Flue gas flow determination method, device, equipment, medium and product

Abstract

The invention relates to the technical field of carbon emission metering, and discloses a flue gas flow determination method, device and equipment, a medium and a product, and the method comprises the following steps: obtaining a flue gas flow actual value and a flue gas flow correlation index; processing the flue gas flow correlation index by using a flue gas flow prediction model to obtain a flue gas flow prediction value; based on the flue gas flow actual value and the flue gas flow predicted value, a flue gas flow residual value and a flue gas flow standardized residual value are obtained; based on the flue gas flow residual value and the flue gas flow standardized residual value, the flue gas flow actual value is judged, and target flue gas flow abnormal data is obtained; and replacing the target flue gas flow abnormal data with the corresponding flue gas flow predicted value to obtain updated flue gas flow data. Abnormality judgment is performed through the flue gas flow residual value and the standardized residual value, the target flue gas flow abnormal data are accurately obtained, the target flue gas flow abnormal data are replaced with the flue gas flow predicted value, and the accuracy of the flue gas flow data is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of carbon emission measurement, and specifically relates to a method, device, equipment, medium and product for determining flue gas flow rate. Background Art

[0002] The accurate and reliable carbon emission data is the basic guarantee for the effective and standardized operation of the carbon market. The calculation of carbon emissions generally adopts the nuclear method or the continuous monitoring method. Among them, the technical principle of continuous carbon emission monitoring is to use a continuous emission monitoring system to online monitor parameters such as CO2 concentration, flue gas flow rate, temperature, and humidity in the flue gas, and calculate the product of the CO2 concentration and the flue gas flow rate in a certain period of time in real time to obtain the carbon emission.

[0003] Current research results show that for continuous carbon emission monitoring technology, the monitoring of CO2 concentration generally does not produce large deviations, while the deviation of flue gas flow rate monitoring is relatively large, which is the key influencing factor affecting the monitoring result of carbon emissions. Therefore, carrying out research on flue gas flow rate monitoring technology is a current hot topic, but the judgment technology for abnormal data of flue gas flow rate is relatively lacking in the related technologies. Summary of the Invention

[0004] In view of this, the present disclosure provides a method, device, equipment, medium and product for determining flue gas flow rate to solve the problem of judging abnormal data of flue gas flow rate.

[0005] In a first aspect, the present disclosure provides a method for determining flue gas flow rate, the method comprising:

[0006] Obtaining the actual value of flue gas flow rate and the associated indicators of flue gas flow rate;

[0007] Processing the associated indicators of flue gas flow rate by using a flue gas flow rate prediction model to obtain a predicted value of flue gas flow rate;

[0008] Based on the actual value of flue gas flow rate and the predicted value of flue gas flow rate, obtaining a residual value of flue gas flow rate and a standardized residual value of flue gas flow rate;

[0009] Judging the actual value of flue gas flow rate based on the residual value of flue gas flow rate and the standardized residual value of flue gas flow rate to obtain target abnormal data of flue gas flow rate;

[0010] Replacing the target abnormal data of flue gas flow rate with the corresponding predicted value of flue gas flow rate to obtain updated flue gas flow rate data.

[0011] In the embodiments of the present disclosure, by obtaining the actual value of the flue gas flow rate and the associated index of the flue gas flow rate; processing the associated index of the flue gas flow rate by using the flue gas flow rate prediction model to obtain the predicted value of the flue gas flow rate; based on the actual value of the flue gas flow rate and the predicted value of the flue gas flow rate, obtaining the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate; judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate to obtain the abnormal data of the target flue gas flow rate; replacing the abnormal data of the target flue gas flow rate with the corresponding predicted value of the flue gas flow rate to obtain the updated flue gas flow rate data. Since the embodiments of the present disclosure perform abnormal judgment through the residual value of the flue gas flow rate and the standardized residual value, accurately obtain the abnormal data of the target flue gas flow rate, and replace the abnormal data of the target flue gas flow rate with the predicted value of the flue gas flow rate, the accuracy of the flue gas flow rate data is improved.

[0012] In an alternative embodiment, judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate to obtain the abnormal data of the target flue gas flow rate includes:

[0013] Judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and a preset rule to obtain the first abnormal data of the flue gas flow rate;

[0014] Judging the actual value of the flue gas flow rate based on the standardized residual value of the flue gas flow rate and a preset threshold to obtain the second abnormal data of the flue gas flow rate;

[0015] When the actual value of the flue gas flow rate is the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is the second abnormal data of the flue gas flow rate, the abnormal data of the target flue gas flow rate is obtained.

[0016] In the embodiments of the present disclosure, by respectively performing abnormal judgment on the actual value of the flue gas flow rate by using the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate, the accuracy of abnormal judgment in the flue gas flow rate monitoring process can be improved, and the abnormal data of the target flue gas flow rate can be accurately obtained.

[0017] In an alternative embodiment, judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and a preset rule to obtain the first abnormal data of the flue gas flow rate includes:

[0018] Fusing the residual value of the flue gas flow rate and the target index in the associated index of the flue gas flow rate to obtain the fused residual value of the flue gas flow rate;

[0019] Sorting the fused residual value of the flue gas flow rate to obtain a sorting queue;

[0020] Obtaining the first residual value located at the first preset position and the second residual value located at the second preset position in the sorting queue;

[0021] Based on the first residual value and the second residual value, obtaining the target threshold;

[0022] Screen the actual value of the flue gas flow rate based on the target threshold to obtain the first abnormal data of the flue gas flow rate.

