Factor determination method and device, electronic equipment and storage medium

Abstract

The invention discloses a factor determination method and device, electronic equipment and a storage medium. The method comprises the steps that a target data subset is determined from a data set according to current operation data of the coal-fired boiler, the data set comprises a plurality of data subsets, and each piece of operation data comprises boiler efficiency and at least two operation factors; calculating an efficiency deviation according to the boiler efficiency of the current operation data and the boiler efficiency of the benchmarking operation data of the target data subset; if the efficiency deviation is greater than a first preset threshold value, obtaining an efficiency prediction model corresponding to the target data subset, and determining an efficiency influence parameter of each operation factor of the current operation data on the coal-fired boiler according to the efficiency prediction model corresponding to the target data subset; and determining an analysis factor according to the efficiency influence parameter. The scheme provided by the invention can accurately and quickly determine the operation factor which has a relatively large influence degree on the boiler efficiency of the coal-fired boiler, and provides a data basis for optimizing the coal-fired boiler.

Description

Technical Field

[0001] The present invention relates to the field of energy technology, and in particular to a factor determination method, device, electronic equipment and storage medium. Background Art

[0002] With the continuous advancement of the low-carbon transformation project of coal-fired power, a large number of coal-fired units are about to carry out large-scale biomass blending transformation. However, there are currently few successful cases of coal-fired units blending biomass in large proportions for a long time. This is because the combustion characteristics of biomass fuel and coal are very different. Coal-fired units burning fuels that are far away from the design parameters will inevitably have poor combustion effects. Therefore, how to analyze the factors affecting boiler efficiency at different blending ratios of biomass based on the original coal-fired boilers of coal-fired power plants has become an urgent problem to be solved. Summary of the invention

[0003] The present invention provides a factor determination method, device, electronic device and storage medium, which can accurately and quickly determine the operating factors that have a greater impact on the boiler efficiency of a coal-fired boiler, and provide a data basis for optimizing the coal-fired boiler.

[0004] According to one aspect of the present invention, a factor determination method is provided, comprising: determining a target data subset from a data set based on current operating data of a coal-fired boiler, wherein the data set includes several data subsets, one data subset corresponds to an efficiency prediction model, one data subset includes a benchmark operating data, and each operating data includes boiler efficiency and at least two operating factors; calculating an efficiency deviation based on the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset; if the efficiency deviation is greater than a first preset threshold, obtaining the efficiency prediction model corresponding to the target data subset, and determining the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler according to the efficiency prediction model corresponding to the target data subset; and determining the analysis factor based on the efficiency influence parameters.

[0005] Optionally, the operating factors include at least a first factor and a second factor, and the data set includes M*N data subsets, where M and N are both positive integers, and a data subset also includes a number of non-benchmark operating data; before selecting a target data subset from the data set based on the current operating data of the coal-fired boiler, it also includes: obtaining the historical operating data of the coal-fired boiler; sorting the historical operating data based on the first factor, and dividing the sorted historical operating data into M first sets; for each first set, sorting the historical operating data in the first set based on the second factor, and dividing the sorted historical operating data in the first set into N second sets; for each second set, taking the second set as a data subset, and taking the historical operating data with the highest boiler efficiency in the second set as the benchmark operating data of the data subset, and taking the other historical operating data in the second set as the non-benchmark operating data of the data subset.

[0006] Optionally, based on the current operating data of the coal-fired boiler, a target data subset is determined from the data set, including: using a first factor and a second factor of the current operating data as retrieval parameters to determine the target data subset from the data set; wherein the first factor is the boiler main steam flow rate, and the second factor is the biomass blending ratio.

[0007] Optionally, for any data subset, the efficiency prediction model corresponding to the data subset is determined by the following method: obtaining current training data from the data subset; inputting at least two operating factors of the current training data into the back-propagation BP neural network model to obtain training efficiency, wherein the BP neural network model includes several hidden layers; determining the loss function according to the training efficiency and the boiler efficiency of the current training data; if the training end condition is met, using the current BP neural network model as the efficiency prediction model corresponding to the data subset; if the training end condition is not met, adjusting the parameters of the BP neural network model according to the loss function, and re-obtaining the current training data from the data subset, and returning to execute the step of inputting at least two operating factors of the current training data into the BP neural network model to obtain the training efficiency.

[0008] Optionally, for any operating factor of the current operating data, the efficiency impact parameters of the operating factor on the coal-fired boiler are determined according to the efficiency prediction model corresponding to the target data subset, including: replacing the factor corresponding to the operating factor in the benchmark operating data of the target data subset with the operating factor to obtain intermediate operating data; inputting the intermediate operating data into the efficiency prediction model corresponding to the target data subset to obtain intermediate efficiency; and calculating the efficiency impact parameters of the operating factor on the coal-fired boiler based on the intermediate efficiency and the boiler efficiency of the benchmark operating data of the target data subset.

