Boiler combustion monitoring method and system based on multi-model joint simulation

Abstract

The invention discloses a boiler combustion monitoring method and system based on multi-model joint simulation, and relates to the technical field of boiler monitoring, and the method comprises the steps: obtaining prediction output data of the same physical quantity of a CFD-AI model and a Modelica model, and calculating a precision difference coefficient; calculating a data scale coefficient according to the maximum value of the predicted output data; acquiring an error of data transmission of the same physical quantity between the CFD-AI model and the Modelica model, and calculating a parameter transmission error coefficient according to the error of data transmission; an error accumulation coefficient between the models is obtained according to the precision difference coefficient, the data scale coefficient and the parameter transfer error coefficient, the error accumulation coefficient is compared with a preset error accumulation coefficient threshold value, and the accuracy of boiler combustion data monitored according to simulation is judged according to a comparison result. Error accumulation of cooperative work between the CFD-AI model and the Modelica model can be judged, the reliability of a final simulation result is ensured, and boiler combustion monitoring data are accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of boiler monitoring, and in particular to a boiler combustion monitoring method and system based on multi-model joint simulation. Background Art

[0002] The boiler combustion monitoring method based on multi-model joint simulation refers to the joint simulation of the three-dimensional CFD-AI model and the Modelica model, obtaining the actual furnace wall temperature and other data through the simulation results, passing it to the CFD-AI model, performing cyclic simulation calculations, and outputting data results such as heat flow after a period of time; then inputting the heat flow data results into the FMU model, simulating a step time, and outputting data results such as wall temperature; finally, the output results of the FMU are input into the CFD-AI model to monitor the boiler combustion situation in real time; through real-time cyclic simulation and data interaction, the accuracy and response speed of the boiler operation can be effectively improved, thereby realizing accurate monitoring of the boiler combustion state, fault warning and optimized scheduling, and improving the safety, efficiency and economy of the boiler.

[0003] In the above technologies, the collaborative work between the CFD-AI model and the Modelica model involves the interaction and information transfer between two key models (CFD-AI and Modelica); although these two models have powerful capabilities in fluid mechanics, thermodynamics, control systems, etc., they may encounter several challenges when implementing multi-physics field simulation, especially in terms of accuracy differences, parameter transfer, data scale mismatch, etc., which lead to error accumulation and affect the reliability of the final simulation results. Summary of the invention

[0004] The purpose of the present invention is to solve the above-mentioned problems and provide a boiler combustion monitoring method and system based on multi-model joint simulation.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: The boiler combustion monitoring method based on multi-model joint simulation includes the following steps: Obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the accuracy difference coefficient based on the predicted output data; Obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the data scale coefficient based on the maximum value of the predicted output data; Obtain the error of data transmission of the same physical quantity between the CFD-AI model and the Modelica model, and calculate the parameter transmission error coefficient based on the error of data transmission; The error accumulation coefficient between models is obtained according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, and the error accumulation coefficient is compared with the preset error accumulation coefficient threshold, and the accuracy of the boiler combustion data monitored by the simulation is judged according to the comparison result.

[0006] A further improvement of the present invention is to obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the accuracy difference coefficient according to the predicted output data, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Indicates that at time step The moment above, and They represent the prediction outputs of the CFD-AI model and the Modelica model at this time step respectively; Calculate the difference between the predictions of the CFD-AI model and the Modelica model at each time step:

[0007] in, Indicates that at time step The difference between the predicted outputs of the two models when ; For all time steps , calculate the sum of the differences: ; is the total number of time steps; Calculate the average value of the output of the CFD-AI model and the Modelica model respectively and : ,

[0008] The precision difference coefficient is calculated based on these two average values. The calculation formula is: , is the coefficient of variation of precision.

[0009] A further improvement of the present invention is to obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the data scale coefficient according to the maximum value of the predicted output data, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Represents the time step The moment on; Calculate the maximum value of the CFD-AI model over all time steps:

[0010] is the total number of time steps; is the maximum predicted output value of the CFD-AI model in all time steps; Compute the maximum value of the Modelica model over all time steps:

[0011] is the maximum predicted output value of the Modelica model in all time steps; Calculate the data scaling factor:

[0012] is the data scaling factor.

