Abrasion prediction optimization method for boiler water wall system

Abstract

The invention relates to the technical field of coal-fired boiler application, and particularly provides a boiler water-cooled wall system wear prediction optimization method, which comprises the following steps: carrying out gridding partitioning on a water-cooled wall system of a boiler to obtain a plurality of detection regions, and obtaining wear historical data corresponding to the plurality of detection regions respectively; constructing a wear prediction model based on the wear historical data, wherein the wear prediction model is used for representing a corresponding relationship between the wear historical data and monitoring operation parameters of a plurality of historical detection times in the wear historical data; based on the monitoring operation parameters, establishing a numerical simulation model of the water-cooled wall system, and generating wear evaluation data corresponding to the target wear area; and predicting the current wall thickness data of the target wear area by adopting the wear prediction model, and optimizing the monitoring operation parameters under the condition that the difference value between the wear evaluation data and the current wall thickness data is greater than the preset threshold value, so that the predicted wear can be continuously optimized under the condition of considering the monitoring operation parameters in the hearth, and the prediction accuracy is improved. Therefore, the wear prediction accuracy is improved.

Description

Technical Field

[0001] This application relates to the technical field of coal-fired boiler applications, and particularly to a method for predicting and optimizing the wear of a boiler water wall system. Background Art

[0002] The water wall system of a CFB boiler is a key component of the CFB boiler. Its main functions are to absorb the high-temperature radiant heat in the furnace, turn water into a steam-water mixture to generate steam, protect the furnace wall, reduce high-temperature damage, extend the service life of the boiler, and maintain the long-term stable operation of large power plants. However, due to the circulating flow of materials in the circulating fluidized bed boiler, the water wall system needs to withstand long-term material erosion and wear. Among them, in some areas such as the burner area and the area near the soot blower, due to the strong scouring effect of the air flow, or large fluctuations in temperature, the scouring intensity of materials, etc., the wear is aggravated, forming severely worn areas. The wear of the water wall system will cause damage to its sealing performance and leakage, which will affect the steam quality, easily lead to safety accidents, and also weaken the heat absorption capacity of the water wall tubes, reduce the thermal efficiency of the boiler, increase the operation cost. In particular, severe wear may damage the structural integrity of the water wall, shorten the service life of the boiler, and even may cause overall damage to the boiler, requiring large-scale repairs or replacements, resulting in huge economic losses.

[0003] For the calculation of the wear stress of the water wall, the pipe stress calculation process established based on the boiler operation principle can obtain relatively accurate judgment results. However, in actual applications, due to the relatively complex application scenarios and the difficulty in obtaining some data, in the current anti-wear and explosion-proof inspections of a large number of water walls, it is usually necessary to rely on "touching and looking" during shutdown or through the measurement of simple instruments to carry out the stages of appearance inspection and preliminary automated detection (such as patent CN119063667A).

[0004] The patent application with the publication number CN116362039A discloses a system for analyzing and predicting the deterioration of water wall tubes based on maintenance history records. It collects the maintenance history records into the established maintenance history record database, processes them to form the required data, then analyzes the processed data, establishes a corresponding mathematical model, calculates the deterioration probability, and then performs a weighted calculation on the deterioration probability. Combining time and status information, it obtains the prediction information on the operation status and time of the water wall on the boiler side, and displays the results to the operators through the water wall tube deterioration prediction analysis curve graph.

[0005] For the obtained maintenance history records, the prediction method of the above system can only be limited to the detection data of the water wall to predict the deterioration trend. Due to ignoring the operating environment conditions inside the furnace, it will affect the accuracy of the prediction results of the water wall deterioration conditions, resulting in a certain error between the prediction results and actual applications. Summary of the Invention

[0006] In view of the above problems, the present application provides a method for predicting and optimizing the wear of a boiler water wall system. By obtaining the wear history data corresponding to each of the multiple detection areas, a wear prediction model is constructed based on the wear history data to predict the current wall thickness data of the target wear area; and when the difference between the current wall thickness data and the wear evaluation data corresponding to the target wear area is greater than a preset threshold, the monitored operating parameters are optimized, so that the predicted wear can be continuously optimized considering the monitored operating parameters in the furnace, and the accuracy of wear prediction is improved.

[0007] To achieve the object of the present application, the following technical solutions are provided in the present application:

[0008] In a first aspect, the present application provides a method for predicting and optimizing the wear of a boiler water wall system, including:

[0009] The water wall system of the boiler is divided into a grid to obtain multiple detection areas, and the wear history data corresponding to each of the multiple detection areas is obtained; the wear history data includes at least the first wear rate of each detection area between the two adjacent historical detection times.

[0010] A wear prediction model is constructed based on the wear history data, and the wear prediction model is used to represent the corresponding relationship between the wear history data and the monitored operating parameters at multiple historical detection times in the wear history data.

