Method, system and electronic device for predicting total amount of nox based on ai recognition

Abstract

The application provides a method and system for predicting total NOx based on AI recognition and an electronic device, and belongs to the technical field of thermal power denitration. The method comprises the following steps: obtaining first image information of coal fed into a furnace based on AI recognition; determining the coal blending type of the coal fed into the furnace based on the first image information and a deep learning model, and generating a power plant coal quality report; wherein the deep learning model is a convolutional neural network model, and the power plant coal quality report comprises coal quality parameters; obtaining the load of the thermal power plant; inputting the coal blending type of the coal fed into the furnace, the coal quality parameters, and the load of the thermal power plant into a NOx total amount prediction model to calculate the total amount of NOx. The application can accurately and efficiently calculate the total amount of NOx, thereby accurately calculating the corresponding ammonia injection amount, accurately controlling the ammonia injection amount during deep peak regulation, avoiding excessive ammonia injection, effectively reducing ammonia escape, reducing resource waste and environmental pollution, and having strong ease of use and practicality.

Description

Technical Field

[0001] The present application relates to the field of thermal power denitrification technology, and specifically to a method, system, and electronic equipment for AI-based identification and prediction of total NOx. Background Art

[0002] Deep peak regulation will have a significant impact on the denitrification equipment of thermal power plants, such as increased ammonia slip. Coal contains a certain amount of nitrogen, which will produce nitrogen oxides (NOx) after combustion. Ammonia needs to be sprayed during denitrification to remove NOx. In order to meet the needs of deep peak regulation, it may be necessary to increase or decrease the amount of ammonia sprayed to maintain denitrification efficiency and control ammonia slip. However, if the total amount of NOx in the flue gas at the denitrification inlet cannot be accurately predicted, it is difficult to accurately calculate the corresponding amount of ammonia sprayed. Excessive ammonia spraying will lead to increased ammonia slip. Therefore, how to accurately obtain the total amount of NOx has become a problem that needs to be solved. Summary of the Invention

[0003] The purpose of this application is to provide a method for predicting the total amount of NOx based on AI, which can solve the problem of how to accurately obtain the total amount of NOx in the existing technology.

[0004] In a first aspect, an embodiment of the present application provides a method for identifying and predicting total NOx based on AI, the method comprising:

[0005] Based on AI recognition, the first image information of the coal entering the furnace is obtained; based on the first image information and the deep learning model, the type of coal blending of the coal entering the furnace is determined, and a coal quality report for the power plant is generated; wherein, the deep learning model is a convolutional neural network model, and the coal quality report for the power plant includes coal quality parameters; the load of the thermal power plant is obtained; the type of coal blending of the coal entering the furnace, the coal quality parameters, and the load of the thermal power plant are input into the NOx total amount prediction model to calculate the total NOx amount.

[0006] In a possible implementation of the first aspect, determining the type of coal blended for feeding into the furnace based on the first image information and the deep learning model includes:

[0007] Based on the deep learning model, feature extraction and classification recognition are performed on the first image information to determine the type of coal blending into the furnace.

[0008] In a possible implementation of the first aspect, the first image information of the coal entering the furnace includes:

[0009] The color, texture, shape, and size of the coal entering the furnace.

[0010] In a possible implementation of the first aspect, the method further includes:

[0011] Acquire the second image information of fly ash after combustion of coal fed into the furnace based on AI recognition;

[0012] determine a carbon content of the fly ash based on the second image information of the fly ash;

[0013] adjust a blending type of the coal fed into the furnace based on the carbon content of the fly ash.

[0014] In a possible implementation manner of the first aspect, the method further includes:

[0015] adjust the blending type of the coal fed into the furnace based on the carbon content of the fly ash and the total amount of NOx.

[0016] In a possible implementation manner of the first aspect, the method further includes:

[0017] compare the determined blending type with an actual blending type to obtain a first comparison result.

[0018] In a possible implementation manner of the first aspect, the method further includes:

[0019] compare the determined carbon content of the fly ash with a laboratory test result of the fly ash to obtain a second comparison result.

[0020] In a second aspect, an embodiment of the present application provides a system for predicting a total amount of NOx based on AI recognition, which includes:

[0021] a collection device configured to acquire first image information of the coal fed into the furnace based on AI recognition;

[0022] a determination device configured to determine a blending type of the coal fed into the furnace based on the first image information and a deep learning model, and generate a coal quality report of the power plant; wherein the deep learning model is a convolutional neural network model, and the coal quality report includes a coal quality parameter;

[0023] an acquisition device configured to acquire a load amount of the thermal power plant;

[0024] a calculation device configured to input the blending type of the coal fed into the furnace, the coal quality parameter, and the load amount of the thermal power plant into a NOx total amount prediction model, and calculate to obtain the total amount of NOx.

