An intelligent early warning method for boiler anti-abrasion and explosion prevention based on quantitative risk analysis

Abstract

The present invention discloses an intelligent early warning method for boiler abrasion and explosion prevention based on quantitative risk analysis, which relates to the technical field of intelligent early warning for boiler abrasion and explosion prevention. The method includes collecting key data and processing the data; quantifying the data, determining the risk of wall thickness loss based on the tube wall thickness loss rate algorithm; determining the overall explosion risk, and performing intelligent early warning for boiler abrasion and explosion prevention based on the quantified data. By introducing a three-dimensional model, the intelligent early warning method for boiler abrasion and explosion prevention provided by the present invention enables the visualization display of the overall structure of the boiler and the states of its various components, assisting the operation and maintenance personnel to operate the boiler equipment more precisely and efficiently. Based on the early warning data, subtle prompts for the equipment are provided to ensure that the operation and maintenance personnel can notice the faulty areas. The present invention achieves better effects in terms of efficiency, accuracy, and auxiliary effect.

Description

Technical Field

[0001] The present invention relates to the technical field of boiler anti-abrasion and explosion-proof intelligent early warning, and particularly to a boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis. Background Art

[0002] As one of the core devices in the power and heat systems, the safe and stable operation of boilers directly affects the power generation efficiency and safety. In recent years, with the increase in boiler operating load and the aggravation of equipment aging, boiler anti-abrasion and explosion-proof technologies have received extensive attention. Modern boiler anti-abrasion and explosion-proof technologies rely on the integration of multiple technologies such as real-time monitoring, data acquisition, risk analysis, and early warning systems. The progress of sensor technology, Internet of Things (IoT), and data analysis technology has gradually brought boiler anti-abrasion and explosion-proof management into the intelligent stage. By real-time monitoring and quantitative analysis of key data such as temperature, pressure, and wall thickness of boiler equipment, potential wear, corrosion, and tube burst risks can be effectively identified, and then effective preventive measures can be taken in advance. In addition, combined with three-dimensional modeling and virtual simulation technologies, it also provides a more intuitive and dynamic display method for the health status monitoring of boilers.

[0003] Although the current boiler anti-abrasion and explosion-proof technologies have made significant progress in the construction of real-time monitoring and early warning systems, there are still some deficiencies in the existing technologies. First of all, most of the existing monitoring systems rely on single-sensor data acquisition, such as temperature, pressure, flow rate, and wall thickness. Although these data can provide basic equipment status information, they do not consider the combined effects of multiple risk factors. For example, the interaction of temperature fluctuations, pressure fluctuations, and wall thickness loss has an important impact on the safety of boiler equipment, and the existing systems cannot effectively integrate and analyze these multi-dimensional risk factors, resulting in the inability to comprehensively evaluate the overall risk level of the boiler. Therefore, the existing technologies often cannot accurately identify potential risks of equipment in complex operating environments. Especially under the interaction effects of temperature, pressure, and wall thickness loss, traditional monitoring methods may miss some hidden dangers.

[0004] Secondly, most of the existing boiler anti-abrasion and explosion-proof systems focus on single fault mode identification, such as pipe bursting or wall thickness loss, but lack the intelligent analysis ability for the comprehensive health status of boilers. Most of the early warning mechanisms of the existing systems rely on fixed thresholds to trigger, without considering the dynamic changes of boilers under different loads and operating conditions. Therefore, when facing complex factors such as temperature and pressure fluctuations and wall thickness loss during the long-term operation of boilers, traditional methods may give premature or late warnings, resulting in low warning accuracy. In addition, the system integration of the existing technologies is poor, lacking a digital management platform that can comprehensively and real-time reflect the overall state of boilers, making the transmission, analysis, and decision support of data unable to be synchronized in real time. Summary of the Invention

[0005] In view of the above problems, the present invention is proposed.

[0006] Therefore, the technical problems solved by the present invention are: existing boiler anti-abrasion and explosion-proof monitoring methods have single data monitoring, cannot comprehensively consider multi-dimensional risk factors, have low accuracy of the early warning system, and how to analyze the overall risk of the boiler in real time and comprehensively.

