Boiler steam-water side two-dimensional mechanism modeling method and system based on CFD-AI

Abstract

The invention discloses a CFD-AI-based boiler steam-water side two-dimensional mechanism modeling method and system, and relates to the technical field of model optimization, and the method comprises the steps: obtaining the total type of a sensor, calculating the data transmission delay coefficient and the data transmission instability coefficient of the sensor for each type of sensor, and calculating the data transmission delay coefficient and the data transmission instability coefficient of the sensor; comparing with a preset data transmission delay coefficient threshold value and a preset data transmission delay coefficient threshold value, judging whether the data transmission of the sensor is delayed and stable, and taking corresponding processing measures; the processed sensor transmits boiler operation parameters in real time, continuously adjusts and optimizes a steam-water side model and controls specific numerical values of the boiler operation parameters, data transmission delay and instability of the sensor can be optimized, the processed sensor transmits the boiler operation parameters in real time, and continuously adjusts and optimizes the steam-water side model. The operation state of the boiler is simulated, the specific numerical values of the operation parameters of the boiler are controlled, the influence on the real-time control decision is reduced, and the optimization effect is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of model optimization, and in particular to a two-dimensional mechanism modeling method and system for a boiler steam-water side based on CFD-AI. Background Art

[0002] Based on the boiler combustion CFD-AI model and data-driven model, it means that the combustion area, burnout area, water-cooled wall area, screen-pass area, high-pass / high-in area, low-pass / low-in area and other areas are discretely modeled to different degrees for the steam-water measuring unit model according to the granularity of CFD-AI simulation, ensuring that the wall temperature measuring points of DCS are distributed in different discrete areas, and integrated with the FMU model formed by order reduction of the CFD simulation results; and determining the boundary conditions of the boiler combustion model and the steam-water model, including fuel supply, air inlet, steam-water supply, outlet, etc., determining the importance of the boundary conditions of the boiler combustion model and the steam-water model, including fuel supply, air inlet, steam-water supply and outlet, etc. The boundary conditions need to take into account the actual situation and match the mathematical model to ensure the accuracy of the simulation results; Generally speaking, the CFD-AI model is directly coupled with the system model, and the system model is directly involved in the debugging. That is, the accuracy of the entire pulverized coal side is not considered, and the model of the steam-water side is continuously adjusted and optimized. The system model and components are created using the lumped parameter method; thereby achieving accurate simulation and real-time optimization of the thermodynamic behavior of various areas of the boiler (such as the combustion zone, water-cooled wall zone, superheater, etc.). Through the coupling between the fine boundary conditions provided by the CFD-AI model and the system model (lumped parameter method), the operating parameters of the steam-water side, such as water flow rate, cooling water temperature, etc., can be continuously adjusted and optimized to ensure that the temperature and pressure distribution of the boiler are within a safe range, while improving the overall operating efficiency. This method enables the boiler control system to perform adaptive adjustments in actual operation, achieving more accurate control, prediction, and fault prevention.

[0003] In the above optimization process, real-time optimization relies on accurate sensor data, including temperature, pressure, flow and other parameters; however, in actual boiler operation, the collection of these data may be affected by sensor data transmission delays and instability, which may affect real-time control decisions and thus affect the optimization effect of the system. Summary of the invention

[0004] The purpose of the present invention is to solve the above-mentioned problems and provide a two-dimensional mechanism modeling method and system for the steam-water side of a boiler based on CFD-AI.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: The two-dimensional mechanism modeling method of boiler steam-water side based on CFD-AI includes the following steps: During boiler operation, the total types of sensors are obtained, and for each type of sensor, the transmission data time of each sensor and the preset data transmission time interval are obtained to obtain the data transmission delay coefficient of the sensor; For each type of sensor, the data transmission time of each sensor is obtained, and the data transmission instability coefficient of the sensor is obtained according to the data transmission time of each sensor; Compare the data transmission delay coefficient of the sensor with the preset data transmission delay coefficient threshold to determine whether the data transmission of the sensor is delayed. If there is no delay, directly output the sensor data; if there is an extension, make up for the missing data and then output it; Compare the data transmission instability coefficient of the sensor with the preset data transmission instability coefficient threshold to determine whether the data transmission of the sensor is stable; if the transmission is stable, execute the next step; if the transmission is unstable, process the sensor data and then execute the next step; The processed sensors transmit the boiler operating parameters in real time, and continuously adjust and optimize the model on the steam-water side to simulate the boiler operating status and control the specific values ​​of the boiler operating parameters.