[0025] In a possible implementation manner of the second aspect,

[0026] the collection device is further configured to acquire second image information of fly ash after combustion of the coal fed into the furnace based on AI recognition;

[0027] the determination device is further configured to determine a carbon content of the fly ash based on the second image information of the fly ash;

[0028] The system further includes:

[0029] an adjustment device configured to:

[0030] Adjust the coal blending type of the coal entering the furnace based on the carbon content of the fly ash; or

[0031] Adjust the coal blending type based on the carbon content of the fly ash and the total amount of NOx.

[0032] In a third aspect, the embodiments of the present application provide a device for predicting the total amount of NOx based on AI recognition, which comprises:

[0033] A first acquisition unit is configured to acquire first image information of the coal entering the furnace based on AI recognition;

[0034] A processing unit is configured to determine the coal blending type of the coal entering the furnace based on the first image information and a deep learning model, and generate a coal quality report of the power plant; wherein the deep learning model is a convolutional neural network model, and the coal quality report comprises coal quality parameters.

[0035] A second acquisition unit is configured to acquire the load of the thermal power plant;

[0036] A calculation unit is configured to input the coal blending type of the coal entering the furnace, the coal quality parameters, and the load of the thermal power plant into a NOx total amount prediction model, and calculate the total amount of NOx.

[0037] In a fourth aspect, the embodiments of the present application provide an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for predicting the total amount of NOx based on AI recognition according to any one of the first aspect when executing the computer program.

[0038] In a fifth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the method for predicting the total amount of NOx based on AI recognition according to any one of the first aspect.

[0039] In a sixth aspect, the embodiments of the present application provide a computer program product, which, when running on an electronic device, causes the electronic device to execute the method for predicting the total amount of NOx based on AI recognition according to any one of the first aspect.

[0040] The embodiments of the present application acquire the first image information of the coal entering the furnace through AI recognition, determine the coal blending type of the coal entering the furnace by using the convolutional neural network model in the deep learning model, generate the coal quality report comprising the coal quality parameters, and then input the coal blending type, the coal quality parameters, and the load of the thermal power plant into the NOx total amount prediction model to calculate the total amount of NOx.

[0041] By adopting the solution of the present application, the total amount of NOx can be calculated accurately and efficiently, so that the corresponding ammonia injection amount can be accurately calculated. During the deep peak regulation period, the ammonia injection amount can be accurately controlled to avoid excessive ammonia injection, which can effectively reduce ammonia escape, reduce resource waste and environmental pollution, and has strong ease of use and practicality.

[0042] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 This is a schematic diagram of an application scenario of the method for identifying and predicting total NOx based on AI provided in an embodiment of the present application;

[0045] Figure 2 Schematic diagram of the structure of the fly ash sampler provided in the embodiment of the present application;

[0046] Figure 3 This is a schematic diagram of the steps of the method for identifying and predicting the total amount of NOx based on AI in an embodiment of the present application;

[0047] Figure 4 This is a structural block diagram of a system for AI-based identification and prediction of total NOx levels provided in an embodiment of the present application;

[0048] Figure 5 Schematic diagram of the structure of the device for AI-based identification and prediction of total NOx amount provided in an embodiment of the present application;

[0049] Figure 6 Schematic diagram of an electronic device provided in an embodiment of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] 110-coal conveyor belt, 120-monitoring equipment, 130-fly ash sampler, 140-monitoring equipment, 132-sampling branch pipe, 134-automatic valve, 136-pulley, 138-sampling tank. DETAILED DESCRIPTION

[0052] In the following description, specific details such as specific system structures and technologies are provided for illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present application with unnecessary details.

[0053] It will be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0054] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0055] It should be further understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0056] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0057] In addition, in the description of the present application, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0058] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present invention. Thus, phrases such as "in one embodiment," "in some embodiments," "in some other embodiments," and "in some other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0059] Deep peak regulation has a significant impact on the denitrification equipment of thermal power plants, mainly including: increased ammonia escape, increased risk of corrosion and blockage of air preheaters, and decreased operational stability of denitrification equipment. Coal contains a certain amount of nitrogen, which produces nitrogen oxides (NOx) after combustion. Ammonia needs to be sprayed during denitrification to remove NOx. In order to meet the needs of deep peak regulation, it may be necessary to increase or decrease the amount of ammonia sprayed to maintain denitrification efficiency and control ammonia escape. However, if the total amount of NOx in the flue gas at the denitrification inlet cannot be accurately predicted, it is difficult to accurately calculate the corresponding amount of ammonia sprayed. Excessive ammonia spraying will lead to increased ammonia escape. Therefore, how to accurately obtain the total amount of NOx has become a problem that needs to be solved.

