control parameters and the corresponding control parameters at each moment under each delay condition, the correlation analysis results and the one-way variance analysis results under each delay condition are obtained, and the range of the parameter delay is determined according to the correlation analysis results and the one-way variance analysis results under each delay condition. This method only needs to perform statistical operations on the historical data to determine the range of the parameter delay, which overcomes the problem of the original method's strong reliance on the prior knowledge of domain experts, has a certain degree of versatility, can be used for parameter delay analysis of different control processes, and solves the versatility problem of the delay estimation process. Moreover, this method does not require human participation, which improves the efficiency of determining the parameter delay.

[0078] Above Figure 2 The embodiment introduces a method for determining the parameter delay, and the following focuses on another implementation method for determining the target control parameter, such as Figure 3 As shown, the following steps are included:

[0079] S301, performing time-series superposition transformation on the control parameters at each moment to obtain candidate control parameters at each moment.

[0080] In this embodiment, the formula The control parameters at each moment are transformed by time series superposition, where y(t) represents the candidate control parameter at each moment, y(i) represents the control parameter at each moment, and n is the time series superposition amount. Assume that n is equal to 5, and the control parameters at each moment are y(1), y(2), y(3), y(4), y(5), y(6), and y(7). Because n>t must be satisfied, when n=5, four candidate control parameters y(1), y(2), y(3), and y(4) can be calculated, which are y(1)=y(1)+y(2)+y( Alternatively, the reverse time-series superposition transformation y(2)=y(1)+y(2), y(3)=y(1)+y(2)+y(3), y(4)=y(1)+y(2)+y(3)+y(4), y(5)=y(1)+y(2)+y(3)+y(4)+y(5).

[0081] S302, performing time shift changes on candidate control parameters at each moment according to multiple delay conditions, to obtain target control parameters at each moment under each delay condition.

[0082] In this embodiment, the target control parameters at each moment obtained by each delay condition are different. Assume that the moments are t0, t1, t2, ..., t100, ..., and the candidate control parameters corresponding to each moment are y0, y1, y2, ..., y100, ..., that is, the candidate control parameter corresponding to moment t0 is y0, the candidate control parameter corresponding to moment t1 is y1, ..., and the candidate control parameter corresponding to moment t100 is y100. Delay condition 1 is to move the candidate control parameters forward by one moment, that is, the target control parameters at each moment under delay condition 1 are: the target control parameter corresponding to moment t0 is y1, and the target control parameter corresponding to moment t1 is y100. y2, ..., the target control parameter corresponding to time t100 is y101; delay condition 2 is to move the candidate control parameters forward 2 time points, that is, the target control parameters at each moment under delay condition 2 are: the target control parameter corresponding to time t0 is y2, the target control parameter corresponding to time t1 is y3, ..., the target control parameter corresponding to time t100 is y102; delay condition 100 is to move the candidate control parameters forward 100 time points, that is, the target control parameters at each moment under delay condition 100 are: the target control parameter corresponding to time t0 is y100, the target control parameter corresponding to time t1 is y101, ..., the target control parameter corresponding to time t100 is y200.

[0083] Optionally, in actual applications, the influence of the controlled parameters on the target control parameters will not occur immediately, that is, the range of the parameter delay will not occur near time t0, so the delay condition 1 can be appropriately determined to move the candidate control parameters forward by multiple time points to simplify the calculation amount.

[0084] In this embodiment, the control parameters at each moment are transformed in time series to obtain candidate control parameters at each moment, and then the control parameters are shifted in time to obtain target control parameters at each moment under each delay condition. The method performs operations such as time series transformation on the control parameters at each moment, which can accumulate the influence of the controlled parameters on the control parameters, improve the correlation analysis effect between the two, and has a certain general effect.

[0085] The above embodiment introduces the implementation process of determining the target control parameters. Next, the specific process of obtaining the correlation analysis results and the one-way variance analysis results is mainly introduced. Figure 4 As shown, the following steps are included:

[0086] S401, determining a data group corresponding to each delay condition according to the target control parameters at each moment under each delay condition and the controlled parameters corresponding to each moment; the data group includes the target control parameters at each moment and the corresponding controlled parameters.