[0023] In the embodiments of the present disclosure, by using the residual value of the flue gas flow rate to obtain the target threshold and using the target threshold to screen the actual value of the flue gas flow rate, the accuracy of abnormal judgment in the process of flue gas flow rate monitoring can be improved, and the first abnormal data of the flue gas flow rate can be accurately obtained.

[0024] In an alternative embodiment, judge the actual value of the flue gas flow rate based on the standardized residual value of the flue gas flow rate and a preset threshold to obtain the second abnormal data of the flue gas flow rate, including:

[0025] Generate a standardized residual plot based on the standardized residual value of the flue gas flow rate and the predicted value of the flue gas flow rate;

[0026] Judge whether the standardized residual value of the flue gas flow rate is included in the preset threshold based on the standardized residual plot;

[0027] In the case where the standardized residual value of the flue gas flow rate is not included in the preset threshold, obtain the second abnormal data of the flue gas flow rate.

[0028] In the embodiments of the present disclosure, by using the standardized residual value of the flue gas flow rate and the predicted value of the flue gas flow rate to generate a standardized residual plot, and using the standardized residual plot and the preset threshold to perform abnormal judgment on the actual value of the flue gas flow rate, the accuracy of abnormal judgment in the process of flue gas flow rate monitoring can be improved, and the second abnormal data of the flue gas flow rate can be accurately obtained.

[0029] In an alternative embodiment, the method further includes:

[0030] In the case where the actual value of the flue gas flow rate is the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is not the second abnormal data of the flue gas flow rate, mark the actual value of the flue gas flow rate;

[0031] In the case where the actual value of the flue gas flow rate is not the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is the second abnormal data of the flue gas flow rate, mark the actual value of the flue gas flow rate;

[0032] In the case where the actual value of the flue gas flow rate is not the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is not the second abnormal data of the flue gas flow rate, determine that the actual value of the flue gas flow rate is non-abnormal data.

[0033] In the embodiments of the present disclosure, by marking the flue gas flow rate data in the actual value of the flue gas flow rate that is the first abnormal flue gas flow rate data or the second abnormal flue gas flow rate data, and determining the flue gas flow rate data that is neither the first abnormal flue gas flow rate data nor the second abnormal flue gas flow rate data in the actual value of the flue gas flow rate as non-abnormal data, the utilization efficiency of the flue gas flow rate data can be improved, and the stability and reliability of the flue gas flow rate monitoring system can be ensured.

[0034] In an alternative embodiment, after replacing the target abnormal flue gas flow rate data with the corresponding predicted value of the flue gas flow rate to obtain the updated flue gas flow rate data, the method further includes:

[0035] Adjusting the model parameters of the flue gas flow rate prediction model by using the updated flue gas flow rate data to obtain an updated flue gas flow rate prediction model.

[0036] In the embodiments of the present disclosure, by updating the flue gas flow rate prediction model by using the updated flue gas flow rate data, the prediction ability of the flue gas flow rate prediction model can be enhanced, and the accuracy of the flue gas flow rate data can be improved.

[0037] In a second aspect, the present disclosure provides a device for determining the flue gas flow rate, the device includes:

[0038] An acquisition module, configured to acquire the actual value of the flue gas flow rate and the flue gas flow rate correlation index;

[0039] A processing module, configured to process the flue gas flow rate correlation index by using the flue gas flow rate prediction model to obtain a predicted value of the flue gas flow rate;

[0040] An obtaining module, configured to obtain a flue gas flow rate residual value and a normalized flue gas flow rate residual value based on the actual value of the flue gas flow rate and the predicted value of the flue gas flow rate;

[0041] A judgment module, configured to judge the actual value of the flue gas flow rate based on the flue gas flow rate residual value and the normalized flue gas flow rate residual value to obtain target abnormal flue gas flow rate data;

[0042] A replacement module, configured to replace the target abnormal flue gas flow rate data with the corresponding predicted value of the flue gas flow rate to obtain updated flue gas flow rate data.

[0043] In a third aspect, the present disclosure provides a computer device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method for determining the flue gas flow rate according to the first aspect or any corresponding embodiment thereof.

[0044] Fourthly, the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the method for determining the flue gas flow rate according to the first aspect or any corresponding embodiment thereof as described above.

[0045] Fifthly, the present disclosure provides a computer program product, including computer instructions, and the computer instructions are used to cause a computer to execute the method for determining the flue gas flow rate according to the first aspect or any corresponding embodiment thereof as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the following will briefly introduce the drawings required to be used in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0047] Figure 1 is a flowchart of the method for determining the flue gas flow rate according to an embodiment of the present disclosure;

[0048] Figure 2 is a flowchart of another method for determining the flue gas flow rate according to an embodiment of the present disclosure;

[0049] Figure 3 is a system architecture diagram of the method for determining the flue gas flow rate according to an embodiment of the present disclosure;

[0050] Figure 4 is a structural block diagram of the device for determining the flue gas flow rate according to an embodiment of the present disclosure;

[0051] Figure 5 is a schematic hardware structure diagram of the computer device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present disclosure.

[0053] The accuracy and reliability of carbon emission data are the basic guarantees for the effective and standardized operation of the carbon market. The calculation of carbon emissions generally adopts the nuclear method or the continuous monitoring method. The nuclear method calculates and determines the carbon emissions by multiplying the consumption of fossil fuels by a certain emission factor coefficient; the continuous monitoring method uses a monitoring system to collect the real-time emissions of flue gas carbon dioxide to determine the carbon emissions. For the situation of complex coal quality and large changes in coal-fired power generation load, the nuclear method has defects such as insufficient scientificity, high management costs, and large human interference factors.