[0060] In response to the above-mentioned defects, an embodiment of the present application provides a method for predicting the total amount of NOx based on AI (Artificial Intelligence). The method collects the first image information of the incoming coal through AI recognition, uses the convolutional neural network model in the deep learning model to determine the type of coal blending of the incoming coal, and generates a coal quality report including coal quality parameters. The type of coal blending, coal quality parameters, and the load of the thermal power plant are then input into the total amount of NOx prediction model to calculate the total amount of NOx. The solution of the present application utilizes AI recognition technology to identify the image information of the incoming coal and uses the convolutional neural network model to determine the type of coal blending of the incoming coal. Therefore, the total amount of NOx can be calculated accurately and efficiently, thereby accurately calculating the corresponding ammonia injection amount. During the deep peak regulation period, the ammonia injection amount can be accurately controlled, which can avoid excessive ammonia injection, effectively reduce ammonia escape, reduce resource waste and environmental pollution, and has strong ease of use and practicality.

[0061] See Figure 1 , Figure 1 This is a schematic diagram of the application scenario of the method for AI-based identification and prediction of total NOx amount provided in an embodiment of the present application.

[0062] like Figure 1As shown, a monitoring device 120 is installed near the coal belt 110, which can be a high-definition camera or other types of monitoring devices. The monitoring device 120 performs AI image recognition on the coal entering the coal belt 110, collects image information of the coal, and determines the type of coal blending. The fly ash sampler 130 is embedded in the lower part of the flue at the end of the economizer, and a monitoring device 140 is installed therein. The monitoring device 140 performs AI image recognition on the fly ash in the fly ash sampler 130, collects image information of the fly ash, and determines the carbon content in the fly ash.

[0063] Please refer to Figure 2 , Figure 2 is a structural schematic diagram of a fly ash sampler provided by the embodiments of the present application.

[0064] As shown in Figure 2 , the fly ash sampler 130 includes a sampling branch pipe 132, an automatic valve 134, a belt pulley 136, and a sampling tank 138. The fly ash sampler 130 is a sealed system and is embedded in the lower part of the flue at the end of the economizer. During the normal operation of the thermal power plant, when the automatic valve 134 is in the closed state, a very small amount of fly ash generated after the combustion of the coal entering the furnace will freely fall on the belt pulley 136 through the sampling branch pipe 132 and enter the sampling tank 138 as the belt pulley 136 operates; when the automatic valve 134 is in the open state, the fly ash sampler 130 is in a negative pressure state, and the fly ash inside is sucked away by the negative pressure, and the fly ash in the sampling tank 138 is also sucked away. A manual valve is provided on the sampling tank 138, and when collecting fly ash, the manual valve is closed to keep the fly ash sampler 130 in a sealed state.

[0065] The monitoring device 140 performs AI image recognition on the fly ash on the belt pulley 136, collects image information of the fly ash, and determines the carbon content in the fly ash. The fly ash collected in the sampling pipe 138 is used for laboratory testing, and the laboratory test results are compared with the carbon content of the fly ash determined based on AI recognition to verify the accuracy of AI recognition.

[0066] Based on the above application scenario, the embodiments of the present application provide a method for predicting the total amount of NOx based on AI recognition. The specific process of implementing the method will be introduced through specific embodiments below.

[0067] Please refer to Figure 3 , Figure 3 is a step schematic diagram of a method for predicting the total amount of NOx based on AI recognition provided by the embodiments of the present application. The method is realized through an AI recognition coal blending system and an AI recognition fly ash carbon content feedback system, and the two systems interact with the control system of the thermal power plant, while the monitoring device is a hardware execution end. As shown in Figure 3 , the method can include the following steps:

[0068] S301, obtaining first image information of coal entering the furnace based on AI recognition.

[0069] According to one embodiment of the present application, the first image information of the coal entering the furnace includes: the color, texture, shape and size of the coal entering the furnace.