[0087] In this embodiment, under each delay condition, the target control parameter and the controlled parameter at each moment have a one-to-one correspondence. Still based on the above embodiment, under delay condition 1, the controlled parameter corresponding to moment t0 is x0, and the target control parameter is y1; the controlled parameter corresponding to moment t1 is x1, and the target control parameter is y2, ...; the controlled parameter corresponding to moment t100 is x100, and the target control parameter is y101. Then the data group corresponding to delay condition 1 is [x0 y1, x1 y2, x2y3, ..., x100 y101], ...; under delay condition 100, the controlled parameter corresponding to moment t0 is x0, and the target control parameter is y100; the controlled parameter corresponding to moment t1 is x1, and the target control parameter is y102, ...; the controlled parameter corresponding to moment t100 is x100, and the target control parameter is y200. Then the data group corresponding to delay condition 100 is [x0 y100, x1 y101, x2 y102,...,x100 y200].

[0088] S402, performing correlation analysis on the data group corresponding to each delay condition to obtain the correlation analysis result corresponding to each delay condition.

[0089] In this embodiment, the Pearson correlation coefficient can be used to analyze the data group corresponding to each delay condition, and the covariance between the controlled parameters and the target control parameters, as well as the standard deviation of the controlled parameters and the target control parameters are calculated based on the data group. The Pearson correlation coefficient corresponding to each delay condition is calculated based on the covariance and the respective standard deviations, that is, the correlation analysis result corresponding to each delay condition; the Spearman correlation coefficient can also be used to analyze the data group corresponding to each delay condition, sort the controlled parameters and the target control parameters, and obtain the rank based on the sorted controlled parameters and target control parameters, so as to obtain the Spearman correlation coefficient based on the rank and the number of variables in the data group, that is, the correlation analysis result corresponding to each delay condition.

[0090] S403, performing one-way ANOVA on the data group corresponding to each delay condition to obtain the one-way ANOVA result corresponding to each delay condition.

[0091] In this embodiment, a one-way ANOVA is performed on the data group corresponding to each delay condition, and the mean, error sum of the controlled parameter and target control parameter are calculated based on the data group, thereby calculating the one-way ANOVA result corresponding to each delay condition.

[0092] In an embodiment of the present application, based on the target control parameters at each moment under each delay condition and the controlled parameters corresponding to each moment, the data group corresponding to each delay condition is determined, and the correlation analysis results and the one-way variance analysis results corresponding to each delay condition are obtained by using correlation analysis and one-way variance analysis. In this method, two methods are used to determine the relationship between the target control parameters and the controlled parameters, which lays an important foundation for the subsequent determination of the range of parameter delay.

[0093] Above Figure 4 The embodiment introduces the implementation process of obtaining the correlation analysis results and the one-way variance analysis results. Next, the specific method of determining the delay range is mainly introduced, such as Figure 5 As shown, the following steps are included:

[0094] S501, performing linear fitting on the correlation analysis results under each delay condition to obtain a correlation data curve.

[0095] In this embodiment, a correlation analysis result can be obtained under each delay condition, and the correlation analysis results under multiple delay conditions are linearly fitted in the order of the delay conditions to obtain a correlation data curve. For example, the first correlation analysis result is to move the target control parameter forward by one time, and the second correlation analysis result is to move the target control parameter forward by two time, and the correlation analysis results are linearly fitted in accordance with the first correlation analysis result and the second correlation analysis result.

[0096] S502, performing linear fitting on the one-way variance analysis results under each delay condition to obtain a one-way data curve.

[0097] In this embodiment, similarly, the one-way ANOVA result is linearly fitted according to the method of step S501 to obtain a one-way data curve.

[0098] S503, determining a range of parameter delay according to a first inflection point on the correlation data curve and a second inflection point on the single factor data curve.

[0099] In this embodiment, the correlation data curve is differentiated to obtain the first inflection point moment on the correlation data curve, and the single factor data curve is differentiated to obtain the second inflection point moment on the single factor data curve. The time difference between the first inflection point moment and the second inflection point moment can be determined as the range of the parameter delay; the time difference between the first inflection point moment and the second inflection point moment can also be determined as the range of the parameter delay by reducing the time difference by a certain preset value.

[0100] Specifically, Figure 6 As shown, "determine the range of parameter delay according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve." includes the following steps:

[0101] S601, obtaining a time difference between a first inflection point and a second inflection point.

[0102] In this embodiment, the time difference between the first inflection point moment and the second inflection point moment is obtained. It is assumed that the historical data of the thermal power unit acquired by the computer device is collected every 1 second, the first inflection point moment is the inflection point moment corresponding to the delay condition 50, and the second inflection point moment is the inflection point moment corresponding to the delay condition 80. The delay condition 50 is to move the target control parameter forward by 50 seconds, and the delay condition 80 is to move the target control parameter forward by 80 seconds. The time difference between the first inflection point moment and the second inflection point moment is 30 seconds.

