Primary air leveling method and device, medium, equipment and program product
By using the backpropagation neural network prediction model, the problem of the difficulty of air leveling in the next coal mixing method is solved, and accurate and rapid leveling is achieved, which improves combustion efficiency and reduces the risk of slag coking.
Patent Information
- Application Number
- CN202411561579.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-04
- Publication Date
- 2025-03-14
AI Technical Summary
Under the coal mixing method, it is difficult for the prior art to accurately and quickly perform air-leveling, especially when the coal types are diversified, resulting in low combustion efficiency and increased risk of slag and coking.
The backpropagation neural network prediction model is used to obtain parameters such as the axis power of the primary fan, the boiler coal mixing method, and other parameters, to predict the optimal values of the opening degree of each coal powder tube and the wind speed of the primary wind, and adjust the corresponding parameters according to the predicted value to achieve primary wind leveling.
It achieves more precise and rapid air leveling under the conditions of mixed coal combustion, improves combustion efficiency and reduces the risk of slag coking.
Smart Images
Figure CN119617462A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of boiler combustion optimization, and in particular, to a primary air leveling method, device, medium, equipment and program product. Background Art
[0002] During the operation of the boilers of coal-fired power plants, different types of coal are usually mixed due to the different types of coal supplied, that is, mixed coal combustion. Due to the different combustion characteristics of different types of coal powder, the required primary air volume is different, and the primary air needs to be controlled in real time to ensure combustion efficiency. Primary air refers to the primary air entering the boiler burner, which is used to transport coal powder to the burner and participate in combustion. Primary air leveling refers to adjusting the primary air volume of each coal powder pipeline before the hot start of the boiler, so that the difference before and after is controlled within a certain range, so as to optimize boiler combustion and prevent slagging and coking.
[0003] However, the mixed coal combustion method needs to consider the parameters such as the coarseness of coal powder and the ratio of primary air and secondary air due to the diversity of coal types, which increases the difficulty of primary air leveling. It is difficult to accurately and quickly perform primary air leveling under the mixed coal combustion method by relying on manual experience judgment or simple linear control. Summary of the invention
[0004] In order to overcome the problems existing in the related art, the present application provides a primary air leveling method, device, medium, equipment and program product.
[0005] According to a first aspect of the present application, a primary wind leveling method is provided, comprising: When the shaft power of the primary fan and / or the mixed coal combustion mode of the boiler changes, a first parameter is obtained, wherein the first parameter includes one or more of the following parameters: the current of the primary fan, the shaft power of the primary fan, the dynamic pressure of the primary air, the static pressure of the primary air, the wind temperature of the primary air, the blade opening of the primary fan, the ratio of the primary air to the secondary air, the power generation load, the furnace pressure, the coarseness of the coal powder, the coal quality test parameters, the emission parameters of the boiler, and the benefit parameters of the boiler; Inputting the first parameter into a prediction model to obtain a predicted value of a second parameter, wherein the prediction model is a back propagation neural network updated after the second parameter was determined last time, and the second parameter includes the opening of each pulverized coal pipe and the wind speed of the primary wind; Determine whether the predicted value is abnormal according to the change of the shaft power of the primary fan and the mixed coal combustion mode of the boiler; When the predicted value is normal, the opening of each pulverized coal pipe is adjusted according to the predicted value of the opening of each pulverized coal pipe, and the operating parameters of the primary fan are adjusted according to the predicted value of the primary wind speed to achieve primary wind leveling.
[0006] Optionally, judging whether the predicted value is abnormal according to the change of the shaft power of the primary fan and the mixed coal combustion mode of the boiler includes: In the case where the shaft power of the primary fan increases and / or the mixed coal combustion mode of the boiler changes, resulting in the need to increase the shaft power, if the increase in the predicted value of the opening of any pulverized coal pipe relative to the historical value is within a first preset range, the predicted value is determined to be normal; otherwise, the predicted value is determined to be abnormal, and the historical value is the opening of the pulverized coal pipe determined last time; When the shaft power of the primary fan is reduced and / or the mixed coal combustion mode of the boiler changes, resulting in the need to reduce the shaft power, if the decrease in the predicted value of the opening of any pulverized coal pipe relative to the historical value is within the first preset range, the predicted value is judged to be normal; otherwise, the predicted value is judged to be abnormal.