[0070] In some embodiments, monitoring equipment can use AI image recognition to collect first image information of incoming coal on a coal conveyor belt in a thermal power plant, such as the color, texture, shape, or size of the incoming coal. This image information can reflect the quality of the incoming coal.

[0071] S302, based on the first image information and the deep learning model, determine the type of coal blended into the furnace and generate a coal quality report for the power plant; wherein the deep learning model is a convolutional neural network model, and the coal quality report for the power plant includes coal quality parameters.

[0072] In some embodiments, the monitoring device can input the collected first image information of the incoming coal into a pre-trained convolutional neural network (CNN) model to determine the incoming coal blending type. After determining the incoming coal blending type, the monitoring device can generate a power plant coal quality report. The power plant coal quality report describes the coal quality parameters of the incoming coal in the coal blending plan, such as the content of elements such as nitrogen, sulfur, carbon, and hydrogen.

[0073] According to one embodiment of the present application, determining the type of coal blending for feeding into a furnace based on the first image information and a deep learning model includes the following steps:

[0074] Based on the deep learning model, feature extraction and classification recognition are performed on the first image information to determine the type of coal blending into the furnace.

[0075] In some embodiments, the monitoring equipment can use a convolutional neural network model to extract and classify features such as color, texture, shape, and size in the first image information of the coal entering the furnace, so as to determine the type of coal blending entering and leaving the furnace, that is, to identify the type of coal blending by the color, texture, shape or size of the coal entering the furnace.

[0076] It should be noted that the use of a convolutional neural network model can accurately and efficiently extract features and classify the first image information of the coal entering the furnace, thereby determining the type of coal blending entering and leaving the furnace.

[0077] According to one embodiment of the present application, the method may further include the following steps:

[0078] The determined coal blending type is compared with the actual coal blending type to obtain a first comparison result.

[0079] In some embodiments, to verify the accuracy of AI recognition of the first image information of the incoming coal, the monitoring device may compare the coal blending type determined by AI recognition with the actual coal blending type records and calculate the recognition accuracy rate. If the coal blending type determined by AI recognition is consistent with the actual coal blending type records, then the AI ​​recognition accuracy rate of the first image information of the incoming coal is high. The monitoring device may continuously optimize AI recognition based on the recognition accuracy rate of the first image information of the incoming coal, thereby accurately recognizing the first image information of the incoming coal.

[0080] S303: Obtain the load of the thermal power plant.

[0081] In some embodiments, the monitoring device can obtain operating parameters of the thermal power plant during coal-fired power generation, such as load and other parameters.

[0082] S304: Input the type of coal blended into the furnace, coal quality parameters, and the load of the thermal power plant into the total NOx amount prediction model to calculate the total NOx amount.

[0083] In some embodiments, the monitoring device can construct and train a total NOx prediction model. The trained model uses the type of coal blended into the furnace, the coal quality parameters from the coal quality report, and the load of the thermal power plant as input data. The model then calculates the total amount of NOx (e.g., NO or NO2) produced by the combustion of the coal blended into the furnace. NOx is a pollutant.

[0084] Furthermore, during deep peak shaving, the amount of ammonium bisulfate generated in the flue gas may increase. This ammonium bisulfate easily condenses and accumulates dust on the cold end of the air preheater, increasing the risk of corrosion and blockage. Deep peak shaving can lead to frequent changes in the operating conditions of the denitrification unit. These changes can cause control system imbalances and accelerate catalyst aging, thereby reducing the operational stability of the denitrification unit. Therefore, how to reduce the risk of air preheater corrosion and blockage and improve the operational stability of the denitrification unit remain unresolved challenges.

[0085] According to one embodiment of the present application, the method may further include the following steps:

[0086] Based on AI recognition, the second image information of the fly ash after the coal entering the furnace is burned is obtained; based on the second image information of the fly ash, the carbon content of the fly ash is determined; based on the carbon content of the fly ash, the type of coal blended into the furnace is adjusted.

[0087] Fly ash is produced after the coal fed into the furnace is burned. In some embodiments, the monitoring equipment can also collect second image information of the fly ash produced after the coal fed into the furnace is burned, and use image segmentation and color recognition algorithms to determine the carbon content in the fly ash from the second image information of the fly ash, and then make corresponding adjustments to the type of coal blended into the furnace according to the carbon content in the fly ash. If the carbon content in the fly ash exceeds the preset carbon content threshold, it means that the coal quality of the coal fed into the furnace is low, the carbon content in the fly ash produced after combustion is large, the combustion is incomplete, and the combustion efficiency is low. It is necessary to adjust the type of coal blending and select coal fed into the furnace with higher coal quality. If the carbon content in the fly ash does not exceed the preset carbon content threshold, it means that the coal quality of the coal fed into the furnace is high, the carbon content in the fly ash produced after combustion is small, the combustion is relatively complete, the combustion efficiency is high, and there is no need to adjust the type of coal blending.