[0103] S602: Determine a range of parameter delay according to the time difference and a preset threshold.

[0104] In this embodiment, the preset threshold value may be 20, or 30, etc., and the embodiment of the present application does not limit this. It is possible to determine whether the time difference is less than the preset threshold value. If the time difference is less than the preset threshold value, the range of the parameter delay is determined according to the time range between the first inflection point moment and the second inflection point moment; or the quotient of the time difference and the preset threshold value is obtained. If the quotient value is less than 1, the range of the parameter delay is determined according to the time range between the first inflection point moment and the second inflection point moment.

[0105] Specifically, “determining the range of parameter delay according to the time difference and the preset threshold value” may include the following two aspects:

[0106] In a first aspect, if the time difference is less than or equal to a preset threshold, the range between the first inflection point moment and the second inflection point moment is determined as the range of the parameter delay.

[0107] In this embodiment, still taking the above steps as an example, it is assumed that the preset threshold is 50s and the time difference is 30s. It can be found that the time difference is less than the preset threshold, and the range between the first inflection point moment and the second inflection point moment is determined as the range of the parameter delay, that is, the range of the parameter delay is 50s to 80s.

[0108] Secondly, if the time difference is greater than the preset threshold, the process returns to the step of obtaining historical data of the thermal power unit, or the process updates the delay condition and uses the new delay condition to perform a time displacement change on the control parameters at each moment.

[0109] In this embodiment, when the time difference is greater than the preset threshold, there may be a problem with the acquired set of historical data, and it is necessary to re-acquire the historical data of the thermal power unit. There may also be a problem with the preset delay condition selection, and the delay condition is updated, and the new delay condition is used to perform the step of momentary displacement change of the control parameters at each moment.

[0110] In an embodiment of the present application, linear fitting is performed on the correlation analysis results and the one-way variance analysis results under each delay condition to obtain a correlation data curve and a one-way data curve, and the first inflection point moment of the correlation data curve and the second inflection point moment of the one-way data curve are further solved, and the range of the parameter delay is determined according to the first inflection point moment and the second inflection point moment. This method uses a linear fitting method to enhance the observability of the data, making it easier to find the inflection point moment of the curve, and by analyzing the correlation results and the one-way results, the method is universal in determining the range of the parameter delay. Furthermore, when the time difference is greater than a preset threshold, the above steps can be returned to redetermine the range of the parameter delay, forming a closed loop, which can effectively determine the range of the parameter delay.

[0111] Furthermore, if Figure 7 As shown, the method for determining the parameter delay also includes the following steps:

[0112] S701, obtaining historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0113] S702, performing time series superposition transformation on the control parameters at each moment to obtain candidate control parameters at each moment;

[0114] S703, performing time shift changes on candidate control parameters at each moment according to multiple delay conditions, to obtain target control parameters at each moment under each delay condition;

[0115] S704, determining a data group corresponding to each delay condition according to the target control parameter at each moment under each delay condition and the controlled parameter corresponding to each moment; the data group includes the target control parameter at each moment and the corresponding controlled parameter;

[0116] S705, performing correlation analysis on the data group corresponding to each delay condition to obtain the correlation analysis result corresponding to each delay condition;

[0117] S706, performing one-way ANOVA on the data group corresponding to each delay condition to obtain the one-way ANOVA result corresponding to each delay condition;

[0118] S707, performing linear fitting on the correlation analysis results under each delay condition to obtain a correlation data curve;

[0119] S708, performing linear fitting on the one-way ANOVA results under each delay condition to obtain a one-way data curve;

[0120] S709, obtaining a time difference between the first inflection point and the second inflection point;

[0121] S710, if the time difference is less than or equal to a preset threshold, determining a range between the first inflection point moment and the second inflection point moment as a range of the parameter delay;

[0122] S711, if the time difference is greater than the preset threshold, return to step S701, or update the delay condition and return to step S702.

[0123] In the embodiment of the present application, by obtaining the historical data of the thermal power unit, the historical data includes the controlled parameters and control parameters corresponding to multiple moments, the control parameters at each moment are shifted according to the preset multiple delay conditions, and the target control parameters at each moment under each delay condition are obtained. According to the target control parameters at each moment under each delay condition and the corresponding control parameters, the correlation analysis results and the one-way variance analysis results under each delay condition are obtained, and the range of the parameter delay is determined according to the correlation analysis results and the one-way variance analysis results under each delay condition. This method only needs to perform statistical operations on the historical data to determine the range of the parameter delay, which overcomes the problem of the original method's strong reliance on the expert's prior knowledge, has a certain degree of versatility, can be used for parameter delay analysis of different control processes, solves the versatility problem of the delay estimation process, and does not require human participation, which improves the efficiency of determining the parameter delay.

