Method, device, medium and equipment for monitoring metal part of thermal power generating unit

Abstract

The invention provides a thermal power generating unit metal part monitoring method, device, medium and equipment, and relates to the technical field of chemical equipment, the monitoring method comprises the following steps: obtaining monitoring data of a plurality of monitoring points, the plurality of monitoring points being arranged on a metal pipeline of a thermal power generating unit, the monitoring data comprises the in-pipe steam temperature and the thermal load of the periphery of the outer wall of the pipe on the section of the pipe corresponding to each monitoring point; determining a target critical temperature difference according to the in-pipe steam temperature and the thermal load of the periphery of the outer wall of the pipe corresponding to the plurality of monitoring points; at least according to the target critical temperature difference, the oxide skin falling risk condition of the metal pipeline is predicted. According to the method and the device, the oxide skin falling risk condition can be predicted through real-time monitoring data, so that operation and maintenance personnel can take treatment measures before the oxide skin falls off, the oxide skin falling risk is reduced or the fallen oxide skin is cleaned in time, and the equipment failure rate and the maintenance cost are reduced.

Description

Technical Field

[0001] The present disclosure relates to the technical field of chemical equipment, and in particular to a monitoring method, device, medium and equipment for metal parts of a thermal power unit. Background Art

[0002] In the related art, the number of metal parts in thermal power units is large and the distribution is scattered. When the metal parts operate in a high-temperature and high-pressure steam environment, steam oxidation will inevitably occur, generating a certain thickness of oxide scale. As the unit's operating time increases, the thickness of the oxide scale continues to increase and the oxide scale falls off. The oxide scale shedding will not only block the boiler heating surface pipes, causing serious overheating and even causing pipe bursts, but also cause erosion and wear on the steam turbine's steam chamber blades, impellers, nozzles, steam pipe valves and other components, which will have a significant impact on power generation and its stability. Summary of the invention

[0003] According to a first aspect of an embodiment of the present disclosure, a method for monitoring metal parts of a thermal power unit is provided, comprising: Acquire monitoring data of a plurality of monitoring points, wherein the plurality of monitoring points are arranged on a metal pipe of a thermal power unit, and the monitoring data include the steam temperature inside the pipe and the heat load on the outer wall of the pipe at a pipe section corresponding to each of the monitoring points; Determining a target critical temperature difference according to the steam temperature in the tube and the heat load on the outer wall of the tube corresponding to the plurality of monitoring points; The risk of oxide scale shedding of the metal pipeline is predicted at least based on the target critical temperature difference.

[0004] Optionally, determining the target critical temperature difference according to the steam temperature in the tube and the peripheral heat load of the tube outer wall corresponding to the plurality of monitoring points includes: Determine the predicted oxide scale thickness corresponding to the metal pipeline according to the steam temperature in the pipeline and the peripheral heat load of the outer wall of the pipeline corresponding to the multiple monitoring points; The target critical temperature difference is determined according to the predicted oxide scale thickness and the critical temperature difference model, wherein the critical temperature difference model is used to characterize the mapping relationship between the oxide scale thickness and the critical temperature difference corresponding to oxide scale shedding.

[0005] Optionally, determining the predicted oxide scale thickness corresponding to the metal pipeline according to the steam temperature in the pipeline and the peripheral heat load of the outer wall of the pipeline corresponding to the multiple monitoring points includes: For each monitoring point, the tube inner wall temperature of the monitoring point is determined according to the tube inner steam temperature, the tube outer wall perimeter heat load and a temperature calculation model, wherein the temperature calculation model is used to characterize the mapping relationship between the tube inner steam temperature, the maximum value of the tube outer wall perimeter heat load and the tube inner wall temperature; The predicted oxide scale thickness corresponding to the metal pipeline is determined according to the inner wall temperature of the pipe at the plurality of monitoring points.

[0006] Optionally, determining the predicted oxide scale thickness corresponding to the metal pipeline according to the inner wall temperature of the plurality of monitoring points includes: Determine a target monitoring point that meets a preset condition according to the tube inner wall temperatures of the multiple monitoring points, wherein the preset condition indicates that the duration of the target tube inner wall temperature corresponding to the target monitoring point is greater than a preset duration, and the target tube inner wall temperature is greater than a preset temperature value; The predicted oxide scale thickness corresponding to the metal pipeline is determined according to the target pipe inner wall temperature corresponding to the target monitoring point, the duration of the target pipe inner wall temperature and the oxide scale thickness model, wherein the oxide scale thickness model is used to characterize the mapping relationship between the pipe inner wall temperature, the duration of the pipe inner wall temperature and the oxide scale thickness.

[0007] Optionally, the calculation formula of the oxide scale thickness model is:

[0008] Where Dox is the predicted oxide film thickness corresponding to a monitoring point; Y is the proportional factor between the inner and outer oxide film thicknesses; K p is the pressure correction factor corresponding to the monitoring point; t is the duration of the inner wall temperature of the tube corresponding to the monitoring point; n is the oxide film generation rate index; Kox is the reaction rate constant related to the inner wall temperature of the tube corresponding to the monitoring point, Kox= ; A is the Arrhenius constant; Q is the activation energy of the metal pipe corresponding to the monitoring point; R is the universal gas constant; T b is the inner wall temperature of the pipe corresponding to the monitoring point.

[0009] Optionally, the calculation formula of the temperature calculation model is:

[0010] Among them, T b is the inner wall temperature of the tube corresponding to a monitoring point; T gz is the steam temperature in the pipe corresponding to the monitoring point; β is the diameter ratio of the metal pipe corresponding to the monitoring point; μ is the flow coefficient; q max is the maximum value of the heat load on the outer wall of the pipe corresponding to the monitoring point; δ is the wall thickness of the metal pipe corresponding to the monitoring point; λ is the thermal conductivity of the metal pipe corresponding to the monitoring point; α2 is the heat transfer coefficient of the steam temperature in the pipe corresponding to the monitoring point to the pipe wall.