[0006] A further improvement of the present invention is that the data transmission delay coefficient of the sensor is obtained by obtaining the transmission data time of each sensor and the preset data transmission time interval, including: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; The preset data transmission time interval is marked as , the data transmission time interval The data transmission time interval is compared with the preset data transmission time interval, and the data transmission time interval greater than the preset data transmission time interval is Data transmission interval Re-label and mark as , =1, 2, 3, 4, ..., , is an integer; Calculate the data transmission delay coefficient of the sensor, the calculation formula is: ; In the formula, is the data transmission delay coefficient.

[0007] A further improvement of the present invention is that comparing the data transmission delay coefficient of the sensor with a preset data transmission delay coefficient threshold, and determining whether the data transmission of the sensor is delayed includes: If the data transmission delay coefficient of the sensor is less than the preset data transmission delay coefficient threshold, it means that there is no delay in the data transmission of the sensor, and the boiler operation parameters are directly transmitted in real time according to the sensor, and the model of the steam-water side is continuously adjusted and optimized to simulate the state of boiler operation and control the specific values ​​of the boiler operation parameters; If the data transmission delay coefficient of the sensor is not less than the preset data transmission delay coefficient threshold, it means that the data transmission of the sensor is delayed. The missing real-time data is generated through the interpolation algorithm to make up for the information gap caused by the delay; and the real-time data smoothing algorithm is introduced to reduce the sensor data transmission delay.

[0008] A further improvement of the present invention is that the data transmission instability coefficient of the sensor is obtained according to the data transmission time of each sensor, including: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; Calculation of data transmission instability coefficient , the calculation formula is:

[0009] in, is the average value of the transmission time interval sequence, and the expression obtained is: .

[0010] A further improvement of the present invention is that the data transmission instability coefficient of the sensor is compared with a preset data transmission instability coefficient threshold to determine whether the data transmission of the sensor is stable, and corresponding processing measures are taken, including: If the data transmission instability coefficient of the sensor is less than the preset data transmission instability coefficient threshold, it means that the data transmission of the sensor is not unstable, and the boiler operation parameters are directly transmitted in real time according to the sensor, and the model of the steam-water side is continuously adjusted and optimized to simulate the state of boiler operation and control the specific values ​​of the boiler operation parameters; If the data transmission instability coefficient of the sensor is not less than the preset data transmission instability coefficient threshold, it means that the data transmission of the sensor is unstable. The sensor data is processed using the sliding average method and Kalman filtering, and the sampling frequency of the internal operating parameters of the boiler is reduced.

[0011] The two-dimensional mechanism modeling system of boiler steam-water side based on CFD-AI includes: The first data acquisition module is used to acquire the total types of sensors during boiler operation, and for each type of sensor, acquire the transmission data time of each sensor and a preset data transmission time interval to obtain the data transmission delay coefficient of the sensor; A second data acquisition module is used to acquire the data transmission time of each sensor of each type, and obtain the data transmission instability coefficient of the sensor according to the data transmission time of each sensor; The first comparison module is used to compare the data transmission delay coefficient of the sensor with a preset data transmission delay coefficient threshold to determine whether the data transmission of the sensor is delayed. If there is no delay, the sensor data is directly output; if there is an extension, the missing data is compensated and then output; The second comparison module is used to compare the data transmission instability coefficient of the sensor with a preset data transmission instability coefficient threshold to determine whether the data transmission of the sensor is stable; if the transmission is stable, execute the next step; if the transmission is unstable, execute the next step after processing the sensor data; The execution module is used to transmit the processed sensor data to the boiler operating parameters in real time, and continuously adjust and optimize the model on the steam-water side, simulate the state of boiler operation, and control the specific values ​​of boiler operating parameters.