[0088] The preset carbon content threshold value of the carbon content in the fly ash may be determined based on specific circumstances in actual application scenarios and is not specifically limited here.

[0089] According to another embodiment of the present application, the method may further include the following steps:

[0090] Adjust the type of coal blended into the furnace based on the carbon content and total NOx content of the fly ash.

[0091] In some embodiments, when adjusting the type of coal blended into the furnace, adjustments can also be made based on the carbon content in the fly ash and the calculated total NOx amount. If the carbon content in the fly ash does not exceed the preset carbon content threshold, but the total NOx amount exceeds the preset total NOx threshold, it means that the quality of the coal entering the furnace is relatively low. Although the carbon content in the fly ash produced after combustion is not large, the pollutants produced after combustion are relatively large. It is necessary to adjust the type of coal blended and select coal entering the furnace with higher quality. If the carbon content in the fly ash does not exceed the preset carbon content threshold, and the total NOx amount does not exceed the preset total NOx threshold, it means that the quality of the coal entering the furnace is relatively high, the carbon content in the fly ash produced after combustion is relatively small, the combustion is relatively complete, the combustion efficiency is relatively high, and the pollutants produced after combustion are relatively small. It is not necessary to adjust the type of coal blended.

[0092] Among them, the preset total NOx threshold can be determined according to the specific circumstances in the actual application scenario and is not specifically limited here.

[0093] According to one embodiment of the present application, the method may further include the following steps:

[0094] The determined carbon content of the fly ash is compared with the laboratory test result of the fly ash to obtain a second comparison result.

[0095] In some embodiments, in order to verify the accuracy of AI identification of the carbon content in fly ash, the fly ash produced after the combustion of the coal fed into the furnace can be subjected to laboratory testing to determine the carbon content in the fly ash actually produced after the combustion of the coal fed into the furnace. The monitoring equipment can compare the carbon content in the fly ash identified by the AI ​​with the laboratory test results of the fly ash, and calculate the recognition accuracy. If the carbon content in the fly ash identified by the AI ​​is consistent with the laboratory test results of the fly ash, it proves that the accuracy of AI identification of the carbon content in the fly ash is high. The monitoring equipment can continuously optimize the AI ​​identification based on the recognition accuracy of the carbon content in the fly ash, so that the carbon content in the fly ash can be accurately identified.

[0096] In some embodiments, the AI ​​recognition and coal blending system collects first image information such as the color, texture, shape, and size of the coal entering the furnace through AI image recognition, and then determines the type of coal blending of the coal entering the furnace based on the first image information and the convolutional neural network model, and generates a coal quality report for the power plant including coal quality parameters, and then obtains the load of the thermal power plant. Finally, the type of coal blending, coal quality parameters, and load of the thermal power plant of the coal entering the furnace are input into the NOx total amount prediction model to calculate the total NOx amount.

[0097] It should be noted that the type of coal blended into the furnace will affect the combustion process and emission characteristics of the coal. The fly ash produced by burning coal with higher coal quality has a lower carbon content, the combustion is more complete, the combustion efficiency is higher, and fewer pollutants are emitted after combustion; the fly ash produced by burning coal with lower coal quality has a higher carbon content, the combustion is incomplete, the combustion efficiency is lower, and more pollutants are generated after combustion.

[0098] In some embodiments, there is a feedback and adjustment relationship between the AI ​​identification coal blending system and the AI ​​identification fly ash carbon content feedback system: the fly ash carbon content data provided by the AI ​​identification fly ash carbon content feedback system can serve as an important feedback signal of the AI ​​identification coal blending system, and the AI ​​identification coal blending system makes corresponding adjustments to the type of coal blending entering the furnace based on the feedback signal.

[0099] Correspondingly, the AI ​​recognition of fly ash carbon content feedback system can collect the second image information of the fly ash generated after the combustion of the coal entering the furnace, and use image segmentation and color recognition algorithms to determine the carbon content in the fly ash from the second image information of the fly ash. The carbon content in the fly ash serves as an important feedback signal of the AI ​​recognition coal blending system. Then, the AI ​​recognition coal blending system makes corresponding adjustments to the type of coal blending according to the carbon content in the fly ash or according to the carbon content in the fly ash and the calculated total NOx amount.

