A method for detecting and correcting abnormal operation data of a power plant and related equipment

Abstract

The application discloses a kind of power plant abnormal operation data detection and correction method and related equipment.The method determines the measurement redundancy of target thermal system, if greater than 0, obtains the measurement value of each process variable and the accuracy level of corresponding instrument;According to the accuracy level, the measurement mean square deviation of each variable is calculated;Establish the data correction mathematical model with each variable correction value as the variable to be solved, with the minimum weighted correction quantity square sum as the objective function, and containing physical conservation constraint equation;Solving the model obtains the correction value of each variable;For each variable, according to its measurement value, correction value and measurement mean square deviation, calculate detection factor, and compare with preset threshold value, if greater than threshold value, it is judged that the measurement value exists significant error.The application realizes redundancy judgment, precision weighted correction, physical constraint optimization and statistical test, so that the corrected data satisfies the conservation law, improves the data reliability, and can quantitatively identify fault instrument.

Description

Technical Field

[0001] This invention relates to the field of power plant operation data processing and unit performance monitoring technology, specifically to a method and related equipment for detecting and correcting abnormal power plant operation data. Background Technology

[0002] During power plant operation, various sensors and transmitters collect a large amount of process data in real time. This data is widely used for unit performance monitoring, energy consumption diagnosis, and operation optimization. Due to the complex on-site measurement environment and the drift or malfunction of instruments during long-term operation, the measured data inevitably contains random and significant errors. If the raw, unprocessed data is used directly for analysis and calculation, results that violate basic physical laws are often obtained. For example, when calculating boiler efficiency based on the positive balance method, the calculated result sometimes exceeds 100%, which clearly does not conform to the principle of energy conservation.

[0003] For error detection and correction of power plant operation data, existing methods often fail to meet the actual engineering needs when applied to complex thermal systems. The corrected data still contains unreasonable aspects, affecting the accuracy of subsequent performance monitoring and energy loss diagnosis. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides a method and related equipment for detecting and correcting abnormal operating data of power plants. Its purpose is to improve the correction quality of power plant operating data, ensuring that the corrected data strictly meets the basic physical laws and avoids unreasonable results that violate the law of conservation of energy. At the same time, by distinguishing the accuracy differences of different measuring instruments, the correction results are made more consistent with the actual reliability of each variable, and the measured values ​​with significant errors and their corresponding faulty instruments are quantitatively identified.

[0005] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution: According to a first aspect of the present invention, a method for detecting and correcting abnormal operating data of a power plant is provided, comprising: Determine the measurement redundancy of the target thermal system. If the measurement redundancy is greater than 0, obtain the measured values ​​of each process variable in the target thermal system and the accuracy class of the measuring instrument corresponding to each process variable. Calculate the measurement root mean square error of each process variable based on the accuracy class of the measuring instrument corresponding to each process variable; A data correction mathematical model is established, wherein the correction values ​​of each process variable are the variables to be solved, and the objective function is to minimize the sum of squares of the weighted corrections of each process variable. The data correction mathematical model also includes the physical conservation constraint equations that the target thermodynamic system must satisfy, wherein the weighting coefficients of each process variable are determined based on the corresponding measurement root mean square error. Solve the mathematical model for data correction to obtain the corrected values ​​for each process variable; For each process variable, a detection factor is calculated based on its measured value, correction value, and measurement mean square error. The detection factor is then compared with a preset threshold. If the detection factor is greater than the preset threshold, it is determined that the measured value of the process variable has a significant error.

[0006] In one possible implementation of the first aspect, determining the measurement redundancy of the target thermodynamic system specifically involves: The difference between the number of process variables measured in the target thermodynamic system and the minimum number of measurements required to determine the system state is calculated; this difference is the measurement redundancy.

[0007] In one possible implementation of the first aspect, the step of calculating the measurement root mean square error of each process variable based on the accuracy class of the measuring instrument corresponding to each process variable specifically involves: The absolute error is determined based on the accuracy class of the measuring instrument, a confidence probability is set, the corresponding quantile is determined based on the confidence probability, and the absolute error is divided by the quantile to obtain the measurement root mean square error of the process variable.