[0007] Optionally, the method further comprises: When the predicted value is abnormal, output abnormal prompt information; receiving and storing a correction value of a second parameter input by a user, wherein the correction value is the opening of each pulverized coal pipe and the wind speed of the primary air set by the user based on field operation experience; According to the correction value, the opening of each pulverized coal pipe and the wind speed of the primary air are adjusted to achieve primary air leveling; The first parameter is used as an input feature and the correction value is used as a label to update and train the prediction model to obtain a back propagation neural network after this update.
[0008] Optionally, the initial prediction model used when the second parameter is initially determined is obtained by the following steps: Acquire test data of primary wind leveling under different operating conditions, wherein the operating conditions include operating conditions under different power generation load conditions covering a second preset range, and the test data include operating parameters under different power generation loads; According to the experimental data of the primary wind leveling, a training sample set including input features and corresponding labels is constructed; The initial back propagation neural network is trained using the training sample set to obtain an initial prediction model.
[0009] Optionally, the training sample set includes training samples corresponding to each working condition, and each training sample includes input features and labels; The input characteristics include one or more of the following parameters: current of the primary fan, shaft power of the primary fan, dynamic pressure of the primary air, static pressure of the primary air, wind temperature of the primary air, blade opening of the primary fan, ratio of primary air to secondary air, power generation load, furnace pressure, coal powder coarseness, coal quality test parameters, boiler emission parameters and boiler efficiency parameters; The labels include the opening of each pulverized coal pipeline and the wind speed of the primary air.
[0010] Optionally, in all training samples, the difference in opening degree of the same pulverized coal pipeline corresponding to the same operating condition is within the first preset range.
[0011] According to a second aspect of the present application, a primary air leveling device is provided, comprising: A data acquisition module is used to acquire a first parameter when the shaft power of the primary fan and / or the mixed coal combustion mode of the boiler changes, wherein the first parameter includes one or more of the following parameters: the current of the primary fan, the shaft power of the primary fan, the dynamic pressure of the primary air, the static pressure of the primary air, the wind temperature of the primary air, the blade opening of the primary fan, the ratio of the primary air to the secondary air, the power generation load, the furnace pressure, the coarseness of the coal powder, the coal quality test parameters, the emission parameters of the boiler, and the benefit parameters of the boiler; A prediction output module, used for inputting the first parameter into a prediction model to obtain a predicted value of a second parameter, wherein the prediction model is a back propagation neural network updated after the second parameter was determined last time, and the second parameter includes the opening of each pulverized coal pipe and the wind speed of the primary wind; An abnormality determination module is used to determine whether the predicted value is abnormal according to the change of the shaft power of the primary fan and the mixed coal combustion mode of the boiler; The equipment adjustment module is used to adjust the opening of each pulverized coal pipe according to the predicted value of the opening of each pulverized coal pipe and adjust the operating parameters of the primary fan according to the predicted value of the wind speed of the primary wind to achieve primary wind leveling when the predicted value is normal.
[0012] According to the third aspect of the present application, a non-temporary computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods provided in the first aspect of the present application are implemented.
[0013] According to a fourth aspect of the present application, there is provided an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any one of the methods provided in the first aspect of the present application.
[0014] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods provided in the first aspect of the present application.
[0015] Through the above technical solution, a back propagation neural network prediction model is established, and multiple parameters such as the current, shaft power, dynamic and static pressure, wind temperature of the primary fan, as well as coal characteristics such as coal powder coarseness and coal quality test parameters are used as input, which can adaptively predict the optimal value of each coal powder pipe opening and primary wind speed. In view of the differences in the characteristics of different types of coal during mixed coal combustion, the complex nonlinear relationship between the parameters learned can be used to quickly give an accurate adjustment plan when the coal type changes. Therefore, the above technical solution can achieve primary air leveling under mixed coal combustion conditions more accurately and quickly.
[0016] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 is a flow chart showing a primary wind leveling method according to an exemplary embodiment; Figure 2 is a schematic diagram of using a back propagation neural network for prediction according to an exemplary embodiment; Figure 3 is a block diagram of a primary air leveling device according to an exemplary embodiment; Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0018] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.