[0011] Optionally, the calculation formula of the critical temperature difference model is:

[0012] in, is the target critical temperature difference for the oxide scale at a monitoring point to fall off under stress; F is the interface fracture energy between the metal pipe and the oxide scale corresponding to the monitoring point; Dox is the predicted oxide scale thickness corresponding to the monitoring point; E cx is the elastic modulus; a m a is the linear expansion coefficient of the metal pipe corresponding to the monitoring point; cx is the linear expansion coefficient of the oxide scale; is Poisson's ratio.

[0013] Optionally, determining the target critical temperature difference according to the predicted oxide scale thickness and critical temperature difference model includes: The target critical temperature difference is determined according to a target oxide scale thickness in the predicted oxide scale thickness that is greater than a preset thickness value.

[0014] Optionally, the monitoring data further includes the flue gas fly ash concentration and flue gas flow rate corresponding to each monitoring point. After predicting the oxide scale shedding risk of the metal pipeline at least according to the target critical temperature difference, the method further includes: Determining the pipe wall thinning rate of the metal pipe according to the flue gas fly ash concentration, the flue gas flow rate and the operation cycle of the metal pipe; The remaining life of the metal pipeline is predicted based on the pipe wall thinning rate and the oxide scale shedding risk.

[0015] Optionally, after predicting the oxide scale shedding risk of the metal pipe at least according to the target critical temperature difference, the method further comprises: When the oxide scale falling risk situation indicates that there is a risk of oxide scale in the metal pipe falling off, a warning message is output.

[0016] According to a second aspect of an embodiment of the present disclosure, a monitoring device for metal parts of a thermal power unit is provided, comprising: An acquisition module, used to acquire monitoring data of a plurality of monitoring points, wherein the plurality of monitoring points are arranged on a metal pipe of a thermal power unit, and the monitoring data include the steam temperature in the pipe and the heat load of the outer wall of the pipe on the pipe section corresponding to each of the monitoring points; A determination module, used to determine a target critical temperature difference according to the steam temperature in the tube and the heat load on the outer wall of the tube corresponding to the plurality of monitoring points; A prediction module is used to predict the risk of oxide scale shedding of the metal pipeline based at least on the target critical temperature difference.

[0017] According to a third aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for monitoring metal parts of a thermal power unit provided by the first aspect of the embodiment of the present disclosure is implemented.

[0018] According to a fourth aspect of an embodiment of the present disclosure, there is provided an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the method for monitoring metal parts of a thermal power unit provided in the first aspect of an embodiment of the present disclosure.

[0019] The present invention obtains the steam temperature in the corresponding pipe section and the heat load on the outer wall of the pipe by setting multiple monitoring points on the metal pipe of the thermal power unit, determines the target critical temperature difference, and predicts the risk of oxide scale shedding of the metal pipe at least according to the target critical temperature difference. In this way, the risk of oxide scale shedding can be predicted through real-time monitoring data, so that the operation and maintenance personnel can take treatment measures before the oxide scale shedding occurs, so as to reduce the risk of oxide scale shedding or clean up the shed oxide scale in time, thereby reducing the equipment failure rate and maintenance cost.

[0020] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0022] Figure 1 The present invention is a flow chart showing a method for monitoring metal parts of a thermal power unit according to an exemplary embodiment.

[0023] Figure 2 The present invention is a block diagram of a device for monitoring metal parts of a thermal power unit according to an exemplary embodiment.

[0024] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0025] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0026] In the related art, the oxide scale thickness and state are mainly evaluated through oxide scale accumulation detection and pipe cutting test. These offline methods are difficult to track the growth process of the oxide scale inside the metal pipe and cannot predict the risk of oxide scale shedding.

[0027] Reference Figure 1 , Figure 1 is a flow chart of a method for monitoring metal parts of a thermal power unit according to an exemplary embodiment. Figure 1 As shown, the method for monitoring metal parts of a thermal power unit includes the following steps.

[0028] In step S101, monitoring data of multiple monitoring points are obtained. The multiple monitoring points are set on the metal pipeline of the thermal power unit. The monitoring data include the steam temperature inside the pipe and the heat load of the outer wall of the pipe on the pipe section corresponding to each monitoring point.

[0029] In step S102, the target critical temperature difference is determined according to the steam temperature in the tube and the heat load on the outer wall of the tube corresponding to the plurality of monitoring points.

[0030] In step S103, the oxide scale shedding risk of the metal pipeline is predicted based on at least the target critical temperature difference.

[0031] For example, the metal pipelines of the thermal power unit include the main steam pipeline, the reheat steam hot section pipeline, the reheat steam cold section pipeline and the main feed water pipeline, which together constitute the main metal pipeline system of the thermal power plant. Multiple monitoring points are set on the same metal pipeline, and multiple monitoring points can be set on each metal pipeline, so that the monitoring data of each position of a metal pipeline can be obtained in real time.

[0032] For example, a method for monitoring metal parts of a thermal power unit can be executed by a computing device, wherein monitoring data can be obtained based on docking with a SIS (Safety Instrumented System), and the field instrument corresponding to the SIS system is the monitoring data obtained by the monitoring point, and the monitoring data includes, for example, temperature data, pressure data, and the like.

