Boiler heating surface expansion monitoring method based on 5G Internet of Things

Abstract

The invention discloses a boiler heating surface expansion monitoring method based on the 5G Internet of Things, and the method comprises the following steps: A1, building a temperature data model, A2, building a relation model with combustion adjustment in the temperature data model in the step A1, A3, installing resonant wavelength temperature measurement assemblies on the surface of a boiler pipeline and the surface of a boiler, and A4, carrying out the measurement of the relation between the temperature data model and the combustion adjustment. Collecting real-time temperature data of the boiler pipeline surface and the boiler surface; and A4, establishing a digital twinborn model on computer equipment. A set of efficient and intelligent anti-abrasion and anti-explosion twinning perspective system for the boiler is developed by applying a digital twinning technology. The functions of three-dimensional visual display, wall pipe overtemperature early warning and the like of the boiler are achieved, and the safety and economical efficiency of boiler operation are improved. And meanwhile, the compatibility, the stability and the real-time performance of the system are improved, so that the operation and maintenance management requirements of boilers of different types and different scales are met.

Description

Technical Field

[0001] This invention relates to the field of power plant boiler condition monitoring technology, specifically to a method and system for online monitoring of boiler heating surface expansion based on 5G Internet of Things and digital twin technology. Background Technology

[0002] Under current deep peak-shaving conditions, rapid load changes lead to unstable combustion. The tangential burners exhibit flame center deviation, causing overheating, coking, and high-temperature corrosion on the fire-side of the water-cooled walls. This combustion deviation also results in temperature discrepancies on the superheater and reheater tube walls. Uneven combustion adjustment further exacerbates overheating of the superheater and reheater tube walls. The actual coal quality differs significantly from the design coal quality, with the actual coal exhibiting a higher sulfur content. This further exacerbates coking and high-temperature corrosion. Besides coal quality factors, the evenness of air-coal combustion is also closely related. Uneven air-coal combustion causes large thermal deviations in the flue gas on both sides of the furnace, leading to localized overheating of the heated metal surfaces and severely impacting the boiler's combustion safety and economy.

[0003] The boilers all use old mechanical boiler expansion indicators. Traditional mechanical expansion indicators require manual inspection and recording of boiler expansion changes. Information transmission is not timely and cannot be connected to the boiler 3D visualization system. As a result, the on-duty personnel cannot see the correlation between the combustion process and boiler expansion and cracking in a timely and intuitive manner, and cannot use advanced artificial intelligence technology to identify safety hazards and issue warnings.

[0004] During the boiler's life cycle, it goes through three periods: the initial construction period, the stable management period, and the accelerated aging period. The number of boiler accidents also goes through three stages: "occurring irregularly in concentrated periods, occasional occurrences, and sudden increases due to aging." The third stage, the "accelerated aging period," lays the groundwork for potential problems in the first two stages. In the second stage, the "stable management period," we must not let our guard down because of the "health benefits" of the equipment.

[0005] In June 2022, the group issued the "National Energy Group Boiler 'Four Tubes' Anti-Wear and Anti-Explosion Work Manual", which strictly controls the rate of change of heating surface wall temperature and working fluid temperature during deep peak load adjustment of deep adjustment units, strictly controls the coal-water ratio, strictly prevents coal-water ratio imbalance, and strictly prohibits forced load under overheating conditions. In order to solve these problems, it is urgent to establish a temperature monitoring system for the main heating surfaces of the boiler, and replace the traditional local thermocouple single-point measurement with comprehensive multi-point temperature measurement, so as to provide data support for operation adjustment and automatic combustion control.

[0006] Thermal power generating units involve large systems and unique control and operation methods. Given the current urgent need to improve the flexibility of thermal power generation, traditional temperature monitoring technologies are no longer sufficient. In particular, during rapid and flexible operation across all operating conditions, units face problems such as insufficient combustion stability, overheating of heating surfaces, and accelerated wear and tear on critical components. Therefore, intelligent and digital methods are urgently needed to address the pain points encountered during unit operation. (1) Coal-fired boilers operate in a high-temperature and high-pressure environment, and existing temperature measurement methods are insufficient to monitor all tube wall temperature data. Coal-fired boiler equipment is large and the system is complex. Under high-temperature and high-pressure operating conditions, the location and number of measurement points that can be installed using thermocouples are limited, and the measuring devices are also difficult to operate reliably for a long time. Existing measurement methods alone cannot obtain data that can completely describe the working status of the boiler. Therefore, advanced fusion resonant wavelength temperature measurement technology is adopted to achieve full coverage of tube wall temperature measurement on the main heating surfaces such as superheaters and reheaters, so as to realize refined detection of tube wall temperature during unit operation under deep peak shaving conditions.