[0008] In one possible implementation of the first aspect, the objective function is specifically:

[0009] in, For the first The measured values ​​of each process variable, For the first Correction values ​​for each process variable, For the first The measurement mean square error of each process variable. This represents the total number of process variables.

[0010] In one possible implementation of the first aspect, the physical conservation constraint equations include a matter balance equation and / or an energy balance equation.

[0011] In one possible implementation of the first aspect, solving the data correction mathematical model to obtain the correction values ​​for each process variable specifically involves: The Lagrange multiplier method is used to obtain the correction values ​​of each process variable by constructing the Lagrange function and solving the partial derivative equations.

[0012] In one possible implementation of the first aspect, the calculation of the detection factor for each process variable based on its measured value, correction value, and measurement root mean square error specifically involves: The detection factor is obtained by calculating the absolute value of the difference between the measured value and the corrected value and dividing it by the measurement root mean square error.

[0013] In one possible implementation of the first aspect, the target thermal system specifically comprises: The boiler system, wherein the process variables include at least one or more of the following: feedwater flow rate, coal feed rate, and lower heating value of coal feed.

[0014] According to a second aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned method for detecting and correcting abnormal operating data of a power plant.

[0015] According to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned method for detecting and correcting abnormal operating data of a power plant.

[0016] According to a fourth aspect of the present invention, a computer program product is provided, which, when executed by a processor, implements the aforementioned method for detecting and correcting abnormal operating data of a power plant.

[0017] Compared with the prior art, the present invention has at least the following beneficial effects: The method for detecting and correcting abnormal operation data in power plants provided by this invention first determines the measurement redundancy of the target thermal system and only executes subsequent steps when the redundancy is greater than 0. This avoids invalid calculations when the system lacks correctability conditions, ensuring the necessity and reliability of the correction operation. Based on this, the measurement root mean square error is calculated according to the accuracy level of the measuring instruments corresponding to each process variable, and this error is incorporated as a weighting coefficient into a data correction mathematical model aimed at minimizing the sum of squares of the weighted correction amounts. This allows for smaller adjustments to the measurement values ​​of high-precision instruments during the correction process, while allowing for larger adjustments to the measurement values ​​of low-precision instruments. Thus, under the premise of satisfying physical conservation constraints such as material balance and energy balance, a set of corrected data that conforms to basic physical laws and has the smallest deviation from the original measurement values ​​is obtained. Finally, for each process variable, a detection factor is calculated using the measured value, the corrected value, and the measurement root mean square error, and compared with a preset threshold. When the detection factor is greater than the threshold, a significant error in the measured value is quantitatively determined, thereby accurately locating the faulty instrument. This method not only ensures that the corrected data meets the physical conservation law and avoids unreasonable results such as boiler efficiency calculations exceeding 100%, but also makes the correction results more consistent with the actual credibility of each variable through precision weighting. At the same time, it uses statistical testing mechanisms to achieve quantitative identification of significant errors and location of faulty instruments. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the specific embodiments of the present invention, the drawings used in the description of the specific embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a flowchart of a method for detecting and correcting abnormal operating data in a power plant according to the present invention.

[0020] Figure 2 This is a schematic diagram of the energy balance of a boiler system. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] This invention provides a method for detecting and correcting abnormal operating data in power plants. This method addresses the problem of random and significant errors in measurement data in power plant thermal systems. Based on system measurement redundancy and differences in instrument accuracy, it establishes a weighted optimization model with physical constraints to obtain corrected data that conforms to basic physical laws and quantitatively identifies instruments with significant errors.

[0023] like Figure 1 As shown, the specific implementation steps of the present invention are as follows: S1. Determine the measurement redundancy of the target thermal system. If the measurement redundancy is greater than 0, obtain the measured values ​​of each process variable in the target thermal system and the accuracy class of the measuring instrument corresponding to each process variable.

[0024] Specifically, measurement redundancy refers to the number of process variables measured beyond the data required to determine the system state. For example, in a simple branched flow system, if only the inlet flow rate is measured, the state of the two branches cannot be determined, resulting in a redundancy of -1. When the inlet flow rate and the flow rate of the first branch are measured, the flow rate of the second branch can be calculated, resulting in a redundancy of 0. If the inlet flow rate and the flow rates of both branches are measured simultaneously, the obtained data exceeds the data required to describe the system state, resulting in a measurement redundancy of 1.

