A method and device for controlling corrosion of generator set pipelines

Abstract

This application provides a method and apparatus for controlling corrosion in generator set pipelines. The method includes: performing feature normalization processing on the original dataset to obtain a target dataset; constructing an iron ion concentration prediction model based on the iron ion concentration in the target dataset and the unit operating parameters; calculating the predicted iron ion concentration using the iron ion concentration prediction model and real-time unit operating parameters; calculating the real-time corrosion rate using a corrosion rate physical model and the predicted iron ion concentration; obtaining the monitoring result based on the relationship between the real-time corrosion rate and a corrosion rate threshold; and adjusting the unit operating parameters in reverse when the real-time corrosion rate exceeds the corrosion rate threshold until the real-time corrosion rate falls back to within the corrosion rate threshold. By predicting the predicted iron ion concentration under real-time unit operating parameters and combining it with the corrosion rate physical model for online monitoring and control of the corrosion rate, this method solves the problems of significant lag and insufficient accuracy in existing boiler steam-water system corrosion monitoring and control methods.

Description

Technical Field

[0001] This invention relates to the field of corrosion control technology for steam and water systems of coal-fired boilers, and particularly to a method and device for controlling corrosion of generator set pipelines. Background Technology

[0002] Corrosion in the steam-water system of coal-fired boilers remains a core factor restricting the safe and efficient operation of boilers. During operation, corrosion can lead to malfunctions such as thinning of pipe walls and peeling of oxide scale, which not only reduces the service life of the unit but may also threaten operational stability due to structural failures caused by corrosion. Such corrosion problems involve complex physicochemical processes and are closely related to unit operating parameters (such as load and water pH), the formation, migration, and peeling behavior of corrosion products. Therefore, dynamic monitoring and precise control are crucial requirements for achieving long-term safe operation of the boiler.

[0003] Existing monitoring and control technologies for corrosion in boiler steam-water systems mainly fall into two categories: periodic sampling and detection technologies, and parameter monitoring combined with experience-based adjustment technologies. However, both have significant limitations. Periodic sampling and detection technologies periodically collect samples from relevant parts of the steam-water system and analyze indicators such as corrosion product concentration to assess the corrosion status. However, this method has a long detection cycle and significant lag, failing to reflect the corrosion process in real-time and dynamically, making timely control of corrosion difficult, often resulting in a severe stage by the time a fault is detected. Parameter monitoring combined with experience-based adjustment technologies rely on monitoring simple parameters such as wall temperature and thickness, combined with operational experience for corrosion control adjustments. However, this method lacks precise model support and cannot fully correlate the complex relationships between unit operating parameters, corrosion product behavior, and wall corrosion status. This leads to a lack of scientific basis for operational adjustments, often exacerbating corrosion risks due to improper control, further threatening the safe operation of the boiler. Summary of the Invention

[0004] This invention provides a method and apparatus for controlling corrosion of generator set pipelines, which solves the problems of significant lag and insufficient accuracy in existing corrosion monitoring and control methods for boiler steam-water systems.

[0005] In a first aspect, the present invention provides a method for controlling corrosion of generator set pipelines, comprising: The original dataset is subjected to feature normalization to obtain the target dataset; A model for predicting iron ion concentration is constructed using the iron ion concentration and unit operating parameters in the target dataset. The predicted iron ion concentration is calculated using the iron ion concentration prediction model and real-time unit operating parameters obtained at a preset frequency. The real-time corrosion rate is calculated using a preset physical model of corrosion rate and the predicted iron ion concentration. The monitoring results are obtained based on the relationship between the real-time corrosion rate and the preset corrosion rate threshold. When the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold, the unit operating parameters are adjusted in the opposite direction until the real-time corrosion rate falls back to within the corrosion rate threshold. When the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold, the unit operating parameters are adjusted in the opposite direction until the real-time corrosion rate falls back to within the corrosion rate threshold.

[0006] Optionally, using the iron ion concentration and unit operating parameters in the target dataset, an iron ion concentration prediction model is constructed, including: A linear regression model was established with the iron ion concentration as the dependent variable and the unit operating parameters as the independent variables. The optimal weighting coefficients of the unit operating parameters that minimize the prediction error of the linear regression model are determined by the least squares method. Based on the unit operating parameters and the corresponding optimal weighting coefficients, the iron ion concentration prediction model is constructed.

[0007] Optionally, the step of adjusting the unit operating parameters in reverse when the monitoring result shows that the real-time corrosion rate exceeds the corrosion rate threshold, until the real-time corrosion rate falls back to within the corrosion rate threshold, specifically includes: When the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold, the corresponding unit operating parameters are adjusted in reverse order according to the optimal weight coefficient from high to low, until the real-time corrosion rate falls back to within the corrosion rate threshold.