[0009] Optionally, the analysis factor is determined according to the efficiency impact parameter, including: taking the operating factor whose efficiency impact parameter is greater than or equal to the preset parameter as the analysis factor; or arranging the operating factors in descending order of the efficiency impact parameter; taking the operating factors whose efficiency impact parameters are in the first P as the analysis factor, where P is a positive integer.

[0010] Optionally, it also includes: if the efficiency deviation is less than a second preset threshold, adding the current operating data to the target data subset, and after changing the benchmark operating data of the target data subset to non-benchmark operating data, using the current operating data as the benchmark operating data of the target data subset; wherein the first preset threshold is greater than the second preset threshold, and the second preset threshold is 0 or a negative value.

[0011] According to another aspect of the present invention, a factor determination device is provided, comprising: a data subset determination module, an efficiency deviation calculation module, an influencing parameter determination module and an analysis factor determination module; the data subset determination module is used to determine a target data subset from a data set according to current operating data of the coal-fired boiler, wherein the data set includes a plurality of data subsets, one data subset corresponds to an efficiency prediction model, one data subset includes a benchmark operating data, and each operating data includes boiler efficiency and at least two operating factors; the efficiency deviation calculation module is used to calculate the efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset; the influencing parameter determination module is used to obtain the efficiency prediction model corresponding to the target data subset if the efficiency deviation is greater than a first preset threshold, and determine the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler according to the efficiency prediction model corresponding to the target data subset; the analysis factor determination module is used to determine the analysis factor according to the efficiency influence parameter.

[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the factor determination method of any embodiment of the present invention.

[0013] According to another aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the factor determination method of any embodiment of the present invention when executed.

[0014] The technical solution of the embodiment of the present invention is to find the target data subset from the data set through the current operating data of the coal-fired boiler, and then calculate the efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset; when the efficiency deviation is greater than the first preset threshold, the efficiency prediction model corresponding to the target data subset is obtained, and the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler are determined respectively according to the efficiency prediction model corresponding to the target data subset, so as to further determine the analysis factor. On the one hand, since the data set includes several data subsets, the target data subset determined according to the current operating data is the subset that best matches the current operating conditions, so it can provide a data basis for the subsequent accurate determination of the analysis factor. On the other hand, when the efficiency deviation is greater than the first preset threshold, that is, when the boiler efficiency under the current operating conditions is poor, the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler are determined respectively based on the efficiency prediction model corresponding to the target data subset. Since the efficiency prediction model corresponding to the target data subset is a model trained for the target data subset, it can accurately and quickly determine the parameters affecting the efficiency of each operating factor on the coal-fired boiler, and the analysis factors determined are more accurate, providing a data basis for the subsequent optimization of coal-fired boilers, thereby improving the economic benefits of coal-fired power plants. Thirdly, the efficiency prediction model can be continuously iterated and optimized as the operating data increases, which can further enhance the accuracy, adaptability and generalization ability of the efficiency prediction model.

[0015] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 is a flowchart of a factor determination method provided in Embodiment 1 of the present invention;

[0018] Figure 2 is a flowchart of a factor determination method provided in Embodiment 2 of the present invention;

[0019] Figure 3 is a schematic diagram of the structure of a factor determination device provided in Embodiment 3 of the present invention;

[0020] Figure 4is a schematic diagram of the structure of another factor determination device provided in Embodiment 3 of the present invention;

[0021] Figure 5 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", "target", "intermediate", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] Embodiment 1

[0025] Figure 1 It is a flow chart of a factor determination method provided in Example 1 of the present invention. This embodiment can be applied to the situation of determining factors affecting the boiler efficiency of a coal-fired boiler. The method can be executed by a factor determination device. The factor determination device can be implemented in the form of hardware and / or software. The factor determination device can be configured in an electronic device (such as a computer device, an analysis device, etc.).

[0026] like Figure 1 As shown, the method includes:

[0027] S110. Determine a target data subset from the data set based on current operating data of the coal-fired boiler, wherein the data set includes several data subsets, one data subset corresponds to an efficiency prediction model, one data subset includes a benchmark operating data, and each operating data includes boiler efficiency and at least two operating factors.

[0028] In the present invention, the coal-fired boiler can be a boiler that uses coal as fuel, or a boiler that uses biomass mixed with coal in a certain proportion as fuel. Since the technology of boilers that use coal as fuel is relatively mature, the present invention is particularly suitable for boilers that mix biomass with coal. Among them, biomass mixing is to use biomass resources such as agricultural and forestry waste, sand plants, and energy plants to implement coal-fired power units coupled with biomass power generation to reduce coal consumption and carbon emissions.