[0025] In this embodiment, for the target thermal system, the difference between the total number of measurements of process variables in the system and the minimum number of measurements required to determine the system state is calculated; this difference is the measurement redundancy. If the redundancy is greater than 0, it indicates that the system has the conditions for data correction, and subsequent steps are executed; if the measurement redundancy is equal to or less than 0, the detection and correction process of abnormal operating data is terminated.

[0026] The measurement redundancy is calculated as the difference between the total number of measurements of process variables in the system and the minimum number of measurements required to determine the system state. If the redundancy is greater than 0, it indicates that the system has the conditions for data correction; if the measurement redundancy is equal to or less than 0, the detection and correction process for abnormal operating data is terminated.

[0027] S2. Calculate the measurement root mean square error of each process variable according to the accuracy class of the measuring instrument corresponding to each process variable.

[0028] It should be noted that the measurement root mean square error reflects the degree of dispersion of the measured values. In actual measurements, it is assumed that the system... n Measured values ​​of process variables Follows a normal distribution , measured value Compared with the true value Error between Follow the mean =0, variance = The normal distribution, likelihood function for:

[0029] According to the maximum likelihood principle, the time when the likelihood function is maximized... The value is the actual value of the process variable. Maximum likelihood estimate Taking the logarithm of both sides above, we want the likelihood function to... maximum, The following conditions must be met:

[0030] The precision of each process variable is different, depending on the instruments and meters used for measurement.

[0031] Specifically, the absolute error is determined based on the accuracy class of the measuring instrument. Set a confidence probability, determine the corresponding quantile based on the confidence probability, and divide the absolute error by the quantile to obtain the measurement root mean square error of the process variable. For example, for a single measurement value Assign confidence probability =95%, the measurement result can be expressed as: Integrating the normal distribution density function, the root mean square error of the process variable can be obtained as follows:

[0032] Wherein, 1.96 is the two-sided quantile corresponding to the 95% confidence probability under the standard normal distribution.

[0033] S3. Establish a data correction mathematical model. The data correction mathematical model uses the correction values ​​of each process variable as the variables to be solved, and takes the minimum of the sum of squares of the weighted correction amounts of each process variable as the objective function. The data correction mathematical model also includes the physical conservation constraint equations that the target thermodynamic system must satisfy, wherein the weighting coefficients of each process variable are determined based on the corresponding measurement root mean square error.

[0034] For the system under study, n Maximum likelihood estimates of process variables It must also satisfy certain constraint equations, such as equality constraint equations derived from the system's material or energy balance, or inequality constraint equations derived from the entropy principle. Therefore, for the system... n Measured values ​​of process variables To perform correction, we need to determine the process variables. True value Maximum likelihood estimate Its mathematical model is:

[0035]

[0036]

[0037] This is a constrained objective function optimization problem. Specifically, the objective function contains... This is the measurement root mean square error calculated in step S2, which appears in the denominator, resulting in higher accuracy. The smaller the value of the variable, the greater its residual. The greater the contribution to the objective function, the smaller the allowable adjustment range during the correction process; conversely, the lower the precision of a variable, the larger the allowable adjustment range. Equality constraints. Including material balance equations and / or energy balance equations, inequality constraints For example, thermodynamic inequalities based on the principle of entropy increase.

[0038] That is, the objective function, specifically:

[0039] in, For the first The measured values ​​of each process variable, For the first Correction values ​​for each process variable, For the first The measurement mean square error of each process variable. This represents the total number of process variables.

[0040] It should be noted that the constraint equations in the data correction mathematical model include equality constraints and / or inequality constraints. Specifically, equality constraints include material balance equations and energy balance equations, while inequality constraints include thermodynamic inequalities based on the principle of entropy increase.

[0041] For example, Figure 2 The energy balance relationship of the boiler system is shown, and its specific form can be determined according to the actual physical laws of different thermodynamic systems.

[0042] S4. Solve the mathematical model for data correction to obtain the correction values ​​for each process variable.

[0043] In one feasible approach, the mathematical model is solved using the Lagrange multiplier method. Specifically, a Lagrange function is constructed, the objective function and equality constraints are combined, and then partial derivatives are calculated for each variable to be solved and each Lagrange multiplier. Setting these partial derivatives to zero yields a system of nonlinear equations. Solving this system of partial derivative equations provides the correction values ​​for each process variable.