[0007] To solve the above technical problems, the present invention provides the following technical solution: an intelligent anti-abrasion and explosion-proof early warning method for boilers based on quantitative risk analysis, including collecting key data and processing the data. Quantify the data, determine the risk of wall thickness loss based on the tube wall thickness loss rate algorithm. Determine the overall explosion risk, and conduct intelligent anti-abrasion and explosion-proof early warning based on the quantified data.

[0008] As a preferred solution of the intelligent anti-abrasion and explosion-proof early warning method for boilers based on quantitative risk analysis according to the present invention, wherein: the collecting of key data and the preprocessing of the data include installing sensors at the heating surface pipes, headers, and pipe connectors of the boiler to collect real-time data.

[0009] The sensors include:

[0010] Temperature sensors monitor the surface and internal temperatures of various components of the boiler.

[0011] Pressure sensors monitor the pressure changes of the boiler.

[0012] Ultrasonic thickness gauges detect the wall thickness changes of boiler pipes according to a preset period.

[0013] Flow sensors detect the flow rates of flue gas, steam, and water.

[0014] Upload the data collected by all sensors to the digital ledger for boiler anti-abrasion and explosion-proof management.

[0015] Extract historical maintenance data, equipment installation information, and historical fault records from the equipment management system of the power plant. The historical data includes:

[0016] The inspection scope, repaired parts, and defect types of each maintenance.

[0017] The material of the equipment, the design temperature range, the design pressure range, and the installation drawings.

[0018] Historical fault modes and occurrence frequencies.

[0019] Upload the data of the management system to the digital ledger for boiler anti-abrasion and explosion-proof management.

[0020] Construct a 3D model based on the digital ledger for boiler anti-abrasion and explosion-proof management. The overall shape of the boiler body heating surface, the spatial structure of the furnace tubes, and the tube screen layout method are presented in the model.

[0021] As a preferred solution of the boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis according to the present invention, wherein: the quantification of the data includes the risk quantification assessment of the difference between temperature and pressure, and a temperature change rate risk assessment model is constructed, expressed as:

[0022]

[0023] Wherein, T t is the equipment temperature at the current moment, T t-1 is the equipment temperature at the previous moment, γ T is the temperature change adjustment coefficient, T max and T min are the maximum and minimum design temperatures of the boiler respectively.

[0024] Construct a pressure change rate risk assessment model, expressed as:

[0025]

[0026] Wherein, P t is the boiler pressure at the current moment, P t-1 is the boiler pressure at the previous moment, γ P is the adjustment coefficient of pressure fluctuation, P max is the maximum design pressure of the boiler.

[0027] As a preferred solution of the boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis according to the present invention, wherein: determining the risk of wall thickness loss based on the tube wall thickness loss rate algorithm includes, when a change in wall thickness is detected, marking the corresponding pipeline yellow in the 3D model, and constructing a wall thickness loss change rate risk assessment model to evaluate the wall thickness loss risk, expressed as:

[0028]

[0029] Wherein, ΔB = B t -B t-1 is the wall thickness change between the current moment and the previous moment, B max is the initial wall thickness of the boiler pipeline, γ B is the sensitivity coefficient of wall thickness change, ΔB history is the historical wall thickness change rate, θ B is the smoothing coefficient of wall thickness change, α T is the acceleration coefficient of boiler operation time on wall thickness loss, and T is the cumulative operation time of the boiler.

[0030] As a preferred solution of the boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis according to the present invention, wherein: the determination of the overall explosion risk includes system identification of the temperature change rate risk R T , the pressure change rate risk R P and the pipe wall loss change rate risk R BL . When all three indicators do not exceed the preset first risk threshold, a comprehensive risk assessment of the boiler equipment is carried out, which is expressed as:

[0031]

[0032] Among them, R i represents each individual risk score, α i is the weighting coefficient of each risk factor, w i is the weight of each risk, and n is the total number of risk assessment items.

[0033] As a preferred solution of the boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis according to the present invention, wherein: the anti-abrasion and explosion-proof intelligent early warning based on quantitative data includes giving a boiler status early warning when one of the three indicators exceeds the preset first risk threshold.

