Boiler heating surface state monitoring method and related equipment

Abstract

The invention discloses a boiler heating surface state monitoring method and related equipment, and aims to solve the technical problem of monitoring lag of the existing monitoring technology. The method comprises the following steps: acquiring data such as temperature field distribution, tube wall thickness change and ash deposition thickness in real time through a three-dimensional sensor array deployed on a boiler heating surface tube panel, and generating an original monitoring data set; the data are combined with real-time operation working condition parameters to construct a heat transfer dynamic reference model, and a temperature difference gradient index TGI representing the deterioration degree of the heating surface is calculated. Meanwhile, the TGI and historical damage data are input into a multi-physical field coupling model, a residual life prediction curve with a confidence interval is generated, and real-time and accurate monitoring of the state of the heating surface of the boiler is achieved. According to the method, through real-time data acquisition, dynamic model construction and intelligent prediction, monitoring blind areas are effectively reduced, the evaluation precision is improved, potential problems are warned in advance, and safe, stable and economical operation of the boiler is ensured.

Description

Technical Field

[0001] The present invention relates to the field of boiler status monitoring, and in particular to a boiler heating surface status monitoring method and related equipment. Background Art

[0002] During boiler operation, monitoring the status of the heating surface is crucial. Traditional manual inspection methods have significant lags, usually with a 6-8 hour monitoring blind spot. Ash and slag accumulation can only be detected when the thickness reaches 3mm or more, at which point the boiler's thermal efficiency may have dropped by 2-3%. At the same time, the existing DCS system can only monitor overall steam parameters and cannot accurately locate wear or corrosion hotspots in local tube rows. For example, in areas where the flow rate exceeds 12m / s, the tube wall may become thinner but difficult to detect in time. In addition, the single temperature monitoring method is greatly affected by combustion conditions, with a false alarm rate of up to 35% during load fluctuations, further highlighting the shortcomings of existing monitoring technology in terms of accuracy. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and related equipment for monitoring the state of a boiler heating surface, so as to overcome the technical problem of monitoring lag in existing monitoring technology.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] In a first aspect, the present invention provides a method for monitoring the state of a boiler heating surface, comprising:

[0006] The three-dimensional sensor array deployed on the heating surface tube panel collects and generates original monitoring data sets including temperature field distribution, tube wall thickness changes, and dust accumulation thickness;

[0007] Based on the original monitoring data set and real-time operating parameters, a dynamic heat transfer benchmark model is constructed to output the Temperature Gradient Index (TGI) that characterizes the degree of degradation of the heating surface.

[0008] Based on the TGI and historical damage data input into the multi-physics field coupling model, a remaining life prediction curve with confidence interval is generated to realize the condition monitoring of the heated surface.

[0009] The three-dimensional sensor array deployed on the heated surface tube panel includes:

[0010] MEMS temperature sensors arranged at a spacing of 500-800mm;

[0011] Pulsed eddy current array probe for pipe wall thickness monitoring;

[0012] Flue gas side laser scattering dust accumulation monitor.

[0013] The MEMS temperature sensor is embedded and its head is flush with the outer surface of the pipe wall. The installation spacing is set dynamically according to the flow rate of the pipe panel:

[0014] Areas with a flow rate of ≤10m / s are arranged at a spacing of 800mm;

[0015] Areas with flow rates greater than 10m / s are arranged at intervals of 500mm.

[0016] Based on the original monitoring data set and real-time operating parameters, a dynamic heat transfer benchmark model is constructed to output the temperature gradient index (TGI) that characterizes the degree of degradation of the heating surface, including:

[0017] A digital twin heat transfer model is established based on real-time combustion parameters and steam flow, and the theoretical wall temperature distribution is output;

[0018] Calculate the temperature gradient index TGI = Σ(ΔT_measured / ΔT_theoretical);

[0019] When TGI>1.15 and lasts for ≥10 minutes, the dust accumulation warning signal is triggered.

[0020] The multiphysics coupled model includes:

[0021] High temperature creep damage calculation module based on Larson-Miller parameters;

[0022] The model is trained using historical failure data processed by LSTM neural network;

[0023] The confidence interval of the output remaining life prediction curve is a 95% probability interval.