[0044] S5. For each process variable, calculate the detection factor based on its measured value, correction value, and measurement mean square error, and compare the detection factor with a preset threshold. If the detection factor is greater than the preset threshold, it is determined that the measured value of the process variable has a significant error.

[0045] Based on the measured values ​​of process variables and measurement mean square error By solving the above constrained objective function optimization model, the measured values ​​can be obtained. correction value In one feasible approach, the detection factor is calculated as follows: the absolute value of the difference between the measured value and the calibration value is divided by the measurement root mean square error to obtain the detection factor. .

[0046] Preferably, the preset threshold is 1.96, which corresponds to the two-sided quantile with a 95% confidence probability under the standard normal distribution.

[0047] like If the measured value is greater than 1.96, then the measured value is... Confidence probability Data below 5% is considered outlier, indicating significant error, and requires further investigation of process variables. The corresponding transmitter or instrument should be calibrated. like ≤1.96, then the measured value fall into The range is defined as follows: the probability of falling within this range is 95%, and the measurement value is reliable.

[0048] Preferably, after determining that the measured value of a certain process variable has a significant error, a prompt message is issued indicating that the measuring instrument corresponding to the process variable needs to be calibrated.

[0049] The following is an analysis of the effects of the technical solution of this invention. Compared with directly using the original measurement data, the correction data obtained by this invention satisfies the basic physical laws such as material balance, energy balance, and the principle of entropy increase, avoiding situations that violate physical laws, such as boiler efficiency calculations exceeding 100%. By introducing a weighting coefficient based on instrument accuracy, the measurement values ​​of high-precision instruments are adjusted less during the correction process, while low-precision instruments are allowed to adjust more, making the correction results more consistent with the actual reliability of each variable. This invention organically combines the principle of measurement redundancy, the maximum likelihood estimation method, and the basic physical laws of power plant thermal systems, overcoming the shortcomings of traditional data processing methods. By calculating the detection factor and comparing it with 1.96, instruments with significant errors can be quantitatively identified with a 95% confidence probability, providing a clear basis for instrument maintenance and avoiding blind calibration.

[0050] The above method will be explained in detail below using the boiler system of a 300MW thermal power unit as the target thermal system. The feedwater flow rate of a thermal power plant has the greatest impact on the accuracy of unit performance monitoring. Most power plants have significant errors in feedwater flow rate measurement; therefore, feedwater flow rate is selected as the parameter that needs to be detected and corrected. Other parameters that need to be corrected include the amount of coal fed into the boiler and the received lower heating value of the coal. This unit is equipped with a subcritical, single-reheat, controlled-cycle drum boiler, model SG-1025 / 18.3-M840, with specific parameters shown in Table 1 below.

[0051] Table 1 Main Operating Parameters

[0052] Figure 2 The boiler's energy balance diagram is given in the figure. This refers to the amount of coal fed into the boiler; for a direct-fired pulverizing system, It is the sum of the output of all operating coal mills; boiler efficiency Obtained using the reverse equilibrium method; lower heating value These are laboratory analysis results; reheater inlet heat... The feedwater flow rate is calculated based on the steam extraction and heating systems. Coal input to the furnace and low heat generation These are process variables that need to be corrected.

[0053] Water supply flow Coal input to the furnace and low heat generation Data correction involves solving the objective function optimization problem with the following nonlinear constraints:

[0054]

[0055]

[0056] The Lagrangian function of the above optimization problem for:

[0057] Solving the following system of equations will yield the following results. , and Correction results , , ,Right now:

[0058]

[0059]

[0060]

[0061] Based on the instruments and meters used in the measurement, the absolute errors of the above variable measurements can be obtained as follows: t / h, kJ / k, t / h, and assuming a 95% confidence level for a single measurement result, the measurement standard deviations are obtained as follows: =3.827, =76.531, =0.357.

[0062] Table 2 presents the correction results for water supply flow rate, coal feed rate, and lower heating value, as well as the main economic indicators after correction. Field verification shows that the corrected coal consumption for power generation is more reasonable and basically consistent with the actual on-site operation.

