Boiler wall attachment gas delivery method and system for reducing ash deposition

Abstract

The application discloses a boiler wall-attached gas conveying method and system for reducing ash deposition and slagging, and relates to the field of boiler cleaning. The method comprises the following steps: collecting a pipeline ash deposition detection sample, counting pipeline ash deposition thickness distribution and pipeline ash deposition adhesion force distribution; configuring a boiler wall-attached gas conveying scheme; processing rotational flow wind speed, rotational flow wind direction, pipeline internal pressure, cleaning duration, pipeline ash deposition thickness distribution and pipeline ash deposition adhesion force distribution through a residual ash thickness prediction model, and outputting residual ash thickness distribution; processing rotational flow wind speed, rotational flow wind direction, pipeline internal pressure and cleaning duration through an energy consumption prediction model, and outputting a cleaning energy consumption prediction value; when residual ash thickness at any place of the residual ash thickness distribution is less than or equal to a residual ash thickness threshold value, and the cleaning energy consumption prediction value is less than or equal to an energy consumption threshold value, performing boiler wall-attached gas conveying control according to the boiler wall-attached gas conveying scheme, and executing in-furnace pipeline cleaning. The method solves the problem that surrounding pipeline residual ash cannot be cleaned in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of boiler cleaning, in particular to a boiler wall-attached gas delivery method and system for reducing ash and slag accumulation. BACKGROUND

[0002] With the development of industry, boilers are increasingly widely used in various production activities. However, the traditional boiler cleaning method uses a straight-through blowing device, which can only clean some obvious accumulated ash, and it is difficult to effectively clean the residual ash on the surrounding pipes. The residual ash attached to the pipes for a long time causes pipe corrosion, pipe perforation and water leakage. If the pipe leaks after water leakage, the boiler needs to be shut down for maintenance, causing unnecessary losses, shortening the service life of the boiler, and even causing safety accidents. SUMMARY

[0003] The embodiments of the present application provide a boiler wall-attached gas delivery method and system for reducing ash and slag accumulation, which solves the technical problem that the prior art cannot clean a large amount of residual ash on the surrounding pipes.

[0004] The technical solutions of the present application for solving the above technical problems are as follows:

[0005] In a first aspect, the present application provides a boiler wall-attached gas delivery method for reducing ash and slag accumulation, which comprises:

[0006] Collecting a pipe ash detection sample set with the constraints of the boiler operating parameters, the boiler model and the boiler airflow monitoring parameters of the target boiler, and counting the pipe ash thickness distribution and the pipe ash adhesion force distribution;

[0007] Configuring a boiler wall-attached gas delivery scheme, wherein the boiler wall-attached gas delivery scheme includes cyclone wind speed, cyclone wind direction, pipe internal pressure and cleaning duration;

[0008] Processing the cyclone wind speed, the cyclone wind direction, the pipe internal pressure, the cleaning duration, the pipe ash thickness distribution and the pipe ash adhesion force distribution through a residual ash thickness prediction model bound to the target boiler, and outputting a residual ash thickness distribution;

[0009] Processing the cyclone wind speed, the cyclone wind direction, the pipe internal pressure and the cleaning duration through an energy consumption prediction model bound to the target boiler, and outputting a cleaning energy consumption prediction value;

[0010] In a second aspect, the present application provides a boiler wall-attached gas delivery system for reducing ash and slag accumulation, which comprises:

[0011] A sample collection module is configured to collect a pipe ash detection sample set with the constraints of the boiler operating parameters, the boiler model and the boiler airflow monitoring parameters of the target boiler, and count the pipe ash thickness distribution and the pipe ash adhesion force distribution.

[0012] a scheme configuration module, configured to configure a boiler wall-attached gas delivery scheme, wherein the boiler wall-attached gas delivery scheme comprises a rotational flow air speed, a rotational flow air direction, an internal pipe pressure, and a cleaning duration;

[0013] a soot thickness prediction module, configured to process the rotational flow air speed, the rotational flow air direction, the internal pipe pressure, the cleaning duration, the pipe soot thickness distribution, and the pipe soot adhesion force distribution by a residual soot thickness prediction model bound to the target boiler, and output a residual soot thickness distribution;

[0014] an energy consumption output module, configured to process the rotational flow air speed, the rotational flow air direction, the internal pipe pressure, and the cleaning duration by an energy consumption prediction model bound to the target boiler, and output a cleaning energy consumption prediction value;

[0015] a scheme execution module, configured to perform a boiler wall-attached gas delivery control according to the boiler wall-attached gas delivery scheme when residual soot thickness at any position of the residual soot thickness distribution is less than or equal to a residual soot thickness threshold value and the cleaning energy consumption prediction value is less than or equal to an energy consumption threshold value, and perform an in-furnace pipe cleaning.

[0016] The application provides one or more technical solutions, which have at least the following technical effects or advantages:

[0017] The boiler wall-attached gas delivery method and system provided by the application can reduce the soot and slag accumulation, statistically analyze the pipe soot accumulation by comprehensively considering the parameters of the boiler operation, and predict the residual soot thickness and the cleaning energy consumption by using the prediction model, so that the cleaning effect can be ensured and the energy consumption can be effectively controlled. The boiler wall-attached gas delivery control is performed when the residual soot thickness and the energy consumption meet the requirements by setting the threshold value, so that the in-furnace pipe cleaning is efficient and energy-saving. When the threshold condition is not met, the scheme fitness is calculated by setting the weight, and the particle swarm optimization method is combined, so that the gas delivery scheme can be continuously optimized, a more suitable target gas delivery scheme can be finally found, and the cleaning effect and the energy utilization efficiency are further improved.

[0018] By the above technical solution, the pipe soot thickness and the pipe soot adhesion force distribution of the target boiler are collected, the boiler wall-attached gas delivery scheme is configured, and then the residual soot thickness distribution and the cleaning energy consumption prediction value are output by the residual soot thickness prediction model and the energy consumption prediction model respectively. The problem that the residual soot in the surrounding pipes cannot be cleaned in the prior art is solved, the occurrence of pipe corrosion, perforation and other situations is reduced, the loss caused by the shutdown for maintenance due to pipe leakage is avoided, the service life of the boiler is prolonged, the risk of safety accidents is reduced, and the stable operation of the boiler in industrial production is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0020] Figure 1 is a flowchart of a boiler wall-attached gas conveying method for reducing ash deposition and slagging provided by an embodiment of the present application;

[0021] Figure 2 is a structural schematic diagram of a boiler wall-attached gas conveying system for reducing ash deposition and slagging provided by an embodiment of the present application.

[0022] In the drawings, the components represented by the respective reference numerals are as follows:

[0023] The sample collection module 11, the scheme configuration module 12, the ash thickness prediction module 13, the energy consumption output module 14, and the scheme execution module 15. DETAILED DESCRIPTION

[0024] The present application provides a boiler wall-attached gas conveying method for reducing ash deposition and slagging, which is used to solve the technical problem that the residual coal ash in the peripheral pipeline cannot be cleaned in the prior art.

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings of the embodiments of the present application. Obviously, the described embodiments only constitute some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort belong to the scope of protection of the present application.