[0013] A further improvement of the present invention is to obtain the error of data transmission of the same physical quantity between the CFD-AI model and the Modelica model, and calculate the parameter transmission error coefficient according to the error of data transmission, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Represents the index at different time steps (or space steps), and Represents the CFD-AI model and Modelica model at time step The predicted output at the moment; For each time step , calculate the error between the CFD-AI model and the Modelica model: ; It is The error at a time step represents the difference between the predicted values ​​of the CFD-AI model and the Modelica model at that time step; The errors over all time steps are averaged to get the overall average error ; The parameter transfer error coefficient is calculated based on the ratio of the average error to the maximum predicted value:

[0014] is the parameter transfer error coefficient.

[0015] A further improvement of the present invention is that the error accumulation coefficient between models is obtained according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, including:

[0016] In the formula, is the error accumulation coefficient, 、 、 are the accuracy difference coefficient, data scale coefficient and parameter transfer error coefficient respectively. 、 、 They are 、 、 The preset scaling factor of the points, and 、 、 Both are greater than 0.

[0017] A further improvement of the present invention is to compare the error accumulation coefficient with a preset error accumulation coefficient threshold, and judge the accuracy of the boiler combustion data monitored by the simulation according to the comparison result, including: If the error accumulation coefficient is less than the preset error accumulation coefficient threshold, the boiler combustion data monitored by the simulation is accurate; If the error accumulation coefficient is not less than the preset error accumulation coefficient threshold, the boiler combustion data monitored by the simulation is inaccurate.

[0018] The boiler combustion monitoring system based on multi-model joint simulation includes: The precision difference coefficient acquisition module obtains the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculates the precision difference coefficient based on the predicted output data; The data scale coefficient acquisition module obtains the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculates the data scale coefficient according to the maximum value of the predicted output data; The parameter transfer error coefficient acquisition module obtains the error of data transfer of the same physical quantity between the CFD-AI model and the Modelica model, and calculates the parameter transfer error coefficient based on the error of data transfer; The analysis and judgment module obtains the error accumulation coefficient between models according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, compares the error accumulation coefficient with the preset error accumulation coefficient threshold, and judges the accuracy of the boiler combustion data monitored by the simulation according to the comparison results.

[0019] A further improvement of the present invention is that, in the precision difference coefficient acquisition module, the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model are acquired, and the precision difference coefficient is calculated according to the predicted output data, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Indicates that at time step The moment above, and They represent the prediction outputs of the CFD-AI model and the Modelica model at this time step respectively; Calculate the difference between the predictions of the CFD-AI model and the Modelica model at each time step:

[0020] in, Indicates that at time step The difference between the predicted outputs of the two models when ; For all time steps , calculate the sum of the differences: ; is the total number of time steps; Calculate the average value of the output of the CFD-AI model and the Modelica model respectively and : ,

[0021] The precision difference coefficient is calculated based on these two average values. The calculation formula is: , is the coefficient of variation of precision.

[0022] A further improvement of the present invention is that, in the data scale coefficient acquisition module, the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model are acquired, and the data scale coefficient is calculated according to the maximum value of the predicted output data, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Represents the time step The moment on; Calculate the maximum value of the CFD-AI model over all time steps:

[0023] is the total number of time steps; is the maximum predicted output value of the CFD-AI model in all time steps; Compute the maximum value of the Modelica model over all time steps:

[0024] is the maximum predicted output value of the Modelica model in all time steps; Calculate the data scaling factor:

[0025] is the data scaling factor.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a boiler combustion monitoring method based on multi-model joint simulation.