[0019] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.
[0020] Herein, the terms "first", "second", etc. are only used to distinguish one element from another element, and do not require or imply any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa.
[0021] Figure 1 is a flow chart of a primary wind leveling method according to an exemplary embodiment. Figure 1 As shown, the method includes the following steps.
[0022] In step 110, when the shaft power of the primary fan and / or the mixed coal combustion mode of the boiler changes, a first parameter is obtained, and the first parameter includes one or more of the following parameters: the current of the primary fan, the shaft power of the primary fan, the dynamic pressure of the primary air, the static pressure of the primary air, the wind temperature of the primary air, the blade opening of the primary fan, the ratio of the primary air and the secondary air, the power generation load, the furnace pressure, the coarseness of the coal powder, the coal quality test parameters, the emission parameters of the boiler and the efficiency parameters of the boiler.
[0023] In step 120, the first parameter is input into a prediction model to obtain a predicted value of a second parameter. The prediction model is a back propagation neural network updated after the second parameter was last determined. The second parameter includes the opening of each pulverized coal pipe and the wind speed of the primary wind.
[0024] In step 130, it is determined whether the predicted value is abnormal based on the change in the shaft power of the primary fan and the mixed coal combustion mode of the boiler.
[0025] In step 140, when the predicted value is normal, the opening of each pulverized coal pipe is adjusted according to the predicted value of the opening of each pulverized coal pipe and the operating parameters of the primary fan are adjusted according to the predicted value of the primary wind speed to achieve primary wind leveling.
[0026] Here, the primary fan is a device that delivers primary air to the boiler. The shaft power of the primary fan refers to the actual output power of the primary fan when it is running. The dynamic pressure of the primary air refers to the pressure generated by the movement of the airflow in the primary air. The static pressure of the primary air refers to the pressure of the gas itself in the primary air. The boilers of coal-fired power plants are usually equipped with multiple coal mills, and each coal mill usually has multiple pulverized coal pipes. The pulverized coal pipes are used to transport the ground coal to the boiler's burner for combustion. Backpropagation Neural Network (BPNN) is a supervised learning algorithm. Its training process adjusts the internal parameters of the network by backpropagating the network output error, and ultimately achieves the prediction of the input data.
[0027] The first parameter can be obtained from a distributed control system (DCS), a safety instrumented system (SIS) or a corresponding sensor. The first parameter is closely related to the boiler primary air leveling, and the specific relationship is as follows.
[0028] The current and shaft power of the primary fan can directly reflect the operating status and output capacity of the primary fan, and are important parameters for determining the size of the primary air volume. The blade opening of the primary fan directly controls the size of the primary air volume and also affects the operating efficiency of the primary fan. The dynamic pressure of the primary air reflects the change in wind speed, and the static pressure of the primary air reflects the change in the resistance of the pulverized coal pipe. The two together affect the conveying effect and distribution uniformity of the pulverized coal. The wind temperature of the primary air affects the drying effect of the pulverized coal and the pipeline resistance during the conveying process, thereby affecting the combustion efficiency of the pulverized coal. The ratio of primary air and secondary air affects the integrity of the combustion and determines the combustion temperature distribution. The power generation load determines the total primary air volume required for pulverized coal combustion. The furnace pressure affects the safe operation of the boiler during combustion. The coarseness of the pulverized coal affects the conveying resistance and determines the required wind speed. The coal quality test parameters include the calorific value and moisture of the coal, which determine the primary air volume required for pulverized coal combustion.
[0029] The emission parameters of the boiler and the benefit parameters of the boiler are different under different power generation loads. Different power generation loads correspond to different national standards. For example, the benefit of the boiler should increase within a certain range as the power generation load increases. The emission parameters of the boiler include emission values such as NOx and SO2, which reflect the combustion quality and determine the primary air volume required for pulverized coal combustion. The benefit parameters of the boiler include thermal efficiency, coal consumption, etc., which also determine the primary air volume required for pulverized coal combustion. The first parameter mentioned above has a nonlinear effect on the primary air volume.