[0008] Optionally, feature normalization is performed on the acquired raw dataset to obtain the target dataset, including: The 3σ criterion was used to detect and eliminate outliers in the iron ion concentration and the unit operating parameters. Linear interpolation or K-nearest neighbor interpolation is performed to fill in the iron ion concentration and the unit operating parameters; The iron ion concentration and the unit operating parameters after filling were subjected to Min-Max feature normalization to obtain the target dataset.

[0009] Optionally, the optimal weighting coefficients of the unit operating parameters that minimize the prediction error of the linear regression model are determined using the least squares method, including: Construct a total error function with the weighting coefficients of the operating parameters of each unit as variables; By minimizing the total error function, the optimal weighting coefficients of each unit operating parameter that minimizes the error are calculated.

[0010] Optionally, the physical model for the corrosion rate is: ; in, The rate of mass change of corrosion products in the working fluid. The mass transfer coefficient is . This represents the concentration of iron ions near the metal-matrix interface, which is approximately equal to the saturation concentration. This represents the iron ion concentration.

[0011] Secondly, the present invention provides a device for controlling corrosion of generator set pipelines, characterized in that it includes: The data preprocessing module is used to perform feature normalization on the acquired raw dataset to obtain the target dataset; The model building module is used to build an iron ion concentration prediction model based on the iron ion concentration and unit operating parameters in the target dataset. The concentration prediction module is used to calculate the predicted iron ion concentration by using the iron ion concentration prediction model and combining it with the real-time unit operating parameters obtained at a preset frequency. The corrosion rate calculation module is used to calculate the real-time corrosion rate using a preset physical model of corrosion rate and the predicted iron ion concentration. The monitoring module is used to obtain monitoring results based on the relationship between the real-time corrosion rate and the preset corrosion rate threshold. The adjustment module is used to reverse the adjustment of the unit operating parameters when the monitoring result shows that the real-time corrosion rate exceeds the corrosion rate threshold, until the real-time corrosion rate falls back to within the corrosion rate threshold.

[0012] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the steps of the method provided in the first aspect above.

[0013] Fourthly, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the method provided in the first aspect above.

[0014] Fifthly, the present invention provides a computer program product comprising a computer program that, when executed by a processor, performs the steps of the method provided in the first aspect above.

[0015] As can be seen from the above technical solutions, the present invention has the following advantages: This invention provides a method and apparatus for controlling corrosion in generator set pipelines. The method includes: performing feature normalization processing on the acquired raw dataset to obtain a target dataset; constructing an iron ion concentration prediction model using the iron ion concentration and unit operating parameters in the target dataset; calculating the predicted iron ion concentration using the iron ion concentration prediction model and real-time unit operating parameters acquired at a preset frequency; calculating the real-time corrosion rate using a preset corrosion rate physical model and the predicted iron ion concentration; obtaining a monitoring result based on the relationship between the real-time corrosion rate and a preset corrosion rate threshold; and adjusting the unit operating parameters in reverse when the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold until the real-time corrosion rate falls back to within the corrosion rate threshold. By constructing an iron ion concentration model to predict the predicted iron ion concentration under real-time unit operating parameters and combining it with the corrosion rate physical model for online monitoring and control of the corrosion rate, this method solves the problems of significant lag and insufficient accuracy in existing boiler steam-water system corrosion monitoring and control methods. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the steps of a method for controlling corrosion of generator set pipelines according to the present invention. Figure 2 This is a flowchart illustrating the steps of a second embodiment of the method for controlling corrosion of generator set pipelines according to the present invention. Figure 3 This is a schematic diagram of the placement of an online iron ion monitoring instrument in a steam-water circulation system, which is a second embodiment of a method for controlling corrosion of generator set pipelines according to the present invention. Figure 4 This is a schematic diagram of pipeline installation in Embodiment 2 of a method for controlling pipeline corrosion in generator sets according to the present invention; Figure 5 This is a structural block diagram of an embodiment of a generator set pipeline corrosion control device according to the present invention. Detailed Implementation

[0018] This invention provides a method and apparatus for controlling corrosion of generator set pipelines, which addresses the significant lag and insufficient accuracy of existing methods for monitoring and controlling corrosion in boiler steam-water systems.