[0124] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0125] Based on the same inventive concept, the embodiment of the present application also provides a parameter delay determination device for implementing the parameter delay determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more parameter delay determination devices provided below can refer to the limitations of the parameter delay determination method above, and will not be repeated here.

[0126] In one embodiment, Figure 8 As shown, a device for determining a parameter delay is provided, the device comprising: a first acquisition module 11, a first determination module 12, a second acquisition module 13 and a second determination module 14, wherein:

[0127] The first acquisition module 11 is used to acquire historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0128] The first determination module 12 is used to perform a time displacement change on the control parameters at each moment according to a plurality of preset delay conditions to obtain a target control parameter at each moment under each delay condition;

[0129] The second acquisition module 13 is used to obtain the correlation analysis results and the one-way variance analysis results under each delay condition according to the target control parameters and the corresponding control parameters at each moment under each delay condition;

[0130] The second determination module 14 is used to determine the range of parameter delay according to the correlation analysis results and the one-way variance analysis results under various delay conditions.

[0131] In one embodiment, Fig. 9 As shown, a device for determining parameter delay is provided, and the device also includes:

[0132] The third determination module 15 is used to perform time-series superposition transformation on the control parameters at each moment to obtain candidate control parameters at each moment;

[0133] The first determination module 12 is further used to determine the range of parameter delay according to the correlation analysis results and the one-way variance analysis results under various delay conditions.

[0134] In one embodiment, Fig.10 As shown, the second acquisition module 13 includes:

[0135] The first determining unit 131 is used to determine the data group corresponding to each delay condition according to the target control parameter at each moment under each delay condition and the controlled parameter corresponding to each moment; the data group includes the target control parameter at each moment and the corresponding controlled parameter;

[0136] A first analysis unit 132 is used to perform correlation analysis on the data group corresponding to each delay condition to obtain a correlation analysis result corresponding to each delay condition;

[0137] The second analysis unit 133 is used to perform a one-way ANOVA on the data group corresponding to each delay condition to obtain a one-way ANOVA result corresponding to each delay condition.

[0138] In one embodiment, Fig.11 As shown, the second determination module 14 includes:

[0139] The first fitting unit 141 is used to perform linear fitting on the correlation analysis results under each delay condition to obtain a correlation data curve;

[0140] The second fitting unit 142 is used to perform linear fitting on the single-factor variance analysis results under each delay condition to obtain a single-factor data curve;

[0141] The second determining unit 143 is used to determine the range of the parameter delay according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve.

[0142] In one embodiment, the second determining unit 143 is further configured to obtain a time difference between the first inflection point moment and the second inflection point moment; and determine a range of the parameter delay according to the time difference and a preset threshold.

[0143] In one embodiment, the second determination unit 143 is also used to, when the time difference is less than or equal to a preset threshold, determine the range between the first inflection point moment and the second inflection point moment as the range of the parameter delay; when the time difference is greater than the preset threshold, return to execute the step of obtaining the historical data of the thermal power unit, or execute the step of updating the delay condition and using the new delay condition to perform a time displacement change on the control parameters at each moment.

[0144] Each module in the above-mentioned device for determining the parameter delay can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0145] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.12 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining a parameter delay is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball or a touch pad set on the computer device housing, or an external keyboard, touch pad or mouse, etc.

[0146] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0147] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0148] Obtain historical data of thermal power units; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0149] According to the preset multiple delay conditions, the control parameters at each moment are shifted at a certain time to obtain the target control parameters at each moment under each delay condition;

[0150] According to the target control parameters and corresponding control parameters at each moment under each delay condition, the correlation analysis results and one-way variance analysis results under each delay condition are obtained;

[0151] According to the correlation analysis results and one-way variance analysis results under each delay condition, the range of parameter delay is determined.

[0152] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0153] Perform time series superposition transformation on the control parameters at each moment to obtain candidate control parameters at each moment;

[0154] According to the preset multiple delay conditions, the control parameters at each moment are shifted and changed at a certain time, and the target control parameters at each moment under each delay condition are obtained, including:

[0155] According to a plurality of delay conditions, the candidate control parameters at each moment are respectively shifted in time to obtain the target control parameters at each moment under each delay condition.