[0033] For example, the monitoring data may include the steam temperature inside the pipe and the heat load on the outer wall of the pipe. The steam temperature inside the pipe can characterize the temperature of the steam inside the pipe, directly affecting the heat load of the pipe and the thermal stress of the metal material, and can be obtained through a temperature sensor set inside the pipe at the monitoring point. The heat load on the outer wall of the pipe can characterize the heat load on the outer wall of the pipe, which is used to reflect the external thermal environment of the pipe and its impact on the pipe material. The temperature of the outer wall of the pipe can be measured by a temperature sensor set on the outer wall of the pipe at the monitoring point, and the heat load on the outer wall of the pipe can be calculated by the temperature of the outer wall of the pipe and the heat conduction equation.

[0034] For example, the target critical temperature difference can be used to characterize the temperature threshold at which oxide scale may fall off in a metal pipe. The oxide scale risk situation can be used to characterize the risk that the oxide scale in the metal pipe may fall off under specific temperature conditions. In addition to using the target critical temperature difference as a condition for predicting the oxide scale risk situation, the vibration that may occur during the operation of the thermal power unit can also be used as a condition for predicting the oxide scale risk situation.

[0035] For example, in the process of power generation or industrial production, deep peak regulation refers to a significant adjustment of the equipment's operating load, which may cause a sharp change in the temperature inside the equipment, thereby causing thermal expansion and contraction of the oxide scale, and the adhesion and integrity of the oxide scale may be affected, increasing the risk of shedding. During the start-up and shutdown of the equipment, the equipment experiences a sharp change in temperature and stress fluctuations, which may increase the mechanical stress of the oxide scale, thereby increasing the risk of oxide scale shedding. During the operation of the equipment, the load may fluctuate greatly due to demand fluctuations or operational adjustments, resulting in frequent and drastic changes in the temperature of the equipment, affecting the stability of the oxide scale and increasing the possibility of oxide scale peeling. Therefore, when the thermal power unit equipment corresponds to the large load fluctuations that may occur during the start-up and shutdown process, the deep peak regulation process, or the operation process, it may cause frequent or drastic changes in temperature, thereby increasing the risk of the oxide scale breaking and shedding.

[0036] For example, the target critical temperature difference can be determined based on the steam temperature in the pipe and the heat load on the outer wall of the pipe corresponding to multiple monitoring points, and the situation that may cause frequent or drastic temperature changes can be controlled based on the target critical temperature difference. For example, when the target critical temperature difference is lower than the first temperature difference threshold, the situation of large load adjustments during equipment operation can be controlled to reduce. Alternatively, when the target critical temperature difference is lower than the second temperature difference threshold, the operation of the thermal power unit can be stopped, and an alarm message can be output to prompt the operation and maintenance personnel to clean the oxide scale in time, etc. The first temperature difference threshold can be greater than the second temperature difference threshold.

[0037] The present invention obtains the steam temperature in the corresponding pipe section and the heat load on the outer wall of the pipe by setting multiple monitoring points on the metal pipe of the thermal power unit, determines the target critical temperature difference, and predicts the risk of oxide scale shedding of the metal pipe at least according to the target critical temperature difference. In this way, the risk of oxide scale shedding can be predicted through real-time monitoring data, so that the operation and maintenance personnel can take treatment measures before the oxide scale shedding occurs, so as to reduce the risk of oxide scale shedding or clean up the shed oxide scale in time, thereby reducing the equipment failure rate and maintenance cost.

[0038] As an optional embodiment, the target critical temperature difference is determined according to the steam temperature in the tube and the peripheral heat load of the tube outer wall corresponding to the multiple monitoring points, including: Determine the predicted oxide scale thickness corresponding to the metal pipeline based on the steam temperature in the pipe and the heat load on the outer wall of the pipe corresponding to multiple monitoring points; The target critical temperature difference is determined based on the predicted oxide scale thickness and the critical temperature difference model. The critical temperature difference model is used to characterize the mapping relationship between the oxide scale thickness and the critical temperature difference corresponding to oxide scale shedding.

[0039] For example, the critical temperature difference model can be a mathematical model, a neural network model, or a mapping table in a database model, etc. Among them, the oxide scale thickness on the metal pipe is predicted, and the predicted oxide scale thickness takes into account the influence of heat load and temperature on oxide scale growth. Then, the predicted oxide scale thickness is input into the critical temperature difference model, and the critical temperature difference model can determine the corresponding target critical temperature difference based on the relationship between the oxide scale thickness and the critical temperature difference corresponding to oxide scale shedding.

[0040] As an optional embodiment, the calculation formula of the critical temperature difference model is:

[0041] in, is the target critical temperature difference for the oxide scale at a monitoring point to fall off under stress; F is the interface fracture energy between the metal pipe and the oxide scale corresponding to a monitoring point, and this interface fracture energy is related to the performance of the pipe and the oxide scale; Dox is the predicted oxide scale thickness corresponding to a monitoring point; E cx is the elastic modulus; a m is the linear expansion coefficient of the metal pipe corresponding to a monitoring point; a cx is the linear expansion coefficient of the oxide scale; is Poisson's ratio.

[0042] As another optional embodiment, a database model that pre-stores the mapping relationship may be used as a critical temperature difference model. For example, after the predicted oxide scale thickness is input into the database model, the corresponding target critical temperature difference may be directly queried.

[0043] As another optional embodiment, a pre-trained neural network model can be used as a critical temperature difference model. In this case, the neural network model can be trained not only for the oxide scale thickness, but also for the ambient temperature, vibration conditions and other parameters in different operation stages to obtain a trained neural network model. Then, the oxide scale thickness is input, and the neural network model can obtain the corresponding target critical temperature difference according to the current operation stage. The type of neural network model is not limited here.