[0054] The technical principle of continuous carbon emission monitoring is to use a continuous emission monitoring system to on-line monitor parameters such as the CO2 concentration, flue gas flow rate, temperature, and humidity in the flue gas, and calculate the product of the CO2 concentration and the flue gas flow rate in a certain period of time in real time to obtain the carbon emissions. For the continuous carbon emission monitoring technology, current research results show that the monitoring of CO2 concentration generally does not produce large deviations, while the deviation of flue gas flow rate monitoring is relatively large, which is the key influencing factor affecting the monitoring results of carbon emissions. Therefore, carrying out research on flue gas flow rate monitoring technology is a current hot spot, but the judgment technology for abnormal data of flue gas flow rate is relatively lacking in related technologies.

[0055] The flue gas automatic monitoring system in related technologies can classify the data of states such as faults, maintenance, calibration, and backwashing in the process of flue gas flow rate monitoring as invalid data, and perform relevant marking and data replacement on the invalid data. However, for the anomalies caused by fluctuations in flue gas flow rate data due to phenomena such as equipment zero drift, device vibration, flow field turbulence interference, and medium interference during the process of flue gas flow rate monitoring, related technologies do not have relevant calibration and diagnosis methods. In addition, related technologies generally replace invalid data with the maximum value of the effective hourly emissions in a period of time before the previous calibration, and this replacement method cannot reflect the actual situation.

[0056] To solve the above problems, according to an embodiment of the present disclosure, an embodiment of a method for determining flue gas flow rate is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0057] In this embodiment, a method for determining flue gas flow rate is provided, as Figure 1 shown, Figure 1 is a schematic flowchart of a method for determining flue gas flow rate according to an embodiment of the present disclosure. This process can be applied to a server and includes the following steps:

[0058] Step S101, obtain the actual value of the flue gas flow rate and the associated indicators of the flue gas flow rate.

[0059] Optionally, in the embodiments of the present disclosure, the actual value of the flue gas flow rate refers to the flue gas flow rate data measured by a thermal power unit. The associated indicators of the flue gas flow rate include the boiler load rate, the excess air coefficient, the flue gas humidity, etc.

[0060] Among them, the boiler load rate is the ratio of the actual steam output of the boiler to the rated steam output of the boiler, which is used to measure the relationship between the actual load and the rated load of the boiler and reflects the operating load level of the boiler at a certain moment.

[0061] The excess air coefficient is the ratio of the actual amount of air supplied during the combustion process to the amount of air required for complete theoretical combustion. The excess air coefficient under different operating conditions will affect the measurement of the flue gas flow rate. During the combustion process, an appropriate excess air coefficient can ensure complete combustion of the fuel and improve the combustion efficiency; if the excess air coefficient is too small, the fuel cannot be completely burned, resulting in energy waste and increased pollutant emissions; if the excess air coefficient is too large, the heat loss of the exhaust gas will increase and the boiler efficiency will decrease.

[0062] The flue gas humidity refers to the amount of water vapor in the flue gas, which is usually measured by absolute humidity or relative humidity. Absolute humidity refers to the mass of water vapor contained in a unit volume of flue gas, and relative humidity refers to the ratio of the actual content of water vapor in the flue gas to the saturated water vapor content at the same temperature. The change of flue gas humidity will affect the density and volume of the flue gas, and thus affect the measurement result of the flue gas flow rate.

[0063] Specifically, the server measures the flue gas flow rate data through the thermal power unit at regular intervals (such as time levels of hours or minutes, etc.) to obtain the actual values of the flue gas flow rate (Q1, Q2, Q3...), and measures the boiler load rate, the excess air coefficient, the flue gas humidity, etc., to obtain the associated indicators of the flue gas flow rate, including the boiler load rate (η1, η2, η3...), the excess air coefficient (α1, α2, α3...), the flue gas humidity (φ1, φ2, φ3...), etc.

[0064] Step S102: Process the associated indicators of the flue gas flow rate by using the flue gas flow rate prediction model to obtain the predicted value of the flue gas flow rate.

[0065] Optionally, in the embodiments of the present disclosure, the flue gas flow rate prediction model is where k represents a constant related to the value, the value range of k can be 0.96 to 1.08, α represents the actual value of the excess air coefficient, α0 represents the reference value of the excess air coefficient, γ represents a constant related to the value, the value range of γ can be 1.0 to 1.06, φ represents the actual value of the flue gas humidity, φ0 represents the reference value of the flue gas humidity, η represents the boiler load rate, and A and B are constants. The predicted value of the flue gas flow rate refers to the flue gas flow rate data predicted by the flue gas flow rate prediction model.

[0066] Specifically, the server first calculates the ratio of the reference value α0 of the excess air coefficient to the measured excess air coefficients (α1, α2, α3, …) to obtain the result of the excess air coefficient ratio. Then, it selects appropriate k1, k2, k3, … according to the result of the excess air coefficient ratio, and then calculates the ratio of the reference value φ0 of the flue gas humidity to the measured flue gas humidities (φ1, φ2, φ3, …) to obtain the result of the flue gas humidity ratio. And it selects appropriate γ1, γ2, γ3, … according to the result of the flue gas humidity ratio. After that, the server inputs the flue gas flow rate correlation index into the flue gas flow rate prediction model to calculate the predicted values of the flue gas flow rate (Q1′, Q2′, Q3′, …).

[0067] In addition, before obtaining the predicted value of the flue gas flow rate using the flue gas flow rate prediction model, the server can establish the flue gas flow rate prediction model in advance.