[0100] If the carbon content in the fly ash exceeds the preset carbon content threshold, it indicates that the coal quality of the coal fed into the furnace is low, the carbon content in the fly ash generated after combustion is large, the combustion is insufficient, the combustion efficiency is low, and the type of coal blending needs to be adjusted to select coal with higher coal quality to improve the combustion efficiency. If the carbon content in the fly ash does not exceed the preset carbon content threshold, but the total amount of NOx exceeds the preset total amount of NOx threshold, it indicates that the coal quality of the coal fed into the furnace is low, although the carbon content in the fly ash generated after combustion is not large, but the pollutants generated after combustion are more, and the type of coal blending needs to be adjusted to select coal with higher coal quality to improve the combustion efficiency and reduce the emission amount of pollutants.

[0101] In some embodiments, the AI-identified coal blending system and the AI-identified fly ash carbon content feedback system have a synergistic optimization relationship: the two systems work together, the AI-identified fly ash carbon content feedback system monitors the carbon content in the fly ash, and the AI-identified coal blending system continuously adjusts the type of coal blending for the coal fed into the furnace according to the carbon content in the fly ash or according to the carbon content in the fly ash and the calculated total amount of NOx, so as to find a balance point, so that the combustion efficiency is the highest, and the pollutants emitted are the least, and the real-time optimization of the combustion process and emission characteristics of the thermal power plant can be realized.

[0102] In some embodiments, the AI-identified coal blending system and the AI-identified fly ash carbon content feedback system have a data sharing and interaction relationship: data sharing and interaction between the two systems is needed, and such data sharing and interaction can be realized through the control system or data platform of the thermal power plant. For example, the AI-identified coal blending system needs to transmit the determined type of coal blending to the control system, and also needs to receive the fly ash carbon content data from the AI-identified fly ash carbon content feedback system as a feedback signal through the control system.

[0103] The method for predicting the total amount of NOx based on AI identification provided by the embodiments of the present application comprises the following steps: collecting first image information of the coal fed into the furnace through AI identification, determining the type of coal blending of the coal fed into the furnace by using a convolutional neural network model, and generating a coal quality report comprising coal quality parameters, and then inputting the type of coal blending, the coal quality parameters, and the load of the thermal power plant into a NOx total amount prediction model to calculate the total amount of NOx. In addition, the carbon content in the fly ash after combustion of the coal fed into the furnace collected by AI identification is determined, and then the type of coal blending of the coal fed into the furnace is adjusted based on the carbon content in the fly ash, or the type of coal blending of the coal fed into the furnace is adjusted based on the carbon content in the fly ash and the calculated total amount of NOx.

[0104] By adopting the solution of the present application, AI recognition technology is used to identify the image information of the coal entering the furnace, and a convolutional neural network model is used to determine the type of coal blending entering the furnace. Therefore, the total amount of NOx can be calculated accurately and efficiently, and the corresponding ammonia injection amount can be accurately calculated. During the deep peak regulation period, the ammonia injection amount can be accurately controlled to avoid excessive ammonia injection, effectively reduce ammonia escape, and reduce resource waste and environmental pollution. At the same time, accurately controlling the ammonia injection amount can reduce the consumption of denitrification reducing agent (ammonia or urea), bringing significant economic and environmental benefits to the enterprise.

[0105] In addition, the coal blending scheme can be adjusted according to the carbon content of fly ash produced after combustion of the feed coal or according to the carbon content of fly ash and the calculated total NOx amount, and the coal blending scheme can be adjusted to feed coal with better coal quality. Feed coal with better coal quality can be fully burned and produces less total NOx, thereby improving the combustion efficiency of feed coal and reducing pollutant emissions; feed coal with better coal quality has less sulfur content, produces less SO2 and SO3 after combustion, and produces less ammonium bisulfate produced by reaction with ammonia, which can effectively reduce the risk of air preheater corrosion and blockage, reduce maintenance costs, and ensure safe and stable operation of the unit; stabilize the operating conditions of the denitrification device, avoid control system disorders, delay catalyst aging, and improve the operating stability of the denitrification device; and has strong ease of use and practicality.