[0012] A further improvement of the present invention is that, in the first data acquisition module, obtaining the transmission data time of each sensor and the preset data transmission time interval to obtain the data transmission delay coefficient of the sensor includes: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; The preset data transmission time interval is marked as , the data transmission time interval The data transmission time interval is compared with the preset data transmission time interval, and the data transmission time interval greater than the preset data transmission time interval is Data transmission interval Re-label and mark as , =1, 2, 3, 4, ..., , is an integer; Calculate the data transmission delay coefficient of the sensor, the calculation formula is: ; In the formula, is the data transmission delay coefficient.

[0013] A further improvement of the present invention is that, in the first comparison module, comparing the data transmission delay coefficient of the sensor with a preset data transmission delay coefficient threshold, and determining whether the data transmission of the sensor is delayed includes: If the data transmission delay coefficient of the sensor is less than the preset data transmission delay coefficient threshold, it means that there is no delay in the data transmission of the sensor, and the boiler operation parameters are directly transmitted in real time according to the sensor, and the model of the steam-water side is continuously adjusted and optimized to simulate the state of boiler operation and control the specific values ​​of the boiler operation parameters; If the data transmission delay coefficient of the sensor is not less than the preset data transmission delay coefficient threshold, it means that the data transmission of the sensor is delayed. The missing real-time data is generated through the interpolation algorithm to make up for the information gap caused by the delay; and the real-time data smoothing algorithm is introduced to reduce the sensor data transmission delay.

[0014] A further improvement of the present invention is that, in the second data acquisition module, obtaining the data transmission instability coefficient of the sensor according to the data transmission time of each sensor includes: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; Calculation of data transmission instability coefficient , the calculation formula is:

[0015] in, is the average value of the transmission time interval sequence, and the expression obtained is: .

[0016] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the two-dimensional mechanism modeling method of boiler steam-water side based on CFD-AI.

[0017] Compared with the prior art, the present invention has at least the following beneficial technical effects: The present invention proposes a two-dimensional mechanism modeling method for the steam-water side of a boiler based on CFD-AI. During boiler operation, the total types of sensors are obtained. For each type of sensor, the data transmission delay coefficient and the data transmission instability coefficient of the sensor are calculated, and compared with the preset data transmission delay coefficient threshold and the preset data transmission delay coefficient threshold, respectively, to determine whether the data transmission of the sensor is delayed and whether it is stable, and take corresponding processing measures; the processed sensors transmit the boiler operating parameters in real time, and continuously adjust and optimize the model of the steam-water side, simulate the state of boiler operation, and control the specific values ​​of the boiler operating parameters, which can optimize the sensor data transmission delay and instability. The processed sensors transmit the boiler operating parameters in real time, and continuously adjust and optimize the model of the steam-water side, simulate the state of boiler operation, and control the specific values ​​of the boiler operating parameters, thereby reducing the impact on real-time control decisions and ensuring the optimization effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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.

[0019] Figure 1 This is a flow chart of the two-dimensional mechanism modeling method of the boiler steam-water side based on CFD-AI.

[0020] Figure 2 This is the structural block diagram of the two-dimensional mechanism modeling system of the boiler steam-water side based on CFD-AI. DETAILED DESCRIPTION

[0021] 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.

[0022] 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.

[0023] 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.

[0024] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] 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.

[0026] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0027] Example 1 The embodiment of the present invention provides a two-dimensional mechanism modeling method for the steam-water side of a boiler based on CFD-AI. Figure 1 , Figure 1 A flow chart of a two-dimensional mechanism modeling method for boiler steam-water side based on CFD-AI provided in an embodiment of the present invention. The method comprises the following steps: During boiler operation, the total types of sensors are obtained, and for each type of sensor, the transmission data time of each sensor and the preset data transmission time interval are obtained to obtain the data transmission delay coefficient of the sensor; For each type of sensor, the data transmission time of each sensor is obtained, and the data transmission instability coefficient of the sensor is obtained according to the data transmission time of each sensor; Compare the data transmission delay coefficient of the sensor with the preset data transmission delay coefficient threshold, determine whether the data transmission of the sensor is delayed, and take corresponding processing measures; Compare the data transmission instability coefficient of the sensor with the preset data transmission instability coefficient threshold to determine whether the data transmission of the sensor is stable and take corresponding processing measures; The processed sensors transmit the boiler operating parameters in real time, and continuously adjust and optimize the model on the steam-water side to simulate the boiler operating status and control the specific values ​​of the boiler operating parameters.