[0044] As an optional embodiment, the predicted oxide scale thickness corresponding to the metal pipeline is determined according to the steam temperature in the pipeline and the peripheral heat load of the outer wall of the pipeline corresponding to multiple monitoring points, including: For each monitoring point, the inner wall temperature of the pipe at the monitoring point is determined according to the inner steam temperature of the pipe, the outer wall perimeter heat load and the temperature calculation model. The temperature calculation model is used to characterize the mapping relationship between the inner steam temperature of the pipe, the maximum value of the outer wall perimeter heat load and the inner wall temperature of the pipe; According to the inner wall temperature of the pipe at multiple monitoring points, the predicted oxide scale thickness corresponding to the metal pipe is determined.

[0045] For example, the temperature calculation model can be a mathematical model, a neural network model, or a mapping table in a database model, etc. Among them, for each monitoring point, the inner wall temperature of the pipe corresponding to the monitoring point is determined according to the steam temperature in the pipe, the heat load of the outer wall of the pipe, and the temperature calculation model. Then, the predicted oxide scale thickness corresponding to the metal pipe can be determined according to the inner wall temperature of the pipe at multiple monitoring points.

[0046] As an optional embodiment, the calculation formula of the temperature calculation model is:

[0047] Among them, T b is the inner wall temperature of the tube corresponding to a monitoring point; T gz is the steam temperature in the pipe corresponding to a monitoring point; β is the diameter ratio of the metal pipe corresponding to a monitoring point; μ is the flow coefficient; q max is the maximum value of the heat load on the outer wall of the pipe corresponding to a monitoring point, in units of W / (㎡·℃); δ is the wall thickness of the metal pipe corresponding to a monitoring point, in units of m; λ is the thermal conductivity of the metal pipe corresponding to a monitoring point, in units of W / (㎡·℃); α2 is the heat transfer coefficient of the steam temperature inside the pipe to the pipe wall corresponding to a monitoring point, in units of W / (㎡·℃).

[0048] As another optional embodiment, a database model that pre-stores the mapping relationship can be used as a temperature calculation model. For example, after the steam temperature inside the tube and the heat load around the outer wall of the tube are input into the database model, the corresponding inner wall temperature of the tube can be directly queried.

[0049] As another optional embodiment, a pre-trained neural network model can be used as a temperature calculation model. The neural network model can be trained using the steam temperature inside the tube, the heat load on the outer wall of the tube, and the corresponding measured inner wall temperature of the tube, so that the neural network model learns the mapping relationship between the steam temperature inside the tube, the heat load on the outer wall of the tube, and the corresponding measured inner wall temperature of the tube, and obtains a trained neural network model. Then, the neural network model can output the corresponding inner wall temperature of the tube according to the current steam temperature inside the tube and the heat load on the outer wall of the tube. In addition, when training the neural network model, the diameter ratio of different metal pipes, the thermal conductivity of the pipe, etc. can also be used as environmental influencing factors to train the neural network model, thereby obtaining a trained neural network model. The type of neural network model is not limited here.

[0050] As an optional embodiment, determining the predicted oxide scale thickness corresponding to the metal pipeline according to the inner wall temperature of the pipeline at multiple monitoring points includes: Determine a target monitoring point that meets a preset condition according to the pipe inner wall temperatures of multiple monitoring points, wherein the preset condition indicates that the duration of the target pipe inner wall temperature corresponding to the target monitoring point is greater than a preset duration, and the target pipe inner wall temperature is greater than a preset temperature value; The predicted oxide scale thickness corresponding to the metal pipeline is determined according to the target pipe inner wall temperature corresponding to the target monitoring point, the duration of the target pipe inner wall temperature and the oxide scale thickness model, wherein the oxide scale thickness model is used to characterize the mapping relationship between the pipe inner wall temperature, the duration of the pipe inner wall temperature and the oxide scale thickness.

[0051] For example, the preset condition can be used to limit the target monitoring points that need to be focused on. The preset condition is set to the duration corresponding to the inner wall temperature of the pipe greater than the preset temperature value is greater than the preset duration. Under the preset condition, the thickness of the oxide scale growth may be greater, so the possibility of creep occurring at the pipeline monitoring point corresponding to the preset condition is greater. Choosing to calculate and predict the oxide scale thickness for the target monitoring point can save most of the computing resources and reduce the computing burden of the equipment.

[0052] For example, the duration can be obtained based on the time of continuous monitoring of the monitoring point. For example, when the temperature of the inner wall of the pipe at the monitoring point is greater than the preset temperature value, the timing starts, and when the oxide scale thickness is currently calculated, the previous timing is used as the duration; once the temperature of the inner wall of the pipe at the monitoring point is less than or equal to the preset temperature value, the timing is stopped. In this case, the timing may be performed multiple times within a period of time before the calculation to obtain multiple durations. Therefore, when the oxide scale thickness is currently calculated, the duration may be taken as the cumulative duration corresponding to the multiple durations obtained previously.

[0053] For example, the oxide scale thickness model may be a mathematical model, a neural network model, or a mapping relationship table in a database model, and the like.

[0054] As an optional embodiment, the calculation formula of the oxide scale thickness model is:

[0055] Where Dox is the predicted oxide film thickness corresponding to a monitoring point; Y is the proportional factor between the inner and outer oxide film thicknesses, which is generally 1 and can be corrected based on the SEM analysis of the cut pipe; K p is the pressure correction factor corresponding to a monitoring point, which is related to the steam pressure and is pre-fitted according to the experimental and field data; t is the duration of the inner wall temperature of the tube corresponding to a monitoring point, in units of h; n is the oxide film formation rate index, which can be obtained according to the parabolic law; Kox is the reaction rate constant related to the inner wall temperature of the tube corresponding to a monitoring point, and Kox= ; A is the Arrhenius constant, which is related to the material's oxidation resistance and is obtained based on experimental and field data in um / h; Q is the activation energy of the metal pipe corresponding to a monitoring point, which is related to the material's oxidation resistance and can be obtained based on experimental and field data in kj / mol; R is the universal gas constant; T b is the inner wall temperature of the tube corresponding to a monitoring point, that is, the temperature at which the oxide film grows.