[0034] When R T exceeds the first risk threshold, it is identified that there is a risk of bursting due to cracks in the heating surface pipes, unstable boiler load, or overheated steam leakage. The 3D model issues a high-temperature risk early warning, locates the abnormal area through the boiler 3D model and temperature monitoring sensors, and the 3D model marks the furnace tubes, welds, and inlet and outlet pipes in red.

[0035] When R P exceeds the first risk threshold, it is identified that there is a risk of bursting due to cracking of the welding points or valve failure. The 3D model issues a pressure risk early warning, locates the abnormal area through the boiler 3D model and pressure monitoring sensors, and the 3D model marks the headers, manifolds, and welding points in red.

[0036] When R BL exceeds the first risk threshold, it is identified that there is a risk of pipe bursting or steam leakage. The 3D model issues a warning about boiler pipe wear and corrosion, and the 3D model marks the tube screens, headers, and welds in red.

[0037] As a preferred solution of the boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis according to the present invention, wherein: the anti-abrasion and explosion-proof intelligent early warning based on quantitative data further includes that when all three indicators do not exceed the preset first risk threshold, but R T and R BLWhen both are greater than the second risk threshold, it is identified that there is an overheated steam leak, a prompt to reduce the boiler load is issued, and the welding points and the four-pipe connection parts are marked red in the 3D model.

[0038] When R T and R P When both are greater than the second risk threshold, it is identified that there is a valve failure, a prompt to reduce the boiler load is issued, and the valves and headers are marked red in the 3D model.

[0039] When R P and R BL When both are greater than the second risk threshold, it is identified that there is a gas-liquid leak, a prompt to reduce the boiler load is issued, and the headers, four-pipe connections, and welding points are marked red in the 3D model.

[0040] Another object of the present invention is to provide a boiler anti-abrasion and explosion-proof intelligent early warning system based on quantitative risk analysis, which can comprehensively quantify multiple key risk factors such as temperature change, pressure fluctuation, and wall thickness loss rate, so as to more accurately evaluate the overall risk level of boiler equipment. It solves the problem that the current boiler anti-abrasion and explosion-proof monitoring methods only have single data monitoring and cannot comprehensively consider multi-dimensional risk factors.

[0041] As a preferred embodiment of the boiler anti-abrasion and explosion-proof intelligent early warning system based on quantitative risk analysis according to the present invention, it includes: a data acquisition module, a data quantification module, and an explosion-proof early warning module. The data acquisition module is used for collecting key data and processing the data. The data quantification module is used for quantifying the data and determining the risk of wall thickness loss based on the tube wall thickness loss rate algorithm. The explosion-proof early warning module is used for determining the overall explosion risk and performing anti-abrasion and explosion-proof intelligent early warning based on the quantified data.

[0042] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis are implemented.

[0043] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the steps of the boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis are implemented.

[0044] Advantages of the present invention: The intelligent early warning method for boiler abrasion and explosion prevention based on quantitative risk analysis provided by the present invention visualizes the overall structure of the boiler and the states of its various components by introducing a 3D model, enabling maintenance personnel to operate the boiler equipment more precisely and efficiently. Subtle equipment alerts based on the early warning data are provided to ensure that maintenance personnel can notice the faulty areas. The present invention achieves better results in terms of efficiency, accuracy, and auxiliary effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0046] Figure 1 FIG. 1 is an overall flowchart of an intelligent early warning method for boiler abrasion and explosion prevention based on quantitative risk analysis provided by the first embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made with reference to the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention shall fall within the scope of protection of the present invention.

[0048] Example 1, referring to Figure 1 , which is an embodiment of the present invention, provides an intelligent early warning method for boiler abrasion and explosion prevention based on quantitative risk analysis, including:

[0049] S1: Collect key data and process the data.

[0050] Furthermore, collecting key data and preprocessing the data includes installing sensors at the heating surface pipes, headers, and pipe connectors of the boiler for real-time data collection.

[0051] The sensors include:

[0052] Temperature sensors monitor the surface and internal temperatures of various components of the boiler.

[0053] Pressure sensors monitor the pressure changes of the boiler.