[0007] (2) The number of boiler expansion indicators is small and cannot fully reflect the expansion of each heating surface of the boiler. During the boiler start-up phase, manual inspection is required to read data from each monitoring point of the boiler, which not only consumes manpower but also has poor real-time data. After the boiler is running normally, manual inspection requires climbing up and down and is also affected by nighttime light and personnel condition, making the process cumbersome and unsafe. Data recording uses paper and pen reports, which cannot intuitively and in real time display the expansion changes of the boiler, and cannot provide early warning of excessive boiler expansion.

[0008] (3) Lack of comprehensive data integration and analysis, resulting in data silos. The DCS control system of thermal power units stores massive amounts of real-time and historical operating data. This data is characterized by its large capacity, complex format, and intricate relationships, which makes it difficult for most operating unit operators to utilize DCS data effectively. They often rely solely on experience to judge the operating status of various boiler systems, lacking quantitative, clear, accurate, and visual analysis methods.

[0009] Therefore, it is necessary to carry out comprehensive data integration and analysis of thermal power plants. By deeply mining the collected pipe wall temperature data and combining it with on-site operation data, various parameter data and algorithms, we can use intuitive temperature data to analyze and deeply explore the underlying combustion problems beneath the surface temperature data. This approach uses specific data to connect with operational data, thereby achieving integrated data integration and analysis.

[0010] (4) Different performance indicators of the boiler are mutually restrictive, and the effect of single-factor control of combustion in the furnace is limited. The combustion mechanism in the furnace is complex, and there are many parameters affecting the boiler combustion process with complex correlations. Different performance indicators are mutually restrictive, and the optimization of a single parameter may lead to the instability or inconsistency of other parameters. There is an over-reliance on personal experience rather than real-time monitoring data to adjust combustion parameters. This may result in the tube wall temperature not being accurately controlled, especially when fuel quality, boiler load or other conditions change. The control system of some boilers may be relatively outdated and unable to achieve automatic adjustment and optimization of tube wall temperature and combustion parameters. This may result in an imprecise combustion process and large fluctuations in tube wall temperature. The lack of clear operating procedures or standards leads to a lack of clear guidance for operators when adjusting combustion parameters, making it difficult to combine tube wall temperature with combustion parameters. Insufficient training has resulted in an in-depth understanding of the relationship between combustion adjustment and tube wall temperature. In addition, regular maintenance of the equipment may also be inadequate, leading to a deviation in the relationship between combustion parameters and tube wall temperature. The data and information generated during the management process are scattered in various places (such as equipment management system and SIS system), and have not been comprehensively analyzed and utilized. Furthermore, the level of intelligence and informatization is not high, and there is still a heavy reliance on personal work experience. There is a lack of effective information tools for systematic data management and analysis, and the system has failed to achieve scientific equipment status perception, hazard analysis, and intelligent maintenance guidance based on data. Summary of the Invention

[0011] In view of the above-mentioned defects or deficiencies in the existing technology, it is desirable to provide a method for monitoring the expansion of boiler heating surfaces based on 5G Internet of Things.

[0012] According to the technical solution provided in the embodiments of this application, a method for monitoring the expansion of a boiler heating surface based on 5G Internet of Things includes the following steps: A1. Establish a temperature data model, obtain the average values ​​of superheater and reheater temperatures and combustion parameters through experimental data and numerical simulation, and then establish a correlation model between superheater and reheater temperatures and combustion parameters based on the average values. A2. Establish a relationship model between the temperature data model described in step A1 and the combustion adjustment, wherein the combustion adjustment includes combustion intensity, the position of the flame center in the furnace, fuel ratio, air supply volume and burner arrangement; thereby obtaining the historical information of the boiler heating surface; A3. Install resonant wavelength temperature measuring components on the surface of boiler pipes and boiler surface to collect real-time temperature data of boiler pipe surfaces and boiler surface. A4. Establish a digital twin model on a computer device to achieve image-model navigation and data linkage. The digital twin model receives the temperature data from step A3 through a 5G IoT module, thereby obtaining the real-time heating surface conditions of the boiler pipe surface and the boiler surface. This data is then compared with the historical conditions of the boiler heating surface in step A2 to achieve boiler heating surface expansion monitoring. Simultaneously, the digital twin model includes the following modules: The system includes a 3D data interaction and display module, a standardized work management module, a wall temperature status monitoring and analysis module, a temperature field distribution module, an over-temperature statistics module, an over-temperature creep trend early warning module, a wall thickness prediction module, a leakage alarm device detection module, an oxide scale risk pre-control module, and a risk and life assessment module.