[0068] Specifically, the server first measures the flue gas flow rate data through a thermal power unit at regular intervals (such as every hour or minute) within a period of time (such as 3 months) to obtain historical flue gas flow rate data (Q1″, Q2″, Q3″, …), and measures the boiler load rate, excess air coefficient, flue gas humidity, etc. to obtain the flue gas flow rate correlation index, including the boiler load rate (η1′, η2′, η3′, …), excess air coefficient (α1′, α2′, α3′, …), flue gas humidity (φ1′, φ2′, φ3′, …), etc.

[0069] Then, the server can screen the obtained data, eliminate the data with relatively large relative deviations (such as relative deviations greater than 20%) between adjacent time intervals (such as adjacent minutes), and obtain the mean data of the data after elimination within a certain period of time (such as hourly mean data).

[0070] Next, the server uses the mean data to calculate the parameters of the initial flue gas flow rate prediction model and constructs multiple (such as 3) initial flue gas flow rate prediction models: And it obtains the correlation coefficients R1, R2, and R3 between the historical flue gas flow rate data and the flue gas flow rate correlation index in each initial flue gas flow rate prediction model.

[0071] After that, the server determines the parameters and correlation coefficients in each initial flue gas flow prediction model. If any of the correlation coefficients R1, R2, and R3 is less than the target correlation coefficient (e.g., 0.96), or the relative deviation between A1, A2, and A3 is greater than the first deviation (e.g., 1%), or the relative deviation between B1, B2, and B3 is greater than the second deviation (e.g., 8%), then the historical flue gas flow data with large deviations is removed, and the initial flue gas flow prediction model is updated until the correlation coefficients R1, R2, and R3 are all greater than the target correlation coefficient (e.g., 0.96), and the relative deviation between A1, A2, and A3 does not exceed the first deviation (e.g., 1%), and the relative deviation between B1, B2, and B3 does not exceed the second deviation (e.g., 8%). Calculate the mean value of A1, A2, and A3 to obtain the parameter A (e.g., Or ), calculate the mean value of B1, B2, and B3 to obtain the parameter B (e.g., Or Thus, the flue gas flow prediction model is obtained

[0072] Step S103: Based on the actual flue gas flow value and the predicted flue gas flow value, obtain the flue gas flow residual value and the standardized flue gas flow residual value.

[0073] Optionally, in the embodiments of the present disclosure, after the server obtains the actual flue gas flow value and the predicted flue gas flow value, it calculates the flue gas flow residual values (m1, m2, m3...) between the actual flue gas flow value and the predicted flue gas flow value. The calculation formula is as follows: m1 = Q1 - Q1′, m2 = Q2 - Q2′, m3 = Q3 - Q3′...

[0074] Then, the server calculates the standardized flue gas flow residual value by using the flue gas flow residual value. Taking the historical flue gas flow data of 1440 minutes as an example, the calculation formula of the standardized flue gas flow residual value is as follows:

[0075]

[0076] Wherein, represents the average value of the flue gas flow residual value, σ m represents the standard deviation of the flue gas flow residual value, and δ i represents the standardized flue gas flow residual value.

[0077] Step S104: Based on the flue gas flow residual value and the standardized flue gas flow residual value, judge the actual flue gas flow value to obtain the target flue gas flow abnormal data.

[0078] Optionally, in the embodiments of the present disclosure, the target flue gas flow abnormal data refers to the abnormal data in the actual flue gas flow value.

[0079] Specifically, the server first judges the actual flue gas flow value based on the residual value of the flue gas flow and a preset rule (such as the interquartile range method) to obtain the first abnormal flue gas flow data, and then judges the actual flue gas flow value based on the standardized residual value of the flue gas flow and a preset threshold (such as [2, 2]) to obtain the second abnormal flue gas flow data. Finally, when the actual flue gas flow value is the first abnormal flue gas flow data and the actual flue gas flow value is the second abnormal flue gas flow data, the corresponding actual flue gas flow value is determined as the target abnormal flue gas flow data.

[0080] Step S105: Replace the target abnormal flue gas flow data with the corresponding predicted flue gas flow value to obtain the updated flue gas flow data.

[0081] Optionally, in the embodiment of the present disclosure, the server obtains the predicted flue gas flow value corresponding to the target abnormal flue gas flow data, and replaces the target abnormal flue gas flow data with the corresponding predicted flue gas flow value to obtain the updated flue gas flow data.

[0082] In the embodiment of the present disclosure, by obtaining the actual flue gas flow value and the flue gas flow correlation index; using the flue gas flow prediction model to process the flue gas flow correlation index to obtain the predicted flue gas flow value; based on the actual flue gas flow value and the predicted flue gas flow value, obtaining the residual value of the flue gas flow and the standardized residual value of the flue gas flow; judging the actual flue gas flow value based on the residual value of the flue gas flow and the standardized residual value of the flue gas flow to obtain the target abnormal flue gas flow data; replacing the target abnormal flue gas flow data with the corresponding predicted flue gas flow value to obtain the updated flue gas flow data. Since the embodiment of the present disclosure performs abnormal judgment through the residual value of the flue gas flow and the standardized residual value, accurately obtains the target abnormal flue gas flow data, and replaces the target abnormal flue gas flow data with the predicted flue gas flow value, the accuracy of the flue gas flow data is improved.

[0083] In some alternative embodiments, the present embodiment provides a method for determining the flue gas flow, such as Figure 2 shown Figure 2 is a schematic flowchart of another method for determining the flue gas flow according to the embodiment of the present disclosure. This process can be applied to a server and includes the following steps:

[0084] Step S201: Obtain the actual flue gas flow value and the flue gas flow correlation index. For details, please refer to Figure 1 Step S101 of the embodiment shown, which will not be elaborated here.