[0028] Based on the two-dimensional mechanism modeling method of the boiler steam-water side based on CFD-AI provided in an embodiment of the present invention, through the above method, in actual boiler operation, the sensor data transmission delay and instability can be optimized, the processed sensor transmits the boiler operating parameters in real time, and continuously adjusts and optimizes the steam-water side model to simulate the state of boiler operation and control the specific values ​​of the boiler operating parameters, thereby reducing the impact on real-time control decisions and ensuring the optimization effect.

[0029] In one embodiment, obtaining the data transmission time of each sensor and the preset data transmission time interval to obtain the data transmission delay coefficient of the sensor includes: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; The preset data transmission time interval is marked as , the data transmission time interval The data transmission time interval is compared with the preset data transmission time interval, and the data transmission time interval greater than the preset data transmission time interval is Re-label and mark as , =1, 2, 3, 4, ..., , is an integer; Calculate the data transmission delay coefficient of the sensor, the calculation formula is: ; In the formula, is the data transmission delay coefficient.

[0030] It should be noted that all sensor types in the boiler system (such as temperature sensors, pressure sensors, flow sensors, etc.) are identified, and the transmission data time of each type of sensor is recorded in real time, and the preset data transmission time interval (such as 0.5 seconds, 1 second, etc.) is stored. The specific preset data transmission time interval depends on the actual situation and is not limited or elaborated.

[0031] It should be noted that the data transmission delay coefficient of the sensor is used to measure the impact of the sensor data transmission delay in the actual boiler operation. The larger the data transmission delay coefficient of the sensor, the more likely it is to affect the real-time control decision, and thus affect the optimization effect of the system. The reason is that the real-time control system needs to rely on sensor data to provide accurate and timely boiler operation parameters, such as temperature, pressure and flow, and these parameters are the core inputs of the control algorithm and optimization strategy. Once the data transmission delay is too large, the control system may not be able to respond to changes in the boiler's operating status in a timely manner, resulting in delayed decision adjustments, which in turn affects the balance of temperature and pressure distribution, and may even cause safety hazards in boiler operation. In addition, the accumulation of delays will also interfere with the dynamic optimization process, resulting in reduced combustion efficiency, increased energy consumption, and even weakening the system's sensitivity to abnormal conditions, which significantly reduces the effect of fault prediction and prevention. Therefore, timely evaluation and optimization of sensor data transmission delays are crucial to ensure system stability and improve overall operating efficiency.

[0032] In one embodiment, obtaining the data transmission instability coefficient of each sensor according to the data transmission time of each sensor includes: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; Calculation of data transmission instability coefficient , the calculation formula is:

[0033] in, is the average value of the transmission time interval sequence, and the expression obtained is: .

[0034] It should be noted that the sensor data transmission instability coefficient is used to measure the impact of sensor data transmission instability in actual boiler operation. The larger the sensor data transmission instability coefficient, the more likely it is to affect the real-time control decision, and then affect the optimization effect of the system. The reason is that the real-time control system needs to adjust the boiler operation parameters in time based on the stable input of sensor data, and the instability of the transmission time interval will lead to uneven distribution of the time points of the collected data, affecting the continuity and integrity of the data. This will not only weaken the control system's accurate perception of the boiler's operating status, but may also lead to model prediction deviations and feedback delays in the optimization algorithm, thereby affecting the dynamic adjustment of operating parameters. In addition, unstable data transmission may also cause information loss or redundancy at critical moments, reduce the accuracy of fault prediction and system optimization, and further increase the safety risks in boiler operation. Therefore, evaluating and reducing the instability of sensor data transmission is of great significance to ensure the efficient and safe operation of the system.