[0011] Based on the monitored operating parameters, a numerical simulation model of the water wall system is established to generate wear evaluation data corresponding to the target wear area; wherein, the target wear area is at least one detection area determined based on the first wear rate of each detection area.

[0012] The wear prediction model is used to predict the current wall thickness data of the target wear area, and when the difference between the wear evaluation data and the current wall thickness data is greater than a preset threshold, the monitored operating parameters are optimized.

[0013] In a possible implementation, constructing the wear prediction model based on the wear history data includes: preprocessing the first wear rate of each detection area to generate a wear database; performing feature analysis on the wear database through regression analysis, histogram, and spearman correlation analysis methods to obtain wear feature data; splitting the wear feature data into a training set and a test set by means of stratified sampling, where the ratio of the training set to the test set is 4:1; constructing an initial wear prediction model based on the training set and validating the initial wear prediction model based on the test set; and determining the initial wear prediction model as the wear prediction model when the verification result is qualified.

[0014] In a possible implementation, establishing the numerical simulation model of the water-cooled wall system based on the monitored operating parameters and generating the wear assessment data corresponding to the target wear area includes: establishing a 3D model of the boiler based on the boiler drawings and importing the 3D model of the boiler into the Barracuda software for mesh generation and boundary condition setting, where the boundary conditions are determined based on the monitored operating parameters, and the monitored operating parameters include fuel quantity, furnace temperature, furnace negative pressure, and air distribution condition; simulating the fluid-particle phase entering the boiler by the Barracuda software based on the Euler-Lagrange framework to generate the numerical simulation model; performing water-cooled wall wear assessment for the target wear area in the numerical simulation model to obtain the wear assessment data for the target wear area; where at least one detection area determined based on the first wear rate of each detection area refers to: determining any detection area with the first wear rate greater than the preset wear threshold in the furnace water-cooled wall and the extended wall water-cooled wall as the target wear area, and the target wear area is one or multiple adjacent detection areas.

[0015] In a possible implementation, establishing the 3D model of the boiler based on the boiler drawings includes: determining the component list corresponding to the 3D model; performing digital modeling and 3D rendering of the components based on the component list to form a digital boiler 3D model of the components and constructing a basic component library; where a data model of the boiler is established based on the boiler model and the specification attributes of the internally configured water-cooled wall, and the model data is cached based on Redis, and the feature ID information of the digital boiler 3D model is used as the Key key information to associatively map the attributes of the digital boiler 3D model; importing the digital boiler 3D model into the visualization platform and setting the parameters and display methods to be accessed.

[0016] In a possible implementation, when the difference between the wear evaluation data and the current wall thickness data is greater than a preset threshold, optimizing the monitored operating parameters includes: optimizing at least one of the monitored operating parameters based on a genetic algorithm.

[0017] In a possible implementation, the boiler water wall system includes a furnace water wall and an extended wall water wall. Dividing the boiler water wall system into a grid to obtain multiple detection areas includes: establishing a longitudinal line based on the axis where each water wall tube in the furnace water wall and the extended wall water wall is located; establishing a reference horizontal line of the boiler water wall system at preset intervals from the furnace bottom as the transverse line of the multiple grid areas; determining the multiple detection areas based on the intersection points of the longitudinal line and the transverse line; where each intersection point corresponds to a detection area.

[0018] In a possible implementation, the wear history data includes the wall thickness data of the detection area at each historical detection time; the method further includes: obtaining at least three water wall thicknesses of the water wall tubes in each detection area; for each historical detection time, comparing the magnitudes of the at least three water wall thicknesses to obtain the minimum wall thickness of the detection area, and using the minimum wall thickness as the wall thickness data corresponding to the current detection time; summarizing the wall thickness data of each historical detection time to obtain the wall thickness data corresponding to the multiple detection areas respectively.

[0019] In a possible implementation, after obtaining the wear history data corresponding to the multiple detection areas respectively, the method further includes: establishing a scaled model sand table of the boiler based on the boiler 3D model, and synchronizing the wear history data of the water wall system in real time in the scaled model sand table to display the wear data of the water wall system.

[0020] In a possible implementation, the method further includes using the wear prediction model to predict the current wall thickness data of the target wear area at regular intervals, and when the current wall thickness data reaches a first warning threshold, warning the current wall thickness data through the boiler 3D model and the scaled model sand table.

[0021] In a possible implementation, the wear history data further includes a second wear rate for each detection area, where the second wear rate is the ratio of the difference in the water wall tube thickness between the start time of use of the water wall tube and the most recent historical detection time to the operating duration of the water wall tube; the method further includes: calculating the second wear rate for each detection area; and when the second wear rate reaches a second warning threshold, issuing a warning through the boiler 3D model and the scaled model sand table.