[0024] Furthermore, the data collection frequency is dynamically adjusted according to the TGI value and the pipe wall thickness change rate when collecting and generating the original monitoring data set:

[0025] When TGI≤1.1 and the tube wall thickness change rate is less than 0.01mm / h, maintain the 1Hz reference sampling frequency;

[0026] When TGI>1.1 or the pipe wall thickness change rate is ≥0.01mm / h, the sampling frequency of the three-dimensional sensor array is increased to 10Hz.

[0027] Furthermore, it also includes deploying edge computing equipment at the boiler platform layer, which:

[0028] With IP67 protection grade and 650℃ high temperature resistance;

[0029] Integrated self-learning algorithm to update the heat transfer dynamic benchmark model every 72 hours based on combustion adjustment data;

[0030] The monitoring data is transmitted via a hybrid communication protocol of optical fiber and LoRa.

[0031] In a second aspect, the present invention provides a boiler heating surface status monitoring system, comprising:

[0032] The data acquisition module is used to collect and generate original monitoring data sets including temperature field distribution, tube wall thickness changes, and dust accumulation thickness through the three-dimensional sensor array deployed on the heating surface tube panels;

[0033] The dynamic model construction module is used to build a dynamic heat transfer benchmark model based on the original monitoring data set and real-time operating parameters, and output the temperature gradient index (TGI) that characterizes the degree of degradation of the heating surface;

[0034] The prediction output module is used to input the multi-physics field coupling model based on TGI and historical damage data to generate a remaining life prediction curve with a confidence interval, thereby realizing condition monitoring of the heated surface.

[0035] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for monitoring the status of a boiler heating surface are implemented.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which implements the steps of the above-mentioned method for monitoring the state of a boiler heating surface when executed by a processor.

[0037] Compared with the prior art, the present invention has the following beneficial technical effects:

[0038] This solution deploys a three-dimensional sensor array on the heating surface tube panel to collect key data such as temperature field distribution, tube wall thickness changes, and dust accumulation thickness in real time to form an original monitoring data set. A dynamic heat transfer benchmark model is constructed in combination with real-time operating condition parameters, and the temperature gradient index (TGI) that characterizes the degree of degradation of the heating surface is calculated to achieve real-time quantitative assessment of the heating surface state. At the same time, the TGI and historical damage data are input into a multi-physics field coupling model to generate a remaining life prediction curve with confidence intervals, providing forward-looking condition monitoring. These measures work together to effectively reduce monitoring blind spots, improve assessment accuracy, and provide early warning of potential problems, thereby overcoming the lag of existing monitoring technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of a method for monitoring the state of a boiler heating surface according to an embodiment of the present invention.

[0040] Figure 2 This is a flow chart of a boiler heating surface status monitoring process in an embodiment of the present invention.

[0041] Figure 3Schematic diagram of a boiler heating surface status monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] During boiler operation, monitoring the status of the heating surface is crucial. Traditional manual inspection methods have significant lags, usually with a 6-8 hour monitoring blind spot. Ash and slag accumulation can only be detected when the thickness reaches 3mm or more, at which point the boiler's thermal efficiency may have dropped by 2-3%. At the same time, the existing DCS system can only monitor overall steam parameters and cannot accurately locate wear or corrosion hotspots in local tube rows. For example, in areas where the flow rate exceeds 12m / s, the tube wall may become thinner but difficult to detect in time. In addition, the single temperature monitoring method is greatly affected by combustion conditions, with a false alarm rate of up to 35% during load fluctuations, further highlighting the shortcomings of existing monitoring technology in terms of accuracy.

[0043] Based on the above background, the present invention proposes a boiler heating surface condition monitoring method and related equipment. By proposing a dynamic reference value calculation method for the inter-tube temperature field, the influence of load disturbance is eliminated. A multi-physics field coupling damage model is developed to achieve a mode transition from "threshold alarm" to "trend warning", solving the technical problem of monitoring lag in existing monitoring technologies.

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0045] Reference Figure 1 FIG. 1 is a specific embodiment of the method for monitoring the state of a boiler heating surface provided by the present invention, comprising:

[0046] S1, through the three-dimensional sensor array deployed on the heating surface tube panel, collects and generates the original monitoring data set including temperature field distribution, tube wall thickness change and dust accumulation thickness;

[0047] S2, based on the original monitoring data set and real-time operating parameters, builds a heat transfer dynamic benchmark model and outputs the temperature gradient index (TGI) that characterizes the degree of degradation of the heating surface;

[0048] S3, based on the TGI and historical damage data input into the multi-physics field coupling model, generates a remaining life prediction curve with a confidence interval to achieve condition monitoring of the heated surface.