[0106] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0107] Corresponding to the method of the above embodiment, Figure 4 A structural block diagram of a system for AI-based identification and prediction of total NOx amount provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0108] Reference Figure 4 , the system comprises:

[0109] The acquisition device 401 is used to obtain first image information of the coal entering the furnace based on AI recognition;

[0110] Determining means 402, for determining the type of coal blended into the furnace based on the first image information and a deep learning model, and generating a power plant coal quality report; wherein the deep learning model is a convolutional neural network model, and the power plant coal quality report includes coal quality parameters;

[0111] The acquisition device 403 is used to obtain the load of the thermal power plant;

[0112] The computing device 404 is configured to input the blending type of the coal for the furnace, the coal quality parameters, and the load of the thermal power plant into the NOx total amount prediction model to calculate the NOx total amount.

[0113] According to an embodiment of the present application, the collecting device 401 is further configured to acquire second image information of fly ash after combustion of the coal for the furnace based on AI recognition;

[0114] The determining device 402 is further configured to determine the carbon content of the fly ash based on the second image information of the fly ash.

[0115] The system further comprises:

[0116] The adjusting device 405 is configured to:

[0117] adjust the blending type of the coal for the furnace based on the carbon content of the fly ash; or

[0118] adjust the blending type based on the carbon content of the fly ash and the NOx total amount.

[0119] The method corresponding to the above embodiment, Figure 5 The structural block diagram of the device for predicting the NOx total amount based on AI recognition provided by the embodiments of the present application is shown, and only the parts related to the embodiments of the present application are shown for the convenience of description.

[0120] With reference to Figure 5 The device comprises:

[0121] The first acquiring unit 501 is configured to acquire first image information of the coal for the furnace based on AI recognition.

[0122] The processing unit 502 is configured to determine the blending type of the coal for the furnace based on the first image information and a deep learning model, and generate a power plant coal quality report; wherein the deep learning model is a convolutional neural network model, and the power plant coal quality report comprises coal quality parameters.

[0123] The second acquiring unit 503 is configured to acquire the load of the thermal power plant.

[0124] The computing unit 504 is configured to input the blending type of the coal for the furnace, the coal quality parameters, and the load of the thermal power plant into the NOx total amount prediction model to calculate the NOx total amount.

[0125] According to an embodiment of the present application, the processing unit 502 determines the blending type of the coal for the furnace based on the first image information and the deep learning model, comprising:

[0126] The first image information is subjected to feature extraction and classification recognition based on the deep learning model to determine the blending type of the coal for the furnace.

[0127] According to one embodiment of the present application, the first image information of the coal entering the furnace includes: the color, texture, shape and size of the coal entering the furnace.

[0128] According to one embodiment of the present application, the device further includes:

[0129] The first acquisition unit 501 is further configured to acquire second image information of fly ash after combustion of the coal fed into the furnace based on AI recognition;

[0130] The processing unit 502 is further configured to determine the carbon content of the fly ash based on the second image information of the fly ash;

[0131] The processing unit 502 is further configured to adjust the type of coal blended into the furnace based on the carbon content of the fly ash.

[0132] According to one embodiment of the present application, the processing unit 502 is further configured to adjust the type of coal blended into the furnace based on the carbon content and the total amount of NOx in the fly ash.

[0133] According to an embodiment of the present application, the processing unit 502 is further configured to compare the determined coal blending type with the actual coal blending type to obtain a first comparison result.

[0134] According to an embodiment of the present application, the processing unit 502 is further configured to compare the determined carbon content of the fly ash with a laboratory test result of the fly ash to obtain a second comparison result.

[0135] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0137] Figure 6A structural schematic diagram of an electronic device 6 is provided for an embodiment of the present application. As shown in the figure, the electronic device 6 of this embodiment includes at least one processor 601 (only one is shown in the figure), a memory 603, and a computer program 602 stored in the memory 603 and executable on the at least one processor 601, and the processor 601 implements the steps in the method embodiments described above when executing the computer program 602. Figure 6 Figure 6 The processor 601 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0138] The electronic device 6 can be a high-definition camera or other monitoring device. The electronic device 6 can include, but is not limited to, the processor 601 and the memory 603. Those skilled in the art can understand that the electronic device 6 is only an example and does not constitute a limitation on the electronic device 6, and can include more or fewer components than shown in the figure, or combine certain components, or different components, for example, can also include input / output devices, network access devices, etc. Figure 6

[0139] The memory 603 can be an internal storage unit of the electronic device 6 in some embodiments, for example, a hard disk or a memory of the electronic device 6. The memory 603 can also be an external storage device of the electronic device 6 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD), a flash card, etc. equipped on the electronic device 6. Further, the memory 603 can include both the internal storage unit and the external storage device of the electronic device 6. The memory 603 is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The memory 603 can also be used to temporarily store data that has been output or will be output.