[0022] The boiler water-cooled wall system wear prediction and optimization method provided by this application divides the water-cooled wall system of the boiler into grid partitions to obtain multiple detection areas, and acquires the wear history data corresponding to each of the multiple detection areas; constructs a wear prediction model based on the wear history data, and the wear prediction model is used to characterize the corresponding relationship between the wear history data and the monitored operating parameters at multiple historical detection times in the wear history data; establishes a numerical simulation model of the water-cooled wall system based on the monitored operating parameters, and generates wear evaluation data corresponding to the target wear area; uses the wear prediction model to predict the current wall thickness data of the target wear area, and when the difference between the wear evaluation data and the current wall thickness data is greater than a preset threshold, optimizes the monitored operating parameters, so that the predicted wear can be continuously optimized considering the monitored operating parameters in the furnace, improving the prediction accuracy, and at the same time providing optimization guidance for the boiler site. Description of the Drawings

[0023] The drawings are used to provide further understanding of this application, and form a part of the specification. Together with the embodiments of this application, they are used to explain this application and do not constitute a limitation to this application;

[0024] Figure 1 It is an optional flowchart of the boiler water-cooled wall system wear prediction and optimization method provided by the embodiment of this application;

[0025] Figure 2 It is a curve relationship diagram between the collision angle coefficient and the collision angle for wear amount calculation provided by the embodiment of this application;

[0026] Figure 3 It is an optional flowchart of the boiler water-cooled wall system wear prediction and optimization method provided by the embodiment of this application;

[0027] Figure 4 It is a functional structure diagram of the digital boiler 3D model in the application scenario provided by the embodiment of this application;

[0028] Figure 5 It is a structure diagram of the equal-proportion model sand table in the application scenario provided by the embodiment of this application;

[0029] Figure 6 It is a warning diagram of the digital boiler 3D model in the application scenario provided by the embodiment of this application;

[0030] Figure 7 It is a structure diagram of the boiler water-cooled wall system wear prediction and optimization device provided by the embodiment of this application. Detailed Embodiments

[0031] To make the objectives, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below with reference to the accompanying drawings in this application. Obviously, the described embodiments are some but not all of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without making creative efforts fall within the scope of protection of this application.

[0032] The terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features; in the description of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0033] During the existing boiler shutdown detection process, the wall thickness of the water-cooled wall tubes is usually monitored by setting monitoring points. Due to the requirements of detection accuracy, data needs to be detected for the water-cooled wall tubes every 500 mm. Thus, the number of detection data points for the water-cooled wall tubes in the furnace of a single boiler will exceed 50,000. Obtaining the wear detection data is time-consuming and requires a large amount of manual or equipment and instrument workload. For the obtained wear data, it is also difficult to completely, intuitively and accurately judge the concentrated wear area of the water-cooled wall, analyze the wear cause of the water-cooled wall tubes, and it is difficult to guide the operation adjustment of the boiler based on the detected wear data, such as reducing the gas-solid two-phase wear of the water-cooled wall while ensuring the normal combustion condition of the boiler by reasonably controlling the in-furnace operation air volume.

[0034] The present invention proposes the following technical solutions and corresponding embodiments.

[0035] Embodiment 1

[0036] The following Figures 1 to 7 describes the technical solutions of the present invention in conjunction with the

[0037] Figure 1 shown embodiment: Figure 1 As shown in the schematic flow chart of the wear prediction and optimization method for the boiler water-cooled wall system according to the embodiment of this application, the wear prediction and optimization method for the boiler water-cooled wall system in the embodiment of this application includes the following steps S101 to S104:

[0038] S101. Divide the water-cooled wall system of the boiler into grid-based zones to obtain a plurality of detection zones, and acquire the wear history data respectively corresponding to the plurality of detection zones; the wear history data includes at least the first wear rate of each detection zone between the two adjacent previous historical detection times.

[0039] In the embodiments of the present application, the wear history data refers to the summary of parameters such as the wall thickness and bulging of the water wall tubes based on a fixed detection area obtained during each regular or irregular water wall inspection. The method of obtaining the wear history data during the inspection can be in the form of electronic or paper records. In the case where the acquisition method is paper, the paper-recorded wear history data needs to be converted into electronic form.

[0040] In the embodiments of the present application, the water wall system is divided into grid zones and numbered. Among them, the numbering position is the actual measurement position, and one detection data is obtained for each detection area. In the embodiments of the present application, the boiler water wall system includes the left wall of the furnace, the left extension wall, the right wall of the furnace, the right extension wall, the front wall of the furnace, the front extension wall, the rear wall of the furnace, the rear extension wall, and the top of the furnace. To improve the accuracy of the inspection and ensure coverage, the grid division and numbering refer to the division and numbering carried out according to the arrangement of the water wall tubes on different walls and the elevation, forming the fixed-point coordinates of the longitude and latitude positions inside the furnace. Then, after standardizing the naming and numbering of the detection point positions, importing data into the wear prediction model based on the detection point positions can form the historical change trend of the detection data (wear history data) corresponding to the detection point positions. It should be noted that the fixed-point coordinates of the longitude and latitude positions are the detection point positions (detection areas), and a standardized template for detection data is used during each inspection process to standardize and manage the detection data.