[0049] Specifically, S1 collects and generates original monitoring data sets including temperature field distribution, tube wall thickness changes, and dust accumulation thickness through a three-dimensional sensor array deployed on the heated surface tube panel. The three-dimensional sensor array deployed on the heated surface tube panel includes:

[0050] MEMS temperature sensors arranged at a spacing of 500-800mm;

[0051] Pulsed eddy current array probe for pipe wall thickness monitoring;

[0052] Flue gas side laser scattering dust accumulation monitor.

[0053] The MEMS temperature sensor is embedded, with its head flush with the outer surface of the pipe wall. The installation spacing is dynamically set according to the flow rate of the pipe panel:

[0054] Areas with a flow rate of ≤10m / s are arranged at a spacing of 800mm;

[0055] Areas with flow rates greater than 10m / s are arranged at intervals of 500mm.

[0056] When installing the MEMS temperature sensor, first use laser drilling technology to open a hole on the surface of the tube panel with a hole diameter of Φ3mm and a depth of 2mm. Then use high-temperature ceramic glue (temperature resistance ≥800℃) to fix the sensor to ensure heat conduction efficiency.

[0057] Deploying a three-dimensional sensor array on the boiler's heating surface tube panels is fundamental to achieving accurate condition monitoring. This array includes multiple sensor types to meet diverse monitoring needs. MEMS temperature sensors are arranged according to specific rules: in areas with flow velocities ≤10 m / s, they are installed at 800 mm intervals; in areas with flow velocities greater than 10 m / s, the spacing is shortened to 500 mm. This design ensures sufficiently accurate temperature data under varying flow conditions. All MEMS temperature sensors are embedded, with their heads flush with the outer surface of the tube wall, minimizing interference with fluid flow and reducing the risk of sensor wear. In addition to temperature monitoring, pipe wall thickness monitoring utilizes a pulsed eddy current array probe, which can penetrate the pipe material and accurately detect changes in wall thickness. A flue gas-side laser scattering ash deposit monitor is used to measure ash thickness. Its operating principle is to use laser scattering technology to determine ash thickness by analyzing the characteristics of scattered light. These sensors work together to generate original monitoring data sets that include temperature field distribution, pipe wall thickness changes, and dust accumulation thickness, providing a comprehensive and accurate data foundation for subsequent data analysis and model building.

[0058] Specifically, S2 builds a dynamic heat transfer benchmark model based on the original monitoring data set and real-time operating parameters, and outputs the temperature gradient index (TGI) that characterizes the degree of degradation of the heating surface, including:

[0059] A digital twin heat transfer model is established based on real-time combustion parameters and steam flow, and the theoretical wall temperature distribution is output;

[0060] Calculate the temperature gradient index TGI = Σ(ΔT_measured / ΔT_theoretical);

[0061] When TGI>1.15 and lasts for ≥10 minutes, the dust accumulation warning signal is triggered.

[0062] Reference Figure 2 The figure shows the specific flow chart of this step. First, the combustion parameters (such as fuel flow, air flow, combustion temperature distribution) and steam flow data are collected in real time. These parameters are the basic inputs of the model.

[0063] Based on the collected combustion parameters, computational fluid dynamics (CFD) software is used to simulate the combustion process within the furnace. CFD simulations predict the flame temperature field and flue gas flow characteristics within the furnace by solving the Navier-Stokes equations and the energy equation.

[0064] The temperature field obtained from the CFD simulation is combined with the steam flow rate to construct a heat transfer model for the boiler's heating surface. This model must account for multiple heat transfer modes, including heat conduction through the tube wall, convection between the flue gas and the tube wall, and radiation.

[0065] The theoretical temperature distribution of the tube wall is calculated using the heat transfer formula:

[0066]

[0067] Among them, T 壁 is the tube wall temperature, T 烟气 is the flue gas temperature, q is the heat flux density, h is the convection heat transfer coefficient, r is the tube wall radius, and k is the thermal conductivity of the tube.

[0068] The calculated tube wall temperature distribution is used as the output of the digital twin heat transfer model, namely the theoretical wall temperature distribution.