[0027] Compared with the prior art, the present invention has at least the following beneficial technical effects: The boiler combustion monitoring method and system based on multi-model joint simulation provided by the present invention calculate the accuracy difference coefficient by obtaining the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model; and calculate the data scale coefficient according to the maximum value of the predicted output data; obtain the error of the data transmission of the same physical quantity between the CFD-AI model and the Modelica model, and calculate the parameter transfer error coefficient according to the error of the data transmission; obtain the error accumulation coefficient between the models according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, and compare the error accumulation coefficient with the preset error accumulation coefficient threshold, and judge the accuracy of the boiler combustion data monitored by the simulation according to the comparison result, so that the error accumulation of the collaborative work between the CFD-AI model and the Modelica model can be judged, the reliability of the final simulation result is ensured, and the boiler combustion monitoring data is accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 This is a flow chart of the boiler combustion monitoring method based on multi-model joint simulation.

[0030] Figure 2 This is the structural block diagram of the boiler combustion monitoring system based on multi-model joint simulation. DETAILED DESCRIPTION

[0031] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0032] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0033] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0034] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0035] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0036] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0037] Example 1 The embodiment of the present invention provides a boiler combustion monitoring method based on multi-model joint simulation. Figure 1 , Figure 1 A flow chart of a boiler combustion monitoring method based on multi-model joint simulation provided by an embodiment of the present invention. The method comprises the following steps: Obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the accuracy difference coefficient based on the predicted output data; Obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the data scale coefficient based on the maximum value of the predicted output data; Obtain the error of data transmission of the same physical quantity between the CFD-AI model and the Modelica model, and calculate the parameter transmission error coefficient based on the error of data transmission; The error accumulation coefficient between models is obtained according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, and the error accumulation coefficient is compared with the preset error accumulation coefficient threshold, and the accuracy of the boiler combustion data monitored by the simulation is judged according to the comparison result.

[0038] Based on the boiler combustion monitoring method based on multi-model joint simulation provided by the embodiment of the present invention, the error accumulation of the collaborative work between the CFD-AI model and the Modelica model can be judged through the above method, thereby ensuring the reliability of the final simulation results and making the boiler combustion monitoring data accurate.

[0039] In one embodiment, calculating the precision difference coefficient includes: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Indicates that at time step The moment above, and They represent the prediction outputs of the CFD-AI model and the Modelica model at this time step respectively; Calculate the difference between the predictions of the CFD-AI model and the Modelica model at each time step:

[0040] in, Indicates that at time step The difference between the predicted outputs of the two models when ; For all time steps , calculate the sum of the differences: ; is the total number of time steps; Calculate the average value of the output of the CFD-AI model and the Modelica model respectively and : ,

[0041] The precision difference coefficient is calculated based on these two average values. The calculation formula is: , is the coefficient of variation of precision.

[0042] It should be noted that a physical quantity can be various parameters related to the boiler combustion process, such as furnace wall temperature, heat flow, combustion gas temperature, pressure, gas flow rate, etc. These physical quantities are key indicators of the boiler combustion state and can reflect the efficiency, stability and safety of the combustion process. The data acquisition method involved in the calculation of the accuracy difference coefficient includes extracting the predicted output of the same physical quantity from the CFD-AI model and the Modelica model. The CFD-AI model calculates the local changes of the physical quantity through numerical simulation and AI optimization algorithm, while the Modelica model describes the overall behavior through system-level equations. By comparing the predicted values ​​of the two at the same time, these data can be obtained and used for subsequent error analysis and optimization.

[0043] It should be noted that the larger the accuracy difference coefficient, the greater the error accumulation between the CFD-AI model and the Modelica model, and the lower the accuracy of the boiler combustion data monitored by the simulation, because the larger the accuracy difference coefficient, the more significant the difference between the CFD-AI model and the Modelica model in predicting the same physical quantity, which means that there is a large deviation in the understanding and simulation of the boiler combustion process between the two. If this difference is not corrected or calibrated in time, the error will gradually accumulate as the simulation process progresses, resulting in a further decrease in the accuracy of the simulation results. In multi-physics field simulation, the CFD-AI model usually focuses on local details (such as microscopic heat flow, local temperature field, etc.), while the Modelica model focuses more on the overall macroscopic behavior of the system. There are inherent differences between the two in modeling methods and simulation scales. When the accuracy difference coefficient is large, it means that the deviation of the physical quantity prediction results between the two models is large, which may lead to errors in the transmission of key parameters (such as furnace temperature, heat flow, etc.) in the subsequent multi-model joint simulation process, and ultimately affect the reliability of the boiler combustion monitoring results. Therefore, the increase in the accuracy difference coefficient usually means that the accuracy of the simulated monitoring data is lower, and further optimization and adjustment are necessary to ensure the effectiveness and accuracy of the boiler combustion monitoring system.