[0085] Step S202: Use the flue gas flow prediction model to process the flue gas flow correlation index to obtain the predicted flue gas flow value. For details, please refer to Figure 1 Step S102 of the embodiment shown, which will not be elaborated here.

[0086] Step S203: Based on the actual value and the predicted value of the flue gas flow rate, obtain the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate. For details, please refer to Figure 1 Step S103 of the embodiment shown, which will not be elaborated here.

[0087] Step S204: Judge the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate to obtain the abnormal data of the target flue gas flow rate.

[0088] Specifically, the above-mentioned step S204 includes:

[0089] Step S2041: Judge the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and a preset rule to obtain the first abnormal data of the flue gas flow rate.

[0090] Optionally, in the embodiments of the present disclosure, the preset rule may be the interquartile range method. The first abnormal data of the flue gas flow rate refers to the abnormal data obtained by judging the abnormality through the residual value of the flue gas flow rate.

[0091] Specifically, the interquartile range method is a statistical method used to describe the degree of data dispersion. After the server arranges the residual value data of the flue gas flow rate in ascending order, the data is divided into four equal parts, and the values at the three splitting points are the quartiles. Among them, the first quartile (Q1) is also called the lower quartile, which is the value at the 25% position in the data; the second quartile (Q2) is the median, which divides the data into upper and lower parts, each accounting for 50%; the third quartile (Q3) is also called the upper quartile, which is at the 75% position in the data. The interquartile range (IQR) is the difference between the third quartile (Q3) and the first quartile (Q1), that is, IQR = Q3 - Q1.

[0092] In some alternative embodiments, the above-mentioned step S2041 includes:

[0093] Step a1: Integrate the residual value of the flue gas flow rate and the target index in the flue gas flow rate correlation index to obtain the integrated residual value of the flue gas flow rate.

[0094] Step a2: Sort the integrated residual value of the flue gas flow rate to obtain a sorted queue.

[0095] Step a3: Obtain the first residual value at the first preset position and the second residual value at the second preset position in the sorted queue.

[0096] Step a4: Based on the first residual value and the second residual value, obtain the target threshold.

[0097] Step a5: Screen the actual value of the flue gas flow rate based on the target threshold to obtain the first abnormal data of the flue gas flow rate.

[0098] Optionally, in the embodiments of the present disclosure, the target index refers to the boiler load rate in the flue gas flow rate related indexes. The first preset position refers to the 25% position in the sorting queue, and the first residual value refers to the residual value at the first preset position in the sorting queue, that is, the first quartile. The second preset position refers to the 75% position in the sorting queue, and the second residual value refers to the residual value at the second preset position in the sorting queue, that is, the third quartile. The target threshold refers to the threshold of the flue gas flow rate residual value.

[0099] Specifically, the server first divides the flue gas flow rate residual value by the corresponding boiler load rate to obtain the fused flue gas flow rate residual values (x1, x2, x3...), and the calculation formula is as follows:

[0100] Then, the server arranges the fused flue gas flow rate residual values in ascending order to obtain a sorting queue, and obtains the first residual value at the 25% position in the sorting queue, that is, the first quartile (Q1), and obtains the second residual value at the 75% position in the sorting queue, that is, the third quartile (Q3). Then, calculate the difference between the first residual value and the second residual value to obtain the interquartile range (IQR), and calculate the target threshold (Q1 - 1.5IQR to Q3 + 1.5IQR) based on the first quartile (Q1), the third quartile (Q3), and the interquartile range (IQR).

[0101] After that, the server screens the actual value of the flue gas flow rate according to the target threshold. If the actual value of the flue gas flow rate is included in the target threshold, the corresponding actual value of the flue gas flow rate is determined as the first abnormal data of the flue gas flow rate.

[0102] In the above implementation manner, by using the flue gas flow rate residual value to obtain the target threshold and using the target threshold to screen the actual value of the flue gas flow rate, the accuracy of abnormal judgment in the flue gas flow rate monitoring process can be improved, and the first abnormal data of the flue gas flow rate can be accurately obtained.

[0103] Step S2042: Judge the actual value of the flue gas flow rate based on the standardized residual value of the flue gas flow rate and the preset threshold to obtain the second abnormal data of the flue gas flow rate.

[0104] Optionally, in the embodiments of the present disclosure, the preset threshold refers to the threshold of the standardized residual value of the flue gas flow rate, such as [2, 2]. The second abnormal data of the flue gas flow rate refers to the abnormal data obtained by abnormal judgment through the standardized residual value of the flue gas flow rate.

[0105] Specifically, the server screens the actual value of the flue gas flow rate according to a preset threshold. If the actual value of the flue gas flow rate is not included in the preset threshold, the corresponding actual value of the flue gas flow rate is determined as the second abnormal data of the flue gas flow rate.

[0106] In some alternative embodiments, step S2042 includes:

[0107] Step b1, generating a standardized residual plot based on the standardized residual value of the flue gas flow rate and the predicted value of the flue gas flow rate.

[0108] Step b2, determining whether the standardized residual value of the flue gas flow rate is included in a preset threshold based on the standardized residual plot.

[0109] Step b3, obtaining the second abnormal data of the flue gas flow rate when the standardized residual value of the flue gas flow rate is not included in the preset threshold.

[0110] Optionally, in the embodiments of the present disclosure, the standardized residual plot refers to a plot with the predicted value of the flue gas flow rate as the abscissa and the standardized residual value of the flue gas flow rate as the ordinate.

[0111] Specifically, the server first uses the predicted value of the flue gas flow rate as the abscissa and the standardized residual value of the flue gas flow rate as the ordinate, and plots the standardized residual value of the flue gas flow rate at each observation point on the coordinate plane to generate a standardized residual plot.