[0069] The calculation process of the temperature gradient index (TGI) is as follows:

[0070] Collect the measured temperature T of each measuring point on the heating surface tube panel 实测 , obtain the theoretical temperature T of the corresponding measuring point from the digital twin heat transfer model 理论 . Calculate the temperature difference ratio of each measuring point:

[0071]

[0072] Among them, T 环境 is the ambient temperature.

[0073] The temperature gradient index (TGI) is obtained by summing the temperature difference ratios of all measuring points:

[0074]

[0075] Finally, a threshold is set: when the TGI exceeds 1.15 and lasts for 10 minutes or more, a dust accumulation warning signal is triggered. The warning signal is promptly notified to the operator through the monitoring system so that appropriate cleaning or adjustment measures can be taken.

[0076] Specifically, S3 inputs TGI and historical damage data into a multi-physics coupling model to generate a remaining life prediction curve with a confidence interval, enabling condition monitoring of the heated surface. The multi-physics coupling model includes:

[0077] High temperature creep damage calculation module based on Larson-Miller parameters;

[0078] The model is trained using historical failure data processed by LSTM neural network;

[0079] The confidence interval of the output remaining life prediction curve is a 95% probability interval.

[0080] The high-temperature creep damage calculation module is based on the Larson-Miller parameter, a widely used indicator in the field of high-temperature creep life prediction of materials. By integrating the material's characteristic parameters (such as activation energy, stress coefficient, etc.) and actual operating conditions (temperature, stress distribution, etc.), the Larson-Miller equation is used to calculate the cumulative damage caused by creep on the heated surface pipe in a high-temperature environment. Specifically, the Larson-Miller equation can be expressed as:

[0081] P=t×(C1+C2×T)×ln(σ / σ0)

[0082] Where P represents the creep damage parameter, t is time, T is temperature, σ is stress, C1 and C2 are material constants, and σ0 is the reference stress.

[0083] Through this module, the damage degree of the heated surface pipes under high temperature conditions can be accurately assessed, and basic data support can be provided for subsequent remaining life prediction.

[0084] The LSTM neural network module processes historical failure data. This data includes past damage records of heated surface pipes, failure times, and corresponding operating conditions. Through its unique memory units and gating mechanism, the LSTM neural network effectively learns long-term dependencies in time series data, thereby capturing the patterns and laws of damage evolution. The training process involves inputting historical data, updating hidden states, and iteratively calculating outputs. Ultimately, the model can accurately predict future damage trends based on new input data (such as TGI and current operating conditions).

[0085] During model training, a loss function (such as mean squared error) is used to measure the difference between the predicted results and actual historical data. A backpropagation algorithm is then used to continuously adjust network parameters to minimize this difference. A fully trained model can accurately predict the development of damage to heated surface pipes.

[0086] The multi-physics coupling model integrates the results of the high-temperature creep damage calculation module and the LSTM neural network module to generate a remaining life prediction curve. This curve reflects the remaining life trend of the heated surface pipe over a period of time.

[0087] Statistical analysis and uncertainty quantification methods are used to determine the confidence interval of the remaining life prediction curve. This confidence interval is calculated based on the variance and covariance matrix of the model's prediction results, typically using a 95% probability interval, indicating a 95% probability that the prediction curve will fall within this interval. This provides decision makers with a quantitative assessment of the reliability of the prediction results, helping to develop more scientific and reasonable maintenance and overhaul strategies.

[0088] When working, the TGI value calculated in real time and the historical damage data that has been sorted and pre-processed are first provided as input to the multi-physics field coupling model. The high-temperature creep damage calculation module in the model calculates creep damage based on the current working conditions (such as temperature, stress, etc.) and material characteristic parameters; the LSTM neural network module predicts the development trend of damage based on historical failure data and current input data. The results of the two modules are integrated within the model, comprehensively considering the impact of high-temperature creep, historical damage patterns and current working conditions on the remaining life of the heated surface pipe. Ultimately, the model generates a remaining life prediction curve and determines its 95% probability confidence interval. In this way, operation and maintenance personnel can understand the remaining service life of the heated surface in advance, provide a scientific basis for preventive maintenance, and thus achieve the purpose of condition monitoring and refined management.