[0013] In this invention, the resonant wavelength temperature measurement component further includes a distributed array of resonant wavelength fiber optic temperature sensors, a signal demodulator, and a data acquisition unit. The sensor array is directly laid or welded to the outer wall of the boiler pipes and key surface areas of the boiler. The real-time temperature data collected is transmitted to the digital twin model through the 5G IoT module.

[0014] Further, this invention includes: A resonant wavelength temperature measuring device is used to be installed on the surface of boiler pipes and boiler surface to collect real-time temperature data. The 5G IoT communication module is used to transmit the temperature data collected by the resonant wavelength temperature measuring device in real time. A data processing and modeling server is used to store historical operating data and execute steps A1 and A2 to establish and update the temperature data model and combustion adjustment relationship model. The digital twin model platform, deployed on a computer device, integrates the aforementioned 3D data interaction and display module, standardized work management module, wall temperature status monitoring and analysis module, temperature field distribution module, over-temperature statistics module, over-temperature creep trend early warning module, wall thickness prediction module, leakage alarm device detection module, oxide scale risk pre-control module, and risk and life assessment module. The platform receives real-time temperature data through the 5G IoT communication module and compares and analyzes it with historical model data in the data processing and modeling server to achieve online monitoring, early warning, and assessment of boiler heating surface expansion.

[0015] In this invention, further, in step A1, a correlation model is established between the superheater and reheater temperatures and combustion parameters. Specifically, a machine learning algorithm or a multivariate nonlinear regression analysis method is used. The combustion parameters include at least the main steam flow rate, feedwater temperature, excess air coefficient, the combination of burners in operation at each layer, the primary air / secondary air ratio, and the flue gas temperature at the furnace outlet.

[0016] In this invention, further, in step A2, a relationship model between the temperature data model and combustion adjustment is established. Specifically, by analyzing the variation law of the correlation model parameters in the historical operating data under different combustion adjustment conditions, the influence of combustion adjustment on the temperature distribution and average value of each region of the superheater and reheater is quantified, forming a mapping relationship that can guide combustion optimization.

[0017] In this invention, further, in step A4, the digital twin model performs the following operations in real time: Using the wall temperature status monitoring and analysis module, the actual wall temperature and its rate of change at each monitoring point are calculated based on real-time temperature data; Using the temperature field distribution module, combined with the boiler structure model and real-time / historical temperature data, the three-dimensional temperature field distribution of the boiler heating surface is dynamically reconstructed and visualized. Using the data linkage function, real-time temperature anomalies or over-temperature events at specific monitoring points can be automatically located on the 3D model and their corresponding physical locations can be highlighted.

[0018] Furthermore, in this invention, the working process of the over-temperature creep trend early warning module includes: Based on real-time monitored wall temperature data, historical overheat statistics data, and a database of material creep properties; Calculate the equivalent creep temperature and cumulative creep damage of the critical pipe section under the current operating conditions; Predict creep life consumption and remaining life within a specified future operating cycle; When the rate of accumulated damage or lifespan depletion exceeds a preset threshold, different levels of creep trend warnings are triggered.

[0019] Furthermore, in this invention, the working process of the oxide scale risk prevention and control module includes: Based on real-time monitoring of metal wall temperature, historical temperature distribution, and oxidation kinetics model; Predict the growth rate and thickness of oxide scale on specific sections of boiler heating surfaces; Based on the characteristics of the pipe material, operating conditions, and the risk criteria for oxide scale peeling; Assess the risk level of oxide scale peeling and blockage, and issue a pre-control alarm when the risk level exceeds the safety threshold, prompting adjustments to combustion or scheduling maintenance.

[0020] Furthermore, in this invention, the leakage alarm device detection module is used to receive and integrate signals from existing leakage detection devices such as acoustic waves, negative pressure waves, or infrared thermal imaging in the boiler. When a suspected leakage signal is detected, it automatically retrieves and associates the real-time and historical temperature field, wall thickness prediction data, and oxide scale risk data of the corresponding area in the digital twin model to perform auxiliary location of the leakage point and preliminary analysis of the cause, and issues a leakage alarm on the three-dimensional model.