[0054] Ultrasonic thickness gauges detect the wall thickness changes of the boiler pipes according to a preset period.

[0055] The flow sensor detects the flow rates of flue gas, steam and water.

[0056] Upload all the data collected by the sensors to the digital ledger for boiler anti-abrasion and explosion-proof management.

[0057] Extract historical maintenance data, equipment installation information, and historical fault records from the power plant's equipment management system. The historical data includes:

[0058] The inspection scope, repaired parts, and defect types for each maintenance.

[0059] The material of the equipment, the designed temperature range, the designed pressure range, and the installation drawings.

[0060] Historical fault modes and occurrence frequencies (such as tube burst, leakage, corrosion, etc.).

[0061] Upload the data from the management system to the digital ledger for boiler anti-abrasion and explosion-proof management.

[0062] Use the sliding window method for data preprocessing. Based on the digital ledger for boiler anti-abrasion and explosion-proof management, construct a three-dimensional model. The overall shape of the boiler's main body heating surface, the spatial structure of the furnace tubes, and the tube screen layout method are presented in the model. All the fine components, including the four tubes, headers, manifolds, inlet and outlet pipes, welds, combustion holes, viewing holes, manholes, sootblowing holes, etc., should be presented in a three-dimensional dynamic virtual digital form through the computer.

[0063] S2: Quantify the data and determine the risk of tube wall thickness loss based on the tube wall thickness loss rate algorithm.

[0064] Furthermore, quantifying the data includes quantitatively evaluating the risk of the temperature and pressure difference, and constructing a risk assessment model for the temperature change rate, expressed as:

[0065]

[0066] where, T t is the equipment temperature at the current moment, T t-1 is the equipment temperature at the previous moment, γ T is the temperature change adjustment coefficient, T max and T min are the maximum and minimum designed temperatures of the boiler respectively.

[0067] Construct a risk assessment model for the pressure change rate, expressed as:

[0068]

[0069] where, P t is the boiler pressure at the current moment, P t-1 is the boiler pressure at the previous moment, γP is the adjustment coefficient of pressure fluctuation, P max is the maximum design pressure of the boiler.

[0070] It should be noted that determining the risk of wall thickness loss based on the tube wall thickness loss rate algorithm includes, when a change in wall thickness is detected, marking the corresponding pipeline yellow in the 3D model, and constructing a risk assessment model for the change rate of wall loss to evaluate the risk of wall loss, which is expressed as:

[0071]

[0072] Among them, ΔB = B t - B t-1 is the change in wall thickness between the current moment and the previous moment, B max is the initial wall thickness of the boiler pipeline, γ B is the sensitivity coefficient of wall thickness change, ΔB history is the historical wall thickness change rate, θ B is the smoothing coefficient of wall thickness change, α T is the acceleration coefficient of boiler operation time on wall thickness loss, and T is the cumulative operation time of the boiler.

[0073] It should also be noted that determining the overall explosion risk includes system identification of the temperature change rate risk R T 、the pressure change rate risk R P and the wall loss change rate risk R BL , when all three indicators do not exceed the preset first risk threshold, a comprehensive risk assessment of the boiler equipment is carried out, which is expressed as:

[0074]

[0075] Among them, R i represents each individual risk score, α i is the weighting coefficient of each risk factor, w i is the weight of each risk, and n is the total number of risk assessment items.

[0076] S3: Determine the overall explosion risk and conduct intelligent anti-wear and anti-explosion early warning based on quantitative data.

[0077] Furthermore, conducting intelligent anti-wear and anti-explosion early warning based on quantitative data includes giving a boiler status warning when one of the three indicators exceeds the preset first risk threshold.

[0078] When R TExceeding the first risk threshold, if there are cracks in the heating surface pipes, unstable boiler load, or risk of tube explosion due to overheated steam leakage, the 3D model issues a high-temperature risk warning. The abnormal area is located through the boiler 3D model and temperature monitoring sensors, and the furnace tubes, weld joints, and inlet and outlet pipes are marked red in the 3D model.