[0089] The solution uses a three-dimensional sensor array to collect data on the temperature, tube wall thickness, and dust accumulation of the boiler's heating surface in real time, forming a comprehensive set of original monitoring data. At the same time, a dynamic heat transfer benchmark model is constructed based on real-time operating condition parameters, and the temperature gradient index (TGI) that characterizes the degradation of the heating surface is calculated to achieve real-time quantitative assessment of the state of the heating surface. When the TGI exceeds the set threshold, the system immediately triggers an early warning to ensure a rapid response at the early stage of the problem. Furthermore, the multi-physics field coupling model integrates real-time monitoring data with historical damage records to generate a remaining life prediction curve with a confidence interval, providing forward-looking guidance for maintenance. In addition, the solution introduces edge computing equipment to process monitoring data on-site and use self-learning algorithms to regularly update the model to ensure the real-time and accuracy of the monitoring system. These measures work together to effectively solve the lag problem existing in traditional monitoring technology and improve the safety and economy of boiler operation.

[0090] Preferably, in another specific embodiment of the boiler heating surface condition monitoring method provided by the present invention, the method further includes dynamically adjusting the data collection frequency according to the TGI value and the tube wall thickness change rate when collecting and generating the original monitoring data set:

[0091] When TGI≤1.1 and the tube wall thickness change rate is less than 0.01mm / h, maintain the 1Hz reference sampling frequency;

[0092] When TGI>1.1 or the pipe wall thickness change rate is ≥0.01mm / h, the sampling frequency of the three-dimensional sensor array is increased to 10Hz.

[0093] During boiler heating surface condition monitoring, the data collection frequency is dynamically adjusted based on the TGI value and the tube wall thickness change rate. This dynamic adjustment mechanism enables more efficient utilization of monitoring resources, ensuring that data collection is reduced when the heating surface condition is normal and increased when the condition is abnormal, thereby improving monitoring accuracy and timeliness. Specifically: When TGI ≤ 1.1 and the tube wall thickness change rate is less than 0.01 mm / h, a baseline sampling frequency of 1 Hz is maintained. This indicates that the heating surface condition is relatively stable and high-frequency data collection is not required, thus saving monitoring resources. When TGI > 1.1 or the tube wall thickness change rate is ≥ 0.01 mm / h, the sampling frequency of the three-dimensional sensor array is increased to 10 Hz. This indicates that the heating surface condition may be abnormal, requiring a higher data collection frequency to promptly capture state changes and provide richer data support for subsequent analysis and decision-making.

[0094] Preferably, another specific embodiment of the boiler heating surface condition monitoring method provided by the present invention further includes deploying edge computing devices with specific protection and performance characteristics at the boiler platform level to enhance the system's reliability and real-time performance. The edge computing devices, installed at the boiler platform level, have an IP67 protection rating, are dust-proof and can withstand short-term water immersion. They can also withstand temperatures up to 650°C, adapting to the harsh operating environment surrounding the boiler. The devices have a built-in self-learning algorithm that regularly (every 72 hours) updates the heat transfer dynamic benchmark model using the latest combustion adjustment data. This allows the model to reflect the actual operating conditions of the boiler heating surface in real time, improving monitoring accuracy and adaptability. The edge computing devices utilize a hybrid optical fiber and LoRa communication protocol to transmit monitoring data. Fiber optic communication, with its high speed, large capacity, and strong resistance to electromagnetic interference, is suitable for the rapid transmission of large amounts of data. The LoRa communication protocol, with its long-distance, low-power consumption advantages, enables reliable data transmission in complex industrial environments. The combination of these two ensures that monitoring data is transmitted to the monitoring center in real time and accurately.

[0095] In order to make the boiler heating surface status monitoring method provided by the present invention easier to understand, a specific implementation method combined with actual application scenarios is provided below. During the operation of the boiler in a certain power plant, the boiler heating surface status monitoring method and related equipment of the present invention were successfully applied. The boiler of this power plant has long had problems such as dust accumulation and wear on the heating surface. Traditional monitoring methods are unable to detect hidden dangers in time, resulting in multiple unplanned shutdowns. To solve this problem, the plant adopted the monitoring system of the present invention.