[0030] The primary air volume is equal to the primary air velocity multiplied by the flow cross-sectional area of the pipeline. The opening of the pulverized coal pipe determines the flow cross-sectional area of the pipeline. The larger the opening, the larger the flow cross-sectional area; the smaller the opening, the smaller the flow cross-sectional area. Therefore, to adjust the primary air volume, it is necessary to adjust the primary air velocity and the opening of each pulverized coal pipe. The primary air velocity can be adjusted by adjusting one or more of the following parameters of the primary fan: the motor speed, the damper opening on the air duct, and the opening of the baffle or valve at the primary fan outlet.
[0031] It should be understood that the output of the primary fan will change during operation, and the ratio of its input power converted to shaft power (the efficiency of the primary fan) will be different. Specifically, the efficiency of the primary fan will decrease as the operating time increases. When the shaft power of the primary fan changes, it means that the actual output primary air volume of the primary fan is also changing. At this time, it is necessary to adjust the primary air volume passing through each pulverized coal pipeline to ensure that the ratio of air and pulverized coal (air-powder ratio) can meet the combustion requirements of pulverized coal. Different types of coal have different combustion characteristics and require different primary air volumes. When the boiler switches to a new type of coal or changes the mixed coal ratio, the original air-powder ratio may no longer be applicable and needs to be re-leveled. Changes in the shaft power of the primary fan and / or the mixed coal combustion method of the boiler can be detected by a distributed control system, a safety instrument system or various sensors.
[0032] During the boiler combustion process, the shaft power of the primary fan and the boiler coal blending method will change many times, and each change requires a wind leveling. Therefore, this method is an iterative process. The prediction model used for this wind leveling is the model updated after the last wind leveling. After this wind leveling is completed, the prediction model will be updated for the next wind leveling.
[0033] Through the above technical solution, a back propagation neural network prediction model is established, and multiple parameters such as the current, shaft power, dynamic and static pressure, wind temperature of the primary fan, as well as coal characteristics such as coal powder coarseness and coal quality test parameters are used as input, which can adaptively predict the optimal value of each coal powder pipe opening and primary wind speed. In view of the differences in the characteristics of different types of coal during mixed coal combustion, the complex nonlinear relationship between the parameters learned can be used to quickly give an accurate adjustment plan when the coal type changes. Therefore, the above technical solution can achieve primary air leveling under mixed coal combustion conditions more accurately and quickly.
[0034] In one embodiment, step 130 may include: when the shaft power of the primary fan increases and / or the mixed coal combustion mode of the boiler changes, resulting in the need to increase the shaft power, if the increase in the predicted value of the opening of any pulverized coal pipe relative to the historical value is within a first preset range, then the predicted value is determined to be normal; otherwise, the predicted value is determined to be abnormal, and the historical value is the opening of the pulverized coal pipe determined last time; when the shaft power of the primary fan decreases and / or the mixed coal combustion mode of the boiler changes, resulting in the need to reduce the shaft power, if the decrease in the predicted value of the opening of any pulverized coal pipe relative to the historical value is within the first preset range, then the predicted value is determined to be normal; otherwise, the predicted value is determined to be abnormal.
[0035] Here, the first preset range is the opening adjustment range specified by the industry standard, which is generally 1% to 5%. If the opening changes too much, it may lead to unstable pulverized coal combustion, destroy the furnace pressure balance, and may cause safety hazards such as flashback, so the predicted value is an abnormal value. If the opening changes too little, it means that the prediction model is not sensitive to changes in shaft power or mixed coal combustion mode, and the predicted value should change but does not change, so the predicted value is also an abnormal value.
[0036] When the boiler's power generation load is increased according to the generation requirements, that is, more pulverized coal is delivered to the furnace, the shaft power of the primary fan will be increased to provide a higher air volume. Alternatively, in order to improve NOx control, the circulating flue gas volume is increased, causing resistance in the entire delivery system, which requires an increase in the shaft power of the primary fan to meet the requirements.
[0037] When the shaft power increases, that is, the output power of the primary fan increases, and a larger air volume is generated, the opening of each pulverized coal pipe needs to be increased accordingly to accommodate a larger air volume, and maintain a suitable conveying wind speed to better convey the pulverized coal. When the shaft power decreases, that is, the output power of the primary fan decreases, the air volume decreases, and the opening of each pulverized coal pipe needs to be reduced accordingly to maintain an appropriate wind speed to avoid coal powder deposition due to too low wind speed.