[0079] Cracks in the heating surface pipes: The boiler heating surface is the part of the boiler most prone to failure. When the temperature is too high, the pipes are prone to thermal fatigue and cracks. Therefore, by continuously monitoring the boiler temperature, the temperature monitoring sensors can promptly detect temperature fluctuations or local overheating, and then identify the risk of potential cracks.

[0080] Unstable boiler load: When the boiler load fluctuates greatly, the temperature and pressure change violently, which easily leads to excessive temperature difference on the heating surface, and then increases the risk of cracks and tube explosion.

[0081] Overheated steam leakage: Steam leakage is usually accompanied by an increase in boiler temperature. When the temperature is too high, the pressure-bearing capacity of the boiler pipes decreases, making them prone to tube explosion.

[0082] When R P Exceeding the first risk threshold, if there is a risk of tube explosion due to cracking of the welding points or valve failure, the 3D model issues a pressure risk warning. The abnormal area is located through the boiler 3D model and pressure monitoring sensors, and the headers, manifolds, and welding points are marked red in the 3D model.

[0083] Cracking of the welding points: The welding points of the boiler are subjected to alternating temperature and pressure, making them prone to fatigue cracking. When the pressure fluctuation intensifies, the welding points may develop cracks due to repeated stress, leading to tube explosion accidents.

[0084] Valve failure: Valves are important safety devices in the boiler system. Once the valves fail, the pressure inside the boiler cannot be effectively regulated, which may cause the boiler to explode. By monitoring the pressure changes in the boiler with pressure sensors, the system can promptly identify valve failures.

[0085] When R BL Exceeding the first risk threshold, if there is a risk of pipe burst or steam leakage, the 3D model issues a warning about boiler pipe wear and corrosion. The tube screens, headers, and weld joints are marked red in the 3D model.

[0086] Pipe wear and corrosion: During the long-term operation of boiler pipes, wear or corrosion may occur due to corrosion and abrasion. These damages will significantly reduce the pressure-bearing capacity of the pipes.

[0087] It should be noted that the intelligent anti-wear and anti-explosion warning based on quantitative data also includes the situation where when all three indicators do not exceed the preset first risk threshold, but R T and R BLWhen both are greater than the second risk threshold, it is identified that there is an overheated steam leakage, a prompt to reduce the boiler load is issued, and the welding points and the four-pipe connection parts are marked red in the 3D model.

[0088] When R T and R P When both are greater than the second risk threshold, it is identified that there is a valve failure, a prompt to reduce the boiler load is issued, and the valves and headers are marked red in the 3D model.

[0089] When R P and R BL When both are greater than the second risk threshold, it is identified that there is a gas-liquid leakage, a prompt to reduce the boiler load is issued, and the headers, four-pipe connections, and welding points are marked red in the 3D model.

[0090] The first risk threshold and the second risk threshold need to be set, and the first risk threshold is higher than the second risk threshold, that is, there are three intervals.

[0091] Example 2, an embodiment of the present invention, provides a boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0092] First of all, in order to verify the effectiveness and innovation of the boiler anti-abrasion and explosion-proof intelligent early warning method based on quantitative risk analysis, the following experimental steps and processes are designed. The test is set on the boiler system of a certain power plant, and the core technologies in this method are adopted, mainly including real-time data acquisition, calculation of the tube wall thickness loss rate, quantitative evaluation of the temperature and pressure change rates, and the intelligent early warning function of the overall explosion risk.

[0093] In the experiment, a variety of sensors are first installed at the heating surface pipes, headers, and pipe connectors of the boiler, including temperature sensors, pressure sensors, ultrasonic thickness gauges, and flow sensors, which are respectively used to collect the following data:

[0094] Temperature sensor: Monitor the surface and internal temperatures of various boiler components (such as heating surface pipes, headers, etc.);

[0095] Pressure sensor: Monitor the pressure changes inside the boiler, especially during load fluctuations and instantaneous load fluctuations;

[0096] Ultrasonic thickness gauge: Regularly detect the changes in the wall thickness of the boiler pipes, mainly focusing on the heating surface pipes;

[0097] Flow sensor: Monitor the flow rates of flue gas, steam, and water to evaluate the working state of the boiler.