[0026] In the description of the present application, the terms "first" and "second" are only used for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0027] In the description of the present application, the term "for example" is used to indicate "serving as an example, instance, or illustration." Any embodiment described as "for example" in this application is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the present application. In the following description, for the purpose of explanation, details are set forth. It is apparent to those skilled in the art that the present application can be practiced without the use of these specific details. In other instances, well-known structures and processes are not elaborated in order not to obscure the description of the present application with unnecessary details. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0028] Embodiment one, as shown in the present application, provides a boiler wall-attached gas conveying method for reducing ash deposition and slagging, comprising: Figure 1

[0029] S10: Collecting a pipe ash detection sample set with the boiler operating parameters, the boiler model and the boiler airflow monitoring parameters of the target boiler as constraints, and statistically analyzing the pipe ash thickness distribution and the pipe ash adhesion force distribution;

[0030] In the embodiments of the present application, first, the pipe ash detection sample set is collected with the boiler operating parameters, the boiler model and the boiler airflow monitoring parameters of the target boiler as constraints, and data quality inspection is performed on the collected pipe ash detection sample set to check whether there are data missing, outliers and the like. If there is data missing, the mean, median and the like method can be used for filling according to the distribution of other data in the sample set; if there are outliers, abnormal data can be identified and removed through statistical analysis methods, such as based on standard deviation.

[0031] The boiler operating parameters are the operating parameters after the last cleaning, and the boiler airflow monitoring parameters are the airflow monitoring parameters after the last cleaning.

[0032] Secondly, the pipe ash thickness distribution and the pipe ash adhesion force distribution obtained by statistical analysis of the pipe ash are visually displayed. For example, a column chart is used to display the pipe ash thickness at different positions, and a line chart is used to display the change trend of the pipe ash adhesion force.

[0033] Specifically, step S10 in the method comprises:

[0034] Collecting a pipe ash detection sample to be analyzed with the boiler model as a constraint, wherein the pipe ash detection sample to be analyzed has a label identifying the boiler operating parameters and a label identifying the boiler airflow monitoring parameters;

[0035] ​When the boiler operation parameters and the any attribute boiler operation parameter deviation of the label identifying the boiler operation parameters are all less than or equal to the corresponding attribute boiler operation parameter deviation threshold, the boiler operation parameters are considered consistent;

[0036] When the boiler airflow monitoring parameters and the any attribute boiler airflow monitoring parameter deviation of the label identifying the boiler airflow monitoring parameters are all less than or equal to the corresponding attribute boiler airflow monitoring parameter deviation threshold, the boiler airflow monitoring parameters are considered consistent;

[0037] When the boiler operation parameters are consistent and the boiler airflow monitoring parameters are consistent, the to-be-analyzed pipeline ash detection sample is added to the pipeline ash detection sample set.

[0038] In the embodiments of the present application, the to-be-analyzed pipeline ash detection sample is collected with the boiler model as a constraint, including the label identifying the boiler operation parameters and the label identifying the boiler airflow monitoring parameters of the to-be-analyzed pipeline ash detection sample.

[0039] After the to-be-analyzed pipeline ash detection sample is collected, the label data is further verified. By comparing with the historical operation data and airflow monitoring data of the boiler, whether the label data conforms to the normal change range and law is checked. If it is found that the label data has obvious unreasonable situation, for example, a certain operation parameter exceeds the normal range of the boiler of this model, or the airflow monitoring parameters do not conform to the actual pipeline layout and gas conveying situation, the sample needs to be further verified or rejected.

[0040] If the boiler operation parameters and the any attribute boiler operation parameter deviation of the label identifying the boiler operation parameters are all less than or equal to the corresponding attribute boiler operation parameter deviation threshold, the boiler operation parameters are considered consistent; if the boiler airflow monitoring parameters and the any attribute boiler airflow monitoring parameter deviation of the label identifying the boiler airflow monitoring parameters are all less than or equal to the corresponding attribute boiler airflow monitoring parameter deviation threshold, the boiler airflow monitoring parameters are considered consistent.

[0041] Exemplarily, it is assumed that the boiler operation parameters include temperature, pressure, water level and other attributes, and the corresponding attribute boiler operation parameter deviation threshold is set to temperature deviation ±5℃, pressure deviation ±0.1MPa, and water level deviation ±2cm. When the label identifying the boiler operation parameters of the to-be-analyzed pipeline ash detection sample collected shows that the temperature is 150℃, the pressure is 2.0MPa, and the water level is 50cm, while the actual operation parameters of the target boiler are temperature 152℃, pressure 2.05MPa, and water level 51cm. At this time, the temperature deviation is 2℃, which is less than the temperature deviation threshold 5℃; the pressure deviation is 0.05MPa, which is less than the pressure deviation threshold 0.1MPa; and the water level deviation is 1cm, which is less than the water level deviation threshold 2cm, and the boiler operation parameters are considered consistent.

[0042] Similarly, it is assumed that the boiler airflow monitoring parameters include wind speed, wind direction, wind pressure and other attributes, and the corresponding attribute boiler airflow monitoring parameter deviation threshold is set to wind speed deviation ±1m / s, wind direction deviation ±5°, and wind pressure deviation ±0.05MPa. If the collected and analyzed pipeline ash detection sample identification boiler airflow monitoring parameter label shows that the wind speed is 5m / s, the wind direction is the positive east direction, and the wind pressure is 1.5MPa, while the actual target boiler airflow monitoring parameters are 5.2m / s, 3° east-north, and 1.52MPa. The wind speed deviation is 0.2m / s, which is less than the wind speed deviation threshold of 1m / s; the wind direction deviation is 3°, which is less than the wind direction deviation threshold of 5°; and the wind pressure deviation is 0.02MPa, which is less than the wind pressure deviation threshold of 0.05MPa. It can be considered that the boiler airflow monitoring parameters are consistent.

[0043] When the boiler operating parameters are consistent and the boiler airflow monitoring parameters are consistent, the analyzed pipeline ash detection sample is added to the pipeline ash detection sample set. Through the data screening process, the accuracy and reliability of the collected pipeline ash detection sample set are ensured, laying a foundation for subsequent accurate statistics of the pipeline ash thickness distribution and the pipeline ash adhesion force distribution, so that the boiler wall-attached gas conveying scheme generated based on the data is more reasonable, and the cleaning effect and energy utilization efficiency of the boiler pipeline are effectively improved.

[0044] Among them, collecting the pipeline ash detection sample set, and statistically analyzing the pipeline ash thickness distribution and the pipeline ash adhesion force distribution, comprising:

[0045] The inner wall of the target boiler pipeline is divided into a grid by a preset grid length, and a boiler pipeline inner wall grid distribution is obtained;

[0046] Based on the boiler pipeline inner wall grid distribution, the pipeline ash detection sample set is divided to obtain a first pipeline grid distribution ash state to a Qth pipeline grid distribution ash state, wherein Q represents the total number of samples, and Q≥30;

[0047] The first pipeline grid distribution ash state to the Qth pipeline grid distribution ash state is integrated into a same grid state to obtain a first grid ash state set to an Mth grid ash state set, wherein M represents the total number of grids;

[0048] The first grid ash state set to the Mth grid ash state set is traversed, and a centroid ash state analysis is performed to obtain the pipeline ash thickness distribution and the pipeline ash adhesion force distribution.

[0049] In the embodiments of the present application, the inner wall of the target boiler pipeline is divided into a grid by a preset grid length, and the complex pipeline inner wall space is discretized, for example, the inner wall of the target boiler pipeline is divided into a small grid of 3cm×3cm, and a boiler pipeline inner wall grid distribution is obtained.

[0050] Firstly, after obtaining the grid distribution of the inner wall of the boiler pipeline, the sample set of pipeline ash deposition detection is divided based on the grid distribution. Each sample corresponds to a pipeline grid distribution ash deposition state, and the sample data is associated with the specific grid position.