[0041] In the embodiments of the present application, the boiler water wall system includes the furnace water wall and the extension wall water wall. As a feasible implementation method, to divide the boiler water wall system into grid zones, a longitudinal line can be first established based on the axis where each water wall tube in the furnace water wall and the extension wall water wall is located. Then, horizontal lines of the boiler water wall system are established at preset intervals from the bottom of the furnace as the horizontal lines of multiple grid zones. Multiple detection areas are determined based on the intersection points of the longitudinal lines and the horizontal lines. Among them, each intersection point corresponds to a detection area (the water wall tube section where the intersection point is located). Exemplarily, L145-01 is the 145th tube at a height of 43 meters on the left wall of the furnace.

[0042] As a feasible implementation method, the detection data for each inspection includes the wall thickness value of the detection area, and this wall thickness value is the minimum value of the detection area. Specifically, during each inspection process, at least three wall thickness values of the water wall tubes in each detection area are obtained, which can be the left wall thickness, the right wall thickness, and the middle wall thickness of the water wall tube at this section position. The sizes of at least three water wall thicknesses are compared to obtain the minimum wall thickness of the detection area, and this minimum wall thickness is used as the wall thickness value of the detection area at the current inspection time. Furthermore, the wall thickness data of each historical inspection time is summarized to obtain the wall thickness data corresponding to each of the multiple detection areas.

[0043] In the embodiment of the present application, the first wear rate is the ratio of the difference in the wall thickness values of a certain detection area between two adjacent detection times to the duration between the two detection times. In the embodiment of the present application, the wear history data may further include parameters such as bulging and the second wear rate of each detection area. Among them, the second wear rate is the ratio of the difference in the thickness of the water wall tube between the starting time of use and the most recent historical detection time to the operating duration of the water wall tube. The second wear rate can be used to issue a wear warning separately through the boiler 3D model and the scaled model sand table when it reaches the second warning threshold, so as to guide maintenance or replace the water wall tube.

[0044] S102. Construct a wear prediction model based on the wear history data, where the wear prediction model is used to represent the corresponding relationship between the wear history data and the monitored operating parameters at multiple historical detection times in the wear history data.

[0045] In the embodiment of the present application, the wear prediction model correlates the monitored operating parameters in the furnace obtained from the operation records of the boiler with the wear data at the corresponding time detected, so that in the subsequent wear prediction process, after inputting operating parameters such as the operating time into the wear prediction model, the wear data under this operating parameter can be predicted and output to predict the wear condition of the water wall system; and combined with the system data analysis, a warning is issued for the wear and bursting of the water wall system to obtain the analysis warning information of the water wall system.

[0046] As a feasible implementation manner, the wear prediction model can be a Support Vector Machine (SVM) prediction model.

[0047] S103. Based on the monitored operating parameters, establish a numerical simulation model of the water wall system and generate wear evaluation data corresponding to the target wear area; where the target wear area is at least one detection area determined based on the first wear rate of each detection area.

[0048] In the embodiment of the present application, a boiler 3D model with a 1:1 actual size of the three-dimensional fluid domain of the boiler entity is established according to the boiler drawings, and then the boiler 3D model is meshed to generate a boiler mesh model.

[0049] In the embodiments of the present application, on the generated boiler grid model, boundary conditions that conform to the actual situation of the boiler, including the feeding rate and fluidization wind speed, etc., are set, and simulation calculation parameters are set according to the actual operating conditions inside the boiler (such as fuel quantity, furnace temperature, furnace negative pressure, air distribution conditions (temperatures and flow rates of primary and secondary air), chemical components, and coal particle size distribution, etc.). Then, the computational particle fluid dynamics (CPFD) numerical simulation algorithm is adopted, combined with the relevant formula equations of aerodynamics, to calculate the operating parameters inside the circulating fluidized bed boiler. Here, the boiler is a circulating fluidized bed boiler. The Barracuda software is used to simulate the fluid-particle phase entering the boiler based on the Euler-Lagrange framework to generate the numerical simulation model

[0050] Among them, the fluid motion equation adopts the N-S equation (Navier-Stokes equations):

[0051]

[0052] Among them, v is the fluid velocity, t is the time, f is the external force received by the fluid per unit volume, ρ is the fluid density, p is the fluid pressure, and μ is the dynamic viscosity

[0053] The solution equation for the particle phase is the following formula two:

[0054]

[0055] Among them, u f is the vector velocity of the fluid phase, u s is the velocity of the particle phase, ρ s is the particle density, θ s is the volume fraction of the particles, τ s is the normal stress of the particles, D p is the diameter of the particles, and g is the acceleration due to gravity

[0056] The momentum coupling expression between the particles and the fluid is the following formula three:

[0057]

[0058] Among them, is the momentum coupling source term, m sk is the particle mass of the k-th component; n sk is the actual number of particles of the k-th component, S ξ,sk is the interpolation operator, V ξ is the calculation unit volume, D sk is the diffusion coefficient of the k-th component, ρ skis the density, N p is the number of particles, is the fluid velocity, is the solid velocity, For pressure.