[0044] In one implementation, the benefits of analyzing the accuracy difference coefficient for judging the error accumulation between the CFD-AI model and the Modelica model, as well as the accuracy of the boiler combustion data monitored by the simulation are: first, it helps reveal the inconsistency in accuracy between the models by quantifying the difference in predictions between the two models on the same physical quantity, and then evaluates the error propagation trend. As the simulation process progresses, the increase in the accuracy difference coefficient indicates that the error is gradually accumulating, which may lead to deviations and unreliability in the boiler combustion data. Therefore, real-time monitoring of the accuracy difference coefficient can timely discover the mismatch and error source between the models, take measures in advance to adjust or optimize, and avoid further expansion of the error. This not only helps to improve the data consistency between models, but also ensures the accuracy of the boiler combustion monitoring results, thereby providing reliable support for the safety of boiler operation, efficiency optimization and fault warning.

[0045] In one embodiment, calculating the data scaling factor includes: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Represents the time step The moment on; Calculate the maximum value of the CFD-AI model over all time steps:

[0046] is the total number of time steps; is the maximum predicted output value of the CFD-AI model in all time steps; Compute the maximum value of the Modelica model over all time steps:

[0047] is the maximum predicted output value of the Modelica model in all time steps; Calculate the data scaling factor:

[0048] is the data scale coefficient, which indicates the degree of difference between the two models in the data scale.

[0049] It should be noted that the larger the data scale coefficient, the greater the error accumulation between the CFD-AI model and the Modelica model, and the lower the accuracy of the boiler combustion data monitored by the simulation, because the larger the data scale coefficient, the more significant the difference in data representation and scale between the CFD-AI model and the Modelica model. This difference indicates that the two models may use different scales, units or data processing methods when processing the same physical quantity. When this scale difference exists, the data conversion and transmission between the models may deviate, resulting in error accumulation. If this error is not effectively controlled or corrected in multiple iterations, it will gradually expand and affect the final simulation results. Specifically in boiler combustion monitoring, the larger the data scale coefficient, the greater the difference in predictions of key parameters such as heat flow and wall temperature in the boiler by different models, which may lead to an increase in the deviation of the monitoring results of the boiler combustion state, thereby affecting the operational safety and efficiency prediction. Therefore, the increase in the data scale coefficient is directly related to the decrease in the prediction accuracy of the model, and the accuracy of the data monitored by the simulation is reduced, which may lead to incorrect operation suggestions or fault warnings, affecting the overall operation and optimization decision of the boiler system.

[0050] In one implementation, the benefits of analyzing the data scale coefficient for judging the error accumulation between the CFD-AI model and the Modelica model, as well as the accuracy of the boiler combustion data monitored by the simulation are as follows: First, the data scale coefficient can quantify the differences in data processing and scale between the two models, providing us with a clear indicator to help identify scale inconsistencies or data conversion problems between models. If the DSC value is large, it indicates that the output difference between the models is large, which means that there may be a large error accumulation, which in turn affects the reliability of the simulation results. In boiler combustion monitoring, this error accumulation may lead to inaccurate predictions of key parameters such as wall temperature and heat flow, thereby affecting the judgment of the boiler state. Therefore, real-time monitoring and analysis of the data scale coefficient can not only help us discover potential problems between models, but also provide a basis for further model adjustment and optimization, ensure the accuracy of boiler combustion data, and thus provide reliable support for safe operation, efficiency optimization, and fault warning of boilers.

[0051] In one embodiment, calculating the parameter transfer error coefficient includes: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Represents the index at different time steps (or space steps), and Represents the CFD-AI model and Modelica model at time step The predicted output at the moment; For each time step , calculate the error between the CFD-AI model and the Modelica model: ; It is The error at a time step represents the difference between the predicted values ​​of the CFD-AI model and the Modelica model at that time step; The errors over all time steps are averaged to get the overall average error ; The parameter transfer error coefficient is calculated based on the ratio of the average error to the maximum predicted value:

[0052] is the parameter transfer error coefficient.