[0156] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0157] According to the target control parameters at each moment under each delay condition and the controlled parameters corresponding to each moment, determining the data group corresponding to each delay condition; the data group includes the target control parameters at each moment and the corresponding controlled parameters;

[0158] Performing correlation analysis on the data group corresponding to each delay condition to obtain the correlation analysis result corresponding to each delay condition;

[0159] One-way ANOVA was performed on the data group corresponding to each delay condition to obtain the one-way ANOVA results corresponding to each delay condition.

[0160] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0161] Perform linear fitting on the correlation analysis results under each delay condition to obtain a correlation data curve;

[0162] Linear fitting was performed on the results of one-way ANOVA under each delay condition to obtain the one-way data curve;

[0163] The range of the parameter delay is determined according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve.

[0164] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0165] Obtaining the time difference between the first inflection point and the second inflection point;

[0166] The range of the parameter delay is determined based on the time difference and the preset threshold.

[0167] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0168] If the time difference is less than or equal to the preset threshold, the range between the first inflection point moment and the second inflection point moment is determined as the range of the parameter delay.

[0169] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0170] If the time difference is greater than the preset threshold, the process returns to the step of obtaining historical data of the thermal power unit, or executes the step of updating the delay condition and using the new delay condition to perform a time displacement change on the control parameters at each moment.

[0171] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0172] Obtain historical data of thermal power units; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0173] According to the preset multiple delay conditions, the control parameters at each moment are shifted at a certain time to obtain the target control parameters at each moment under each delay condition;

[0174] According to the target control parameters and corresponding control parameters at each moment under each delay condition, the correlation analysis results and one-way variance analysis results under each delay condition are obtained;

[0175] According to the correlation analysis results and one-way variance analysis results under each delay condition, the range of parameter delay is determined.

[0176] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0177] Perform time series superposition transformation on the control parameters at each moment to obtain candidate control parameters at each moment;

[0178] According to the preset multiple delay conditions, the control parameters at each moment are shifted and changed at a certain time, and the target control parameters at each moment under each delay condition are obtained, including:

[0179] According to a plurality of delay conditions, the candidate control parameters at each moment are respectively shifted in time to obtain the target control parameters at each moment under each delay condition.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0181] According to the target control parameters at each moment under each delay condition and the controlled parameters corresponding to each moment, determining the data group corresponding to each delay condition; the data group includes the target control parameters at each moment and the corresponding controlled parameters;

[0182] Performing correlation analysis on the data group corresponding to each delay condition to obtain the correlation analysis result corresponding to each delay condition;

[0183] One-way ANOVA was performed on the data group corresponding to each delay condition to obtain the one-way ANOVA results corresponding to each delay condition.

[0184] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0185] Perform linear fitting on the correlation analysis results under each delay condition to obtain a correlation data curve;

[0186] Linear fitting was performed on the results of one-way ANOVA under each delay condition to obtain the one-way data curve;

[0187] The range of the parameter delay is determined according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0189] Obtaining the time difference between the first inflection point and the second inflection point;

[0190] The range of the parameter delay is determined based on the time difference and the preset threshold.

[0191] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0192] If the time difference is less than or equal to the preset threshold, the range between the first inflection point moment and the second inflection point moment is determined as the range of the parameter delay.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0194] If the time difference is greater than the preset threshold, the process returns to the step of obtaining historical data of the thermal power unit, or executes the step of updating the delay condition and using the new delay condition to perform a time displacement change on the control parameters at each moment.

[0195] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0196] Obtain historical data of thermal power units; the historical data includes controlled parameters and control parameters corresponding to multiple moments;

[0197] According to the preset multiple delay conditions, the control parameters at each moment are shifted at a certain time to obtain the target control parameters at each moment under each delay condition;

[0198] According to the target control parameters and corresponding control parameters at each moment under each delay condition, the correlation analysis results and one-way variance analysis results under each delay condition are obtained;

[0199] According to the correlation analysis results and one-way variance analysis results under each delay condition, the range of parameter delay is determined.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0201] Perform time series superposition transformation on the control parameters at each moment to obtain candidate control parameters at each moment;

[0202] According to the preset multiple delay conditions, the control parameters at each moment are shifted and changed at a certain time, and the target control parameters at each moment under each delay condition are obtained, including:

[0203] According to a plurality of delay conditions, the candidate control parameters at each moment are respectively shifted in time to obtain the target control parameters at each moment under each delay condition.