[0051] Secondly, the first pipeline grid distribution ash deposition state to the Qth pipeline grid distribution ash deposition state is divided, where Q represents the total number of samples, Q is greater than or equal to 30, and the larger the value of Q, the more accurate the calculation. This step can eliminate the random error between samples and make the ash deposition state of each grid more accurate and stable.

[0052] Thirdly, the first pipeline grid distribution ash deposition state to the Qth pipeline grid distribution ash deposition state is integrated, and the ash deposition states of multiple samples in the same grid are combined and counted through integration to obtain the first grid ash deposition state set to the Mth grid ash deposition state set. Where M represents the total number of grids.

[0053] Finally, the centroid ash deposition state analysis is performed by traversing the state set. The centroid ash deposition state analysis can find the typical characteristics of each grid ash deposition state, such as average ash deposition thickness, average ash deposition adhesion, etc. Through analysis and summary of the centroid ash deposition state of all grids, the pipeline ash deposition thickness distribution and pipeline ash deposition adhesion distribution can be obtained.

[0054] In performing the centroid ash deposition state analysis, statistical methods are used. For example, for the ash deposition thickness data in each grid ash deposition state set, the mean, median, standard deviation, etc. are calculated to obtain the concentration trend and dispersion degree of the ash deposition thickness. The same method is used to analyze the ash deposition adhesion data.

[0055] For example, the average ash deposition thickness of 50 ash deposition thickness data in a certain grid ash deposition state set is 2mm. The median is calculated by first sorting the data from small to large. If the number of data is odd, the middle number is the median; if the number of data is even, the average of the two middle numbers is the median. Assuming that the two middle numbers after sorting are 2mm and 2.1mm, the median is 2.05mm.

[0056] The standard deviation reflects the dispersion degree of the data, which is obtained by calculating the square root of the average of the square sum of the difference between each data and the mean. If the standard deviation is small, the data is concentrated and the ash deposition thickness is relatively stable; if the standard deviation is large, the data is dispersed and the ash deposition thickness fluctuates greatly.

[0057] For the soot adhesion data, the same statistical analysis is also performed. For example, a certain grid soot state set has 50 soot adhesion data, such as 0.5N, 0.6N, 0.4N, etc. The mean, median and standard deviation are calculated to understand the central tendency and dispersion of the soot adhesion of the grid.

[0058] The soot thickness distribution and soot adhesion distribution of the pipeline obtained by the above steps provide detailed and accurate data support for subsequent configuration of the boiler wall gas conveying scheme.

[0059] Further, the centroid soot state analysis is performed by traversing the first grid soot state set to the Mth grid soot state set, and the pipeline soot thickness distribution and the pipeline soot adhesion distribution are obtained, comprising:

[0060] From the first grid soot state set, a plurality of soot states are extracted, wherein any one of the plurality of soot states includes soot thickness and soot adhesion;

[0061] The plurality of soot states are distributed with the soot thickness normalized value as the first coordinate and the soot adhesion normalized value as the second coordinate to obtain a plurality of soot state distribution coordinates;

[0062] Based on the plurality of soot state distribution coordinates, the LOF outlier factor minimum value is extracted to obtain a centroid soot state distribution coordinate;

[0063] Based on the centroid soot state distribution coordinate, the first grid pipeline soot thickness and the first grid pipeline soot adhesion are extracted;

[0064] When the Mth grid pipeline soot thickness and the Mth grid pipeline adhesion are obtained, the first grid pipeline soot thickness to the Mth grid pipeline soot thickness are integrated to obtain the pipeline soot thickness distribution, and the first grid pipeline soot adhesion to the Mth grid pipeline adhesion are integrated to obtain the pipeline soot adhesion distribution.

[0065] In the embodiments of the present application, when the plurality of soot states are extracted from the first grid soot state set, it is ensured that the extracted soot states are representative and can reflect the overall characteristics of the grid soot state. For soot thickness and soot adhesion, since the dimensions and numerical ranges may be different, normalization processing is required for subsequent analysis and processing. There are many normalization methods, for example, the "minimum-maximum" normalization method maps the soot thickness and soot adhesion data to the [0, 1] interval.

[0066] Further, a plurality of soot states are distributed with the soot thickness normalized value as the first coordinate and the soot adhesion normalized value as the second coordinate, to obtain a plurality of soot state distribution coordinates, and the soot states are visually displayed on a two-dimensional plane.

[0067] Exemplarily, 10 soot states are extracted from a certain grid soot state set, the soot thickness normalized values are 0.2, 0.3, 0.4, etc., and the soot adhesion normalized values are 0.1, 0.2, 0.3, etc. With the soot thickness normalized value as the horizontal coordinate and the soot adhesion normalized value as the vertical coordinate, the 10 soot state distribution coordinates can be obtained, such as (0.7, 0.1), (0.3, 0.2), etc.

[0068] Based on the plurality of soot state distribution coordinates, the LOF outlier factor minimum value is extracted. The LOF local outlier factor is an algorithm for identifying outliers in a data set, which finds points that are relatively isolated from surrounding points by calculating the local outlier factor of each point. The point corresponding to the LOF outlier factor minimum value is extracted, which is the centroid soot state distribution coordinate.

[0069] Exemplarily, the No. 1 sample soot state distribution coordinate is (0.7, 0.1), the No. 2 sample soot state distribution coordinate is (0.3, 0.2), and the No. 3 sample soot state distribution coordinate is (0.99, 0.8).

[0070] The LOF outlier factor minimum value is extracted, LOF = LRD average value of sample k neighbors / LRD of sample itself, the smaller the LOF value, the weaker the outlier, the closer to the local center. Calculation gives ≈1.0936, ≈0.9572, ≈0.9572, After comparison, the LOF values of the No. 2 sample and the No. 3 sample are the smallest and equal, which are local non-outlier samples. The centroid soot state distribution coordinate is (0.3, 0.2), which is the No. 2 sample coordinate.

[0071] Further, based on the centroid soot state distribution coordinate, the first grid pipeline soot thickness and the first grid pipeline soot adhesion are extracted, for example, according to the No. 2 sample coordinate (0.3, 0.2), the first grid pipeline soot thickness and the first grid pipeline soot adhesion are 0.3 and 0.2, respectively.

[0072] Finally, when the Mth grid pipeline soot thickness and the Mth grid pipeline adhesion are obtained, the first grid pipeline soot thickness to the Mth grid pipeline soot thickness are integrated to obtain the pipeline soot thickness distribution.

[0073] The first grid pipeline soot adhesion to the Mth grid pipeline adhesion are integrated to obtain the pipeline soot adhesion distribution.

[0074] By integrating the distribution of the thickness of the pipe ash and the distribution of the adhesion of the pipe ash, when the boiler wall-attached gas delivery scheme is subsequently configured, the direction, speed and pressure and other parameters of the gas delivery are accurately adjusted according to the ash conditions at different positions. For example, for the grid position with a large thickness of ash and a strong adhesion, the pressure and speed of gas delivery are increased to improve the cleaning effect; for the position with thin ash and weak adhesion, the intensity of gas delivery is appropriately reduced to avoid waste of energy.