[0053] It should be noted that the larger the parameter transfer error coefficient, the greater the error accumulation between the CFD-AI model and the Modelica model, and the lower the accuracy of the boiler combustion data monitored by the simulation, because the larger the parameter transfer error coefficient, the greater the error in the data transferred between the CFD-AI model and the Modelica model. This error may be caused by data conversion, accuracy differences, or mismatched parameters between models. When this error accumulates in multi-step simulations, it will cause the output results of the model to deviate from the actual physical situation, thereby affecting the accuracy of the simulation results. In boiler combustion monitoring, if the parameter transfer error is large, it may lead to inaccurate prediction results of key physical quantities (such as wall temperature, heat flow, etc.), which in turn affects the judgment of the boiler combustion state and the formulation of control strategies. Therefore, a higher parameter transfer error coefficient means that the data accuracy of boiler combustion monitoring is reduced, which may lead to incorrect operational decisions or safety risks.

[0054] In one implementation, the benefits of analyzing the parameter transfer error coefficient for determining the error accumulation between the CFD-AI model and the Modelica model, as well as the accuracy of the boiler combustion data monitored by the simulation are: The parameter transfer error coefficient plays a crucial role in determining the error accumulation between the CFD-AI model and the Modelica model and the accuracy of the boiler combustion data during simulation monitoring. By evaluating this coefficient, it is possible to identify whether significant deviations or errors have occurred in the data transfer process between models. If the parameter transfer error is large, it means that there is a large uncertainty in the information transfer between the two models. This uncertainty will gradually accumulate in multiple simulation steps, and eventually cause the monitoring results to deviate from the actual situation. Conversely, a smaller error coefficient indicates that the data transfer is more accurate and can better reflect the actual operating status of the boiler. Therefore, the parameter transfer error coefficient helps to identify and correct potential problems in the simulation process, improve the reliability and accuracy of boiler combustion monitoring, thereby optimizing the operation and control decisions of the boiler and ensuring safe and efficient operation.

[0055] In one embodiment, the error accumulation coefficient between models is obtained according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, including:

[0056] In the formula, is the error accumulation coefficient, 、 、 are the accuracy difference coefficient, data scale coefficient and parameter transfer error coefficient respectively. 、 、 They are 、 、 The preset scaling factor of the points, and 、 、 Both are greater than 0.

[0057] It should be noted that 、 、 It is set by professionals according to the actual situation. Generally, 、 、 The sum of is 1, and the specific value is not limited; in addition, before calculating the error accumulation coefficient, it is necessary to remove the unit from the accuracy difference coefficient, data scale coefficient and parameter transfer error coefficient.

[0058] In one embodiment, comparing the error accumulation coefficient with a preset error accumulation coefficient threshold, and judging the accuracy of the boiler combustion data monitored according to the simulation according to the comparison result includes: If the error accumulation coefficient is less than the preset error accumulation coefficient threshold, the boiler combustion data monitored by the simulation is accurate; If the error accumulation coefficient is not less than the preset error accumulation coefficient threshold, the boiler combustion data monitored by the simulation is inaccurate.

[0059] It should be noted that by comparing the error accumulation coefficient with the preset error accumulation coefficient threshold, the accuracy of the boiler combustion data monitored by the simulation can be effectively judged. If the error accumulation coefficient is less than the preset threshold, it means that the error accumulation between the CFD-AI model and the Modelica model is small, and the error of data transmission is within an acceptable range, thereby ensuring the accuracy of the simulation monitoring results. In this case, the data of boiler combustion monitoring can truly reflect the actual working status of the boiler, and the control system can make effective decisions and adjustments based on the data to ensure safe and efficient operation of the boiler.