[0204] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0205] According to the target control parameters at each moment under each delay condition and the controlled parameters corresponding to each moment, determining the data group corresponding to each delay condition; the data group includes the target control parameters at each moment and the corresponding controlled parameters;

[0206] Performing correlation analysis on the data group corresponding to each delay condition to obtain the correlation analysis result corresponding to each delay condition;

[0207] One-way ANOVA was performed on the data group corresponding to each delay condition to obtain the one-way ANOVA results corresponding to each delay condition.

[0208] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0209] Perform linear fitting on the correlation analysis results under each delay condition to obtain a correlation data curve;

[0210] Linear fitting was performed on the results of one-way ANOVA under each delay condition to obtain the one-way data curve;

[0211] The range of the parameter delay is determined according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve.

[0212] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0213] Obtaining the time difference between the first inflection point and the second inflection point;

[0214] The range of the parameter delay is determined based on the time difference and the preset threshold.

[0215] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0216] If the time difference is less than or equal to the preset threshold, the range between the first inflection point moment and the second inflection point moment is determined as the range of the parameter delay.

[0217] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0218] If the time difference is greater than the preset threshold, the process returns to the step of obtaining historical data of the thermal power unit, or executes the step of updating the delay condition and using the new delay condition to perform a time displacement change on the control parameters at each moment.

[0219] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0220] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0221] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0222] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining parameter delay, characterized in that: The method comprises: Acquire historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments; Performing time-series superposition transformation on the control parameters at each of the moments to obtain candidate control parameters at each of the moments; Performing time displacement changes on the candidate control parameters at each time point according to a plurality of preset delay conditions to obtain target control parameters at each time point under each delay condition; According to the target control parameter and the corresponding control parameter at each moment under each delay condition, obtaining the correlation analysis result and the one-way variance analysis result under each delay condition; The range of the parameter delay is determined according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions.

2. The method according to claim 1, characterized in that The step of obtaining the correlation analysis results and the one-way variance analysis results under each of the delay conditions according to the target control parameters and the corresponding control parameters at each moment under each of the delay conditions includes: Determine a data group corresponding to each of the delay conditions according to the target control parameters at each of the delay conditions and the controlled parameters corresponding to each of the delay conditions; the data group includes the target control parameters at each of the delay conditions and the corresponding controlled parameters; Performing correlation analysis on the data group corresponding to each of the delay conditions to obtain the correlation analysis results corresponding to each of the delay conditions; A one-way ANOVA is performed on the data group corresponding to each of the delay conditions to obtain a one-way ANOVA result corresponding to each of the delay conditions.

3. The method according to claim 1, characterized in that Determining the range of the parameter delay according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions includes: Performing linear fitting on the correlation analysis results under each of the delay conditions to obtain a correlation data curve; Performing linear fitting on the one-way ANOVA results under each of the time-delay conditions to obtain a one-way data curve; The range of the parameter delay is determined according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve.

4. The method according to claim 3, characterized in that Determining the range of the parameter delay according to the first inflection point moment on the correlation data curve and the second inflection point moment on the single factor data curve includes: Obtaining a time difference between the first inflection point moment and the second inflection point moment; The range of the parameter delay is determined according to the time difference and a preset threshold.

5. The method according to claim 4, characterized in that The determining the range of the parameter delay according to the time difference and a preset threshold value includes: If the time difference is less than or equal to a preset threshold, the range between the first inflection point moment and the second inflection point moment is determined as the range of the parameter delay.

6. The method according to claim 5, characterized in that The method further comprises: If the time difference is greater than the preset threshold, the method returns to the step of obtaining the historical data of the thermal power unit, or executes the step of updating the delay condition and adopting the new delay condition to perform a time displacement change on the control parameters at each moment.

7. A device for determining parameter delay, characterized in that: The device comprises: A first acquisition module is used to acquire historical data of the thermal power unit; the historical data includes controlled parameters and control parameters corresponding to multiple moments; A first determination module is used to perform time-series superposition transformation on the control parameters at each of the moments to obtain candidate control parameters at each of the moments; A second determination module is used to perform a time shift change on the candidate control parameters at each time according to a plurality of preset delay conditions to obtain a target control parameter at each time under each delay condition; A second acquisition module is used to acquire the correlation analysis results and the one-way variance analysis results under each of the delay conditions according to the target control parameters and the corresponding control parameters at each moment under each of the delay conditions; The third determination module is used to determine the range of the parameter delay according to the correlation analysis results and the one-way variance analysis results under each of the delay conditions.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.