[0056] As another optional embodiment, a database model that pre-stores the mapping relationship can be used as an oxide scale thickness model. For example, after the inner wall temperature of the tube and the duration of the inner wall temperature of the tube are input into the database model, the corresponding predicted oxide scale thickness can be directly queried.

[0057] As another optional embodiment, a pre-trained neural network model can be used as an oxide scale thickness model. The neural network model can be trained using the tube inner wall temperature, the duration of the tube inner wall temperature, and the corresponding measured oxide scale thickness, so that the neural network model learns the mapping relationship between the tube inner wall temperature, the duration of the tube inner wall temperature, and the corresponding measured oxide scale thickness, and obtains a trained neural network model. Then, the neural network model can output the corresponding predicted oxide scale thickness based on the current tube inner wall temperature and the duration of the tube inner wall temperature. In addition, when training the neural network model, the activation energy and steam pressure of the pipe materials of different metal pipes can also be used as environmental influencing factors to train the neural network model, thereby obtaining a trained neural network model. The type of neural network model is not limited here.

[0058] As an optional embodiment, determining the target critical temperature difference according to the predicted oxide scale thickness and critical temperature difference model includes: The target critical temperature difference is determined according to a target oxide scale thickness in the predicted oxide scale thickness that is greater than a preset thickness value.

[0059] For example, the greater the oxide scale thickness, the greater the risk of falling off. The target critical temperature difference can be determined only for the predicted oxide scale thickness. In this way, the target critical temperature difference can be calculated only for the target oxide scale thickness greater than the preset thickness value, and the corresponding oxide scale falling risk can be determined. In this way, computing power resources can be further saved.

[0060] For example, for each monitoring point, the predicted oxide film thickness on the time series can be calculated, and the oxide film thickness chart can be output, and the time point when the predicted oxide film thickness is greater than the preset thickness value can be marked in the chart. Among them, different preset thickness values ​​can be set for different pipes of metal pipes. For example, taking T91 steel as an example, the critical shedding thickness of the oxide film is 0.2mm, and the preset thickness value can be set to 0.2mm. For 12CrMoV pipes, the preset thickness value can be set to 0.1mm.

[0061] As an optional embodiment, the monitoring data further includes the flue gas fly ash concentration and flue gas flow rate corresponding to each monitoring point. After predicting the oxide scale shedding risk of the metal pipeline at least according to the target critical temperature difference, the method further includes: Determine the wall thinning rate of the metal pipeline according to the flue gas fly ash concentration, flue gas flow rate and the operation cycle of the metal pipeline; Predict the remaining life of metal pipelines based on the wall thinning rate and / or scale loss risk.

[0062] For example, flue gas fly ash concentration refers to the concentration of fly ash (solid particulate matter) suspended in flue gas. Fly ash usually comes from incompletely burned substances during the combustion process, causing wear and corrosion to metal pipes. Flue gas flow rate is the speed at which flue gas flows in the pipe. Flue gas flow rate affects the deposition of fly ash and the scouring effect on the pipe wall. During the operation of metal pipes, the pipe wall becomes thinner due to factors such as high temperature, corrosion, and wear. The wall thinning rate of the metal pipe is determined based on the flue gas fly ash concentration, flue gas flow rate, and the operation cycle of the metal pipe. The wall thinning rate is usually expressed as a thickness reduction or percentage.

[0063] For example, the pipe wall thinning rate can characterize the speed of pipe wall thinning caused by corrosion and wear, so that the current pipe wall thickness can be determined based on the measured pipe wall thickness and the pipe wall thinning rate. The operation cycle here can refer to the total operation time of the thermal power unit equipment between the time when the pipe wall thickness is measured and the current time.

[0064] For example, higher fly ash concentrations and faster flow rates may lead to greater wear and corrosion, and a higher rate of thinning of the pipe wall. Oxide scale shedding due to corrosion can also cause thinning of the pipe wall, and then the remaining life of the metal pipe can be predicted based on the risk of oxide scale shedding and the calculated current pipe wall thickness. Among them, a neural network model can be used to estimate the further thinning and damage of the pipe under existing conditions, thereby predicting the remaining time that the metal pipe can be safely used. According to the predicted pipe wall thinning rate and remaining life, preventive maintenance measures such as maintenance or replacement of the pipe can be arranged in time to reduce the risk of unexpected failures. In the related art, there are already technical means for predicting the remaining life of metal pipes based on the oxide scale thickness and / or pipe wall thinning rate of metal pipes, which are not further restricted here.

[0065] As an optional embodiment, after predicting the oxide scale shedding risk of the metal pipeline at least according to the target critical temperature difference, the method further includes: When the oxide scale shedding risk situation indicates that there is a risk of oxide scale shedding in the metal pipe, an early warning message is output.

[0066] For example, when the oxide scale shedding risk situation indicates that there is a risk of oxide scale shedding in the metal pipe, an early warning message is output to prompt the operation and maintenance personnel to perform corresponding treatment measures. The early warning message can be output in the form of a voice broadcast, or in the form of sending information to the device terminal corresponding to the operation and maintenance personnel, or in the form of displaying the early warning message on the display interface corresponding to the control system of the thermal power unit. The specific output form is not limited here.