[0038] The following changes in the mixed coal combustion method will result in the need to increase shaft power. When low calorific value coal is added, more air volume is required to maintain the same combustion effect and overcome the possible increased conveying resistance. When high-moisture coal is added, more air volume is required to assist in drying and overcome the possible increased conveying resistance. When coal with larger fineness is added, a higher wind speed is required to ensure transportation and prevent sedimentation. The following changes in the mixed coal combustion method will result in the need to reduce shaft power. When high calorific value coal is added, the required air volume is reduced. When low-moisture coal is added, the drying demand is reduced and the conveying resistance is reduced. When coal with smaller fineness is added, the wind speed required for transportation can be reduced, reducing energy consumption.
[0039] The above method can realize timely identification and early warning of abnormal operating conditions by comparing the change range of the predicted value of the pulverized coal pipe opening with the historical value when the primary fan shaft power changes and / or the mixed coal combustion mode changes.
[0040] In one embodiment, the method also includes: when the predicted value is abnormal, outputting an abnormal prompt message; receiving and storing a correction value of a second parameter input by a user, wherein the correction value is the opening of each coal powder pipe and the wind speed of the primary air set by the user based on field operation experience; adjusting the opening of each coal powder pipe and the wind speed of the primary air according to the correction value to achieve primary air leveling; using the first parameter as an input feature and the correction value as a label, updating and training the prediction model to obtain a back propagation neural network after this update.
[0041] Here, the correction value is the opening of each pulverized coal pipe and the wind speed of the primary air that the user receives the abnormal prompt information and manually inputs into the distributed control system or the safety instrument system based on field experience. The correction value for input is received and stored from the distributed control system or the safety instrument system. And the correction value is used to adjust the opening of each pulverized coal pipe and the operating parameters of the primary fan.
[0042] The above method can correct abnormal situations and optimize the accuracy and adaptability of the prediction model through manual correction.
[0043] In one embodiment, the initial prediction model used when initially determining the second parameter is obtained by the following steps: obtaining test data of primary wind leveling under different operating conditions, wherein the operating conditions include operating conditions under different power generation load conditions covering a second preset range, and the test data include operating parameters under different power generation loads; constructing a training sample set including input features and corresponding labels based on the test data of primary wind leveling; and using the training sample set to train an initial back propagation neural network to obtain an initial prediction model.
[0044] Here, the second preset range is the range of power generation load for normal operation of the unit according to national standards and industry standards, usually 30%-100%. For example, different operating conditions can be set to 100% power generation load, 75% power generation load, 50% power generation load and 30% power generation load. The acquired primary wind leveling test data needs to select valid data (non-abnormal data), normalize it, and then divide the input features and corresponding labels.
[0045] Figure 2 is a schematic diagram of using a back propagation neural network for prediction according to an exemplary embodiment, such as Figure 2 As shown in the figure, the training process of the above back-propagation neural network is as follows. (1) The input features are imported into the input layer of the initial back-propagation neural network. (2) Forward propagation is performed: the input features are weightedly calculated from the neurons of the input layer to the hidden layer to obtain the hidden layer output data, and then the output prediction value is obtained through weighted calculation from the hidden layer to the output layer. (3) Loss calculation is performed: the prediction value is compared with the label, the error is calculated, and the loss value is obtained. (4) Error back propagation is performed: based on the loss value, the error is back propagated from the output layer to the input layer in sequence. Specifically, the output layer error is calculated to obtain the output layer error value; the output layer error value is reversely transferred to the hidden layer through the chain rule to obtain the hidden layer error value; based on the output layer error value and the hidden layer error value, the gradient of the weight and bias is calculated to obtain the gradient update value. (5) Weight update is performed: using the gradient update value, the weights and biases of the neurons of each layer are updated through the gradient descent algorithm to obtain the updated weights and bias values, thereby updating the weights of each layer. Finally, repeat the iterations: repeat steps (2) to (5) until the loss value converges to the set threshold range or reaches the preset training rounds to complete the training of the back propagation neural network.