[0035] In one embodiment, comparing the data transmission delay coefficient of the sensor with a preset data transmission delay coefficient threshold to determine whether the data transmission of the sensor is delayed includes: If the data transmission delay coefficient of the sensor is less than the preset data transmission delay coefficient threshold, it means that there is no delay in the data transmission of the sensor, and the boiler operation parameters are directly transmitted in real time according to the sensor, and the model of the steam-water side is continuously adjusted and optimized to simulate the state of boiler operation and control the specific values ​​of the boiler operation parameters; If the data transmission delay coefficient of the sensor is not less than the preset data transmission delay coefficient threshold, it means that the data transmission of the sensor is delayed and corresponding processing measures need to be taken.

[0036] In one embodiment, if the data transmission delay coefficient of the sensor is not less than a preset data transmission delay coefficient threshold, it means that the data transmission of the sensor is delayed, and corresponding processing measures need to be taken, specifically: The missing real-time data is generated through the interpolation algorithm to make up for the information gap caused by the delay; and the real-time data smoothing algorithm is introduced to reduce the sensor data transmission delay.

[0037] It should be noted that if the delay coefficient is not less than the preset threshold, it indicates that there is a significant delay in the sensor data transmission. At this time, a series of processing measures need to be taken to reduce the impact of the delay on system optimization and control. Specific measures include: interpolation algorithm or historical data trend prediction to generate missing data: For example, assuming that there is a transmission delay in the boiler's pressure sensor, the control system may receive longer data intervals, resulting in the system being unable to grasp the boiler's pressure status in real time. At this time, the interpolation algorithm can be used to infer the pressure value within the delay period based on the previous and subsequent pressure data, or the change trend of historical data can be used to predict the pressure value during this period through regression analysis. This ensures that the control system can still make reasonable adjustment decisions when there is no real-time data input.

[0038] Enable redundant sensors or backup data channels: Assume that the boiler's fuel flow sensor has a long data transmission delay, affecting the accuracy of combustion regulation. In order to prevent a single sensor failure or delay from affecting system control, the boiler can be configured with multiple redundant sensors or backup data channels. When the data transmission of the main sensor is delayed, the system can automatically switch to the backup sensor or channel to ensure that the control system can continue to obtain accurate data input, thereby maintaining the normal operation of the boiler.

[0039] Introducing real-time data smoothing algorithm: Assume that the data transmission of the boiler temperature sensor is unstable, resulting in large fluctuations in the collected data. In this case, the real-time data smoothing algorithm can be applied to effectively remove sudden fluctuations, so that the system can obtain more stable and continuous data input, thereby avoiding control decision errors caused by delayed data. In this way, the control system can make more stable boiler state adjustments without being affected by transmission delays.

[0040] The implementation of these processing measures can effectively alleviate the problems caused by sensor data transmission delays and ensure the reliability and stability of the boiler control system in real-time operation.

[0041] In one embodiment, the data transmission instability coefficient of the sensor is compared with a preset data transmission instability coefficient threshold to determine whether the data transmission of the sensor is stable, and taking corresponding processing measures includes: If the data transmission instability coefficient of the sensor is less than the preset data transmission instability coefficient threshold, it means that the data transmission of the sensor is not unstable, and the boiler operation parameters are directly transmitted in real time according to the sensor, and the model of the steam-water side is continuously adjusted and optimized to simulate the state of boiler operation and control the specific values ​​of the boiler operation parameters; If the data transmission instability coefficient of the sensor is not less than the preset data transmission instability coefficient threshold, it means that the data transmission of the sensor is unstable and corresponding processing measures need to be taken.

[0042] In one embodiment, if the data transmission instability coefficient of the sensor is not less than a preset data transmission instability coefficient threshold, it means that the data transmission of the sensor is unstable and corresponding processing measures need to be taken: The sliding average method and Kalman filter are used to process the sensor and reduce the sampling frequency of the internal operating parameters of the boiler.