[0075] S20: configuring a boiler wall-attached gas delivery scheme, wherein the boiler wall-attached gas delivery scheme includes a rotational flow wind speed, a rotational flow wind direction, an in-pipe pressure and a cleaning duration;

[0076] In the embodiments of the present application, the boiler wall-attached gas delivery scheme is configured in combination with the obtained distribution of the thickness of the pipe ash and the distribution of the adhesion of the pipe ash. The boiler wall-attached gas delivery scheme includes a rotational flow wind speed, a rotational flow wind direction, an in-pipe pressure and a cleaning duration;

[0077] For the rotational flow wind speed, a higher rotational flow wind speed is required in the area with a large thickness of ash and a strong adhesion to generate sufficient impact force to remove the ash. For example, when the pipe ash thickness of a certain area exceeds 3 mm and the ash adhesion is greater than 0.8 N, the rotational flow wind speed can be set to 20 m / s; while in the area with thin ash and weak adhesion, such as the ash thickness being less than 1 mm and the ash adhesion being less than 0.2 N, the rotational flow wind speed can be set to 10 m / s.

[0078] For the rotational flow wind direction, it is determined according to the layout of the pipe and the distribution of the ash. For the area with ash dead angle, the rotational flow wind direction is adjusted to directly act on the ash part. For example, the ash is serious at the bend of the pipe, and the rotational flow wind direction needs to be adjusted to be consistent with the tangent direction of the bend to enhance the scouring effect on the ash at the bend.

[0079] For the in-pipe pressure, in the area with serious ash, the in-pipe pressure is appropriately increased to increase the impact force of the gas. For example, when the pipe ash thickness exceeds 2 mm, the in-pipe pressure is set to 0.5 MPa; in the area with thin ash, the in-pipe pressure is reduced to 0.2 MPa to avoid unnecessary pressure damage to the pipe.

[0080] For the cleaning duration, the overall situation of the ash and the operation arrangement of the boiler need to be considered. For example, for the pipe with uniform ash distribution and moderate ash thickness, the cleaning duration can be set to 3 hours; if the ash distribution is uneven and the ash in some areas is serious, the cleaning duration is extended to 5 hours. At the same time, the cleaning duration should be avoided to be too long to affect the normal operation of the boiler, and the cleaning time needs to be reasonably arranged, for example, the ash cleaning can be performed during the low load operation period of the boiler.

[0081] By reasonably configuring the cyclone wind speed, the cyclone wind direction, the pipe pressure and the cleaning time, a more scientific and effective boiler wall-attached gas conveying scheme can be formulated, so as to improve the cleaning effect of the boiler pipeline, reduce the influence of the accumulated ash and slag on the operation of the boiler, and further improve the energy utilization efficiency and the operation stability of the boiler.

[0082] S30: processing the cyclone wind speed, the cyclone wind direction, the pipe pressure, the cleaning time, the pipeline ash thickness distribution and the pipeline ash adhesion force distribution by a residual ash thickness prediction model bound with the target boiler, and outputting a residual ash thickness distribution;

[0083] In the embodiments of the present application, a residual ash thickness prediction model is constructed, and the cyclone wind speed, the cyclone wind direction, the pipe pressure, the cleaning time, the pipeline ash thickness distribution and the pipeline ash adhesion force distribution are input to accurately predict the residual ash thickness distribution in the boiler pipeline after cleaning.

[0084] For example, in the input data, the pipeline ash thickness distribution of a certain area shows that the accumulated ash is relatively thick and the ash adhesion force is relatively strong, while the cyclone wind speed is set to a high value, the pipe pressure is relatively large, and the cleaning time is relatively long, and the model predicts that the residual ash thickness of the area after cleaning may be relatively thick; and for the area with relatively thin accumulated ash and weak adhesion force, if the cyclone wind speed is low, the pipe pressure is small and the cleaning time is short, the model will predict that the residual ash thickness of the area is relatively thin.

[0085] Specifically, step S30 in the method comprises:

[0086] Based on the grid distribution of the inner wall of the boiler pipeline, a graph neural network architecture is constructed, wherein the input nodes of the graph neural network architecture include grid input nodes, gas conveying input nodes and grid output nodes, wherein the grid input nodes and the grid output nodes are one-to-one corresponding to the grid distribution of the inner wall of the boiler pipeline, the gas conveying input nodes correspond to the pipeline air inlet position, the grid input nodes are used to receive the pipeline ash thickness distribution and the pipeline ash adhesion force distribution, the gas conveying input nodes are used to receive the cyclone wind speed, the cyclone wind direction, the pipe pressure and the cleaning time, and the grid output nodes are used to output the residual ash thickness distribution.

[0087] Based on the boiler model, record data of the cyclone wind speed, record data of the cyclone wind direction, record data of the pipe pressure, record data of the cleaning time, record information of the pipeline ash thickness distribution, record information of the pipeline ash adhesion force distribution and a label identifying the residual ash thickness distribution are collected, the graph neural network architecture is trained, and the residual ash thickness prediction model is generated and bound with the target boiler.

[0088] In the embodiments of the present application, based on the grid distribution of the inner wall of the boiler pipeline, the neural network has strong non-linear mapping capability, and the graph neural network architecture is constructed based on the neural network. Based on the effective grid input node, the gas delivery input node and the grid output node, the residual ash thickness prediction model is obtained through iterative training.

[0089] Exemplarily, the iterative training of the residual ash thickness prediction model can be realized through the following technical path:

[0090] Firstly, data preparation, the input nodes of the graph neural network architecture include grid input nodes, gas delivery input nodes and grid output nodes, wherein the grid input nodes and the grid output nodes are one-to-one corresponding to the grid distribution of the inner wall of the boiler pipeline, the gas delivery input nodes correspond to the pipeline air inlet position, the grid input nodes are used to receive the pipeline ash thickness distribution and the pipeline ash adhesion force distribution, the gas delivery input nodes are used to receive the cyclone wind speed, the cyclone wind direction, the pipeline pressure and the cleaning time, and the grid output nodes are used to output the residual ash thickness distribution.

[0091] Secondly, model building, the input layer has a node number equal to the dimension of the input features, such as 10 features including the cyclone wind speed record data, the cyclone wind direction record data, the pipeline pressure record data, the cleaning time record data, the pipeline ash thickness distribution record information, the pipeline ash adhesion force distribution record information and the label for detecting the residual ash thickness distribution, so that the input layer contains 10 nodes; 1-3 hidden layers are set, the number of nodes of each layer is adjusted through experiments, such as 64, 32, etc., and the ReLU activation function is selected; the number of nodes of the output layer is equal to the number of prediction targets, such as 1 node for predicting only the time consumption, and 2 nodes for simultaneously predicting the time consumption and the energy consumption, and the output layer generally does not use the activation function, and directly outputs continuous values.

[0092] Thirdly, model training, the residual ash thickness is predicted as the output, the corresponding prediction sample in the training set is used as the supervision label, the Adam optimizer and the mean square error (MSE) loss function are used to build the training framework, the batch size is set to 32, the total training rounds are set to 50, and the early stopping mechanism (patience=5) is introduced, when the validation set loss does not appear for 5 consecutive rounds, the training process is automatically terminated, and the trained residual ash thickness prediction model is obtained, so that the model overfitting is effectively avoided, and the model reaches the convergence state. The trained residual ash thickness prediction model is bound to the target boiler.

[0093] S40: processing the cyclone wind speed, the cyclone wind direction, the pipeline pressure and the cleaning time through the energy consumption prediction model bound to the target boiler, and outputting a cleaning energy consumption prediction value;

[0094] In the embodiments of the present application, an energy consumption prediction model is constructed, and the rotational flow speed, the rotational flow direction, the pressure in the pipe and the cleaning time are input to accurately predict the energy consumption in the boiler wall-attached gas conveying and cleaning process.