[0112] Then, the server checks each standardized residual value of the flue gas flow rate in the standardized residual plot one by one to determine whether it is included in the preset threshold. If there is a standardized residual value of the flue gas flow rate that is not included in the preset threshold, the corresponding standardized residual value of the flue gas flow rate is determined as the second abnormal data of the flue gas flow rate.

[0113] In the above embodiments, by generating a standardized residual plot using the standardized residual value of the flue gas flow rate and the predicted value of the flue gas flow rate, and using the standardized residual plot and the preset threshold to judge the abnormality of the actual value of the flue gas flow rate, the accuracy of the abnormality judgment in the flue gas flow rate monitoring process can be improved, and the second abnormal data of the flue gas flow rate can be accurately obtained.

[0114] Step S2043, obtaining the target abnormal data of the flue gas flow rate when the actual value of the flue gas flow rate is the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is the second abnormal data of the flue gas flow rate.

[0115] Optionally, in the embodiments of the present disclosure, after the server obtains the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate, it judges the relationship between each actual value of the flue gas flow rate and the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate. If there is an actual value of the flue gas flow rate that is both the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate, the corresponding actual value of the flue gas flow rate is determined as the target abnormal data of the flue gas flow rate.

[0116] Step S2044: When the actual flue gas flow rate is the first abnormal data of the flue gas flow rate and is not the second abnormal data of the flue gas flow rate, mark the actual flue gas flow rate.

[0117] Optionally, in the embodiment of the present disclosure, after the server obtains the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate, it judges the relationship between each actual flue gas flow rate and the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate. If there is an actual flue gas flow rate that is the first abnormal data of the flue gas flow rate and is not the second abnormal data of the flue gas flow rate, mark the corresponding actual flue gas flow rate for subsequent data analysis.

[0118] Step S2045: When the actual flue gas flow rate is not the first abnormal data of the flue gas flow rate and is the second abnormal data of the flue gas flow rate, mark the actual flue gas flow rate.

[0119] Optionally, in the embodiment of the present disclosure, after the server obtains the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate, it judges the relationship between each actual flue gas flow rate and the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate. If there is an actual flue gas flow rate that is not the first abnormal data of the flue gas flow rate and is the second abnormal data of the flue gas flow rate, mark the corresponding actual flue gas flow rate for subsequent data analysis.

[0120] Step S2046: When the actual flue gas flow rate is not the first abnormal data of the flue gas flow rate and is not the second abnormal data of the flue gas flow rate, determine that the actual flue gas flow rate is non-abnormal data.

[0121] Optionally, in the embodiment of the present disclosure, after the server obtains the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate, it judges the relationship between each actual flue gas flow rate and the first abnormal data of the flue gas flow rate and the second abnormal data of the flue gas flow rate. If there is an actual flue gas flow rate that is neither the first abnormal data of the flue gas flow rate nor the second abnormal data of the flue gas flow rate, determine the corresponding actual flue gas flow rate as non-abnormal data.

[0122] Step S205: Replace the target abnormal data of the flue gas flow rate with the corresponding predicted value of the flue gas flow rate to obtain the updated flue gas flow rate data. For details, please refer to Figure 1 Step S105 of the illustrated embodiment, which will not be elaborated here.

[0123] Step S206: Adjust the model parameters of the flue gas flow rate prediction model by using the updated flue gas flow rate data to obtain the updated flue gas flow rate prediction model.

[0124] Optionally, in the embodiments of the present disclosure, the server retrains the flue gas flow prediction model using the updated flue gas flow data, adjusts the model parameters of the flue gas flow prediction model, and obtains an updated flue gas flow prediction model.

[0125] It should be noted that the server can regularly (e.g., every month) use the updated flue gas flow prediction model to process the flue gas flow correlation indicators, obtain new flue gas flow prediction values, and then based on the new actual flue gas flow values and the new flue gas flow prediction values, obtain new flue gas flow residuals and new standardized flue gas flow residuals. Then, based on the new flue gas flow residuals and the new standardized flue gas flow residuals, judge the new actual flue gas flow values to obtain new target flue gas flow abnormal data. After that, replace the new target flue gas flow abnormal data with the corresponding new flue gas flow prediction values to obtain new updated flue gas flow data, and use the new updated flue gas flow data to retrain the flue gas flow prediction model to achieve dynamic update of the flue gas flow prediction model.

[0126] In the embodiments of the present disclosure, by using the flue gas flow residuals and the standardized flue gas flow residuals to respectively judge the abnormality of the actual flue gas flow values, the accuracy of abnormality judgment in the flue gas flow monitoring process can be improved, and the target flue gas flow abnormal data can be accurately obtained. By marking the flue gas flow data that is the first flue gas flow abnormal data or the second flue gas flow abnormal data in the actual flue gas flow values, and determining the flue gas flow data that is neither the first flue gas flow abnormal data nor the second flue gas flow abnormal data in the actual flue gas flow values as non-abnormal data, the utilization efficiency of the flue gas flow data can be improved, and the stability and reliability of the flue gas flow monitoring system can be ensured. By using the updated flue gas flow data to update the flue gas flow prediction model, the prediction ability of the flue gas flow prediction model can be enhanced, and the accuracy of the flue gas flow data can be improved.