[0043] It should be noted that the sliding average method is a simple and effective smoothing technology. By averaging the sensor data within a time window, it can effectively reduce the impact of short-term fluctuations and outliers. For the sensor data in the boiler, there are often sudden interference or short-term fluctuations. The sliding average method can eliminate these instantaneous fluctuations, make the data stable, and reduce the impact of unstable sensor data on the boiler control system. For example, if the boiler's pressure sensor generates instantaneous abnormal data due to external noise, the sliding average method can "suppress" these abnormal data through the average value of multiple samples, thereby ensuring that the system's decision-making is more stable. In addition, the sliding average method is simple to calculate and has a small amount of calculation. It is suitable for boiler control systems that require real-time response and can effectively reduce the negative impact of data fluctuations on control effects.

[0044] Application of Kalman filter and its reasons: Kalman filtering is a recursive filtering algorithm based on a dynamic system model that can make more accurate estimates of sensor data in the presence of noise interference and unstable data. Compared with the sliding average method, Kalman filtering can combine the sensor's measurement value and the system's dynamic model to smooth unstable data by estimating the optimal value of the current system state. Kalman filtering is particularly suitable for data processing where there are changes in system states and are affected by noise. In boiler control systems, Kalman filtering can automatically distinguish sensor noise from real signals by continuously adjusting the weights of the filter, thereby improving data accuracy. Through Kalman filtering, the boiler system can predict the future system state based on the current unstable data, and make corresponding adjustments based on the prediction results to ensure that various parameters of the boiler, such as pressure and temperature, operate within a stable range.

[0045] Reasons and benefits of reducing the sampling frequency of boiler internal operating parameters: When the sensor is unstable, the system often faces frequent data fluctuations, which may cause the boiler control system to overreact and frequently adjust the control parameters, thus affecting the overall stability of the system. Reducing the sampling frequency can reduce unnecessary adjustments caused by data fluctuations and avoid the system from making excessive control decisions when the data is unstable. By reducing the sampling frequency, the system can process data more smoothly, reduce the suddenness of the system response, and adjust the control strategy over a longer period of time, thereby achieving more stable boiler operation. For example, in a temperature control system, too high a sampling frequency may cause the boiler temperature regulator to be adjusted frequently, resulting in excessive fluctuations. By reducing the sampling frequency, the boiler control system can avoid frequent adjustment behaviors, so that the boiler temperature is maintained in a relatively stable state, ensuring that the boiler operates more efficiently and safely. In addition, reducing the sampling frequency can also reduce the system's computational burden and increase processing speed, especially when multiple sensor data are unstable, which can effectively improve the overall responsiveness of the system.

[0046] By combining the sliding average method, Kalman filtering and adjusting the sampling frequency, the boiler control system can better maintain the stability of the system when facing unstable sensor data, ensuring that the boiler operates efficiently and safely in various working environments.

[0047] It should be noted that the processed sensors transmit the boiler operating parameters in real time, and continuously adjust and optimize the model on the steam-water side, simulate the state of boiler operation, and control the specific values ​​of the boiler operating parameters. Specifically, combined with the boundary conditions provided by the CFD-AI model and the coupling of the system model, the system will continuously adjust the boiler operating parameters according to the real-time transmitted data, especially the optimization of the control on the steam-water side. This includes the adjustment of key parameters such as water flow rate and cooling water temperature. Through precise simulation and adjustment, the system can better control the temperature and pressure distribution inside the boiler, avoid dangerous situations such as overheating or overcooling, and ensure that the boiler operates in a safe and stable state.

[0048] Example 2 like Figure 2 As shown, the boiler steam-water side two-dimensional mechanism modeling system based on CFD-AI provided by the present invention includes: The first data acquisition module is used to acquire the total types of sensors during boiler operation, and for each type of sensor, acquire the transmission data time of each sensor and a preset data transmission time interval to obtain the data transmission delay coefficient of the sensor; A second data acquisition module is used to acquire the data transmission time of each sensor of each type, and obtain the data transmission instability coefficient of the sensor according to the data transmission time of each sensor; The first comparison module is used to compare the data transmission delay coefficient of the sensor with a preset data transmission delay coefficient threshold to determine whether the data transmission of the sensor is delayed. If there is no delay, the sensor data is directly output; if there is an extension, the missing data is compensated and then output; The second comparison module is used to compare the data transmission instability coefficient of the sensor with a preset data transmission instability coefficient threshold to determine whether the data transmission of the sensor is stable; if the transmission is stable, execute the next step; if the transmission is unstable, execute the next step after processing the sensor data; The execution module is used to transmit the processed sensor data to the boiler operating parameters in real time, and continuously adjust and optimize the model on the steam-water side, simulate the state of boiler operation, and control the specific values ​​of boiler operating parameters.