[0095] The neural network model can automatically learn the complex mapping relationship between the input variables and the output variables through the combination of multiple layers of neurons. Similarly, an energy consumption prediction model is constructed based on a neural network, and the rotational flow speed, the rotational flow direction, the pressure in the pipe and the cleaning time are processed to predict the cleaning energy consumption.

[0096] Specifically, step S40 in the method comprises:

[0097] With the boiler model as a constraint, the rotational flow speed, the rotational flow direction, the pressure in the pipe, the cleaning time and the label of the energy consumption value are loaded to train a plurality of energy consumption prediction models;

[0098] The output mean value of the plurality of energy consumption prediction base models is taken as an integrated output, and the plurality of energy consumption prediction base models are combined to obtain the energy consumption prediction model.

[0099] In the embodiments of the present application, a plurality of energy consumption prediction base models are trained based on a neural network with the boiler model as a constraint.

[0100] Exemplarily, the training of the energy consumption prediction base model can be realized through the following technical path:

[0101] First, data preparation, the input nodes of the energy consumption prediction model include the rotational flow speed, the rotational flow direction, the pressure in the pipe, the cleaning time and the label of the energy consumption value.

[0102] Second, model building, the number of nodes in the input layer is equal to the dimension of the input features, such as the rotational flow speed, the rotational flow direction, the pressure in the pipe, the cleaning time and the label of the energy consumption value, a total of 10 features, so the input layer contains 10 nodes; 1-3 hidden layers are set, the number of nodes in each layer is adjusted through experiments, such as 64, 32, etc., and the activation function is selected as ReLU; the number of nodes in the output layer is equal to the number of prediction targets, such as 1 node for predicting only the time consumption, and 2 nodes for simultaneously predicting the time consumption and the energy consumption, and the output layer generally does not use the activation function, and directly outputs continuous values.

[0103] Third, model training, the prediction energy consumption is taken as the output, the corresponding prediction samples in the training set are taken as the supervision label, the Adam optimizer and the mean square error (MSE) loss function are used to build the training framework, the batch size is set to 32, the total training rounds are set to 50, and the early stopping mechanism (patience=5) is introduced, when the validation set loss does not appear for 5 consecutive rounds, the training process is automatically terminated, and the trained energy consumption prediction model is obtained, thereby effectively avoiding model overfitting while ensuring that the model reaches a converged state.

[0104] When the energy consumption prediction base model training is completed, the output mean of a plurality of energy consumption prediction base models is an integrated output, a plurality of energy consumption prediction base models are combined to obtain an energy consumption prediction model. The energy consumption prediction model is bound with the target boiler, and the model will output the cleaning energy consumption prediction value. According to the prediction value, energy allocation and cost budget are prepared in advance to avoid waste of energy and unnecessary cost expenditure.

[0105] S50: When the residual ash thickness at any place of the residual ash thickness distribution is less than or equal to the residual ash thickness threshold value, and the cleaning energy consumption prediction value is less than or equal to the energy consumption threshold value, the boiler wall-attached gas conveying control is performed according to the boiler wall-attached gas conveying scheme, and the in-furnace pipeline cleaning is performed.

[0106] In the embodiments of the present application, the residual ash thickness threshold value and the energy consumption threshold value are set. The residual ash thickness threshold value is set according to the normal operation requirements and safety standards of the boiler. If the residual ash thickness is too high, it will affect the thermal efficiency and operation stability of the boiler. The energy consumption threshold value is determined based on the energy consumption index and cost control target of the boiler. Excessive energy consumption will increase the operation cost.

[0107] When the residual ash thickness at any place of the residual ash thickness distribution is less than or equal to the residual ash thickness threshold value, and the cleaning energy consumption prediction value is less than or equal to the energy consumption threshold value, it indicates that the current boiler wall-attached gas conveying scheme can effectively clean the in-furnace pipeline ash and control the energy consumption within a reasonable range. At this time, the boiler wall-attached gas conveying control is performed according to the scheme, the corresponding gas conveying equipment is started, and parameters such as cyclone wind speed, cyclone wind direction, pipe pressure and cleaning time are accurately adjusted to comprehensively clean the in-furnace pipeline.

[0108] Specifically, step S50 in the method comprises:

[0109] When the residual ash thickness at any place of the residual ash thickness distribution is greater than the residual ash thickness threshold value, or / and the cleaning energy consumption prediction value is greater than the energy consumption threshold value, a first weight is configured for the normalized parameter of the mean value of the residual ash thickness distribution, and a second weight is configured for the normalized parameter of the cleaning energy consumption prediction value, wherein the first weight ∈ [0.7, 1], the second weight ∈ [0, 0.3], and the sum of the first weight and the second weight is equal to 1;

[0110] Based on the first weight and the second weight, the residual ash thickness distribution mean normalized parameter and the cleaning energy consumption prediction value normalized parameter are added to obtain a scheme fitness;

[0111] The scheme fitness is stored in association with the boiler wall-attached gas conveying scheme, and is added to the analyzed gas conveying scheme group;

[0112] When the number of analyzed gas delivery schemes is greater than or equal to the threshold value of the number of schemes, and the convergent scheme is still not obtained, the particle swarm optimization is performed based on the analyzed gas delivery scheme group to obtain a target gas delivery scheme for the boiler wall-attached gas delivery control and the in-furnace pipeline cleaning.

[0113] In the embodiments of the present application, when one or more of the residual ash thickness in the residual ash thickness distribution is greater than the threshold value of the residual ash thickness, or / and the predicted cleaning energy consumption value is greater than the threshold value of the energy consumption, it indicates that the current boiler wall-attached gas delivery scheme may have deficiencies and needs to be further adjusted.

[0114] The mean value normalization parameter of the residual ash thickness distribution reflects the average thickness of the residual ash after cleaning. The smaller the value, the thinner the residual ash thickness, and the better the cleaning effect. The predicted cleaning energy consumption value normalization parameter reflects the energy consumption in the cleaning process. The smaller the value, the lower the energy consumption, and the better the economy.

[0115] Further, the first weight is configured for the mean value normalization parameter of the residual ash thickness distribution, and the second weight is configured for the predicted cleaning energy consumption value normalization parameter. The first weight is in the range of [0.7, 1], the second weight is in the range of [0, 0.3], and the sum of the two is equal to 1. For example, the first weight is configured for the mean value normalization parameter of the residual ash thickness distribution, and the value is 0.7; the second weight is configured for the predicted cleaning energy consumption value normalization parameter, and the value is 0.3.

[0116] Based on the first weight and the second weight, the mean value normalization parameter of the residual ash thickness distribution and the predicted cleaning energy consumption value normalization parameter are added to obtain the scheme fitness. The higher the value of the scheme fitness, the better the comprehensive performance of the scheme in cleaning the ash and controlling the energy consumption.

[0117] For example, assuming that for the cleaning of the ash in the pipeline of a certain boiler, scheme A and scheme B are proposed, the mean value normalization parameter of the residual ash thickness distribution of scheme A is 0.2, and the predicted cleaning energy consumption value normalization parameter is 0.6; the mean value normalization parameter of the residual ash thickness distribution of scheme B is 0.4, and the predicted cleaning energy consumption value normalization parameter is 0.2. After weighted calculation, the scheme fitness of scheme A is 0.32, and the scheme fitness of scheme B is 0.34. Comparison shows that A is a better scheme.