[0029] The current operation data of the coal-fired boiler refers to the operation data of the coal-fired data at the current moment. The operation data includes boiler efficiency and at least two operation factors, that is, the operation data includes at least two operation factors in addition to boiler efficiency. Exemplarily, the operation factors can be at least two of the following: main steam flow, main steam pressure, main steam temperature, amount of coal entering the furnace, unit calorific value of coal entering the furnace, biomass blending ratio, unit calorific value of biomass, primary air volume, primary air temperature, secondary air volume, burnout air volume, burnout air temperature, exhaust oxygen volume, and exhaust temperature.

[0030] The data set is determined based on the historical operation data of the coal-fired boiler (or other coal-fired boilers, or coal-fired boilers of this type). The historical operation data of the coal-fired boiler refers to the operation data of the coal-fired data at a historical moment. The data set includes several data subsets.

[0031] In one possible implementation, the historical operation data of the coal-fired boiler may be randomly divided into several data subsets. In another possible implementation, the historical operation data of the coal-fired boiler may be randomly divided into several data subsets according to a preset division method.

[0032] A data subset corresponds to an efficiency prediction model, and a data subset usually includes multiple operating data, among which there is one benchmark operating data and several non-benchmark operating data. The benchmark operating data represents the optimal operating state of the data subset to which it belongs.

[0033] Specifically, according to the current operation data of the coal-fired boiler, the method for determining the target data subset from the data set may be: according to the current operation data of the coal-fired boiler, a data subset closest to the current operation data is retrieved from the data set as the target data subset.

[0034] S120 , calculating the efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset.

[0035] The efficiency deviation is equal to the difference between the boiler efficiency of the benchmark operating data of the target data subset and the boiler efficiency of the current operating data.

[0036] S130. If the efficiency deviation is greater than a first preset threshold, an efficiency prediction model corresponding to the target data subset is obtained, and the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler are determined according to the efficiency prediction model corresponding to the target data subset.

[0037] If the efficiency deviation is greater than the first preset threshold, it means that the boiler efficiency under the current operating condition is poor, and it is necessary to analyze the factors affecting the boiler efficiency of the coal-fired boiler. At this time, the efficiency prediction model corresponding to the target data subset is obtained, and the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler are determined according to the efficiency prediction model corresponding to the target data subset.

[0038] Among them, the efficiency prediction model corresponding to the target data subset is a model trained for the target data subset, which can accurately predict the boiler efficiency under the operating conditions corresponding to the target data subset. Therefore, the efficiency influencing parameters determined based on the efficiency prediction model corresponding to the target data subset can also accurately reflect the influence of operating factors on the efficiency of coal-fired boilers, providing a good data basis for the subsequent determination of analysis factors.

[0039] In one embodiment, the value of the first preset threshold can be set according to actual needs, such as 5%, 10%, 15%, 20%, etc.

[0040] It should also be noted that if the efficiency deviation is less than or equal to the first preset threshold, it means that the boiler efficiency under the current operating conditions is good. At this time, there is no need to analyze the factors affecting the boiler efficiency of the coal-fired boiler, that is, there is no need to execute the subsequent step S140.

[0041] S140. Determine analysis factors based on efficiency influencing parameters.

[0042] In one embodiment, the number of analysis factors may be one or more.

[0043] When there are multiple analysis factors, the method for determining the analysis factors according to the efficiency impact parameter may be: taking the operating factors whose efficiency impact parameters are greater than or equal to the preset parameters as the analysis factors. Alternatively, the operating factors are arranged in descending order according to the efficiency impact parameters; the operating factors whose efficiency impact parameters are in the first P are taken as the analysis factors, where P is a positive integer greater than or equal to 2.

[0044] When the number of analysis factors is one, the method for determining the analysis factor according to the efficiency impact parameter may be: taking the operating factor with the largest efficiency impact parameter as the analysis factor.

[0045] The technical solution of the embodiment of the present invention is to find the target data subset from the data set through the current operating data of the coal-fired boiler, and then calculate the efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset; when the efficiency deviation is greater than the first preset threshold, the efficiency prediction model corresponding to the target data subset is obtained, and the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler are determined respectively according to the efficiency prediction model corresponding to the target data subset, so as to further determine the analysis factor. On the one hand, since the data set includes several data subsets, the target data subset determined according to the current operating data is the subset that best matches the current operating conditions, so it can provide a data basis for the subsequent accurate determination of the analysis factor. On the other hand, when the efficiency deviation is greater than the first preset threshold, that is, when the boiler efficiency under the current operating conditions is poor, the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler are determined respectively based on the efficiency prediction model corresponding to the target data subset. Since the efficiency prediction model corresponding to the target data subset is a model trained for the target data subset, it can accurately and quickly determine the parameters affecting the efficiency of each operating factor on the coal-fired boiler, and the analysis factors determined are more accurate, providing a data basis for the subsequent optimization of coal-fired boilers, thereby improving the economic benefits of coal-fired power plants. Thirdly, the efficiency prediction model can be continuously iterated and optimized as the operating data increases, which can further enhance the accuracy, adaptability and generalization ability of the efficiency prediction model.