[0060] However, when the error accumulation coefficient is not less than the preset threshold, it means that the error accumulation between models is too large, and there may be significant deviations in the data transfer process. This will lead to inaccurate data for boiler combustion monitoring, which will affect the judgment and control strategy of the boiler status. If this happens, the model should be calibrated and optimized in a timely manner, the parameter transfer and data interaction process between the models should be re-evaluated, and potential error sources should be found and corrected. In addition, it is also possible to consider introducing a more accurate physical model or performing additional data verification to ensure the reliability of the simulation results, thereby avoiding safety hazards or reduced efficiency caused by inaccurate data.

[0061] In one implementation, by comparing the error accumulation coefficient with a preset threshold, the accuracy of the boiler combustion monitoring data can be effectively monitored and evaluated, potential error problems can be discovered in a timely manner, and inaccurate data can be prevented from affecting the operation judgment and control decision of the boiler. If the error accumulation coefficient is lower than the threshold, the reliability of the simulation results can be ensured, thereby improving the safety and efficiency of boiler operation; if the threshold is not met, the error accumulation between models can be identified in a timely manner, prompting the optimization and adjustment of the model to prevent risks caused by inaccurate data. Overall, this method helps ensure that the boiler combustion monitoring system can continue to provide accurate feedback, provide high-quality information for decision-making, and ensure the smooth and efficient operation of the boiler.

[0062] Example 2 like Figure 2 As shown, the boiler combustion monitoring system based on multi-model joint simulation provided by the present invention includes: The precision difference coefficient acquisition module obtains the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculates the precision difference coefficient based on the predicted output data; The data scale coefficient acquisition module obtains the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculates the data scale coefficient according to the maximum value of the predicted output data; The parameter transfer error coefficient acquisition module obtains the error of data transfer of the same physical quantity between the CFD-AI model and the Modelica model, and calculates the parameter transfer error coefficient based on the error of data transfer; The analysis and judgment module obtains the error accumulation coefficient between models according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, compares the error accumulation coefficient with the preset error accumulation coefficient threshold, and judges the accuracy of the boiler combustion data monitored by the simulation according to the comparison results.

[0063] Example 3 The present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the boiler combustion monitoring method based on multi-model joint simulation are implemented.

[0064] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0065] The present application is described with reference to the flowcharts and / or block diagrams of the methods, systems and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0066] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0067] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0068] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0069] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A boiler combustion monitoring method based on multi-model joint simulation, characterized in that: The following steps are involved: Obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the accuracy difference coefficient based on the predicted output data; Obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the data scale coefficient based on the maximum value of the predicted output data; Obtain the error of data transmission of the same physical quantity between the CFD-AI model and the Modelica model, and calculate the parameter transmission error coefficient based on the error of data transmission; The error accumulation coefficient between models is obtained according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, and the error accumulation coefficient is compared with the preset error accumulation coefficient threshold, and the accuracy of the boiler combustion data monitored by the simulation is judged according to the comparison result.

2. The boiler combustion monitoring method based on multi-model joint simulation according to claim 1 is characterized in that: Obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the accuracy difference coefficient based on the predicted output data, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Indicates that at time step The moment above, and They represent the prediction outputs of the CFD-AI model and the Modelica model at this time step respectively; Calculate the difference between the predictions of the CFD-AI model and the Modelica model at each time step: in, Indicates that at time step The difference between the predicted outputs of the two models when ; For all time steps , calculate the sum of the differences: ; is the total number of time steps; Calculate the average value of the output of the CFD-AI model and the Modelica model respectively and : ， The precision difference coefficient is calculated based on these two average values. The calculation formula is: , is the coefficient of variation of precision.

3. The boiler combustion monitoring method based on multi-model joint simulation according to claim 2 is characterized in that: Obtain the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculate the data scale coefficient based on the maximum value of the predicted output data, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Represents the time step The moment on; Calculate the maximum value of the CFD-AI model over all time steps: is the total number of time steps; is the maximum predicted output value of the CFD-AI model in all time steps; Compute the maximum value of the Modelica model over all time steps: is the maximum predicted output value of the Modelica model in all time steps; Calculate the data scaling factor: is the data scaling factor.