[0019] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0020] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating the steps of a method for controlling corrosion in generator set pipelines according to an embodiment of the present invention. The method includes: Step S101: Perform feature normalization on the acquired raw dataset to obtain the target dataset; In this embodiment of the application, the original dataset includes iron ion concentration and unit operating parameters, which include, but are not limited to: unit load, water pH value, dissolved oxygen content, conductivity, pipeline temperature, water hardness, steam humidity, steam velocity, feedwater flow rate, feedwater pressure, feedwater temperature, and main steam pressure.

[0021] Step S102: Construct an iron ion concentration prediction model using the iron ion concentration and unit operating parameters in the target dataset; In this embodiment of the application, a linear regression model is established based on the target dataset. This model uses iron ion concentration as the dependent variable (prediction target) and the aforementioned multiple unit operating parameters as independent variables.

[0022] Step S103: Using the iron ion concentration prediction model and combining it with the real-time unit operating parameters obtained at a preset frequency, the predicted iron ion concentration is calculated. In this embodiment, the current unit operating parameters are collected in real time at a sampling frequency of not less than 1 Hz. These real-time parameters are input into the pre-constructed iron ion concentration prediction model, and the current predicted iron ion concentration is output.

[0023] Step S104: Using a preset physical model of corrosion rate and combined with the predicted iron ion concentration, the real-time corrosion rate is calculated. In this embodiment of the application, a preset physical model of corrosion rate is used, combined with the predicted concentration of iron ions, to calculate the real-time corrosion rate, thereby achieving a quantitative assessment of the real-time corrosion rate of the pipeline.

[0024] Step S105: Based on the relationship between the real-time corrosion rate and the preset corrosion rate threshold, the monitoring result is obtained.

[0025] In this embodiment, the calculated real-time corrosion rate is compared with a pre-set corrosion rate threshold. If the real-time corrosion rate is less than or equal to the corrosion rate threshold, the monitoring result is "safe". If the real-time corrosion rate is greater than the corrosion rate threshold, the monitoring result is "corrosion risk exceeds the standard".

[0026] Step S106: When the monitoring result shows that the real-time corrosion rate exceeds the corrosion rate threshold, the unit operating parameters are adjusted in the opposite direction until the real-time corrosion rate falls back to within the corrosion rate threshold.

[0027] In this embodiment of the application, when the real-time corrosion rate exceeds the corrosion rate threshold, it is necessary to reverse the adjustment of the unit operating parameters so that the monitoring results are normal.

[0028] This invention provides a method for controlling corrosion in generator set pipelines, comprising: performing feature normalization on an acquired raw dataset to obtain a target dataset; constructing an iron ion concentration prediction model using the iron ion concentration and generator operating parameters in the target dataset; calculating the predicted iron ion concentration using the iron ion concentration prediction model and real-time generator operating parameters acquired at a preset frequency; calculating the real-time corrosion rate using a preset corrosion rate physical model and the predicted iron ion concentration; obtaining a monitoring result based on the relationship between the real-time corrosion rate and a preset corrosion rate threshold; and adjusting the generator operating parameters in reverse when the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold until the real-time corrosion rate falls back to within the corrosion rate threshold. By constructing an iron ion concentration model to predict the predicted iron ion concentration under real-time generator operating parameters and combining it with a corrosion rate physical model to control the corrosion rate online, this method solves the problems of significant lag and insufficient accuracy in existing boiler steam-water system corrosion monitoring and control methods.

[0029] Example 2 Please see Figure 2 , Figure 2 This is a flowchart illustrating a second embodiment of the method for controlling corrosion in generator set pipelines according to the present invention. The steps include: Step S201: Perform feature normalization on the acquired raw dataset to obtain the target dataset; In this embodiment, the 3σ criterion is used to detect and remove outliers in the iron ion concentration and the unit operating parameters; linear interpolation or K-nearest neighbor interpolation is used to fill in the iron ion concentration and the unit operating parameters; and Min-Max feature normalization is performed on the filled iron ion concentration and the unit operating parameters to obtain the target dataset.

[0030] Please see Figure 3 , Figure 3 This is a schematic diagram illustrating the placement of online iron ion monitors in the steam-water circulation system of a second embodiment of the monitoring method for pipeline corrosion in a generator set according to the present invention. The steam-water circulation system consists of a condenser and condensate system, a deaerator system, a boiler feedwater system, a boiler body system, and a turbine system. Online iron ion monitors are installed on the condensate pump outlet pipes of the condenser and condensate system, on the deaerator inlet and outlet pipes of the deaerator system, on the economizer inlet pipe and related pipes of high-pressure heaters such as the high-pressure heater drain in the boiler feedwater system, and on the main steam outlet pipe of the boiler body system and the reheat steam outlet pipe of the reheat steam system. Specific installation methods are as follows: Figure 4 As shown.