[0046] Embodiment 2

[0047] Figure 2 : is a flow chart of a factor determination method provided by the second embodiment of the present invention. Based on the above-mentioned first embodiment, this embodiment provides a method for determining a data set, a method for determining an efficiency prediction model corresponding to a data subset, and a specific method for determining efficiency influencing parameters. Figure 2 As shown, the method includes:

[0048] S201. Obtain historical operation data of the coal-fired boiler.

[0049] In this embodiment, the historical operation data is the historical operation data of the coal-fired boiler to be analyzed, which makes the data more targeted.

[0050] The number of historical operation data is usually multiple, which can be determined according to actual needs. It is understandable that the more historical operation data there are, the more accurate the subsequent analysis results will be; the fewer historical operation data there are, the faster the analysis speed will be, and the lower the requirement for device computing power will be.

[0051] Optionally, after acquiring the historical operation data, at least one of the following operations may be performed on the historical operation data: outlier processing and standardization processing.

[0052] The operation data includes boiler efficiency and at least two operation factors, that is, the operation data includes at least two operation factors in addition to boiler efficiency. Exemplarily, the operation factors may be at least two of the following: main steam flow, main steam pressure, main steam temperature, amount of coal fed into the furnace, unit calorific value of coal fed into the furnace, biomass blending ratio, unit calorific value of biomass, primary air volume, primary air temperature, secondary air volume, burnout air volume, burnout air temperature, exhaust oxygen volume, and exhaust temperature.

[0053] S202: Sort the historical operation data based on the first factor, and divide the sorted historical operation data into M first sets.

[0054] Wherein, M is a positive integer. The value of M can be set according to requirements in practical applications.

[0055] In one embodiment, the first factor is the main steam flow rate. The main steam flow rate is an important parameter of the coal-fired boiler. The boiler efficiency of the coal-fired boiler varies under different main steam flow rates.

[0056] For example, assuming that there are 1000 historical operation data, and the value of M is 10. Then the specific method of determining the first set can be: sort the 1000 historical operation data in ascending / descending order according to the main steam flow rate, and then divide the sorted 1000 historical operation data into 10 first sets, that is, each first set includes 100 historical operation data. In other words, the historical operation data with the main steam flow rate in the top 1-100 belongs to the first first set, the historical operation data with the main steam flow rate in the top 101-200 belongs to the second first set, and so on, the historical operation data with the main steam flow rate in the top 901-1000 belongs to the tenth first set.

[0057] S203 . For each first set, sort the historical operation data in the first set based on the second factor, and divide the sorted historical operation data in the first set into N second sets.

[0058] Wherein, N is a positive integer. The value of N can be set according to requirements in practical applications.

[0059] Since M first sets are obtained in the above step S202, step S203 is an operation performed on each first set, so step S203 needs to be performed M times.

[0060] In one embodiment, the second factor is the biomass blending ratio, which is the ratio of biomass fuel to coal fuel, and is usually expressed as a percentage of the heat of the biomass fuel to the total heat.

[0061] Taking the first set in the above example as an example, the first set includes 100 historical operation data, and the value of N is 10. Then the specific method of determining the second set can be: sorting the 100 historical operation data in ascending / descending order according to the biomass blending ratio, and then dividing the sorted 100 historical operation data into 10 second sets, that is, each second set includes 10 historical operation data.

[0062] S204. For each second set, take the second set as a data subset, take the historical operating data with the highest boiler efficiency in the second set as the benchmark operating data of the data subset, and take the other historical operating data in the second set as the non-benchmark operating data of the data subset.

[0063] In this way, M*N data subsets can be determined. A data subset includes a benchmark operation data and a plurality of non-benchmark operation data.

[0064] Optionally, the benchmarking operation data of all data subsets can constitute a benchmarking data set for easy comparison.

[0065] S205: training an efficiency prediction model corresponding to each data subset.

[0066] Since the data set includes M*N data subsets, step S205 is to train the efficiency prediction model for each data subset, so step S205 needs to be executed M*N times.

[0067] Specifically, for any data subset, the method for training the efficiency prediction model corresponding to the data subset may include the following 6 steps.

[0068] Step 1: Get the current training data from the data subset.

[0069] The number of current training data can be 1 or more.

[0070] Step 2: Input at least two operating factors of the current training data into a back propagation (BP) neural network model to obtain training efficiency, wherein the BP neural network model includes several hidden layers.