[0046] In the above back propagation neural network training process, the gradient descent algorithm can be a stochastic gradient descent algorithm (SGD) or an adaptive moment estimation algorithm (Adam); the activation function can be a Sigmoid function, a ReLU function or a combination thereof; and the loss calculation part can calculate a mean square error (MSE) or a cross entropy loss.
[0047] Through the training process of the above-mentioned back propagation neural network, the initial prediction model can have a certain prediction ability, can preliminarily learn the mapping relationship between the second parameter and the first parameter, and be put into the actual prediction of the second parameter for the first time.
[0048] In one embodiment, the training sample set includes training samples corresponding to each operating condition, and each training sample includes input features and labels; the input features include one or more of the following parameters: the current of the primary fan, the shaft power of the primary fan, the dynamic pressure of the primary air, the static pressure of the primary air, the wind temperature of the primary air, the blade opening of the primary fan, the ratio of primary air to secondary air, the power generation load, the furnace pressure, the coarseness of the coal powder, the coal quality testing parameters, the emission parameters of the boiler and the efficiency parameters of the boiler; the labels include the opening of each coal powder pipeline and the wind speed of the primary air.
[0049] It should be understood that the input features selected in the training process of the prediction model should be consistent with the composition and arrangement of the first parameters selected in the application process of the prediction model; at the same time, the labels should be consistent with the arrangement of the second parameters.
[0050] In one embodiment, in all training samples, the difference in opening degree of the same pulverized coal pipeline corresponding to the same working condition is within the first preset range.
[0051] It should be understood that during the training process, the test data corresponding to the same pulverized coal pipeline under the same working condition, whose opening difference is within the first preset range, should be selected as training samples, so that the training samples are within a reasonable range, which can better reflect the mapping relationship between the input features and labels of normal primary air leveling. For example, under 80% load, the pulverized coal pipeline X opening of the training sample should be within the range of 40% ± 5%; under 70% load, the pulverized coal pipeline X opening of the training sample should be within the range of 38% ± 5%.
[0052] In summary, the primary wind leveling method can realize the prediction and automatic adjustment of primary wind leveling parameters through continuous learning and adaptive back propagation neural network. When the prediction is abnormal, the prediction model can be corrected and updated in combination with manual experience, and the initial training can be carried out using multi-condition test data to improve the adaptability and reliability under different power generation loads and mixed coal combustion conditions, thereby improving the accuracy and timeliness of primary wind leveling.
[0053] Figure 3 is a block diagram of a primary air leveling device according to an exemplary embodiment. Figure 3 As shown, the device comprises: The data acquisition module 310 is used to acquire a first parameter when the shaft power of the primary fan and / or the mixed coal combustion mode of the boiler changes. The first parameter includes one or more of the following parameters: the current of the primary fan, the shaft power of the primary fan, the dynamic pressure of the primary air, the static pressure of the primary air, the wind temperature of the primary air, the blade opening of the primary fan, the ratio of the primary air to the secondary air, the power generation load, the furnace pressure, the coarseness of the coal powder, the coal quality test parameters, the emission parameters of the boiler, and the benefit parameters of the boiler; A prediction output module 320, configured to input the first parameter into a prediction model to obtain a predicted value of a second parameter, wherein the prediction model is a back propagation neural network updated after the second parameter was determined last time, wherein the second parameter includes the opening of each pulverized coal pipe and the wind speed of the primary wind; The abnormality determination module 330 is used to determine whether the predicted value is abnormal according to the change of the shaft power of the primary fan and the mixed coal combustion mode of the boiler; The equipment adjustment module 340 is used to adjust the opening of each pulverized coal pipe according to the predicted value of the opening of each pulverized coal pipe and adjust the operating parameters of the primary fan according to the predicted value of the wind speed of the primary wind to achieve primary wind leveling when the predicted value is normal.
[0054] Optionally, the abnormality determination module 330 is specifically configured to: In the case where the shaft power of the primary fan increases and / or the mixed coal combustion mode of the boiler changes, resulting in the need to increase the shaft power, if the increase in the predicted value of the opening of any pulverized coal pipe relative to the historical value is within a first preset range, the predicted value is determined to be normal; otherwise, the predicted value is determined to be abnormal, and the historical value is the opening of the pulverized coal pipe determined last time; When the shaft power of the primary fan is reduced and / or the mixed coal combustion mode of the boiler changes, resulting in the need to reduce the shaft power, if the decrease in the predicted value of the opening of any pulverized coal pipe relative to the historical value is within the first preset range, the predicted value is judged to be normal; otherwise, the predicted value is judged to be abnormal.