[0049] 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, it implements the steps of the two-dimensional mechanism modeling method of the boiler steam-water side based on CFD-AI.

[0050] 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.

[0051] 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 boxes.

[0052] 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 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0053] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0054] 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.

[0055] 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 two-dimensional mechanism modeling method for the steam-water side of a boiler based on CFD-AI, characterized in that: The following steps are involved: During boiler operation, the total types of sensors are obtained, and for each type of sensor, the transmission data time of each sensor and the preset data transmission time interval are obtained to obtain the data transmission delay coefficient of the sensor; For each type of sensor, the data transmission time of each sensor is obtained, and the data transmission instability coefficient of the sensor is obtained according to the data transmission time of each sensor; Compare the data transmission delay coefficient of the sensor with the preset data transmission delay coefficient threshold to determine whether the data transmission of the sensor is delayed. If there is no delay, directly output the sensor data; if there is an extension, make up for the missing data and then output it; Compare the data transmission instability coefficient of the sensor with a preset data transmission instability coefficient threshold to determine whether the data transmission of the sensor is stable; If the transmission is stable, proceed to the next step; If the transmission is unstable, the next step is executed after processing the sensor data; The processed sensors transmit the boiler operating parameters in real time, and continuously adjust and optimize the model on the steam-water side to simulate the boiler operating status and control the specific values ​​of the boiler operating parameters.

2. The two-dimensional mechanism modeling method of boiler steam-water side based on CFD-AI according to claim 1 is characterized in that: The data transmission delay coefficient of the sensor obtained by obtaining the transmission data time of each sensor and the preset data transmission time interval includes: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; The preset data transmission time interval is marked as , the data transmission time interval The data transmission time interval is compared with the preset data transmission time interval, and the data transmission time interval greater than the preset data transmission time interval is Data transmission interval Re-label and mark as , =1, 2, 3, 4, ..., , is an integer; Calculate the data transmission delay coefficient of the sensor, the calculation formula is: ; In the formula, is the data transmission delay coefficient.

3. The two-dimensional mechanism modeling method of boiler steam-water side based on CFD-AI according to claim 2 is characterized in that: Comparing the data transmission delay coefficient of the sensor with a preset data transmission delay coefficient threshold to determine whether the data transmission of the sensor is delayed includes: If the data transmission delay coefficient of the sensor is less than the preset data transmission delay coefficient threshold, it means that there is no delay in the data transmission of the sensor, and the boiler operation parameters are directly transmitted in real time according to the sensor, and the model of the steam-water side is continuously adjusted and optimized to simulate the state of boiler operation and control the specific values ​​of the boiler operation parameters; If the data transmission delay coefficient of the sensor is not less than the preset data transmission delay coefficient threshold, it means that the data transmission of the sensor is delayed. The missing real-time data is generated through the interpolation algorithm to make up for the information gap caused by the delay; and the real-time data smoothing algorithm is introduced to reduce the sensor data transmission delay.

4. The two-dimensional mechanism modeling method of boiler steam-water side based on CFD-AI according to claim 1 is characterized in that: The data transmission instability coefficient of the sensor obtained according to the data transmission time of each sensor includes: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; Calculation of data transmission instability coefficient , the calculation formula is: in, is the average value of the transmission time interval sequence, and the expression obtained is: .

5. The two-dimensional mechanism modeling method of boiler steam-water side based on CFD-AI according to claim 4 is characterized in that: Compare the sensor's data transmission instability coefficient with the preset data transmission instability coefficient threshold to determine whether the sensor's data transmission is stable. Take corresponding processing measures, including: If the data transmission instability coefficient of the sensor is less than the preset data transmission instability coefficient threshold, it means that the data transmission of the sensor is not unstable, and the boiler operation parameters are directly transmitted in real time according to the sensor, and the model of the steam-water side is continuously adjusted and optimized to simulate the state of boiler operation and control the specific values ​​of the boiler operation parameters; If the data transmission instability coefficient of the sensor is not less than the preset data transmission instability coefficient threshold, it means that the data transmission of the sensor is unstable. The sensor data is processed using the sliding average method and Kalman filtering, and the sampling frequency of the internal operating parameters of the boiler is reduced.