[0071] The BP neural network model is a multi-layer feedforward neural network, and its core algorithm is error back propagation. The BP neural network model has a strong nonlinear mapping capability and can handle complex data relationships. At the same time, it does not need to determine the mathematical equation of the mapping relationship between input and output in advance, and only learns certain rules through its own training. Therefore, it can adapt well to the operation data of coal-fired boilers.

[0072] In one embodiment, the BP neural network model includes several hidden layers. Preferably, the BP neural network model includes 5 hidden layers, so as to achieve the best performance and generalization ability.

[0073] Step 3: Determine the loss function based on the training efficiency and the boiler efficiency of the current training data.

[0074] The loss function defines a measure of the difference between the model's predictions and the actual results. The loss function can be Cross-Entropy Loss and / or Mean Squared Error (MSE).

[0075] Step 4: Determine whether the training end condition is met. If yes, go to step 5; if no, go to step 6.

[0076] In one embodiment, the training end condition includes at least one of the following three conditions:

[0077] Condition 1: The value of the loss function is less than or equal to the preset loss;

[0078] Condition 2: The loss function converges;

[0079] Condition 3: The current number of training times is equal to the maximum number of training times.

[0080] When the training end condition includes at least two of the above conditions, as long as any one of the conditions is met, it is confirmed that the model training meets the training end condition.

[0081] Step 5: Use the current BP neural network model as the efficiency prediction model corresponding to the data subset.

[0082] When the training end condition is met, it means that the current BP neural network model has been trained. At this time, the current BP neural network model can be used as the efficiency prediction model corresponding to the data subset.

[0083] Step 6: According to the loss function, adjust the parameters of the BP neural network model, reacquire the current training data from the data subset, and return to execute step 2.

[0084] When the training end condition is not met, it means that the current BP neural network model has not been trained. At this time, the parameters of the BP neural network model are adjusted according to the loss function, and the current training data is re-acquired from the data subset, and the execution returns to step 2 until the training end condition is met.

[0085] In the BP neural network, the back propagation algorithm is used to update the network parameters based on the loss function calculation results using the gradient descent algorithm to minimize the prediction error.

[0086] Through the above method, the efficiency prediction model corresponding to each data subset can be trained for subsequent analysis and application.

[0087] It is understandable that the above steps S201-S205 may be pre-executed steps. Steps S201-S205 may be executed only once or periodically. When steps S201-S205 are executed periodically, the efficiency prediction model may be continuously iteratively optimized as the operating data increases, which may further enhance the accuracy, adaptability and generalization ability of the efficiency prediction model.

[0088] S206 , using the first factor and the second factor of the current running data as search parameters, determining a target data subset from the data set.

[0089] The current operation data of the coal-fired boiler refers to the operation data of the coal-fired data at the current moment. After obtaining the current operation data, the first factor and the second factor of the current operation data (i.e., the boiler main steam flow rate and the biomass blending ratio) can be determined, and the boiler main steam flow rate and the biomass blending ratio are used as search parameters to determine the target data subset from the data set.

[0090] Specifically, the boiler main steam flow rate and biomass blending ratio of the current operating data are both within the boiler main steam flow rate range and biomass blending ratio range corresponding to the target data subset.

[0091] S207 . Calculate the efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset.

[0092] The efficiency deviation is equal to the difference between the boiler efficiency of the benchmark operating data of the target data subset and the boiler efficiency of the current operating data.

[0093] S208. Determine the magnitude relationship between the efficiency deviation and a first preset threshold and a second preset threshold, wherein the first preset threshold is greater than the second preset threshold, and the second preset threshold is 0 or a negative value.

[0094] In one embodiment, the first preset threshold is a positive value, the second preset threshold is 0 or a negative value, and the first preset threshold is greater than the second preset threshold. The value of the first preset threshold can be set according to actual needs, such as 5%, 10%, 15%, 20%, etc. The value of the second preset threshold can be set according to actual needs, such as 0, -5%, etc.

[0095] S209: If the efficiency deviation is less than the second preset threshold, the current operating data is added to the target data subset, and after the benchmark operating data of the target data subset is changed to non-benchmark operating data, the current operating data is used as the benchmark operating data of the target data subset.

[0096] When the efficiency deviation is less than the second preset threshold, it means that the boiler efficiency under the current operating conditions is very good (for example, the boiler efficiency of the current operating data is higher than the boiler efficiency of the benchmark operating data of the target data subset). At this time, the current operating data is added to the target data subset, and after the benchmark operating data of the target data subset is changed to non-benchmark operating data, the current operating data is used as the benchmark operating data of the target data subset for subsequent use.