[0059] In addition to the above formulas 1 to 3, data calculations also use the equations of conservation of mass, conservation of energy, and conservation of momentum. Through a series of equations, the velocity, temperature, pressure, and chemical components of the fluid in each grid unit, such as oxygen, nitrogen, carbon dioxide, and water vapor, as well as the number, velocity, temperature, particle size, chemical composition, and other parameters of the particles inside the grid are obtained.

[0060] Based on the above content, the calculation formula for the wear amount of the water-cooled wall system inside the boiler is as follows:

[0061]

[0062] Where, M is the accumulated wear amount, θ k is the angle between the kth particle and the collision avoidance, n p is the total number of collision particles, w(θ k ) is the collision angle coefficient of the kth calculated particle. The relationship between the collision angle coefficient and the collision angle is as follows: Figure 2 As shown, m sk is the mass of the kth calculated particle, Calculate the velocity of the kth particle.

[0063] In an embodiment of the present application, the wear amount corresponding to the target wear area is obtained according to the target wear area, and the wear assessment data of the calibrated target wear area is obtained. The numerical value of the wear amount corresponding to the target wear area is matched by color to generate a wear cloud map based on the boiler 3D model to intuitively display the wear condition inside the boiler. The wear assessment data may specifically include a wall thickness value after wear, which is the difference between the wall thickness value at the last detection time and the wear amount. Among them, the target wear area refers to any detection area in the furnace water-cooled wall and the extension wall water-cooled wall where the first wear rate is greater than the preset wear threshold value, and the target wear area can be one or multiple adjacent detection areas.

[0064] S104, using the wear prediction model to predict current wall thickness data of the target wear area, and optimizing the monitoring operation parameters when the difference between the wear assessment data and the current wall thickness data is greater than a preset threshold.

[0065] In the embodiments of the present application, a computational fluid dynamics (CFD) simulation software (Barracuda software) is used to perform mesh generation and set boundary conditions, where the boundary conditions are determined according to the corresponding monitored operation parameters provided by the power plant; in the case where the difference between the wall thickness value in the wear assessment data and the current wall thickness data is greater than a preset threshold, the monitored operation parameters are optimized, and the accuracy of the optimization result is verified.

[0066] In the embodiments of the present application, in the case where the difference between the wear assessment data and the current wall thickness data is greater than a preset threshold, at least one of the monitored operation parameters is optimized based on a genetic algorithm; wherein, the genetic algorithm is a stochastic global search optimization method originating from computer simulation studies of biological systems, which, by simulating phenomena such as replication, crossover, and mutation occurring in natural selection and genetics, starts from any initial population and generates a group of individuals more suitable for the environment through random selection, crossover, and mutation operations, causing the population to evolve to better and better regions in the search space, and continuously evolving generation by generation until it converges to a group of individuals most adapted to the environment, screening out useless data and retaining useful data, thereby obtaining a high-quality solution to the problem, that is, determining the optimal operation parameters; the operation parameters may include the fuel quantity, furnace temperature, furnace negative pressure, air distribution conditions (i.e., the air volume and velocity of primary air and secondary air, the swing angle of the air duct nozzle, etc.). In the embodiments of the present application, when using the genetic algorithm to optimize the operation parameters based on the wear prediction model, certain limitation ranges can be given to the operation parameters in the actual operation conditions, such as limiting the maximum swing ranges of the fuel quantity, furnace negative pressure, and the swing angle of the air duct nozzle. By narrowing the parameter ranges in the actual operation conditions, the optimization accuracy and efficiency can be improved.

[0067] Exemplarily, during a primary optimization calculation, the furnace temperature is limited to a constant 340 °C, and the air distribution conditions are adjusted as variable parameters to observe the new wear assessment parameters obtained through numerical simulation. It should be noted that the adjustment and optimization of the monitored operation parameters need to ensure the operation load of the boiler, that is, the operation load of the boiler is not adjusted, and at the same time, parameters such as coal quality are restricted to remain unchanged and the same as the actual application conditions to avoid interference with the wear data.

[0068] In the embodiments of the present application, based on the optimization result, key attention / repair is paid to the target wear area, and continuous optimization is carried out based on the prediction results of the updated wear prediction model after optimization.