[0067] In the present invention, when the calculated oxide scale thickness reaches the target oxide scale thickness, the oxide scale peels off in flakes and cross-stacks at the bottom of the heat exchange tube due to the influence of factors such as the temperature difference being greater than or equal to the target critical temperature difference and vibration. The risk of oxide scale shedding during operation can be warned and controlled through big data and expert models, thereby eliminating the basic conditions for oxide scale shedding.

[0068] As an example, the present disclosure also provides a visual monitoring system for metal parts of a thermal power unit, comprising: The real-time data acquisition module is used to collect real-time data of the metal parts of the thermal power unit to obtain monitoring data; An evaluation module, used to execute the steps of the method for monitoring metal parts of a thermal power unit disclosed in the present invention, to analyze and calculate the monitoring data, thereby evaluating the remaining life of the metal parts and the risk of oxide scale shedding; The visualization module is used to visualize the warning information, remaining life information, predicted oxide scale shedding risk, monitoring data corresponding to each monitoring point, etc. output from the monitoring method of the metal parts of the thermal power unit; The early warning module is used to issue an early warning for abnormal information issued by the evaluation module. For example, the abnormal information may include that the remaining life is less than a preset number of days and the risk of oxide scale shedding is greater than a preset probability value.

[0069] The present disclosure realizes visualization of monitoring data through real-time data acquisition module, evaluation module, visualization module and early warning module, and provides collected data and calculated data for users to query and browse, thereby improving the convenience of thermal power unit maintenance.

[0070] In an exemplary embodiment, the evaluation module can be used to analyze the erosion and wear patterns, predict the rate of wall thickness loss due to corrosion inside and outside the pipe, and determine the life of the pipe due to overheating creep. It can also execute a monitoring method for metal components of thermal power units to achieve early warning of oxide scale growth and risk of oxide scale shedding, thereby achieving comprehensive monitoring of metal components.

[0071] In an exemplary embodiment, the present disclosure may also provide a monitoring system for metal parts of a thermal power unit, wherein the monitoring system is provided with a multi-integrated database for storing the entire life cycle of metal parts, and intelligent data entry can be realized by entering monitoring data of the entire life cycle of metal parts, including existing static data, periodically updated dynamic data, and real-time collected monitoring data, and based on algorithms and programs for automatic data reading and entry. The monitoring system may also judge the importance level of parts and data through classification and sorting procedures and information importance performance judgment basis, and can classify and display. In addition, the monitoring system can also realize the interaction between the maintenance data and the three-dimensional model through the interface program of the three-dimensional model corresponding to the metal parts of the thermal power unit. For example, by clicking on different parts of the three-dimensional model in the human-computer interaction interface of the monitoring system, the health management files such as the design, installation, and inspection of the corresponding metal parts will pop up, and the alarm information of the over-temperature and over-pressure conditions of each metal part will be output, and the failure risk of the parts will be predicted according to the historical trend. For example, based on the above-mentioned monitoring method of the metal parts of the thermal power unit, based on the monitoring data collected by the SIS system, the monitoring system automatically calculates the oxide scale growth risk, oxide scale shedding risk, cumulative damage and remaining life of each component, and evaluates and predicts them for users to query and browse. Specifically, through big data algorithm analysis, the cumulative effect of soot blowing at each position and the cumulative effect of over-temperature conditions on the thinning of the heating surface of the superheater and reheater are analyzed. The superheat and reheat big data model is formed by comprehensive calculation data to quantify the thinning rate and remaining life, extract the prediction characteristics of oxide scale shedding risk, determine the monitoring characteristics of furnace tube blockage risk, and realize the online alarm function of oxide scale shedding. Through big data and expert model early warning, the basic conditions for its shedding are eliminated.

[0072] Reference Figure 2 , Figure 2FIG. 1 is a block diagram of a monitoring device for metal parts of a thermal power plant according to an exemplary embodiment. Figure 2 As shown, the monitoring device for metal parts of a thermal power unit includes an acquisition module 201 , a determination module 202 and a prediction module 203 .

[0073] An acquisition module 201 is used to acquire monitoring data of multiple monitoring points, where the multiple monitoring points are set on the metal pipes of the thermal power unit, and the monitoring data include the steam temperature inside the pipe and the heat load on the outer wall of the pipe on the pipe section corresponding to each monitoring point; A determination module 202 is used to determine a target critical temperature difference according to the steam temperature in the tube and the heat load on the outer wall of the tube corresponding to the plurality of monitoring points; The prediction module 203 is used to predict the risk of oxide scale shedding of the metal pipeline at least based on the target critical temperature difference.

[0074] As an optional embodiment, the determining module 202 is further configured to: Determine the predicted oxide scale thickness corresponding to the metal pipeline based on the steam temperature in the pipe and the heat load on the outer wall of the pipe corresponding to multiple monitoring points; The target critical temperature difference is determined based on the predicted oxide scale thickness and the critical temperature difference model. The critical temperature difference model is used to characterize the mapping relationship between the oxide scale thickness and the critical temperature difference corresponding to oxide scale shedding.

[0075] As an optional embodiment, the determining module 202 is further configured to: For each monitoring point, the inner wall temperature of the pipe at the monitoring point is determined according to the inner steam temperature of the pipe, the outer wall perimeter heat load and the temperature calculation model. The temperature calculation model is used to characterize the mapping relationship between the inner steam temperature of the pipe, the maximum value of the outer wall perimeter heat load and the inner wall temperature of the pipe; According to the inner wall temperature of the pipe at multiple monitoring points, the predicted oxide scale thickness corresponding to the metal pipe is determined.