[0097] S210: If the efficiency deviation is greater than or equal to the second preset threshold and less than or equal to the first preset threshold, the process ends.

[0098] When the efficiency deviation is greater than or equal to the second preset threshold and less than or equal to the first preset threshold, it means that the boiler efficiency under the current operating conditions is good. At this time, there is no need to analyze the factors affecting the boiler efficiency of the coal-fired boiler and the process ends directly.

[0099] S211. If the efficiency deviation is greater than a first preset threshold, obtaining an efficiency prediction model corresponding to the target data subset.

[0100] When the efficiency deviation is greater than the first preset threshold, it means that the boiler efficiency under the current operating condition is poor, and factors affecting the boiler efficiency of the coal-fired boiler need to be analyzed. At this time, the efficiency prediction model corresponding to the target data subset is obtained.

[0101] S212: For any operating factor of the current operating data, replace the factor corresponding to the operating factor in the benchmark operating data of the target data subset with the operating factor to obtain intermediate operating data.

[0102] Exemplarily, taking the operating factor as the unit calorific value of biomass as an example, the value of the unit calorific value of biomass in the benchmark operating data of the target data subset is replaced with the value of the unit calorific value of biomass in the current operating data to obtain the intermediate operating data.

[0103] S213. Input the intermediate operation data into the efficiency prediction model corresponding to the target data subset to obtain the intermediate efficiency.

[0104] S214. Calculate the efficiency impact parameters of the operating factors on the coal-fired boiler based on the intermediate efficiency and the boiler efficiency of the benchmark operating data of the target data subset.

[0105] Among them, the efficiency impact parameter of the operating factor on the coal-fired boiler is equal to the difference between the boiler efficiency of the benchmark operating data of the target data subset and the intermediate efficiency.

[0106] S215. Determine analysis factors based on efficiency influencing parameters.

[0107] The analysis factors can provide a data basis for the subsequent optimization of coal-fired boilers, thereby improving the economic benefits of coal-fired power plants.

[0108] In one embodiment, the number of analysis factors may be one or more.

[0109] When the number of analysis factors is one, the method for determining the analysis factor according to the efficiency impact parameter may be: taking the operating factor with the largest efficiency impact parameter as the analysis factor.

[0110] When there are multiple analysis factors, the method for determining the analysis factors according to the efficiency impact parameter may be: taking the operating factors whose efficiency impact parameters are greater than or equal to the preset parameters as the analysis factors. Alternatively, the operating factors are arranged in descending order according to the efficiency impact parameters; the operating factors whose efficiency impact parameters are in the first P are taken as the analysis factors, where P is a positive integer greater than or equal to 2.

[0111] For example, it is assumed that the operating factors and their parameters affecting the efficiency of the coal-fired boiler are: main steam flow (6%), main steam pressure (3%), main steam temperature (5%), coal quantity (1%), unit calorific value of coal (3%), biomass blending ratio (10%), unit calorific value of biomass (2%), primary air volume (0.1%), primary air temperature (1.2%), secondary air volume (3%), burnout air volume (4%), burnout air temperature (3%), exhaust oxygen (2%), exhaust temperature (2.5%). If the value of P is 3, the analysis factors affecting the boiler efficiency of the coal-fired boiler are: biomass blending ratio, main steam flow and main steam temperature.

[0112] It should also be noted that the tail flue of the coal-fired boiler provided by the present invention can be installed with a real-time detection device for fly ash carbon content, which can monitor the fly ash carbon content of the coal-fired boiler in real time, thereby correcting the boiler efficiency in real time according to the fly ash carbon content, making the operating data more accurate.

[0113] The technical solution of the embodiment of the present invention is to find the target data subset from the data set through the current operating data of the coal-fired boiler, and then calculate the efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset; when the efficiency deviation is greater than the first preset threshold, the efficiency prediction model corresponding to the target data subset is obtained, and the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler are determined respectively according to the efficiency prediction model corresponding to the target data subset, so as to further determine the analysis factor. On the one hand, since the data set includes several data subsets, the target data subset determined according to the current operating data is the subset that best matches the current operating conditions, so it can provide a data basis for the subsequent accurate determination of the analysis factor. On the other hand, when the efficiency deviation is greater than the first preset threshold, that is, when the boiler efficiency under the current operating conditions is poor, the efficiency influence parameters of each operating factor of the current operating data on the coal-fired boiler are determined respectively based on the efficiency prediction model corresponding to the target data subset. Since the efficiency prediction model corresponding to the target data subset is a model trained for the target data subset, it can accurately and quickly determine the parameters affecting the efficiency of each operating factor on the coal-fired boiler, and the analysis factors determined are more accurate, providing a data basis for the subsequent optimization of coal-fired boilers, thereby improving the economic benefits of coal-fired power plants. Thirdly, the efficiency prediction model can be continuously iterated and optimized as the operating data increases, which can further enhance the accuracy, adaptability and generalization ability of the efficiency prediction model.