[0118] The scheme fitness is stored in association with the corresponding boiler wall-attached gas delivery scheme and added to the analyzed gas delivery scheme group. The analyzed gas delivery scheme group is used to record and manage all evaluated schemes, facilitating subsequent analysis and comparison.

[0119] When the number of analyzed gas delivery scheme group is greater than or equal to the number of schemes threshold, if the convergence scheme is still not obtained, that is, no scheme is found which can make the residual ash thickness at any place of the residual ash thickness distribution less than or equal to the residual ash thickness threshold, and can make the cleaning energy consumption prediction value less than or equal to the energy consumption threshold, at this time, particle swarm optimization needs to be performed based on the analyzed gas delivery scheme group.

[0120] Particle swarm optimization is an intelligent optimization algorithm, which searches for the optimal solution in the solution space by simulating the group behavior of bird swarm or fish swarm. In this application, the particle swarm optimization algorithm adjusts the position and speed of the particles according to the scheme information in the analyzed gas delivery scheme group, and finds the target gas delivery scheme. The target gas delivery scheme obtained by optimization is used for boiler wall gas delivery control, the corresponding gas delivery equipment is opened, and parameters such as cyclone air speed, cyclone air direction, pipe pressure and cleaning time are accurately adjusted to clean the pipes in the furnace comprehensively, thereby improving the cleaning effect of the boiler pipes, reducing the influence of ash deposition and slagging on the operation of the boiler, and improving the energy utilization efficiency and operation stability of the boiler.

[0121] Exemplarily, the core of particle swarm optimization is to find the optimal solution which minimizes the target function, that is, the scheme fitness, in the parameter space by simulating the cooperative search behavior of the "particle swarm". The normalized residual ash thickness parameter and the normalized cleaning energy consumption parameter are used as the optimization variables of the two dimensions of particle swarm optimization, and real number coding is adopted. Each particle corresponds to a set of parameter combinations, representing a potential ash deposition cleaning scheme. Taking "population size N=20, maximum iteration number T=50" as an example, 20 initial positions of particles are randomly generated, the initial fitness value of each particle is calculated, the A and B schemes are used as two particles in the initial population, 18 randomly generated particles are added, and after 50 iterations, the optimal position is converged, or 3-5 independent particle swarm optimizations are performed. If the optimal fitness value difference of multiple optimization results is less than 5%, it is considered that the result is stable and reliable.

[0122] In summary, compared with the prior art, the boiler wall-attached gas conveying method of the present application accurately predicts the residual ash thickness distribution in the boiler pipeline after cleaning and the energy consumption during the cleaning process by constructing a residual ash thickness prediction model and an energy consumption prediction model. Using a graph neural network architecture, factors such as cyclone wind speed, cyclone wind direction, pipeline pressure, cleaning time, pipeline ash thickness distribution, and pipeline ash adhesion force distribution are fully considered, making the prediction results more accurate and reliable. Through iterative training, a converged residual ash thickness prediction model is obtained, providing solid data support for subsequent cleaning scheme evaluation. With the boiler model as a constraint, several energy consumption prediction base models are trained, and the output mean is taken as the integrated output to obtain an energy consumption prediction model. This model can accurately predict the energy consumption during the boiler wall-attached gas conveying cleaning process, helping to make energy allocation and cost budget in advance, and avoiding waste of energy and unnecessary cost expenditure.

[0123] In addition, the present application also sets residual ash thickness threshold and energy consumption threshold. When the residual ash thickness distribution and the cleaning energy consumption prediction value meet the threshold requirements, the cleaning can be directly performed according to the boiler wall-attached gas conveying scheme; if the requirements are not met, the scheme fitness is calculated and associated with storage, and if a converged scheme is still not obtained, particle swarm optimization is performed to further optimize the gas conveying scheme.

[0124] Embodiment two, as shown in Figure 2 Based on the same inventive concept of the boiler wall-attached gas conveying method for reducing ash deposition and slagging provided in embodiment one, the present application embodiment also provides a boiler wall-attached gas conveying system for reducing ash deposition and slagging, comprising:

[0125] A sample collection module 11 is configured to collect a pipeline ash detection sample set with the boiler operating parameters, boiler model and boiler airflow monitoring parameters of a target boiler as constraints, and to count the pipeline ash thickness distribution and pipeline ash adhesion force distribution.

[0126] A scheme configuration module 12 is configured to configure a boiler wall-attached gas conveying scheme, wherein the boiler wall-attached gas conveying scheme includes cyclone wind speed, cyclone wind direction, pipeline pressure and cleaning time.

[0127] An ash thickness prediction module 13 is configured to process the cyclone wind speed, the cyclone wind direction, the pipeline pressure, the cleaning time, the pipeline ash thickness distribution and the pipeline ash adhesion force distribution through a residual ash thickness prediction model bound to a target boiler, and to output a residual ash thickness distribution.

[0128] An energy consumption output module 14 is configured to process the cyclone wind speed, the cyclone wind direction, the pipeline pressure, and the cleaning time through an energy consumption prediction model bound to a target boiler, and to output a cleaning energy consumption prediction value.

[0129] The scheme execution module 15 is configured to execute in-situ tube cleaning according to the boiler wall-attached gas conveying scheme when the residual ash thickness at any position of the residual ash thickness distribution is less than or equal to a residual ash thickness threshold value and the cleaning energy consumption prediction value is less than or equal to an energy consumption threshold value.

[0130] The information collection module 11 is configured to:

[0131] The information collection module 11 is configured to collect a to-be-analyzed in-situ tube ash detection sample under the constraint of the boiler model, where the to-be-analyzed in-situ tube ash detection sample has a label indicating a boiler operating parameter and a label indicating a boiler airflow monitoring parameter.

[0132] The information collection module 11 is configured to consider the boiler operating parameters consistent when the boiler operating parameters and any attribute boiler operating parameter of the label indicating the boiler operating parameter have a deviation less than or equal to a corresponding attribute boiler operating parameter deviation threshold value.

[0133] The information collection module 11 is configured to consider the boiler airflow monitoring parameters consistent when the boiler airflow monitoring parameters and any attribute boiler airflow monitoring parameter of the label indicating the boiler airflow monitoring parameter have a deviation less than or equal to a corresponding attribute boiler airflow monitoring parameter deviation threshold value.

[0134] The information collection module 11 is configured to add the to-be-analyzed in-situ tube ash detection sample to the in-situ tube ash detection sample set when the boiler operating parameters are consistent and the boiler airflow monitoring parameters are consistent.

[0135] The information collection module 11 is configured to collect an in-situ tube ash detection sample set, and to count a tube ash thickness distribution and a tube ash adhesion force distribution, including:

[0136] The information collection module 11 is configured to perform grid segmentation on the inner wall of the target boiler tube by a preset side length grid to obtain a boiler tube inner wall grid distribution.

[0137] The information collection module 11 is configured to traverse the in-situ tube ash detection sample set based on the boiler tube inner wall grid distribution to obtain a first tube grid distribution ash state to a Qth tube grid distribution ash state, where Q represents a total number of samples and Q≥30.

[0138] The information collection module 11 is configured to perform same-grid state integration on the first tube grid distribution ash state to the Qth tube grid distribution ash state to obtain a first grid ash state set to an Mth grid ash state set, where M represents a total number of grids.

[0139] The information collection module 11 is configured to traverse the first grid ash state set to the Mth grid ash state set to perform a centroid ash state analysis to obtain the tube ash thickness distribution and the tube ash adhesion force distribution.