4. The boiler combustion monitoring method based on multi-model joint simulation according to claim 3 is characterized in that: Obtain the error of data transmission of the same physical quantity between the CFD-AI model and the Modelica model, and calculate the parameter transmission error coefficient based on the error of data transmission, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Represents the index at different time steps (or space steps), and Represents the CFD-AI model and Modelica model at time step The predicted output at the moment; For each time step , calculate the error between the CFD-AI model and the Modelica model: ; It is The error at a time step represents the difference between the predicted values ​​of the CFD-AI model and the Modelica model at that time step; The errors over all time steps are averaged to get the overall average error ; The parameter transfer error coefficient is calculated based on the ratio of the average error to the maximum predicted value: is the parameter transfer error coefficient.

5. The boiler combustion monitoring method based on multi-model joint simulation according to claim 4 is characterized in that: The error accumulation coefficient between models is obtained based on the accuracy difference coefficient, data scale coefficient and parameter transfer error coefficient, including: In the formula, is the error accumulation coefficient, 、 、 are the accuracy difference coefficient, data scale coefficient and parameter transfer error coefficient respectively. 、 、 They are 、 、 The preset scaling factor of the points, and 、 、 Both are greater than 0.

6. The boiler combustion monitoring method based on multi-model joint simulation according to claim 5 is characterized in that: The error accumulation coefficient is compared with a preset error accumulation coefficient threshold, and the accuracy of the boiler combustion data monitored by the simulation is judged according to the comparison result, including: If the error accumulation coefficient is less than the preset error accumulation coefficient threshold, the boiler combustion data monitored by the simulation is accurate; If the error accumulation coefficient is not less than the preset error accumulation coefficient threshold, the boiler combustion data monitored by the simulation is inaccurate.

7. The boiler combustion monitoring system based on multi-model joint simulation is characterized by: include: The precision difference coefficient acquisition module obtains the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculates the precision difference coefficient based on the predicted output data; The data scale coefficient acquisition module obtains the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model, and calculates the data scale coefficient according to the maximum value of the predicted output data; The parameter transfer error coefficient acquisition module obtains the error of data transfer of the same physical quantity between the CFD-AI model and the Modelica model, and calculates the parameter transfer error coefficient based on the error of data transfer; The analysis and judgment module obtains the error accumulation coefficient between models according to the accuracy difference coefficient, the data scale coefficient and the parameter transfer error coefficient, compares the error accumulation coefficient with the preset error accumulation coefficient threshold, and judges the accuracy of the boiler combustion data monitored by the simulation according to the comparison results.

8. The boiler combustion monitoring system based on multi-model joint simulation according to claim 7 is characterized in that: In the precision difference coefficient acquisition module, the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model are obtained, and the precision difference coefficient is calculated based on the predicted output data, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Indicates that at time step The moment above, and They represent the prediction outputs of the CFD-AI model and the Modelica model at this time step respectively; Calculate the difference between the predictions of the CFD-AI model and the Modelica model at each time step: in, Indicates that at time step The difference between the predicted outputs of the two models when ; For all time steps , calculate the sum of the differences: ; is the total number of time steps; Calculate the average value of the output of the CFD-AI model and the Modelica model respectively and : ， The precision difference coefficient is calculated based on these two average values. The calculation formula is: , is the coefficient of variation of precision.

9. The boiler combustion monitoring system based on multi-model joint simulation according to claim 8 is characterized in that: In the data scale coefficient acquisition module, the predicted output data of the same physical quantity of the CFD-AI model and the Modelica model are obtained, and the data scale coefficient is calculated according to the maximum value of the predicted output data, including: Get the predicted output of a certain physical quantity from the CFD-AI model, denoted as ; Get the predicted output of the same physical quantity from the Modelica model, denoted as ; Represents the time step The moment on; Calculate the maximum value of the CFD-AI model over all time steps: is the total number of time steps; is the maximum predicted output value of the CFD-AI model in all time steps; Compute the maximum value of the Modelica model over all time steps: is the maximum predicted output value of the Modelica model in all time steps; Calculate the data scaling factor: is the data scaling factor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the boiler combustion monitoring method based on multi-model joint simulation according to any one of claims 1 to 6.

Images