[0076] As an optional embodiment, the determining module 202 is further configured to: Determine a target monitoring point that meets a preset condition according to the pipe inner wall temperatures of multiple monitoring points, wherein the preset condition indicates that the duration of the target pipe inner wall temperature corresponding to the target monitoring point is greater than a preset duration, and the target pipe inner wall temperature is greater than a preset temperature value; The predicted oxide scale thickness corresponding to the metal pipeline is determined according to the target pipe inner wall temperature corresponding to the target monitoring point, the duration of the target pipe inner wall temperature and the oxide scale thickness model, wherein the oxide scale thickness model is used to characterize the mapping relationship between the pipe inner wall temperature, the duration of the pipe inner wall temperature and the oxide scale thickness.

[0077] As an optional embodiment, the calculation formula of the oxide scale thickness model is:

[0078] Where Dox is the predicted oxide film thickness corresponding to a monitoring point; Y is the proportional factor between the inner and outer oxide film thicknesses; K p is the pressure correction factor corresponding to a monitoring point; t is the duration of the inner wall temperature of the tube corresponding to a monitoring point; n is the oxide film generation rate index; Kox is the reaction rate constant related to the inner wall temperature of the tube corresponding to a monitoring point, Kox= ; A is the Arrhenius constant; Q is the activation energy of the metal pipe corresponding to a monitoring point; R is the universal gas constant; T b is the inner wall temperature of the pipe corresponding to a monitoring point.

[0079] As an optional embodiment, the calculation formula of the temperature calculation model is:

[0080] Among them, T b is the inner wall temperature of the tube corresponding to a monitoring point; T gz is the steam temperature in the pipe corresponding to a monitoring point; β is the diameter ratio of the metal pipe corresponding to a monitoring point; μ is the flow coefficient; q max is the maximum value of the heat load on the outer wall of the pipe corresponding to a monitoring point; δ is the wall thickness of the metal pipe corresponding to a monitoring point; λ is the thermal conductivity of the metal pipe corresponding to a monitoring point; α2 is the heat transfer coefficient of the steam temperature inside the pipe to the pipe wall corresponding to a monitoring point.

[0081] As an optional embodiment, the calculation formula of the critical temperature difference model is:

[0082] in, is the target critical temperature difference for the oxide scale at a monitoring point to fall off under stress; F is the interface fracture energy between the metal pipe and the oxide scale corresponding to a monitoring point; Dox is the predicted oxide scale thickness corresponding to a monitoring point; E cx is the elastic modulus; a m is the linear expansion coefficient of the metal pipe corresponding to a monitoring point; a cx is the linear expansion coefficient of the oxide scale; is Poisson's ratio.

[0083] As an optional embodiment, the determining module 202 is further configured to: The target critical temperature difference is determined according to a target oxide scale thickness in the predicted oxide scale thickness that is greater than a preset thickness value.

[0084] As an optional embodiment, the monitoring data also includes the flue gas fly ash concentration and flue gas flow rate corresponding to each monitoring point, and the monitoring device of the metal parts of the thermal power unit is also used for: Determine the wall thinning rate of the metal pipeline according to the flue gas fly ash concentration, flue gas flow rate and the operation cycle of the metal pipeline; Predict the remaining life of metal pipelines based on the pipe wall thinning rate and the risk of oxide scale shedding.

[0085] As an optional embodiment, the monitoring device for metal parts of a thermal power unit is also used for: When the oxide scale shedding risk situation indicates that there is a risk of oxide scale shedding in the metal pipe, an early warning message is output.

[0086] Regarding the monitoring device for metal parts of a thermal power unit in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the monitoring method for metal parts of the thermal power unit, and will not be elaborated here.

[0087] The present disclosure also provides a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for monitoring metal parts of a thermal power unit of the present disclosure is implemented.

[0088] The present disclosure also provides an electronic device, comprising: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the method for monitoring metal parts of a thermal power unit disclosed in the present invention.

[0089] Figure 3 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 3 As shown, the electronic device 700 may include: a processor 701 , a memory 702 . The electronic device 700 may also include one or more of a multimedia component 703 , an I / O (input / output) interface 704 , and a communication component 705 .

[0090] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned method for monitoring metal parts of a thermal power unit. The memory 702 is used to store various types of data to support the operation of the electronic device 700, and these data may include, for example, instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, which is used to receive external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the above-mentioned other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0091] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned method for monitoring metal parts of thermal power units.

[0092] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned method for monitoring metal parts of a thermal power unit are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions may be executed by the processor 701 of the electronic device 700 to complete the above-mentioned method for monitoring metal parts of a thermal power unit.

[0093] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned method for monitoring metal parts of a thermal power unit when executed by the programmable device.

[0094] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0095] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for monitoring metal parts of a thermal power unit, characterized in that: include: Acquire monitoring data of a plurality of monitoring points, wherein the plurality of monitoring points are arranged on a metal pipe of a thermal power unit, and the monitoring data include the steam temperature inside the pipe and the heat load on the outer wall of the pipe at a pipe section corresponding to each of the monitoring points; Determining a target critical temperature difference according to the steam temperature in the tube and the heat load on the outer wall of the tube corresponding to the plurality of monitoring points; The risk of oxide scale shedding of the metal pipeline is predicted at least based on the target critical temperature difference.

2. The method according to claim 1, characterized in that Determining a target critical temperature difference according to the steam temperature in the tube and the heat load on the outer wall of the tube corresponding to the plurality of monitoring points includes: Determine the predicted oxide scale thickness corresponding to the metal pipeline according to the steam temperature in the pipeline and the peripheral heat load of the outer wall of the pipeline corresponding to the multiple monitoring points; The target critical temperature difference is determined according to the predicted oxide scale thickness and the critical temperature difference model, wherein the critical temperature difference model is used to characterize the mapping relationship between the oxide scale thickness and the critical temperature difference corresponding to oxide scale shedding.