[0069] In an embodiment of the present application, the acquired wear history data may also include operating status data of the boiler in which the water-cooled wall system is located, such as real-time furnace temperature, water quality pH value, outer diameter of water-cooled wall tubes, inner diameter, spacing, distance between water-cooled wall tubes and water-cooled walls, operating time, previous maintenance time, maintenance wall thickness expansion data, water-cooled wall tube replacement time and related configuration parameters, such as the configuration model, configuration specifications, manufacturer, installation date, and replacement water-cooled wall tube manufacturer of the furnace water-cooled wall.

[0070] Through the wear prediction and optimization method for a boiler water-cooled wall system provided in the present application, the water-cooled wall system of the boiler is grid-partitioned to obtain a plurality of detection zones, and wear history data corresponding to the plurality of detection zones are obtained; a wear prediction model is constructed based on the wear history data, and the wear prediction model is used to characterize the correspondence between the wear history data and the monitoring operation parameters of a plurality of historical detection times in the wear history data; based on the monitoring operation parameters, a numerical simulation model of the water-cooled wall system is established to generate wear assessment data corresponding to a target wear area; the wear prediction model is used to predict the current wall thickness data of the target wear area, and when the difference between the wear assessment data and the current wall thickness data is greater than a preset threshold, the monitoring operation parameters are optimized, so that the predicted wear can be continuously optimized while considering the monitoring operation parameters in the furnace, thereby improving the prediction accuracy and providing optimization guidance for the boiler site.

[0071] Example 2

[0072] Based on the above embodiment, this embodiment also provides a method for predicting and optimizing wear of a boiler water wall system. Figure 3 An optional flow chart of the boiler water wall system wear prediction optimization method provided in this embodiment is as follows: Figure 3 As shown, the method for constructing a wear prediction model in this embodiment includes the following steps S301 to S304:

[0073] Step S301: pre-process the first wear rate of each detection area to generate a wear database.

[0074] In the embodiment of the present application, the data of the first wear rate of each detection area is cleaned, and the measured wall thickness value is processed by PYTHON to eliminate the null value data, and then the first wear rate is calculated. After the calculation results are obtained, they are grouped according to different furnace wall surfaces.

[0075] Step S302: Perform feature analysis on the wear database by regression analysis, histogram and spearman correlation analysis to obtain wear feature data.

[0076] Step S303: Split the wear feature data into a training set and a test set by means of stratified sampling, where the ratio of the training set to the test set is 4:1.

[0077] Step S304: Construct an initial wear prediction model based on the training set and verify the initial wear prediction model based on the test set; if the verification result is qualified, determine the initial wear prediction model as the wear prediction model.

[0078] In the embodiment of the present application, the proportion of the training set is 75%, the proportion of the test set is 25%, the three-fold cross-validation method is adopted in the model training process, and the Isolation Forest method is applied to establish a data model.

[0079] Embodiment 3

[0080] Based on the above embodiments, after obtaining the wear history data corresponding to multiple detection areas in the embodiment of the present application, as Figure 4 、 Figure 5 shown, an equal-proportion model sand table of the boiler is established based on the boiler 3D model, and the wear history data of the water wall system is synchronously updated in real time in the equal-proportion model sand table to display the wear data of the water wall system. Among them, after the wear prediction model is used to predict the current wall thickness data of the target wear area at regular intervals, when the current wall thickness data reaches the first warning threshold, the current wall thickness data can be warned through the boiler 3D model and the equal-proportion model sand table.

[0081] Among them, as Figure 4As shown in the figure, after determining the component list corresponding to the digital boiler 3D model, digital modeling and 3D rendering of components are performed based on the component list to form a digital boiler 3D model of the components and build a basic component library. Among them, a data model of the boiler is established based on the boiler model and the specification attributes of the internally configured water wall, and the model data is cached based on Redis. The feature ID information of the digital boiler 3D model is used as the Key key information to associate and map the attributes of the digital boiler 3D model. The boiler 3D model is imported into the visualization platform, and the parameters and display methods to be accessed are set. Based on this, the boiler 3D model of this embodiment has functions such as switching between the external view and the internal view of the electronic 3D model of the furnace water wall tubes, functions such as zooming in, zooming out, rotating, resetting, and perspective of the electronic 3D model of the furnace water wall tubes, functions such as switching between the front, back, left, right, and top views of the electronic 3D model of the furnace water wall tubes, full screen and return functions of the boiler water wall anti-wear and explosion-proof data modeling analysis management platform, function of presenting the distribution of early warning information of the furnace water wall tubes, function of querying and displaying the position of the furnace water wall tubes according to the numbering rules, function of presenting the change curve of the health trend of the furnace water wall, function of presenting the inspection data of the furnace water wall in categories of front, back, left, right, and top, function of presenting the safety early warning information of the furnace water wall, and function of presenting the inlet and outlet headers of the furnace water wall tubes, so as to perform 3D visual analysis and early warning through the boiler water wall anti-wear and explosion-proof data modeling analysis management platform (boiler water-cooled 3D monitoring and early warning system); at the same time, it can make up for the problems such as incomplete inspection and repair ledgers of boiler water wall tubes, un-replaced remaining defects of water walls, and unclear historical records.