[0098] Table 1 Experimental data comparison table

[0099]

[0100] As can be seen from the experimental data table, as the operating time of the boiler equipment extends, the changing trends of parameters such as temperature, pressure, wall thickness, and flow rate become more obvious. For example, from equipment 1 to equipment 6, the temperature gradually rises from 540 °C to 600 °C, and the pressure and flue gas flow rate also show corresponding increasing trends. At the same time, the wall thickness of the pipeline gradually decreases from 14.5 mm to 12.5 mm, which means that during the long-term operation of the boiler, the problems of pipeline wear and corrosion gradually emerge.

[0101] Based on these data, the temperature change rate risk assessment model and pressure change rate risk assessment model of the present invention can accurately quantify the impact of temperature and pressure fluctuations on the boiler equipment. Especially when the temperature and pressure of equipment 5 and 6 change significantly (590 °C and 6.0 MPa, 600 °C and 6.2 MPa respectively), the system can calculate a relatively high risk score based on the data and further evaluate the loss of the pipeline wall thickness through the wall loss change rate risk assessment model.

[0102] It can be seen from the table data that as the temperature and pressure increase, the loss of the pipeline wall thickness also gradually intensifies, which provides data support for the possible risks of pipe explosion and leakage in the boiler. Compared with the prior art's early warning method that only considers temperature or pressure alone, the present invention can accurately predict potential faults of the boiler under complex working conditions through comprehensive evaluation of the temperature, pressure, and wall thickness change rate.

[0103] Example 3, an embodiment of the present invention, provides a boiler anti-wear and explosion-proof intelligent early warning system based on quantitative risk analysis, including a data acquisition module, a data quantification module, and an explosion-proof early warning module.

[0104] Among them, the data acquisition module is used to collect key data and process the data. The data quantification module is used to quantify the data and determine the risk of wall thickness loss based on the tube wall thickness loss rate algorithm. The explosion-proof early warning module is used to determine the overall explosion risk and conduct anti-wear and explosion-proof intelligent early warning based on the quantified data.

[0105] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0106] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0107] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), optical fiber devices, and portable compact disc read-only memories (CDROMs). Additionally, a computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as necessary, and then storing it in a computer memory.

[0108] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques well known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An intelligent early warning method for boiler anti-abrasion and explosion-proof based on quantitative risk analysis, characterized in that Including: Collecting key data and processing the data; Quantifying the data and determining the risk of wall thickness loss based on the pipe wall thickness loss rate algorithm; Determining the overall explosion risk and performing intelligent anti-wear and anti-explosion warning based on the quantified data; The step of collecting key data and preprocessing the data includes installing sensors at the heating surface pipes, headers, and pipe connectors of the boiler for real-time data collection; The sensors include: Temperature sensors monitor the surface and internal temperatures of various components of the boiler; Pressure sensors monitor the pressure changes of the boiler; Ultrasonic thickness gauges detect the wall thickness changes of boiler pipes according to a preset period; Flow sensors detect the flow rates of flue gas, steam, and water; Uploading the data collected by all sensors to the digital ledger for boiler anti-wear and anti-explosion management; Extracting historical maintenance data, equipment installation information, and historical fault records from the equipment management system of the power plant. The historical data includes: The inspection scope, repaired parts, and defect types of each maintenance; The material, design temperature range, design pressure range, and installation drawings of the equipment; Historical fault modes and occurrence frequencies; Uploading the management system data to the digital ledger for boiler anti-wear and anti-explosion management; Constructing a three-dimensional model based on the digital ledger for boiler anti-wear and anti-explosion management. The overall shape of the heating surface of the boiler body, the spatial structure of the furnace tubes, and the tube screen layout method are presented in the model; The step of determining the risk of wall thickness loss based on the pipe wall thickness loss rate algorithm includes, when a wall thickness change is detected, marking the corresponding pipe yellow in the three-dimensional model and constructing a risk assessment model for the wall loss change rate to evaluate the wall loss risk, expressed as: where ΔB = B t - B t-1 is the wall thickness change between the current moment and the previous moment, B max is the initial wall thickness of the boiler pipeline, γ B is the sensitivity coefficient of the wall thickness change, ΔB history is the historical wall thickness change rate, θ B is the smoothing coefficient of the wall thickness change, α T is the acceleration coefficient of the boiler operation time on the wall thickness loss, and T is the cumulative operation time of the boiler; The determination of the overall explosion risk of the system includes the systematic identification of the temperature change rate risk R T , the pressure change rate risk R P and the risk R of the change rate of the wall loss BL . When none of the three indicators exceed the preset first risk threshold, a comprehensive risk assessment of the boiler equipment is carried out, which is expressed as: Among them, R i represents each individual risk score, and α i is the weighting coefficient for each risk factor, w i is the weight for each risk, and n is the total number of items in the risk assessment.