3. The method according to claim 2, characterized in that Determining the predicted oxide scale thickness corresponding to the metal pipeline according to the steam temperature in the pipeline and the heat load on the outer wall of the pipeline corresponding to the plurality of monitoring points includes: For each monitoring point, the tube inner wall temperature of the monitoring point is determined according to the tube inner steam temperature, the tube outer wall perimeter heat load and a temperature calculation model, wherein the temperature calculation model is used to characterize the mapping relationship between the tube inner steam temperature, the maximum value of the tube outer wall perimeter heat load and the tube inner wall temperature; The predicted oxide scale thickness corresponding to the metal pipeline is determined according to the inner wall temperature of the pipe at the plurality of monitoring points.

4. The method according to claim 3, characterized in that Determining the predicted oxide scale thickness corresponding to the metal pipeline according to the inner wall temperature of the plurality of monitoring points includes: Determine a target monitoring point that meets a preset condition according to the tube inner wall temperatures of the multiple monitoring points, wherein the preset condition indicates that the duration of the target tube inner wall temperature corresponding to the target monitoring point is greater than a preset duration, and the target tube inner wall temperature is greater than a preset temperature value; The predicted oxide scale thickness corresponding to the metal pipeline is determined according to the target pipe inner wall temperature corresponding to the target monitoring point, the duration of the target pipe inner wall temperature and the oxide scale thickness model, wherein the oxide scale thickness model is used to characterize the mapping relationship between the pipe inner wall temperature, the duration of the pipe inner wall temperature and the oxide scale thickness.

5. The method according to claim 4, characterized in that The calculation formula of the oxide scale thickness model is: Where Dox is the predicted oxide film thickness corresponding to a monitoring point; Y is the proportional factor between the inner and outer oxide film thicknesses; K p is the pressure correction factor corresponding to the monitoring point; t is the duration of the inner wall temperature of the tube corresponding to the monitoring point; n is the oxide film generation rate index; Kox is the reaction rate constant related to the inner wall temperature of the tube corresponding to the monitoring point, Kox= ; A is the Arrhenius constant; Q is the activation energy of the metal pipe corresponding to the monitoring point; R is the universal gas constant; T b is the inner wall temperature of the pipe corresponding to the monitoring point.

6. The method according to claim 3, characterized in that The calculation formula of the temperature calculation model is: Among them, T b is the inner wall temperature of the tube corresponding to a monitoring point; T gz is the steam temperature in the pipe corresponding to the monitoring point; β is the diameter ratio of the metal pipe corresponding to the monitoring point; μ is the flow coefficient; q max is the maximum value of the heat load on the outer wall of the pipe corresponding to the monitoring point; δ is the wall thickness of the metal pipe corresponding to the monitoring point; λ is the thermal conductivity of the metal pipe corresponding to the monitoring point; α2 is the heat transfer coefficient of the steam temperature in the pipe corresponding to the monitoring point to the pipe wall.

7. The method according to claim 2, characterized in that The calculation formula of the critical temperature difference model is: in, is the target critical temperature difference for the oxide scale at a monitoring point to fall off under stress; F is the interface fracture energy between the metal pipe and the oxide scale corresponding to the monitoring point; Dox is the predicted oxide scale thickness corresponding to the monitoring point; E cx is the elastic modulus; a m a is the linear expansion coefficient of the metal pipe corresponding to the monitoring point; cx is the linear expansion coefficient of the oxide scale; is Poisson's ratio.

8. The method according to any one of claims 2 to 7, characterized in that: Determining the target critical temperature difference according to the predicted oxide scale thickness and critical temperature difference model includes: The target critical temperature difference is determined according to a target oxide scale thickness in the predicted oxide scale thickness that is greater than a preset thickness value.

9. The method according to any one of claims 1 to 7, characterized in that: The monitoring data also includes the flue gas fly ash concentration and flue gas flow rate corresponding to each monitoring point. After predicting the oxide scale shedding risk of the metal pipeline at least according to the target critical temperature difference, the method further includes: Determining the pipe wall thinning rate of the metal pipe according to the flue gas fly ash concentration, the flue gas flow rate and the operation cycle of the metal pipe; The remaining life of the metal pipeline is predicted based on the pipe wall thinning rate and the oxide scale shedding risk.

10. The method according to any one of claims 1 to 7, characterized in that: After predicting the oxide scale shedding risk of the metal pipe at least according to the target critical temperature difference, the method further includes: When the oxide scale falling risk situation indicates that there is a risk of oxide scale in the metal pipe falling off, a warning message is output.

11. A monitoring device for metal parts of a thermal power unit, characterized in that: include: An acquisition module, used to acquire monitoring data of a plurality of monitoring points, wherein the plurality of monitoring points are arranged on a metal pipe of a thermal power unit, and the monitoring data include a pipe internal steam temperature and a pipe outer wall perimeter heat load on a pipe cross section corresponding to each of the monitoring points; A determination module, used to determine a target critical temperature difference according to the steam temperature in the tube and the heat load on the outer wall of the tube corresponding to the plurality of monitoring points; A prediction module is used to predict the risk of oxide scale shedding of the metal pipeline based at least on the target critical temperature difference.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for monitoring metal parts of a thermal power unit according to any one of claims 1 to 10 is implemented.

13. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, used to execute the computer program in the memory to implement the method for monitoring metal parts of a thermal power unit according to any one of claims 1 to 10.

Images