[0021] Furthermore, in this invention, the risk and life assessment module integrates the output results of the wall thickness prediction module, the over-temperature creep trend early warning module, and the oxide scale risk pre-control module, and combines them with equipment design parameters, operating years, and maintenance records to conduct a safety risk level assessment and remaining life prediction for the boiler as a whole or a specific heating surface area, and generates an assessment report; the assessment results guide the formulation or optimization of boiler operating procedures, maintenance plans, and maintenance strategies through the standardized work management module.

[0022] In summary, the beneficial effects of this application are as follows: 1. By utilizing digital twin technology, develop a highly efficient and intelligent boiler anti-wear and explosion-proof twin-view system. This system enables 3D visualization of the boiler and provides early warning of wall tube overheating, thereby improving the safety and economy of boiler operation. Simultaneously, it enhances the system's compatibility, stability, and real-time performance to meet the operation and maintenance management needs of boilers of different types and sizes.

[0023] 2. Integrate a metal heating surface safety system to display the temperature status of the superheater and reheater in three dimensions; embed the temperature models of the superheater and reheater and the metal life model into the management system.

[0024] 3. By leveraging 3D intelligent ledger technology, the complex structure of the heating surface can be displayed in an intuitive 3D model, enabling the visualization and association of boiler ledger information, thereby improving the efficiency and accuracy of ledger management. Attached Figure Description

[0025] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the process of the present invention; Figure 2 This is a flowchart of the over-temperature creep trend early warning module.

[0026] Numbering on the map: Detailed Implementation

[0027] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0028] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0029] like Figure 1 and Figure 2As shown, a method for monitoring the expansion of boiler heating surfaces based on 5G IoT is implemented as follows: Machine learning and deep learning technologies are used to establish boiler superheater and reheater tube wall temperature models, organically combining tube wall temperature data with combustion adjustments. Based on the tube wall temperature change patterns, early warnings and maintenance guidance are provided, primarily regarding tube wall life and tube rupture risk. Simultaneously, resonant wavelength temperature measurement technology is integrated to acquire real-time and accurate temperature data of the boiler's four tube surfaces. This data reflects the thermal state of the pipelines during operation. Analysis of this data allows for timely detection of potential overheating and over-temperature issues, preventing pipeline damage and accidents. Real-time monitoring of heated surface temperature data is further performed, and statistical analysis of overheating data is conducted to generate monthly reports. The system collects original heated surface temperature data and key DCS parameters related to boiler combustion. Through precise spatial positioning, heated surface temperature information is matched with corresponding locations in the boiler's 3D model via a 5G IoT module. A real-time data transmission mechanism is established to ensure that temperature measurement data is updated in the 3D model in real time. In this way, operators can see the real-time temperature distribution and changes in the 3D model, realizing a 3D visualization of the boiler. They can see the welding positions of dissimilar steels and identify different materials based on their colors. The 3D visualization management module supports interconnection with basic ledger information, maintenance records, explosion / leaking accident information, metal wall temperature monitoring information, and deterioration analysis information for the heating surface. Simultaneously, the system perfectly integrates boiler wear and explosion prevention and metal monitoring into the entire PDCA (Plan-Do-Check-Act) process, providing integrated and cyclical management, closely combining with reality for scientific and effective management. It enables simultaneous display on PCs, mobile phones, tablets, and large screens, facilitating direct and convenient remote interaction between the system and users. The system pushes key data on wear and explosion prevention and metal monitoring through multi-functional statistical summaries, various trend curves, and multi-format comparison charts, uncovering the inherent correlation attributes of data indicators. Its maintenance guidance, based on wall temperature monitoring, wear analysis, and maintenance ledgers, provides reference opinions for the next maintenance, improving the overall maintenance efficiency of the boiler by defining key inspection areas and parts. By standardizing boiler ledgers and plans, and making records standardized, we can achieve lean management and precise control, improve the loopholes in the original boiler wear and explosion prevention management of power plants, optimize and improve maintenance content, realize the informatization and digitalization of boiler wear and explosion prevention in power plants, more efficiently grasp every aspect of boilers, and thus maximize risk control and minimize the probability of risk occurrence.