[0082] In the embodiment of the present application, with reference to Figure 6 As shown in the figure, in the case where the wear prediction model predicts that the current tube wall thickness exceeds the limit, information early warning is carried out through the digital boiler 3D model to provide a decision-making basis for managers, which is convenient for better formulating anti-wear and explosion-proof measures and arranging maintenance plans.

[0083] The present invention also provides a wear prediction and optimization device 700 for a boiler water wall system, which can be used to execute the wear prediction and optimization method for the boiler water wall system in any of the above embodiments of the present invention. Figure 7 FIG. is a schematic structural diagram of the wear prediction and optimization device 700 for the boiler water wall system provided by the embodiment of the present application, including an acquisition module 701, a model construction module 702, a numerical simulation module 703, and a prediction and optimization module 704:

[0084] The acquisition module 701 is used to perform grid partitioning on the water wall system of the boiler to obtain a plurality of detection areas, and acquire the wear history data respectively corresponding to the plurality of detection areas; the wear history data at least includes the first wear rate of each detection area between the two adjacent historical detection times.

[0085] A model construction module 702 is configured to construct a wear prediction model based on the wear history data, where the wear prediction model is used to characterize the correspondence between the wear history data and the monitored operation parameters at multiple historical detection times in the wear history data;

[0086] A numerical simulation module 703 is configured to establish a numerical simulation model of the water wall system based on the monitored operation parameters and generate wear evaluation data corresponding to a target wear area; wherein, the target wear area is at least one detection area determined based on the first wear rate of each detection area;

[0087] A prediction optimization module 704 is configured to predict the current wall thickness data of the target wear area by using the wear prediction model, and optimize the monitored operation parameters when the difference between the wear evaluation data and the current wall thickness data is greater than a preset threshold.

[0088] The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes predicting the current wall thickness data of the target wear area by using the wear prediction model in any embodiment of the present application, and optimizing the monitored operation parameters when the difference between the wear evaluation data and the current wall thickness data is greater than a preset threshold. Specifically, a system or device equipped with a storage medium can be provided, on which software program codes for implementing the functions in any of the above embodiments are stored, and the computer (or CPU or MPU) of the system or device is enabled to read and execute the program codes stored in the storage medium.

[0089] Particularly, according to the embodiments of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments of the present invention include a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it executes the above functions defined in the system of the present application.

[0090] It should be noted that the computer-readable storage medium shown in the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable storage medium other than the computer-readable storage medium, and this computer-readable storage medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0092] The units involved in the embodiments of the present invention can be implemented in software or in hardware, and the described units can also be provided in a processor. In some cases, the names of these units do not constitute a limitation on the units themselves.

[0093] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described modules or units can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0094] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented in software or in a manner combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions for causing a computing device (such as a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0095] In several embodiments provided in the present application, it should be understood that the disclosed systems, modules, and methods can be implemented in other ways. For example, the above-described module embodiments are merely illustrative. For example, the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces, modules, or units, and can be in electrical, mechanical, or other forms.

[0096] The above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. The present application is not limited to the exact structures already described and illustrated in the drawings, and it cannot be considered that the specific implementation of the present application is only limited to these descriptions. For those of ordinary skill in the technical field to which the present application belongs, without departing from the concept of the present application, various changes and deformations made should be regarded as falling within the protection scope of the present application.

Claims

1. A method for predicting and optimizing wear of a boiler water wall system, characterized in that: include: Grid-partitioning the water-cooled wall system of the boiler to obtain a plurality of detection areas, and obtaining wear history data corresponding to the plurality of detection areas respectively; The wear history data at least includes a first wear rate of each of the detection areas between two adjacent historical detection times; Building a wear prediction model based on the wear history data, the wear prediction model is used to characterize the corresponding relationship between the wear history data and the monitoring operation parameters of multiple historical detection times in the wear history data; Based on the monitoring operation parameters, a numerical simulation model of the water-cooled wall system is established to generate wear assessment data corresponding to a target wear area; wherein the target wear area is at least one detection area determined based on the first wear rate of each detection area; The wear prediction model is used to predict the current wall thickness data of the target wear area, and when the difference between the wear assessment data and the current wall thickness data is greater than a preset threshold, the monitoring operation parameter is optimized.