[0063] Table 2 Main Operating Parameters

[0064] By calculating the detection factor Significant measurement errors can be detected. Table 3 shows the detection results of water flow rate, coal feed rate and lower heating value.

[0065] Table 3 Measurement Error Detection

[0066] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used in the operation of a method for detecting and correcting abnormal operating data in a power plant.

[0067] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be Random Access Memory (RAM) or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for detecting and correcting abnormal operating data of a power plant in the above embodiments.

[0068] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0069] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] This invention also provides a computer program product for executing any of the above-described methods for detecting and correcting abnormal operating data in power plants. Since the computer program product provided by this invention and the above-described method for detecting and correcting abnormal operating data in power plants belong to the same inventive concept, the computer program product provided by this invention possesses all the advantages of the above-described method for detecting and correcting abnormal operating data in power plants. Therefore, the beneficial effects of the computer program product provided by this invention will not be elaborated upon here.

[0073] In this invention, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0074] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the scope of the technology disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention.

Claims

1. A method for detecting and correcting abnormal operating data in power plants, characterized in that, include: Determine the measurement redundancy of the target thermal system. If the measurement redundancy is greater than 0, obtain the measured values ​​of each process variable in the target thermal system and the accuracy class of the measuring instrument corresponding to each process variable. Calculate the measurement root mean square error of each process variable based on the accuracy class of the measuring instrument corresponding to each process variable; A data correction mathematical model is established, wherein the correction values ​​of each process variable are the variables to be solved, and the objective function is to minimize the sum of squares of the weighted corrections of each process variable. The data correction mathematical model also includes the physical conservation constraint equations that the target thermodynamic system must satisfy, wherein the weighting coefficients of each process variable are determined based on the corresponding measurement root mean square error. Solve the mathematical model for data correction to obtain the correction values ​​for each process variable; For each process variable, a detection factor is calculated based on its measured value, correction value, and measurement mean square error. The detection factor is then compared with a preset threshold. If the detection factor is greater than the preset threshold, it is determined that the measured value of the process variable has a significant error.

2. The method for detecting and correcting abnormal operation data of a power plant according to claim 1, characterized in that, The determination of the measurement redundancy of the target thermal system specifically involves: The difference between the number of process variables measured in the target thermodynamic system and the minimum number of measurements required to determine the system state is calculated; this difference is the measurement redundancy.

3. The method for detecting and correcting abnormal operation data of a power plant according to claim 1, characterized in that, The step of calculating the measurement root mean square error of each process variable based on the accuracy class of the measuring instrument corresponding to each process variable is as follows: The absolute error is determined based on the accuracy class of the measuring instrument, a confidence probability is set, the corresponding quantile is determined based on the confidence probability, and the absolute error is divided by the quantile to obtain the measurement root mean square error of the process variable.

4. The method for detecting and correcting abnormal operation data of a power plant according to claim 1, characterized in that, The objective function is specifically: in, For the first The measured values ​​of each process variable, For the first Correction values ​​for each process variable, For the first The measurement mean square error of each process variable. This represents the total number of process variables.

5. The method for detecting and correcting abnormal operation data of a power plant according to claim 1, characterized in that, The physical conservation constraint equations include the mass balance equation and / or the energy balance equation.

6. The method for detecting and correcting abnormal operation data of a power plant according to claim 1, characterized in that, The process of solving the data correction mathematical model to obtain the correction values ​​for each process variable is as follows: The Lagrange multiplier method is used to obtain the correction values ​​of each process variable by constructing the Lagrange function and solving the partial derivative equations.

7. The method for detecting and correcting abnormal operation data of a power plant according to claim 1, characterized in that, The calculation of the detection factor for each process variable based on its measured value, correction value, and measurement root mean square error is as follows: The detection factor is obtained by calculating the absolute value of the difference between the measured value and the corrected value and dividing it by the measurement root mean square error.

8. The method for detecting and correcting abnormal operation data of a power plant according to claim 1, characterized in that, The target thermal system is specifically: The boiler system, wherein the process variables include at least one or more of the following: feedwater flow rate, coal feed rate, and lower heating value of coal feed.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements a method for detecting and correcting abnormal operating data of a power plant as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements a method for detecting and correcting abnormal operating data of a power plant as described in any one of claims 1 to 8.

Images