2. The intelligent early warning method for boiler abrasion and explosion prevention based on quantitative risk analysis according to claim 1, characterized in that: The step of quantifying the data includes performing risk quantification assessment on the difference between temperature and pressure and constructing a risk assessment model for the temperature change rate, expressed as: Among them, T t is the device temperature at the current moment, T t-1 is the device temperature at the previous moment, γ T is the temperature change adjustment coefficient, T max and T min are the maximum and minimum design temperatures of the boiler respectively; Constructing a risk assessment model for the pressure change rate, expressed as: Among them, P t is the boiler pressure at the current moment, P t-1 is the boiler pressure at the previous moment, γ P is the adjustment coefficient of the pressure fluctuation, P max is the maximum design pressure of the boiler.

3. The intelligent early warning method for boiler anti-abrasion and explosion prevention based on quantitative risk analysis according to claim 2, characterized in that: The step of performing intelligent anti-wear and anti-explosion warning based on the quantified data includes warning the boiler status when the three indicators exceed a preset first risk threshold; When R T exceeds the first risk threshold, it is identified that there are risks of cracks in the heating surface pipes, unstable boiler load, or tube explosion due to overheating steam leakage. The 3D model issues a high-temperature risk warning, locates the abnormal area through the boiler 3D model and temperature monitoring sensors, and the 3D model marks the furnace tubes, weld joints, and inlet and outlet pipes in red; When R P exceeds the first risk threshold, it is identified that there is a risk of pipe explosion due to the cracking of the welding point or the failure of the valve. The 3D model issues a pressure risk warning, locates the abnormal area through the boiler 3D model and the pressure monitoring sensor, and the 3D model marks the headers, manifolds, and welding points in red; When R BL exceeds the first risk threshold, a risk of pipeline burst or steam leakage is identified, and the 3D model issues a warning about boiler pipeline wear and corrosion. The 3D model marks the tube screens, headers, and welds in red.

4. The intelligent early warning method for boiler abrasion and explosion prevention based on quantitative risk analysis according to claim 3, characterized in that: The anti-wear and explosion-proof intelligent early warning based on quantified data further includes that when all three indicators do not exceed the preset first risk threshold, but R T and R BL are both greater than the second risk threshold, it is identified that there is an overheated steam leak, a prompt to reduce the boiler load is issued, and the welding points and the four-pipe connection parts are marked red in the three-dimensional model; When R T and R P are both greater than the second risk threshold, it is identified that there is a valve failure, a prompt to reduce the boiler load is issued, and the valve and the header are marked red in the 3D model; When R P and R BL are both greater than the second risk threshold, it is identified that there is gas-liquid leakage, a prompt to reduce the boiler load is issued, and the headers, four-pipe connections, and welding points in the 3D model are marked in red.

5. A system adopting the intelligent early warning method for boiler abrasion and explosion prevention based on quantitative risk analysis as described in any one of claims 1 to 4, characterized in that: Including a data collection module, a data quantification module, and an explosion prevention warning module; The data collection module is used to collect key data and process the data; The data quantification module is used to quantify the data and determine the risk of wall thickness loss based on the pipe wall thickness loss rate algorithm; The explosion prevention warning module is used to determine the overall explosion risk and perform intelligent anti-wear and anti-explosion warning based on the quantified data.

6. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent anti-wear and anti-explosion warning method for boilers based on quantified risk analysis according to any one of claims 1 to 4.

7. A computer-readable storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent anti-wear and anti-explosion warning method for boilers based on quantified risk analysis according to any one of claims 1 to 4.

Images