[0140] The memory 603 can be an internal storage unit of the electronic device 6 in some embodiments, for example, a hard disk or a memory of the electronic device 6. The memory 603 can also be an external storage device of the electronic device 6 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD), a flash card, etc. equipped on the electronic device 6. Further, the memory 603 can include both the internal storage unit and the external storage device of the electronic device 6. The memory 603 is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The memory 603 can also be used to temporarily store data that has been output or will be output.

[0141] ​​The integrated units described above, if implemented in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can be implemented by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the above-mentioned steps applied in the method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable storage medium at least includes any entity or device capable of carrying the computer program code to the operation device / electronic equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, such as U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable storage medium can not be electrical carrier signal and telecommunication signal.

[0142] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in each of the above-mentioned method embodiments.

[0143] The embodiments of the present application provide a computer program product. When the computer program product is run on an electronic device, the electronic device executes the steps in each of the above-mentioned method embodiments.

[0144] In the above-mentioned embodiments, the description of each embodiment has its own focus. The parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0145] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0146] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. The device / electronic device embodiments described above are merely schematic, and the division of the above modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, and some features can be ignored and not executed. Another point is that the indirect coupling, direct coupling or communication connection between each other shown or discussed can be an indirect coupling, direct coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0147] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for identifying and predicting the total amount of NOx based on AI, characterized in that: The method comprises: Acquire first image information of coal entering the furnace based on AI recognition; Based on the first image information and a deep learning model, determining the type of coal blended for the incoming coal, and generating a power plant coal quality report; wherein the deep learning model is a convolutional neural network model, and the power plant coal quality report includes coal quality parameters; Obtain the load of the thermal power plant; The type of coal blending of the feed coal, the coal quality parameters and the load of the thermal power plant are input into the total NOx amount prediction model to calculate the total NOx amount.

2. The method for identifying and predicting the total amount of NOx based on AI according to claim 1, characterized in that: Determining the type of coal blending for the incoming coal based on the first image information and the deep learning model includes: Based on the deep learning model, feature extraction and classification recognition are performed on the first image information to determine the type of coal blending of the coal entering the furnace.

3. The method for predicting total NOx based on AI according to claim 1, characterized in that: The first image information of the coal entering the furnace includes: The color, texture, shape and size of the coal fed into the furnace.

4. The method for identifying and predicting the total amount of NOx based on AI according to claim 1, characterized in that: The method further comprises: Acquire second image information of fly ash after combustion of the coal fed into the furnace based on AI recognition; determining a carbon content of the fly ash based on the second image information of the fly ash; The type of coal blended into the furnace is adjusted based on the carbon content of the fly ash.

5. The method for identifying and predicting the total amount of NOx based on AI according to claim 4, characterized in that: The method further comprises: The type of coal blended into the furnace is adjusted based on the carbon content of the fly ash and the total amount of NOx.

6. The method for identifying and predicting the total amount of NOx based on AI according to claim 1, characterized in that: The method further comprises: The determined coal blending type is compared with the actual coal blending type to obtain a first comparison result.

7. The method for identifying and predicting the total amount of NOx based on AI according to claim 4, characterized in that: The method further comprises: The determined carbon content of the fly ash is compared with the laboratory test result of the fly ash to obtain a second comparison result.

8. A system for identifying and predicting total NOx levels based on AI, comprising: A collection device, used for obtaining first image information of coal entering the furnace based on AI recognition; a determining device for determining the type of coal blended into the furnace based on the first image information and a deep learning model, and generating a power plant coal quality report; wherein the deep learning model is a convolutional neural network model, and the power plant coal quality report includes coal quality parameters; an acquisition device for acquiring the load of a thermal power plant; The calculation device is used to input the coal blending type of the incoming coal, the coal quality parameters and the load of the thermal power plant into the NOx total amount prediction model to calculate the NOx total amount.

9. The system for identifying and predicting total NOx amount based on AI according to claim 8, characterized in that: The acquisition device is further configured to obtain second image information of fly ash after combustion of the coal fed into the furnace based on AI recognition; The determining device is further configured to determine the carbon content of the fly ash based on the second image information of the fly ash; The system further comprises: Adjusting device for: Adjusting the type of coal blended into the furnace based on the carbon content of the fly ash; or The type of coal blending is adjusted based on the carbon content of the fly ash and the total amount of NOx.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for predicting the total amount of NOx based on AI according to any one of claims 1 to 7 is implemented.

Images