[0030] The 3D model allows for the rendering of standard colors, spatial locations, and orientations of equipment and piping based on their actual conditions. It enables high-fidelity modeling and dynamic 3D virtual digital representation of minute components such as boiler water walls, superheaters, reheaters, economizers, the four main piping systems, headers, headers, inlet and outlet pipes, combustion holes, inspection holes, manholes, and soot blowing holes. Based on 3D digital modeling technology, the main heating surfaces of the boiler are rendered in 3D and assembled into a complete boiler using software programming. The model navigation allows users to browse and navigate, view defect information, and check basic tube bank information.

[0031] Simultaneously, the system enables 3D data interaction and display of basic ledger data, maintenance data, statistical analysis data, and operation monitoring data of metal equipment, thereby empowering traditional boiler wear and explosion prevention management through information technology. The system highly integrates 3D modules with boiler wear and explosion prevention-related data. The 3D visualization module allows for intuitive and efficient browsing of equipment structures, viewing original ledger data, maintenance / inspection ledger data, and operation ledger data, all visualized in 3D, facilitating timely understanding of equipment status and development trends. Based on unit drawing data and supported by a ledger equipment tree, the system utilizes digital twin modeling technology to create 3D models of the main heating surfaces of the boiler, which are then assembled into a complete boiler using software programming. The 3D model allows for free scaling, disassembly, translation, flipping, hiding, and display at any angle. It enables viewing, searching, and locating graphics, and features real-time data synchronization, allowing users to view static design data, dynamic operation data, and troubleshooting information.

[0032] It enables switching between first-person and third-person camera perspectives, fully automatic free navigation of the model, and custom navigation management, as well as the management of multiple navigation tasks. The navigation path nodes are arbitrarily editable. Path node attributes include any combination of the visibility attributes of all components within the boiler's 3D model, the boiler model's first-person perspective, and the movement speed between nodes.

[0033] It also includes the following modules: Standardized Work Management Module The system follows the power plant's management processes and utilizes digital information technology to establish a PDCA (Plan-Do-Check-Act) maintenance management system for explosion-proof work. Users can quickly create plans, rapidly input records, track inspection progress, summarize records, and perform closed-loop management of maintenance data statistics. This module includes welding process information, defect elimination records, pipe replacement records, and pipe cutting inspection records.

[0034] Wall temperature status monitoring and analysis module It continuously and in real time obtains equipment measurement data from the power plant's production database, including temperature data from existing boiler wall temperature measurement points and newly added grating temperature measurement points, and presents the temperature values ​​in real time.

[0035] Based on the metal wall temperature data, the wall temperature measuring points were analyzed for spatial distribution deviation, including visualization analysis of wall temperature field distribution, wall temperature deviation within the same screen, wall temperature deviation within the same row, wall temperature deviation on the left and right sides, and visualization analysis of historical wall temperature deviation.

[0036] Temperature field distribution module Input the unit and component query criteria, and a 2D or 3D graph will display the real-time wall temperature risk of all tube banks of a specific boiler component. Four colors—red, orange, yellow, and green—represent the current risk level of each tube bank. The module intuitively displays the actual physical distribution of current measuring points and wall temperature distribution. It can also perform real-time monitoring and record over-limit history of the boiler's main operating parameters, the "four-tube leakage" system, real-time wall temperature, and sootblower operation status, and establishes a correlation with the equipment ledger and 3D model.

[0037] Using color blocks, the risk distribution of different risk levels is displayed intuitively, and key warnings are issued for monitoring tubes. At the same time, historical wear records are accumulated, and online flow field analysis is used to determine the current flue gas flow field. Different color difference temperature fields (over-temperature area display) are presented at the tube bundle level, providing intuitive furnace temperature distribution for operation.

[0038] Over-temperature statistics module Based on unit and equipment queries, the system displays the real-time over-temperature status of monitoring points. This includes the over-limit level, over-limit threshold, cumulative over-temperature risk, and basic information about the monitoring points.

[0039] The over-temperature early warning module enables online monitoring and graded alarm functions for the unit, equipment, and pipeline wall temperatures. Users can intuitively view the over-limit information and historical curves of each measuring point, providing data support for the optimized combustion regulation of the boiler.