[0140] The ash thickness prediction model 13 is configured to:

[0141] extracting a plurality of soot states from the first grid soot state set, wherein any one of the plurality of soot states comprises a soot thickness and a soot adhesion;

[0142] performing distribution on the plurality of soot states with the soot thickness normalized value as the first coordinate and the soot adhesion normalized value as the second coordinate to obtain a plurality of soot state distribution coordinates;

[0143] based on the plurality of soot state distribution coordinates, performing LOF outlier factor minimum value extraction to obtain a centroid soot state distribution coordinate;

[0144] based on the centroid soot state distribution coordinate, extracting a first grid pipeline soot thickness and a first grid pipeline soot adhesion;

[0145] When the Mth grid pipeline soot thickness and the Mth grid pipeline adhesion are obtained, the first grid pipeline soot thickness is integrated until the Mth grid pipeline soot thickness to obtain the pipeline soot thickness distribution, and the first grid pipeline soot adhesion is integrated until the Mth grid pipeline adhesion to obtain the pipeline soot adhesion distribution.

[0146] Further, the "processing the cyclone wind speed, the cyclone wind direction, the pipeline pressure, the cleaning time, the pipeline soot thickness distribution and the pipeline soot adhesion distribution through the residual soot thickness prediction model bound with the target boiler, and outputting the residual soot thickness distribution" comprises:

[0147] based on the boiler pipeline inner wall grid distribution, constructing a graph neural network architecture, wherein the input nodes of the graph neural network architecture include grid input nodes, gas delivery input nodes and grid output nodes, wherein the grid input nodes and the grid output nodes are one-to-one corresponding to the boiler pipeline inner wall grid distribution, the gas delivery input nodes correspond to the pipeline air inlet position, the grid input nodes are used to receive the pipeline soot thickness distribution and the pipeline soot adhesion distribution, the gas delivery input nodes are used to receive the cyclone wind speed, the cyclone wind direction, the pipeline pressure and the cleaning time, and the grid output nodes are used to output the residual soot thickness distribution;

[0148] based on the boiler model, collecting cyclone wind speed record data, cyclone wind direction record data, pipeline pressure record data, cleaning time record data, pipeline soot thickness distribution record information, pipeline soot adhesion distribution record information and labels identifying residual soot thickness distribution, training the graph neural network architecture to generate the residual soot thickness prediction model, and binding the target boiler.

[0149] The energy consumption output module 14 is specifically configured to:

[0150] Constraining by a boiler model, loading a label of a cyclone air speed, a cyclone air direction, a pipe pressure, a cleaning time length and an energy consumption value, training a plurality of energy consumption prediction base models;

[0151] Combining the plurality of energy consumption prediction base models to obtain the energy consumption prediction model.

[0152] The scheme execution module 15 is specifically configured to:

[0153] When the residual ash thickness at any place of the residual ash thickness distribution is greater than a residual ash thickness threshold value, or / and the cleaning energy consumption prediction value is greater than an energy consumption threshold value, a first weight is configured for a normalized parameter of a mean value of the residual ash thickness distribution, and a second weight is configured for a normalized parameter of the cleaning energy consumption prediction value, wherein the first weight ∈ [0.7, 1], the second weight ∈ [0, 0.3], and the sum of the first weight and the second weight is equal to 1;

[0154] Based on the first weight and the second weight, the residual ash thickness distribution mean value normalized parameter and the cleaning energy consumption prediction value normalized parameter are added to obtain a scheme fitness;

[0155] The scheme fitness is stored in association with the boiler wall sticking gas conveying scheme, and is added to the analyzed gas conveying scheme group;

[0156] When the number of schemes in the analyzed gas conveying scheme group is greater than or equal to a scheme number threshold value, and a convergent scheme has not been obtained, particle swarm optimization is performed based on the analyzed gas conveying scheme group to obtain a target gas conveying scheme for boiler wall sticking gas conveying control and in-pipe cleaning.

[0157] In summary, the embodiments of the present application have at least the following technical effects:

[0158] The embodiment of the present application provides a boiler wall-attached gas conveying method and system for reducing ash deposition and slagging, comprehensively considers parameters of boiler operation, performs statistics and analysis on pipeline ash deposition, simultaneously uses a prediction model to predict residual ash thickness and cleaning energy consumption, can effectively control energy consumption while ensuring cleaning effect. By setting a threshold, when the residual ash thickness and energy consumption meet the requirements, the boiler wall-attached gas conveying control is performed, and efficient and energy-saving pipeline cleaning in the furnace is realized; when the threshold condition is not met, the fitness of the configuration weight calculation scheme is calculated, and the particle swarm optimization mode is combined, so that the gas conveying scheme can be continuously optimized, and finally a more suitable target gas conveying scheme is found, and the cleaning effect and energy utilization efficiency are further improved. Through the above technical scheme, the thickness and adhesion force distribution of the target boiler pipeline ash deposition are collected first, and then the boiler wall-attached gas conveying scheme is configured, and then the residual ash thickness distribution and cleaning energy consumption prediction value are output through the residual ash thickness prediction model and the energy consumption prediction model respectively. The problem that the residual coal ash of the surrounding pipeline cannot be cleaned in the prior art is solved, the occurrence of pipeline corrosion, perforation and the like is reduced, the loss caused by shutdown and maintenance due to pipeline water leakage is avoided, the service life of the boiler is prolonged, the risk of safety accidents is reduced, and the stable operation of the boiler in industrial production is ensured.

[0159] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. Moreover, the above describes specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0160] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0161] The present application and the drawings are only exemplary descriptions of the present application, and are considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalents, the present application intends to include these modifications and changes.

Claims

1. A method for reducing wall deposition in a furnace by means of a gas delivery against the wall, characterized in that, The application is applied to a wall-attached wind control device, comprising: With the boiler operation parameters, the boiler model and the boiler airflow monitoring parameters of the target boiler as constraints, a pipe ash deposition detection sample set is collected, and the pipe ash thickness distribution and the pipe ash adhesion force distribution are counted; A boiler wall-attached gas delivery scheme is configured, wherein the boiler wall-attached gas delivery scheme includes a cyclone wind speed, a cyclone wind direction, a pipe internal pressure and a cleaning duration; Through a residual ash thickness prediction model bound with the target boiler, the cyclone wind speed, the cyclone wind direction, the pipe internal pressure, the cleaning duration, the pipe ash thickness distribution and the pipe ash adhesion force distribution are processed, and a residual ash thickness distribution is output; Through an energy consumption prediction model bound with the target boiler, the cyclone wind speed, the cyclone wind direction, the pipe internal pressure and the cleaning duration are processed, and a cleaning energy consumption prediction value is output; When the residual ash thickness of any place of the residual ash thickness distribution is less than or equal to a residual ash thickness threshold value, and the cleaning energy consumption prediction value is less than or equal to an energy consumption threshold value, the boiler wall-attached gas delivery control is performed according to the boiler wall-attached gas delivery scheme, and the in-furnace pipe cleaning is executed; Through a residual ash thickness prediction model bound with the target boiler, the cyclone wind speed, the cyclone wind direction, the pipe internal pressure, the cleaning duration, the pipe ash thickness distribution and the pipe ash adhesion force distribution are processed, and a residual ash thickness distribution is output, comprising: Based on the boiler pipe inner wall grid distribution, a graph neural network architecture is constructed, wherein the input nodes of the graph neural network architecture include grid input nodes, gas delivery input nodes and grid output nodes, wherein the grid input nodes and the grid output nodes are one-to-one corresponding to the boiler pipe inner wall grid distribution, the gas delivery input nodes correspond to the pipe air inlet position, the grid input nodes are used to receive the pipe ash thickness distribution and the pipe ash adhesion force distribution, the gas delivery input nodes are used to receive the cyclone wind speed, the cyclone wind direction, the pipe internal pressure and the cleaning duration, and the grid output nodes are used to output the residual ash thickness distribution; Based on the boiler model, the cyclone wind speed record data, the cyclone wind direction record data, the pipe internal pressure record data, the cleaning duration record data, the pipe ash thickness distribution record information, the pipe ash adhesion force distribution record information and the label identifying the residual ash thickness distribution are collected, the graph neural network architecture is trained, and the residual ash thickness prediction model is generated and bound with the target boiler.