[0055] Optionally, the device further comprises an abnormality correction module, configured to: When the predicted value is abnormal, output abnormal prompt information; receiving and storing a correction value of a second parameter input by a user, wherein the correction value is the opening of each pulverized coal pipe and the wind speed of the primary air set by the user based on field operation experience; According to the correction value, the opening of each pulverized coal pipe and the wind speed of the primary air are adjusted to achieve primary air leveling; The first parameter is used as an input feature and the correction value is used as a label to update and train the prediction model to obtain a back propagation neural network after this update.
[0056] Optionally, the device further comprises an initial model training module, which is used to: Acquire test data of primary wind leveling under different operating conditions, wherein the operating conditions include operating conditions under different power generation load conditions covering a second preset range, and the test data include operating parameters under different power generation loads; According to the experimental data of the primary wind leveling, a training sample set including input features and corresponding labels is constructed; The initial back propagation neural network is trained using the training sample set to obtain an initial prediction model.
[0057] Optionally, the training sample set includes training samples corresponding to each working condition, and each training sample includes input features and labels; The input characteristics include one or more of the following parameters: current of the primary fan, shaft power of the primary fan, dynamic pressure of the primary air, static pressure of the primary air, wind temperature of the primary air, blade opening of the primary fan, ratio of primary air to secondary air, power generation load, furnace pressure, coal powder coarseness, coal quality test parameters, boiler emission parameters and boiler efficiency parameters; The labels include the opening of each pulverized coal pipeline and the wind speed of the primary air.
[0058] Optionally, in all training samples, the difference in opening degree of the same pulverized coal pipeline corresponding to the same operating condition is within the first preset range.
[0059] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0060] Figure 4 FIG. 4 is a block diagram of an electronic device 400 according to an exemplary embodiment. Figure 4 As shown, the electronic device 400 may include: a processor 401 , a memory 402 . The electronic device 400 may also include one or more of a multimedia component 403 , an input / output (I / O) interface 404 , and a communication component 405 .
[0061] The processor 401 is used to control the overall operation of the electronic device 400 to complete all or part of the steps in the above-mentioned primary wind leveling method. The memory 402 is used to store various types of data to support the operation of the electronic device 400. For example, these data may include instructions for any application or method used to operate on the electronic device 400, and application-related data, such as contact data, messages sent and received, pictures, audio, video, etc. The memory 402 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 403 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 402 or sent through the communication component 405. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 404 provides an interface between the processor 401 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 405 may include: Wi-Fi module, Bluetooth module, NFC module, etc.
[0062] In an exemplary embodiment, the electronic device 400 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned primary wind leveling method.
[0063] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned primary wind leveling method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 402 including program instructions, and the above-mentioned program instructions can be executed by the processor 401 of the electronic device 400 to complete the above-mentioned primary wind leveling method.
[0064] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the primary wind leveling method described above when executed by the programmable device.
[0065] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.
[0066] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.
[0067] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.
Claims
1. A primary air leveling method, characterized in that: include: When the shaft power of the primary fan and / or the mixed coal combustion mode of the boiler changes, a first parameter is obtained, wherein the first parameter includes one or more of the following parameters: the current of the primary fan, the shaft power of the primary fan, the dynamic pressure of the primary air, the static pressure of the primary air, the wind temperature of the primary air, the blade opening of the primary fan, the ratio of the primary air to the secondary air, the power generation load, the furnace pressure, the coarseness of the coal powder, the coal quality test parameters, the emission parameters of the boiler, and the benefit parameters of the boiler; Inputting the first parameter into a prediction model to obtain a predicted value of a second parameter, wherein the prediction model is a back propagation neural network updated after the second parameter was determined last time, and the second parameter includes the opening of each pulverized coal pipe and the wind speed of the primary wind; Determine whether the predicted value is abnormal according to the change of the shaft power of the primary fan and the mixed coal combustion mode of the boiler; When the predicted value is normal, the opening of each pulverized coal pipe is adjusted according to the predicted value of the opening of each pulverized coal pipe, and the operating parameters of the primary fan are adjusted according to the predicted value of the primary wind speed to achieve primary wind leveling.