[0096] The power plant deployed a three-dimensional sensor array on the boiler heating surface tube panels, including MEMS temperature sensors, pulsed eddy current array probes, and laser scattering dust accumulation monitors. The MEMS temperature sensors were arranged at 800mm intervals in areas with flow velocities ≤10m / s and at 500mm intervals in areas with flow velocities >10m / s. These sensors were embedded in the system. This arrangement ensured accurate temperature data under varying flow rates while minimizing interference with fluid flow and reducing the risk of wear on the sensors.

[0097] The system collects data on temperature distribution, tube wall thickness changes, and ash accumulation in real time to generate a raw monitoring data set. On-site data processing is performed using edge computing devices deployed at the boiler platform level. These devices, with an IP67 protection rating and high-temperature resistance up to 650°C, ensure stable operation in harsh environments. The edge computing devices integrate a self-learning algorithm that updates the dynamic heat transfer benchmark model every 72 hours based on combustion adjustment data, ensuring that the model reflects the actual operating conditions of the boiler's heating surfaces in real time.

[0098] A dynamic heat transfer benchmark model is constructed based on real-time operating parameters, calculating the Temperature Gradient Index (TGI), which characterizes the degree of degradation of the heated surface. When the TGI exceeds 1.15 and persists for 10 minutes or longer, the system triggers a dust accumulation warning signal, notifying operators to take immediate action. The multi-physics coupling model integrates real-time monitoring data with historical damage records to generate a remaining life prediction curve with confidence intervals, providing a scientific basis for maintenance decisions.

[0099] Since the system was put into operation, the number of unplanned boiler shutdowns has decreased by more than 60%, boiler efficiency has increased by 0.8-1.2 percentage points, the warning time for tube burst accidents has been shortened to 72 hours, and the error in tube wall thinning detection has been controlled within ±0.3mm. These significant results verify the effectiveness and practicality of the method of the present invention.

[0100] Reference Figure 3 As shown, the present invention also provides a specific embodiment of a boiler heating surface status monitoring system, including:

[0101] The data acquisition module is used to collect and generate original monitoring data sets including temperature field distribution, tube wall thickness changes, and dust accumulation thickness through the three-dimensional sensor array deployed on the heating surface tube panels;

[0102] The dynamic model construction module is used to build a dynamic heat transfer benchmark model based on the original monitoring data set and real-time operating parameters, and output the temperature gradient index (TGI) that characterizes the degree of degradation of the heating surface;

[0103] The prediction output module is used to input the multi-physics field coupling model based on TGI and historical damage data to generate a remaining life prediction curve with a confidence interval, thereby realizing condition monitoring of the heated surface.

[0104] A specific embodiment of the present invention further provides a computer device. Specifically, the computer device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf field programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. It is the computing core and control core of the terminal and is suitable for implementing one or more instructions, specifically loading and executing one or more instructions to implement the corresponding method flow or corresponding function. The processor described in the embodiment of the present invention can be used to operate a boiler heating surface condition monitoring method, including the following steps: using a three-dimensional sensor array deployed on the heating surface tube panel, collecting and generating an original monitoring data set including temperature field distribution, tube wall thickness variation, and dust accumulation thickness; constructing a heat transfer dynamic benchmark model based on the original monitoring data set and real-time operating condition parameters, and outputting a temperature gradient index (TGI) that represents the degree of degradation of the heating surface; and inputting the TGI and historical damage data into a multi-physics field coupling model to generate a remaining life prediction curve with a confidence interval to achieve condition monitoring of the heating surface.

[0105] A storage medium is also provided in a specific embodiment of the present invention, specifically, a computer-readable storage medium, which is a memory device in a terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the relevant methods in the above embodiments; one or more instructions in the computer-readable storage medium are loaded by the processor and execute the following steps: through a three-dimensional sensor array deployed on the heating surface tube panel, an original monitoring data set including temperature field distribution, tube wall thickness change and dust accumulation thickness is collected and generated; based on the original monitoring data set and real-time operating condition parameters, a heat transfer dynamic benchmark model is constructed, and a temperature gradient index TGI representing the degree of deterioration of the heating surface is output; based on the TGI and historical damage data input into the multi-physics field coupling model, a remaining life prediction curve with a confidence interval is generated to realize the status monitoring of the heating surface.

[0106] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0110] 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 that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from all points of view, the embodiments should be regarded as illustrative and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and range of equivalents of the claims are included in the present invention. Any reference signs in the claims should not be construed as limiting the claim to which they relate.