2. The method of claim 1, wherein, With the boiler operation parameters, the boiler model and the boiler airflow monitoring parameters of the target boiler as constraints, a pipe ash deposition detection sample set is collected, and the pipe ash thickness distribution and the pipe ash adhesion force distribution are counted, comprising: With the boiler model as a constraint, a pipe ash deposition detection sample to be analyzed is collected, wherein the pipe ash deposition detection sample to be analyzed has a label identifying the boiler operation parameters and a label identifying the boiler airflow monitoring parameters; When the boiler operation parameters and any attribute boiler operation parameter of the label identifying the boiler operation parameters have a deviation less than or equal to a corresponding attribute boiler operation parameter deviation threshold value, the boiler operation parameters are considered to be consistent; When the boiler flow monitoring parameter and any attribute boiler flow monitoring parameter of the tag identifying the boiler flow monitoring parameter are all less than or equal to the corresponding attribute boiler flow monitoring parameter deviation threshold, the boiler flow monitoring parameters are considered to be consistent; When the boiler operation parameters are consistent and the boiler flow monitoring parameters are consistent, the to-be-analyzed pipeline deposition detection sample is added to the pipeline deposition detection sample set.

3. The method of claim 1, wherein, Collecting a pipeline deposition detection sample set, and statistically analyzing a pipeline deposition thickness distribution and a pipeline deposition adhesion force distribution, comprising: Grid segmentation is performed on the inner wall of the target boiler pipeline through a preset side length grid to obtain a boiler pipeline inner wall grid distribution; Based on the boiler pipeline inner wall grid distribution, the pipeline deposition detection sample set is traversed to obtain a first pipeline grid distribution deposition state to a Qth pipeline grid distribution deposition state, wherein Q represents a total number of samples, and Q≥30; The first pipeline grid distribution deposition state to the Qth pipeline grid distribution deposition state is integrated to obtain a first grid deposition state set to an Mth grid deposition state set, wherein M represents a total number of grids; The first grid deposition state set to the Mth grid deposition state set is traversed to perform centroid deposition state analysis to obtain the pipeline deposition thickness distribution and the pipeline deposition adhesion force distribution.

4. The method of claim 3, wherein, The first grid deposition state set to the Mth grid deposition state set is traversed to perform centroid deposition state analysis to obtain the pipeline deposition thickness distribution and the pipeline deposition adhesion force distribution, comprising: A plurality of deposition states are extracted from the first grid deposition state set, wherein any one of the plurality of deposition states comprises a deposition thickness and a deposition adhesion force; The plurality of deposition states are distributed to obtain a plurality of deposition state distribution coordinates, with a deposition thickness normalized value as a first-dimensional coordinate and a deposition adhesion force normalized value as a second-dimensional coordinate; Based on the plurality of deposition state distribution coordinates, a LOF outlier factor minimum value is extracted to obtain a centroid deposition state distribution coordinate; Based on the centroid deposition state distribution coordinate, a first grid pipeline deposition thickness and a first grid pipeline deposition adhesion force are extracted; When the Mth grid pipeline deposition thickness and the Mth grid pipeline adhesion force are obtained, the first grid pipeline deposition thickness to the Mth grid pipeline deposition thickness is integrated to obtain the pipeline deposition thickness distribution, and the first grid pipeline deposition adhesion force to the Mth grid pipeline adhesion force is integrated to obtain the pipeline deposition adhesion force distribution.

5. The method of claim 1, wherein, The swirling flow speed, the swirling flow direction, the pipeline pressure, and the cleaning time length are processed by an energy consumption prediction model bound to the target boiler to output a cleaning energy consumption prediction value, comprising: A plurality of energy consumption prediction base models are trained by loading the swirling flow speed, the swirling flow direction, the pipeline pressure, the cleaning time length, and a tag identifying an energy consumption value, with a boiler model as a constraint; The plurality of energy consumption prediction base models are combined to obtain the energy consumption prediction model, with an output mean value of the plurality of energy consumption prediction base models as an integrated output.

6. The method of claim 1, wherein, Further comprising: When the residual ash thickness at any position of the residual ash thickness distribution is greater than a residual ash thickness threshold, or / and the cleaning energy consumption prediction value is greater than an energy consumption threshold, a first weight is configured for a normalized parameter of the mean value of the residual ash thickness distribution, and a second weight is configured for a normalized parameter of the cleaning energy consumption prediction value, wherein the first weight ∈ [0.7, 1], the second weight ∈ [0, 0.3], and the sum of the first weight and the second weight is equal to 1; Based on the first weight and the second weight, the residual ash thickness distribution mean value normalized parameter and the cleaning energy consumption prediction value normalized parameter are added to obtain a scheme fitness; The scheme fitness is stored in association with the boiler wall-attached gas delivery scheme, and is added to the analyzed gas delivery scheme group; When the number of schemes in the analyzed gas delivery scheme group is greater than or equal to a scheme number threshold, and a convergent scheme has not been obtained, particle swarm optimization is performed based on the analyzed gas delivery scheme group to obtain a target gas delivery scheme for boiler wall-attached gas delivery control and in-furnace pipeline cleaning.

7. A furnace wall-attached gas delivery system for reducing deposition and slagging, characterized by, A method for performing any one of claims 1-6, comprising: A sample collection module for collecting a pipeline ash deposition detection sample set with the target boiler operation parameters, boiler model, and boiler airflow monitoring parameters as constraints, and statistically analyzing the pipeline ash deposition thickness distribution and the pipeline ash deposition adhesion force distribution; A scheme configuration module for configuring a boiler wall-attached gas delivery scheme, wherein the boiler wall-attached gas delivery scheme includes a rotational flow wind speed, a rotational flow wind direction, a pipeline internal pressure, and a cleaning duration; An ash thickness prediction module for processing the rotational flow wind speed, the rotational flow wind direction, the pipeline internal pressure, the cleaning duration, the pipeline ash deposition thickness distribution, and the pipeline ash deposition adhesion force distribution through a residual ash thickness prediction model bound to the target boiler, and outputting a residual ash thickness distribution; An energy consumption output module for processing the rotational flow wind speed, the rotational flow wind direction, the pipeline internal pressure, and the cleaning duration through an energy consumption prediction model bound to the target boiler, and outputting a cleaning energy consumption prediction value; A scheme execution module for performing boiler wall-attached gas delivery control according to the boiler wall-attached gas delivery scheme when the residual ash thickness at any position of the residual ash thickness distribution is less than or equal to a residual ash thickness threshold, and the cleaning energy consumption prediction value is less than or equal to an energy consumption threshold, and performing in-furnace pipeline cleaning.

Images