6. The two-dimensional mechanism modeling system of boiler steam-water side based on CFD-AI is characterized by: include: The first data acquisition module is used to acquire the total types of sensors during boiler operation, and for each type of sensor, acquire the transmission data time of each sensor and a preset data transmission time interval to obtain the data transmission delay coefficient of the sensor; A second data acquisition module is used to acquire the data transmission time of each sensor of each type, and obtain the data transmission instability coefficient of the sensor according to the data transmission time of each sensor; The first comparison module is used to compare the data transmission delay coefficient of the sensor with a preset data transmission delay coefficient threshold to determine whether the data transmission of the sensor is delayed. If there is no delay, the sensor data is directly output; if there is an extension, the missing data is compensated and then output; A second comparison module is used to compare the data transmission instability coefficient of the sensor with a preset data transmission instability coefficient threshold to determine whether the data transmission of the sensor is stable; If the transmission is stable, proceed to the next step; If the transmission is unstable, the next step is executed after processing the sensor data; The execution module is used to transmit the processed sensor data to the boiler operating parameters in real time, and continuously adjust and optimize the model on the steam-water side, simulate the state of boiler operation, and control the specific values ​​of boiler operating parameters.

7. The two-dimensional mechanism modeling system of boiler steam-water side based on CFD-AI according to claim 6 is characterized in that: In the first data acquisition module, the data transmission delay coefficient of the sensor is obtained by acquiring the transmission data time of each sensor and the preset data transmission time interval, including: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; The preset data transmission time interval is marked as , the data transmission time interval The data transmission time interval is compared with the preset data transmission time interval, and the data transmission time interval greater than the preset data transmission time interval is Data transmission interval Re-label and mark as , =1, 2, 3, 4, ..., , is an integer; Calculate the data transmission delay coefficient of the sensor, the calculation formula is: ; In the formula, is the data transmission delay coefficient.

8. The two-dimensional mechanism modeling system of boiler steam-water side based on CFD-AI according to claim 7 is characterized in that: In the first comparison module, comparing the data transmission delay coefficient of the sensor with a preset data transmission delay coefficient threshold, and determining whether the data transmission of the sensor is delayed includes: If the data transmission delay coefficient of the sensor is less than the preset data transmission delay coefficient threshold, it means that there is no delay in the data transmission of the sensor, and the boiler operation parameters are directly transmitted in real time according to the sensor, and the model of the steam-water side is continuously adjusted and optimized to simulate the state of boiler operation and control the specific values ​​of the boiler operation parameters; If the data transmission delay coefficient of the sensor is not less than the preset data transmission delay coefficient threshold, it means that the data transmission of the sensor is delayed. The missing real-time data is generated through the interpolation algorithm to make up for the information gap caused by the delay; and the real-time data smoothing algorithm is introduced to reduce the sensor data transmission delay.

9. The two-dimensional mechanism modeling system of boiler steam-water side based on CFD-AI according to claim 6 is characterized in that: In the second data acquisition module, obtaining the data transmission instability coefficient of the sensor according to the data transmission time of each sensor includes: Sequence the timestamps actually corresponding to the transmission data of each sensor to obtain a data timestamp sequence; Calculate the difference between every two adjacent timestamps in the data timestamp sequence to obtain a transmission time interval sequence; The transmission time intervals in the transmission time interval sequence are marked as , a number indicating the order of the transmission time interval in the transmission time interval sequence, =1, 2, 3, 4, ..., , is a positive integer; Calculation of data transmission instability coefficient , the calculation formula is: in, is the average value of the transmission time interval sequence, and the expression obtained is: .

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the two-dimensional mechanism modeling method of the boiler steam-water side based on CFD-AI described in any one of claims 1 to 5 are implemented.

Images