2. The wear prediction and optimization method for a boiler water wall system according to claim 1, characterized in that: The step of constructing a wear prediction model based on the wear history data comprises: Preprocessing the first wear rate of each detection area to generate a wear database; Performing feature analysis on the wear database by regression analysis, histogram and spearman correlation analysis methods to obtain wear feature data; The wear characteristic data is split into a training set and a test set by using a stratified sampling method, wherein the ratio of the training set to the test set is 4:1; An initial wear prediction model is constructed based on the training set, and the initial wear prediction model is verified based on the test set; when the verification result is qualified, the initial wear prediction model is determined to be the wear prediction model.

3. The wear prediction and optimization method of boiler water wall system according to claim 1, characterized in that: The step of establishing a numerical simulation model of the water wall system based on the monitored operating parameters and generating wear assessment data corresponding to the target wear area includes: Building a boiler 3D model based on the boiler drawing, and importing the boiler 3D model into Barracuda software for meshing and setting boundary conditions, wherein the boundary conditions are determined based on the monitoring operation parameters, and the monitoring operation parameters include fuel quantity, furnace temperature, furnace negative pressure, and air distribution conditions; The Barracuda software simulates the fluid-particle phase entering the boiler based on the Euler-Lagrangian framework to generate the numerical simulation model; Performing water wall wear assessment on the target wear area in the numerical simulation model to obtain wear assessment data on the target wear area; Among them, the at least one detection zone determined based on the first wear rate of each detection zone refers to: any detection zone in the furnace water-cooled wall and the extension wall water-cooled wall where the first wear rate is greater than a preset wear threshold is determined as the target wear area, and the target wear area is one or multiple adjacent detection zones.

4. The wear prediction and optimization method of a boiler water wall system according to claim 3, characterized in that: The step of establishing a boiler 3D model based on the boiler drawing includes: Determine a component list corresponding to the 3D model; Based on the component list, digital modeling and 3D rendering of the components are performed to form a digital boiler 3D model of the components, and a basic component library is constructed; wherein, a data model of the boiler is established based on the boiler model and the specification attributes of the internally configured water-cooled wall, and based on the Redis cache model data, the characteristic ID information of the digital boiler 3D model is used as the Key information to associate and map the attributes of the digital boiler 3D model; The digital boiler 3D model is imported into the visualization platform, and the parameters and display methods required for access are set.

5. The wear prediction and optimization method of boiler water wall system according to claim 4 is characterized in that: When the difference between the wear assessment data and the current wall thickness data is greater than a preset threshold, optimizing the monitoring operation parameters includes: At least one of the monitoring operation parameters is optimized based on a genetic algorithm.

6. The wear prediction and optimization method of boiler water wall system according to claim 1, characterized in that: The boiler water-cooled wall system includes a furnace water-cooled wall and an extension wall water-cooled wall. The boiler water-cooled wall system is grid-partitioned to obtain multiple detection areas, including: Establishing a longitudinal line based on the axis where each water-cooled wall tube in the furnace water-cooled wall and the extension wall water-cooled wall is located; Establishing elevation horizontal lines of the boiler water wall system at preset intervals from the bottom of the furnace as transverse lines of the plurality of grid areas; The plurality of detection areas are determined based on intersections of the longitudinal lines and the transverse lines; wherein each of the intersections corresponds to a detection area.

7. The wear prediction and optimization method of a boiler water wall system according to claim 6, characterized in that: The wear history data includes the wall thickness data of the detection area at each of the historical detection times; the method further includes: Obtaining the water-cooled wall thickness of at least three locations of the water-cooled wall tube of each of the detection areas; For each of the historical detection times, the wall thicknesses of the at least three water-cooled walls are compared to obtain a minimum wall thickness value of the detection area, and the minimum wall thickness value is used as the wall thickness data corresponding to the current detection time; The wall thickness data at each of the historical detection times are summarized to obtain the wall thickness data corresponding to the multiple detection areas respectively.

8. The wear prediction and optimization method for a boiler water wall system according to claim 3, characterized in that: After acquiring the wear history data respectively corresponding to the plurality of detection areas, the method further includes: A proportional model sandbox of the boiler is established based on the boiler 3D model, and the wear history data of the water-cooled wall system is synchronized in real time in the proportional model sandbox to display the wear data of the water-cooled wall system.

9. The wear prediction and optimization method for a boiler water wall system according to claim 8, characterized in that: The method further comprises The wear prediction model is used to regularly predict the current wall thickness data of the target wear area, and when the current wall thickness data reaches a first warning threshold, a warning is issued for the current wall thickness data through the boiler 3D model and the proportional model sandbox.

10. The wear prediction and optimization method for a boiler water wall system according to any one of claims 1 to 9, characterized in that: The wear history data also includes a second wear rate of each detection zone, wherein the second wear rate is a ratio of a thickness difference of the water-cooled wall tube from the start time of use to the most recent historical detection time to the running time of the water-cooled wall tube; The method further comprises: For each of the detection areas, a second wear rate is calculated; and when the second wear rate reaches a second warning threshold, a warning is issued through the boiler 3D model and the proportional model sand table.

Images