[0127] In some alternative embodiments, such as Figure 3 shown, Figure 3 is a system architecture diagram of the method for determining the flue gas flow according to the embodiments of the present disclosure, including a model establishment and update module ( Figure 3 label 1-1 in Figure 3 ), a data acquisition module ( Figure 3 label 1-2), a data processing and storage module ( Figure 3 label 2), a data judgment module ( Figure 3 label 3), an abnormal data replacement module ( Figure 3 label 4), and a data judgment result statistics and output module (

[0128] Among them, the server imports data such as flue gas flow data and flue gas flow - related indicators through the model establishment and update module, establishes a flue gas flow prediction model according to the machine - learning algorithm, and updates the flue gas flow prediction model based on the updated flue gas flow data to obtain the updated flue gas flow prediction model; obtains data such as flue gas flow data and flue gas flow - related indicators through the data acquisition module; processes and calculates the flue gas flow data and flue gas flow - related indicators and stores the calculation process and results through the data processing and storage module; judges the abnormality of the actual value of the flue gas flow through the data judgment module; replaces the abnormal data of the target flue gas flow through the abnormal data replacement module; and statistically analyzes and outputs the data judgment results through the data judgment result statistics and output module.

[0129] In this embodiment, a device for determining the flue gas flow is also provided. This device is used to implement the above - mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0130] This embodiment provides a device for determining the flue gas flow, as Figure 4 shown, including:

[0131] An acquisition module 401, configured to acquire the actual value of the flue gas flow and the flue gas flow - related indicators;

[0132] A processing module 402, configured to process the flue gas flow - related indicators by using the flue gas flow prediction model to obtain a predicted value of the flue gas flow;

[0133] A obtaining module 403, configured to obtain a residual value of the flue gas flow and a standardized residual value of the flue gas flow based on the actual value of the flue gas flow and the predicted value of the flue gas flow;

[0134] A judgment module 404, configured to judge the actual value of the flue gas flow based on the residual value of the flue gas flow and the standardized residual value of the flue gas flow to obtain abnormal data of the target flue gas flow;

[0135] A replacement module 405, configured to replace the abnormal data of the target flue gas flow with the corresponding predicted value of the flue gas flow to obtain updated flue gas flow data.

[0136] In the embodiments of the present disclosure, by obtaining the actual value of the flue gas flow rate and the associated index of the flue gas flow rate; processing the associated index of the flue gas flow rate by using the flue gas flow rate prediction model to obtain the predicted value of the flue gas flow rate; based on the actual value of the flue gas flow rate and the predicted value of the flue gas flow rate, obtaining the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate; judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate to obtain the abnormal data of the target flue gas flow rate; replacing the abnormal data of the target flue gas flow rate with the corresponding predicted value of the flue gas flow rate to obtain the updated flue gas flow rate data. Since the embodiments of the present disclosure perform abnormal judgment through the residual value of the flue gas flow rate and the standardized residual value, accurately obtain the abnormal data of the target flue gas flow rate, and replace the abnormal data of the target flue gas flow rate with the predicted value of the flue gas flow rate, the accuracy of the flue gas flow rate data is improved.

[0137] In some alternative embodiments, the judgment module 404 includes:

[0138] The first judgment sub-module is used to judge the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and a preset rule to obtain the first abnormal data of the flue gas flow rate;

[0139] The second judgment sub-module is used to judge the actual value of the flue gas flow rate based on the standardized residual value of the flue gas flow rate and a preset threshold to obtain the second abnormal data of the flue gas flow rate;

[0140] The obtaining sub-module is used to obtain the abnormal data of the target flue gas flow rate when the actual value of the flue gas flow rate is the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is the second abnormal data of the flue gas flow rate.

[0141] In some alternative embodiments, the first judgment sub-module includes:

[0142] The fusion unit is used to fuse the residual value of the flue gas flow rate and the target index in the associated index of the flue gas flow rate to obtain the fused residual value of the flue gas flow rate;

[0143] The sorting unit is used to sort the fused residual value of the flue gas flow rate to obtain a sorted queue;

[0144] The obtaining unit is used to obtain the first residual value located at the first preset position and the second residual value located at the second preset position in the sorted queue;

[0145] The first obtaining unit is used to obtain a target threshold based on the first residual value and the second residual value;

[0146] The screening unit is used to screen the actual value of the flue gas flow rate based on the target threshold to obtain the first abnormal data of the flue gas flow rate.

[0147] In some alternative embodiments, the second judgment sub-module includes:

[0148] A generating unit, configured to generate a standardized residual plot based on the standardized residual value of the flue gas flow rate and the predicted value of the flue gas flow rate;

[0149] A judging unit, configured to judge whether the standardized residual value of the flue gas flow rate is included in a preset threshold based on the standardized residual plot;

[0150] A second obtaining unit, configured to obtain second abnormal flue gas flow rate data when the standardized residual value of the flue gas flow rate is not included in the preset threshold.

[0151] In some alternative embodiments, the apparatus further includes:

[0152] A first marking module, configured to mark the actual value of the flue gas flow rate when the actual value of the flue gas flow rate is the first abnormal flue gas flow rate data and the actual value of the flue gas flow rate is not the second abnormal flue gas flow rate data;

[0153] A second marking module, configured to mark the actual value of the flue gas flow rate when the actual value of the flue gas flow rate is not the first abnormal flue gas flow rate data and the actual value of the flue gas flow rate is the second abnormal flue gas flow rate data;

[0154] A determining module, configured to determine that the actual value of the flue gas flow rate is non-abnormal data when the actual value of the flue gas flow rate is not the first abnormal flue gas flow rate data and the actual value of the flue gas flow rate is not the second abnormal flue gas flow rate data.

[0155] In some alternative embodiments, the apparatus further includes:

[0156] An adjusting module, configured to adjust the model parameters of the flue gas flow rate prediction model by using the updated flue gas flow rate data to obtain an updated flue gas flow rate prediction model.

[0157] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding foregoing embodiments, and will not be elaborated herein.