[0114] Embodiment 3

[0115] Figure 3 Schematic diagram of a factor determination device provided by Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a data subset determination module 301, an efficiency deviation calculation module 302, an influence parameter determination module 303 and an analysis factor determination module 304.

[0116] The data subset determination module 301 is used to determine a target data subset from the data set according to the current operation data of the coal-fired boiler, wherein the data set includes a plurality of data subsets, one data subset corresponds to one efficiency prediction model, one data subset includes one benchmark operation data, and each operation data includes boiler efficiency and at least two operation factors;

[0117] An efficiency deviation calculation module 302 is used to calculate the efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset;

[0118] The influencing parameter determination module 303 is used to obtain the efficiency prediction model corresponding to the target data subset if the efficiency deviation is greater than the first preset threshold, and determine the efficiency influence parameter of each operating factor of the current operating data on the coal-fired boiler according to the efficiency prediction model corresponding to the target data subset;

[0119] The analysis factor determination module 304 is used to determine the analysis factor according to the efficiency influencing parameter.

[0120] Optionally, the operation factor includes at least a first factor and a second factor, the data set includes M*N data subsets, M and N are both positive integers, and a data subset also includes a number of non-standard operation data.

[0121] The data subset determination module 301 is also used to obtain historical operating data of the coal-fired boiler; sort the historical operating data based on the first factor, and divide the sorted historical operating data into M first sets; for each first set, sort the historical operating data in the first set based on the second factor, and divide the sorted historical operating data in the first set into N second sets; for each second set, take the second set as a data subset, and take the historical operating data with the highest boiler efficiency in the second set as the benchmark operating data of the data subset, and take the other historical operating data in the second set as the non-benchmark operating data of the data subset.

[0122] Optionally, the data subset determination module 301 is specifically used to determine a target data subset from the data set using a first factor and a second factor of the current operating data as search parameters; wherein the first factor is the boiler main steam flow rate, and the second factor is the biomass blending ratio.

[0123] Optional, combined Figure 3 , Figure 4 FIG. 1 is a schematic diagram of the structure of another factor determination device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device also includes: a model training module 305.

[0124] The model training module 305 is used to obtain the current training data from the data subset; input at least two operating factors of the current training data into the back propagation BP neural network model to obtain the training efficiency, wherein the BP neural network model includes a plurality of hidden layers; determine the loss function according to the training efficiency and the boiler efficiency of the current training data; if the training end condition is met, use the current BP neural network model as the efficiency prediction model corresponding to the data subset; if the training end condition is not met, adjust the parameters of the BP neural network model according to the loss function, and re-acquire the current training data from the data subset, and return to execute the step of inputting at least two operating factors of the current training data into the BP neural network model to obtain the training efficiency.

[0125] Optionally, the influencing parameter determination module 303 is specifically used to replace the factor corresponding to the operating factor in the benchmark operating data of the target data subset with the operating factor to obtain intermediate operating data; input the intermediate operating data into the efficiency prediction model corresponding to the target data subset to obtain the intermediate efficiency; and calculate the efficiency influence parameter of the operating factor on the coal-fired boiler based on the intermediate efficiency and the boiler efficiency of the benchmark operating data of the target data subset.

[0126] Optionally, the analysis factor determination module 304 is specifically used to take the operating factors whose efficiency impact parameters are greater than or equal to the preset parameters as analysis factors; or, arrange the operating factors in order from large to small according to the efficiency impact parameters; and take the operating factors whose efficiency impact parameters are in the first P as analysis factors, where P is a positive integer.

[0127] Optionally, the data subset determination module 301 is also used to add the current operating data to the target data subset if the efficiency deviation is less than a second preset threshold, and after changing the benchmark operating data of the target data subset to non-benchmark operating data, use the current operating data as the benchmark operating data of the target data subset; wherein the first preset threshold is greater than the second preset threshold, and the second preset threshold is 0 or a negative value.

[0128] The factor determination device provided in the embodiment of the present invention can execute the factor determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0129] Embodiment 4

[0130] Figure 5 : is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0131] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0132] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0133] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the factor determination method.

[0134] In some embodiments, the factor determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the factor determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the factor determination method in any other appropriate manner (e.g., by means of firmware).

[0135] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0136] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0137] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0138] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0139] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0140] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0141] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the factor determination method provided by any embodiment of the present invention.