[0040] Over-temperature history: Users can query detailed over-temperature information for equipment and pipes with over-temperature records based on unit information, equipment, and time intervals. Over-temperature statistics: This section summarizes and analyzes the unit's over-temperature information, storing data such as the number of over-temperature events, over-temperature amplitude, over-temperature rate, load during over-temperature, and cumulative over-temperature duration for each over-temperature measuring point, generating historical over-temperature curves, and visual over-temperature trend charts that can be downloaded.

[0041] Over-temperature creep trend early warning module Based on historical temperature trends and current temperatures, the system predicts the temperature trend for the next 5 minutes in real time. At the same time, it provides real-time early warnings and push notifications on the creep damage trend of high-temperature pressure-bearing components caused by metal overheating, guiding operators to adjust unit parameters in advance to prevent metal wall overheating.

[0042] Wall thickness prediction module The corrosion and thinning of boiler heating surfaces are affected by various factors, including the boiler's operating status, sootblower operating status, water quality, and coal quality changes. The system uses measured data and historical inspection thickness data to analyze and calculate the thinning trend and distribution of thinning rate at uniformly inspected parts of the pipe fittings. By calculating and predicting the thinning rate and value of the pipe wall, the system establishes a calculation and prediction model for the thinning of the heating surface pipe wall. This helps users gradually understand the development law of boiler pipe wall deterioration, and thus scientifically arrange maintenance time and take reasonable anti-wear measures.

[0043] Leakage alarm device detection module The system integrates monitoring data from existing leak alarm devices on the boiler, and performs statistical analysis. Historical curves are generated based on leak monitoring data, and alarms are promptly sent to operation monitoring personnel, along with relevant predictive information. The system rapidly links the location of leak points in the 3D model and issues early warnings.

[0044] Oxide Scale Risk Pre-control Module The oxide scale shedding model calculates the amount of oxide scale detached from the heated surface based on the frequency and amplitude of temperature changes. This model allows for timely prediction of oxide scale accumulation within high-temperature heated pipes, significantly reducing the probability of non-stationary shutdowns caused by oxide scale blockage.

[0045] By establishing a mechanistic model, linking historical data on oxide scale blockage risk, and coupling dynamic and static data from multiple sources such as material properties, over-temperature fatigue, temperature change rate, and temperature field, a trend prediction of oxide scale detachment risk is ultimately formed, enabling comprehensive management and control of oxide scale.

[0046] Risk and life assessment module Combining big data algorithm analysis, this study primarily analyzes the impact of cumulative soot blowing effects and overheating conditions on the thinning of the heating surface in superheaters and reheaters. A comprehensive calculation data model is used to quantify the thinning rate and remaining lifespan of the superheaters and reheaters. Based on the input parameters, the remaining lifespan of the tubes is calculated; the output includes a graph and list of the remaining tube lifespan, highlighting the locations with the shortest remaining lifespan.

[0047] The above description is merely a preferred embodiment of this application and an explanation of the technical principles and solutions employed. Furthermore, the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for monitoring the expansion of boiler heating surfaces based on 5G Internet of Things, characterized in that, Includes the following steps: A1. Establish a temperature data model, obtain the average values ​​of superheater and reheater temperatures and combustion parameters through experimental data and numerical simulation, and then establish a correlation model between superheater and reheater temperatures and combustion parameters based on the average values. A2. Establish a relationship model between the temperature data model described in step A1 and the combustion adjustment, wherein the combustion adjustment includes combustion intensity, the position of the flame center in the furnace, fuel ratio, air supply volume and burner arrangement; thereby obtaining the historical information of the boiler heating surface; A3. Install resonant wavelength temperature measuring components on the surface of boiler pipes and boiler surface to collect real-time temperature data of boiler pipe surfaces and boiler surface. A4. Establish a digital twin model on a computer device to achieve image-model navigation and data linkage. The digital twin model receives the temperature data from step A3 through a 5G IoT module, thereby obtaining the real-time heating surface conditions of the boiler pipe surface and the boiler surface. This data is then compared with the historical conditions of the boiler heating surface in step A2 to achieve boiler heating surface expansion monitoring. Simultaneously, the digital twin model includes the following modules: The system includes a 3D data interaction and display module, a standardized work management module, a wall temperature status monitoring and analysis module, a temperature field distribution module, an over-temperature statistics module, an over-temperature creep trend early warning module, a wall thickness prediction module, a leakage alarm device detection module, an oxide scale risk pre-control module, and a risk and life assessment module.

2. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that: The resonant wavelength temperature measurement component includes a distributed array of resonant wavelength fiber optic temperature sensors, a signal demodulator, and a data acquisition unit. The sensor array is directly laid or welded to the outer wall of the boiler pipes and key surface areas of the boiler. The real-time temperature data collected is transmitted to the digital twin model through the 5G IoT module.

3. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that, include: A resonant wavelength temperature measuring device is used to be installed on the surface of boiler pipes and boiler surface to collect real-time temperature data. The 5G IoT communication module is used to transmit the temperature data collected by the resonant wavelength temperature measuring device in real time. A data processing and modeling server is used to store historical operating data and execute steps A1 and A2 to establish and update the temperature data model and combustion adjustment relationship model. The digital twin model platform, deployed on a computer device, integrates the aforementioned 3D data interaction and display module, standardized work management module, wall temperature status monitoring and analysis module, temperature field distribution module, over-temperature statistics module, over-temperature creep trend early warning module, wall thickness prediction module, leakage alarm device detection module, oxide scale risk pre-control module, and risk and life assessment module. The platform receives real-time temperature data through the 5G IoT communication module and compares and analyzes it with historical model data in the data processing and modeling server to achieve online monitoring, early warning, and assessment of boiler heating surface expansion.

4. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that: In step A1, a correlation model between the superheater and reheater temperatures and combustion parameters is established. Specifically, machine learning algorithms or multivariate nonlinear regression analysis methods are used. The combustion parameters include at least the main steam flow rate, feedwater temperature, excess air coefficient, the combination of burners in operation at each level, the primary air / secondary air ratio, and the flue gas temperature at the furnace outlet.

5. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that: In step A2, a relationship model between the temperature data model and combustion adjustment is established. Specifically, by analyzing the variation law of the correlation model parameters in the historical operating data under different combustion adjustment conditions, the influence of combustion adjustment on the temperature distribution and average value of each region of the superheater and reheater is quantified, forming a mapping relationship that can guide combustion optimization.

6. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that: In step A4, the digital twin model performs the following operations in real time: Using the wall temperature status monitoring and analysis module, the actual wall temperature and its rate of change at each monitoring point are calculated based on real-time temperature data; Using the temperature field distribution module, combined with the boiler structure model and real-time / historical temperature data, the three-dimensional temperature field distribution of the boiler heating surface is dynamically reconstructed and visualized. Using the data linkage function, real-time temperature anomalies or over-temperature events at specific monitoring points can be automatically located on the 3D model and their corresponding physical locations can be highlighted.

7. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that: The working process of the over-temperature creep trend early warning module includes: Based on real-time monitored wall temperature data, historical overheat statistics data, and a database of material creep properties; Calculate the equivalent creep temperature and cumulative creep damage of the critical pipe section under the current operating conditions; Predict creep life consumption and remaining life within a specified future operating cycle; When the rate of accumulated damage or lifespan depletion exceeds a preset threshold, different levels of creep trend warnings are triggered.

8. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that: The working process of the oxide scale risk prevention and control module includes: Based on real-time monitoring of metal wall temperature, historical temperature distribution, and oxidation kinetics model; Predict the growth rate and thickness of oxide scale on specific sections of boiler heating surfaces; Based on the characteristics of the pipe material, operating conditions, and the risk criteria for oxide scale peeling; Assess the risk level of oxide scale peeling and blockage, and issue a pre-control alarm when the risk level exceeds the safety threshold, prompting adjustments to combustion or scheduling maintenance.

9. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that: The leakage alarm detection module is used to receive and integrate signals from existing leakage detection devices such as acoustic waves, negative pressure waves, or infrared thermal imaging in the boiler. When a suspected leakage signal is detected, it automatically retrieves and associates the real-time and historical temperature field, wall thickness prediction data, and oxide scale risk data of the corresponding area in the digital twin model to perform auxiliary location of the leakage point and preliminary analysis of the cause, and issues a leakage alarm on the three-dimensional model.

10. The boiler heating surface expansion monitoring method based on 5G Internet of Things according to claim 1, characterized in that: The risk and life assessment module integrates the outputs of the wall thickness prediction module, the over-temperature creep trend early warning module, and the oxide scale risk pre-control module, and combines them with equipment design parameters, operating years, and maintenance records to conduct a safety risk level assessment and remaining life prediction for the boiler as a whole or a specific heating surface area, and generates an assessment report. The assessment results guide the formulation or optimization of boiler operating procedures, maintenance plans, and maintenance strategies through the standardized work management module.

Images