[0158] The apparatus for determining the flue gas flow rate in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0159] This embodiment of the present disclosure further provides a computer device having the Figure 4 apparatus for determining the flue gas flow rate as shown above.

[0160] Please refer to Figure 5 , Figure 5The following is a schematic structural diagram of a computer device provided by an alternative embodiment of the present disclosure. As Figure 5 shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as a server array, a set of blade servers, or a multi-processor system). Figure 5 Here, one processor 10 is taken as an example.

[0161] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above hardware chip can be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above programmable logic device can be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0162] Among them, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0163] The memory 20 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 can optionally include a memory remotely set relative to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0164] The memory 20 can include a volatile memory, such as a random access memory; the memory can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 can also include a combination of the above types of memories.

[0165] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0166] Embodiments of the present disclosure also provide a computer-readable storage medium. The methods according to the embodiments of the present disclosure can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the methods described herein can be stored in such software processes on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods shown in the above embodiments are implemented.

[0167] A part of the present disclosure can be applied as a computer program product, such as computer program instructions. When executed by a computer, through the operation of the computer, the methods and / or technical solutions according to the present disclosure can be invoked or provided. Those skilled in the art should be able to understand that the forms of existence of computer program instructions in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible by the computer.

[0168] Although the embodiments of the present disclosure are described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for determining the flue gas flow rate, characterized in that, The method includes: Obtaining the actual value of the flue gas flow rate and the associated index of the flue gas flow rate; Processing the associated index of the flue gas flow rate by using a flue gas flow rate prediction model to obtain a predicted value of the flue gas flow rate; Based on the actual value of the flue gas flow rate and the predicted value of the flue gas flow rate, obtaining a residual value of the flue gas flow rate and a standardized residual value of the flue gas flow rate; Judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate to obtain abnormal data of the target flue gas flow rate; Replacing the abnormal data of the target flue gas flow rate with the corresponding predicted value of the flue gas flow rate to obtain updated flue gas flow rate data.

2. The method according to claim 1, wherein The judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate to obtain abnormal data of the target flue gas flow rate includes: Judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and a preset rule to obtain first abnormal data of the flue gas flow rate; Judging the actual value of the flue gas flow rate based on the standardized residual value of the flue gas flow rate and a preset threshold to obtain second abnormal data of the flue gas flow rate; When the actual value of the flue gas flow rate is the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is the second abnormal data of the flue gas flow rate, obtaining the abnormal data of the target flue gas flow rate.

3. The method according to claim 2, wherein The judging the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and a preset rule to obtain first abnormal data of the flue gas flow rate includes: Fusing the residual value of the flue gas flow rate and a target index in the associated index of the flue gas flow rate to obtain a fused residual value of the flue gas flow rate; Sorting the fused residual value of the flue gas flow rate to obtain a sorted queue; Obtaining a first residual value at a first preset position and a second residual value at a second preset position in the sorted queue; Based on the first residual value and the second residual value, obtaining a target threshold; Screening the actual value of the flue gas flow rate based on the target threshold to obtain the first abnormal data of the flue gas flow rate.

4. The method according to claim 2, wherein The judging the actual value of the flue gas flow rate based on the standardized residual value of the flue gas flow rate and a preset threshold to obtain second abnormal data of the flue gas flow rate includes: Generating a standardized residual map based on the standardized residual value of the flue gas flow rate and the predicted value of the flue gas flow rate; Judging whether the standardized residual value of the flue gas flow rate is included in the preset threshold based on the standardized residual map; When the standardized residual value of the flue gas flow rate is not included in the preset threshold, obtaining the second abnormal data of the flue gas flow rate.

5. The method according to claim 2, wherein The method further includes: When the actual value of the flue gas flow rate is the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is not the second abnormal data of the flue gas flow rate, marking the actual value of the flue gas flow rate; When the actual value of the flue gas flow rate is not the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is the second abnormal data of the flue gas flow rate, marking the actual value of the flue gas flow rate; When the actual value of the flue gas flow rate is not the first abnormal data of the flue gas flow rate and the actual value of the flue gas flow rate is not the second abnormal data of the flue gas flow rate, determine that the actual value of the flue gas flow rate is non-abnormal data.

6. The method according to claim 1, wherein After replacing the target abnormal data of the flue gas flow rate with the corresponding predicted value of the flue gas flow rate to obtain the updated flue gas flow rate data, the method further includes: Adjust the model parameters of the flue gas flow rate prediction model by using the updated flue gas flow rate data to obtain an updated flue gas flow rate prediction model.

7. A device for determining the flue gas flow rate, characterized in that The device includes: An acquisition module, configured to acquire the actual value of the flue gas flow rate and the flue gas flow rate correlation index; A processing module, configured to process the flue gas flow rate correlation index by using the flue gas flow rate prediction model to obtain a predicted value of the flue gas flow rate; A obtaining module, configured to obtain a residual value of the flue gas flow rate and a standardized residual value of the flue gas flow rate based on the actual value of the flue gas flow rate and the predicted value of the flue gas flow rate; A judging module, configured to judge the actual value of the flue gas flow rate based on the residual value of the flue gas flow rate and the standardized residual value of the flue gas flow rate to obtain target abnormal data of the flue gas flow rate; A replacing module, configured to replace the target abnormal data of the flue gas flow rate with the corresponding predicted value of the flue gas flow rate to obtain updated flue gas flow rate data.

8. A computer device, characterized in that, Includes: A memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method for determining the flue gas flow rate according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the method for determining the flue gas flow rate according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions, and the computer instructions are used to cause a computer to execute the method for determining the flue gas flow rate according to any one of claims 1 to 6.

Images