[0142] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0143] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0144] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A factor determination method, characterized in that: include: According to current operation data of the coal-fired boiler, a target data subset is determined from the data set, wherein the data set includes a plurality of data subsets, one data subset corresponds to an efficiency prediction model, one data subset includes a benchmark operation data, and each operation data includes boiler efficiency and at least two operation factors; Calculating an efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset; If the efficiency deviation is greater than a first preset threshold, the efficiency prediction model corresponding to the target data subset is obtained, and the efficiency influence parameter of each operating factor of the current operating data on the coal-fired boiler is determined respectively according to the efficiency prediction model corresponding to the target data subset; According to the efficiency influencing parameters, the analysis factors are determined.

2. The factor determination method according to claim 1, characterized in that: The operation factors include at least a first factor and a second factor, the data set includes M*N data subsets, M and N are both positive integers, and a data subset also includes a number of non-standard operation data; Before selecting the target data subset from the data set based on the current operation data of the coal-fired boiler, it also includes: Acquiring historical operation data of the coal-fired boiler; Based on the first factor, the historical operation data is sorted, and the sorted historical operation data is divided into M first sets; For each of the first sets, sorting the historical operating data in the first set based on the second factor, and dividing the sorted historical operating data in the first set into N second sets; For each of the second sets, the second set is taken as a data subset, and the historical operating data with the highest boiler efficiency in the second set is taken as the benchmark operating data of the data subset, and the other historical operating data in the second set is taken as the non-benchmark operating data of the data subset.

3. The factor determination method according to claim 2, characterized in that: The step of determining a target data subset from a data set based on current operation data of the coal-fired boiler includes: Using the first factor and the second factor of the current running data as search parameters, determining a target data subset from the data set; The first factor is the main steam flow of the boiler, and the second factor is the biomass blending ratio.

4. The factor determination method according to claim 1, characterized in that: For any data subset, the efficiency prediction model corresponding to the data subset is determined by the following method: Acquire current training data from the data subset; Inputting at least two operating factors of the current training data into a back propagation BP neural network model to obtain training efficiency, wherein the BP neural network model includes a plurality of hidden layers; Determining a loss function according to the training efficiency and the boiler efficiency of the current training data; If the training end condition is met, the current BP neural network model is used as the efficiency prediction model corresponding to the data subset; If the training end condition is not met, the parameters of the BP neural network model are adjusted according to the loss function, and the current training data is reacquired from the data subset, and the step of returning to execute inputting at least two operating factors of the current training data into the BP neural network model to obtain the training efficiency is performed.

5. The factor determination method according to claim 1, characterized in that: For any operating factor of the current operating data, determining the efficiency influence parameter of the operating factor on the coal-fired boiler according to the efficiency prediction model corresponding to the target data subset includes: Replacing the factor corresponding to the operating factor in the benchmark operating data of the target data subset with the operating factor to obtain intermediate operating data; Inputting the intermediate operation data into the efficiency prediction model corresponding to the target data subset to obtain the intermediate efficiency; The efficiency influence parameter of the operating factor on the coal-fired boiler is calculated according to the intermediate efficiency and the boiler efficiency of the benchmark operating data of the target data subset.

6. The factor determination method according to claim 1, characterized in that: The step of determining the analysis factor according to the efficiency influencing parameter comprises: The operating factor whose efficiency impact parameter is greater than or equal to the preset parameter is used as the analysis factor; or, The operating factors are arranged in descending order according to the efficiency impact parameters; the operating factors whose efficiency impact parameters are in the first P are taken as the analysis factors, where P is a positive integer.

7. The factor determination method according to claim 1, characterized in that: Also includes: If the efficiency deviation is less than a second preset threshold, the current operating data is added to the target data subset, and after the benchmark operating data of the target data subset is changed to non-benchmark operating data, the current operating data is used as the benchmark operating data of the target data subset; wherein the first preset threshold is greater than the second preset threshold, and the second preset threshold is 0 or a negative value.

8. A factor determination device, characterized in that: include: Data subset determination module, efficiency deviation calculation module, influencing parameter determination module and analysis factor determination module; The data subset determination module is used to determine a target data subset from a data set according to current operation data of the coal-fired boiler, wherein the data set includes a plurality of data subsets, one data subset corresponds to an efficiency prediction model, one data subset includes a benchmark operation data, and each operation data includes boiler efficiency and at least two operation factors; The efficiency deviation calculation module is used to calculate the efficiency deviation according to the boiler efficiency of the current operating data and the boiler efficiency of the benchmark operating data of the target data subset; The influencing parameter determination module is used to obtain the efficiency prediction model corresponding to the target data subset if the efficiency deviation is greater than a first preset threshold, and determine the efficiency influence parameter of each operating factor of the current operating data on the coal-fired boiler according to the efficiency prediction model corresponding to the target data subset; The analysis factor determination module is used to determine the analysis factor according to the efficiency influencing parameter.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory in communication with the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the factor determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the factor determination method according to any one of claims 1 to 7 when executed.

Images