[0111] In addition, it should be understood that although this specification describes the embodiments, not every embodiment contains only one independent technical solution. This description is for clarity only. Those skilled in the art should consider the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for the purpose of illustrating the technical concept of the present invention and cannot be used to limit the scope of protection of the present invention. Any changes made based on the technical solution in accordance with the technical concept proposed by the present invention fall within the scope of protection of the claims of the present invention.

Claims

1. A method for monitoring the state of a boiler heating surface, characterized in that: include: The three-dimensional sensor array deployed on the heating surface tube panel collects and generates original monitoring data sets including temperature field distribution, tube wall thickness changes, and dust accumulation thickness; Based on the original monitoring data set and real-time operating parameters, a heat transfer dynamic benchmark model is constructed to output the temperature gradient index (TGI) that characterizes the degree of degradation of the heating surface. Based on the TGI and historical damage data input into the multi-physics field coupling model, a remaining life prediction curve with confidence interval is generated to realize the condition monitoring of the heated surface.

2. A method for monitoring the state of a boiler heating surface according to claim 1, characterized in that: The three-dimensional sensor array deployed on the heated surface tube panel includes: MEMS temperature sensors arranged at a spacing of 500-800mm; Pulsed eddy current array probe for pipe wall thickness monitoring; Flue gas side laser scattering dust accumulation monitor.

3. A method for monitoring the state of a boiler heating surface according to claim 2, characterized in that: The MEMS temperature sensor is embedded and its head is flush with the outer surface of the pipe wall. The installation spacing is dynamically set according to the flow rate of the pipe panel: Areas with a flow rate of ≤10m / s are arranged at a spacing of 800mm; Areas with flow rates greater than 10m / s are arranged at intervals of 500mm.

4. A method for monitoring the state of a boiler heating surface according to claim 1, characterized in that: The heat transfer dynamic benchmark model is constructed based on the original monitoring data set and real-time operating condition parameters, and the temperature gradient index TGI representing the degree of degradation of the heating surface is output, including: A digital twin heat transfer model is established based on real-time combustion parameters and steam flow, and the theoretical wall temperature distribution is output; Calculate the temperature gradient index TGI = Σ(ΔT_measured / ΔT_theoretical); When TGI>1.15 and lasts for ≥10 minutes, the dust accumulation warning signal is triggered.

5. The method for monitoring the state of a boiler heating surface according to claim 1, characterized in that: The multi-physics coupling model includes: High temperature creep damage calculation module based on Larson-Miller parameters; The model is trained using historical failure data processed by LSTM neural network; The confidence interval of the output remaining life prediction curve is a 95% probability interval.

6. A method for monitoring the state of a boiler heating surface according to claim 1, characterized in that: It also includes dynamically adjusting the data collection frequency according to the TGI value and the pipe wall thickness change rate when collecting and generating the original monitoring data set: When TGI≤1.1 and the tube wall thickness change rate is less than 0.01mm / h, maintain the 1Hz reference sampling frequency; When TGI>1.1 or the pipe wall thickness change rate is ≥0.01mm / h, the sampling frequency of the three-dimensional sensor array is increased to 10Hz.

7. A method for monitoring the state of a boiler heating surface according to claim 1, characterized in that: It also includes deploying edge computing equipment at the boiler platform level, which: With IP67 protection grade and 650℃ high temperature resistance; Integrated self-learning algorithm to update the heat transfer dynamic benchmark model every 72 hours based on combustion adjustment data; The monitoring data is transmitted via a hybrid communication protocol of optical fiber and LoRa.

8. A boiler heating surface status monitoring system, characterized in that: include: The data acquisition module is used to collect and generate original monitoring data sets including temperature field distribution, tube wall thickness changes, and dust accumulation thickness through the three-dimensional sensor array deployed on the heating surface tube panels; The dynamic model construction module is used to build a dynamic heat transfer benchmark model based on the original monitoring data set and real-time operating parameters, and output the temperature gradient index (TGI) that characterizes the degree of degradation of the heating surface; The prediction output module is used to input the multi-physics field coupling model based on TGI and historical damage data to generate a remaining life prediction curve with a confidence interval, thereby realizing condition monitoring of the heated surface.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the boiler heating surface status monitoring method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the boiler heating surface status monitoring method according to any one of claims 1 to 7 are implemented.

Images