2. The primary air leveling method according to claim 1, characterized in that: The determining whether the predicted value is abnormal according to the change of the shaft power of the primary fan and the mixed coal combustion mode of the boiler includes: In the case where the shaft power of the primary fan increases and / or the mixed coal combustion mode of the boiler changes, resulting in the need to increase the shaft power, if the increase in the predicted value of the opening of any pulverized coal pipe relative to the historical value is within a first preset range, the predicted value is determined to be normal; otherwise, the predicted value is determined to be abnormal, and the historical value is the opening of the pulverized coal pipe determined last time; When the shaft power of the primary fan is reduced and / or the mixed coal combustion mode of the boiler changes, resulting in the need to reduce the shaft power, if the decrease in the predicted value of the opening of any pulverized coal pipe relative to the historical value is within the first preset range, the predicted value is judged to be normal; otherwise, the predicted value is judged to be abnormal.
3. The primary air leveling method according to claim 1, characterized in that: The method further comprises: When the predicted value is abnormal, output abnormal prompt information; receiving and storing a correction value of a second parameter input by a user, wherein the correction value is the opening of each pulverized coal pipe and the wind speed of the primary air set by the user based on field operation experience; According to the correction value, the opening of each pulverized coal pipe and the wind speed of the primary air are adjusted to achieve primary air leveling; The first parameter is used as an input feature and the correction value is used as a label to update and train the prediction model to obtain a back propagation neural network after this update.
4. The primary air leveling method according to any one of claims 1 to 3, characterized in that: The initial prediction model used when first determining the second parameter is obtained by the following steps: Acquire test data of primary wind leveling under different operating conditions, wherein the operating conditions include operating conditions under different power generation load conditions covering a second preset range, and the test data include operating parameters under different power generation loads; According to the experimental data of the primary wind leveling, a training sample set including input features and corresponding labels is constructed; The initial back propagation neural network is trained using the training sample set to obtain an initial prediction model.
5. The primary air leveling method according to claim 4, characterized in that: The training sample set includes training samples corresponding to each working condition, and each training sample includes input features and labels; The input characteristics include one or more of the following parameters: current of the primary fan, shaft power of the primary fan, dynamic pressure of the primary air, static pressure of the primary air, wind temperature of the primary air, blade opening of the primary fan, ratio of primary air to secondary air, power generation load, furnace pressure, coal powder coarseness, coal quality test parameters, boiler emission parameters and boiler efficiency parameters; The labels include the opening of each pulverized coal pipeline and the wind speed of the primary air.
6. The primary air leveling method according to claim 5, characterized in that: In all training samples, the difference in opening degree of the same pulverized coal pipeline corresponding to the same operating condition is within the first preset range.
7. A primary air leveling device, characterized in that: include: A data acquisition module is used to acquire a first parameter when the shaft power of the primary fan and / or the mixed coal combustion mode of the boiler changes, wherein the first parameter includes one or more of the following parameters: the current of the primary fan, the shaft power of the primary fan, the dynamic pressure of the primary air, the static pressure of the primary air, the wind temperature of the primary air, the blade opening of the primary fan, the ratio of the primary air to the secondary air, the power generation load, the furnace pressure, the coarseness of the coal powder, the coal quality test parameters, the emission parameters of the boiler, and the benefit parameters of the boiler; A prediction output module, used for inputting the first parameter into a prediction model to obtain a predicted value of a second parameter, wherein the prediction model is a back propagation neural network updated after the second parameter was determined last time, and the second parameter includes the opening of each pulverized coal pipe and the wind speed of the primary wind; An abnormality determination module is used to determine whether the predicted value is abnormal according to the change of the shaft power of the primary fan and the mixed coal combustion mode of the boiler; The equipment adjustment module is used to adjust the opening of each pulverized coal pipe according to the predicted value of the opening of each pulverized coal pipe and adjust the operating parameters of the primary fan according to the predicted value of the wind speed of the primary wind to achieve primary wind leveling when the predicted value is normal.
8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the primary wind leveling method described in any one of claims 1-6 are implemented.