[0031] In the specific implementation, the 3σ criterion is used to clean the iron ion concentration and unit operating parameters in the original dataset, ensuring that the subsequent model is not interfered with by abnormal noise data. Linear interpolation or K-nearest neighbor interpolation methods are used to fill in missing values, overcoming the possibility of missing data due to sensor failure or transmission interruption. The filled iron ion concentration and unit operating parameters are then subjected to Min-Max feature normalization. Since the dimensions and numerical ranges of the various unit operating parameters (such as unit load "MW", temperature "°C", pH value, etc.) differ greatly, normalization maps all features to the [0,1] interval, and its formula is expressed as: ; in, For sample size, For different characteristic quantities, For the first The first feature One sample; , for the first The minimum value of each feature. , for the first The maximum value of each feature.

[0032] This eliminates the influence of unit of measurement, preventing a single feature from dominating model training due to excessively large values, and ensuring the stability and efficiency of model optimization. The resulting standardized data is the target dataset used for model training.

[0033] In special cases, if a certain characteristic does not fluctuate (e.g., the temperature of a certain pipeline remains constant at 350℃), = ),but =0 (This feature has no effect on erosion and can be removed later). The final standardized dataset is obtained. This is used for subsequent model training.

[0034] Step S202: Establish a linear regression model with the iron ion concentration as the dependent variable and the unit operating parameters as the independent variables; In this embodiment of the application, a linear regression model is established based on the target dataset obtained in step S201. This linear regression model uses iron ion concentration as the dependent variable (i.e., the prediction target) and a series of unit operating parameters as independent variables. The basic form of the linear regression model is as follows: ; in, To calculate the iron ion concentration, For unit load, The pH value of water. This refers to the dissolved oxygen content in water. The electrical conductivity of water. For the temperature of different pipes, For water hardness, For steam humidity, The steam flow rate is... For water supply flow rate, For water supply pressure, For water supply temperature, Main steam pressure, ~ The coefficients used to model the model are also the weights of each parameter. These are modeling constants.

[0035] Step S203: Determine the optimal weighting coefficients of the unit operating parameters that minimize the prediction error of the linear regression model using the least squares method. In this embodiment of the application, a total error function is constructed with the weight coefficients of the operating parameters of each unit as variables; by minimizing the total error function, the optimal weight coefficients of the operating parameters of each unit that minimize the error are calculated.

[0036] In the specific implementation, a total error function, i.e., a loss function, is first constructed, with the weighting coefficients of the operating parameters of each unit as variables. Specifically: ; in, For the total loss, This represents the actual iron ion concentration. For the number of predictions.

[0037] This quantifies the overall difference between the model's predicted values ​​and the actual values. It is usually defined using the least squares method, which is the sum of the squares of the differences between the predicted values ​​and the actual iron ion concentrations of all samples.

[0038] Subsequently, using the least squares method, a set of weighting coefficients is found that minimizes the value of the total error function described above, i.e.: ; in, This represents the loss value that minimizes the error calculation, at which point the weights of each input parameter are obtained. This set of weight coefficients that minimizes the prediction error is the optimal weight coefficient for each unit's operating parameter. These coefficients are not only used for prediction, but their absolute values ​​also directly reflect the importance weight of the corresponding parameter's influence on iron ion concentration.

[0039] Step S204: Based on the unit operating parameters and the corresponding optimal weighting coefficients, construct the iron ion concentration prediction model; In this embodiment, the optimal weight coefficients obtained in step S203 are substituted into the linear regression model in step S202 to obtain a definite iron ion concentration prediction model that can be put into practical application. This model can quickly calculate the predicted iron ion concentration corresponding to the real-time unit operating parameters.

[0040] Step S205: Using the iron ion concentration prediction model and combining it with the real-time unit operating parameters obtained at a preset frequency, the predicted iron ion concentration is calculated. In this embodiment, unit operating parameters are acquired in real time from a sensor network deployed throughout the pipeline at a preset frequency of not less than 1 Hz. These real-time parameters are then input into a pre-constructed iron ion concentration prediction model to output the predicted iron ion concentration in real time.

[0041] Step S206: Using a preset physical model of corrosion rate and the predicted concentration of iron ions, the real-time corrosion rate is calculated. The physical model for the corrosion rate is as follows: ; in, The rate of mass change of corrosion products in the working fluid. The mass transfer coefficient is . This represents the concentration of iron ions near the metal-matrix interface, which is approximately equal to the saturation concentration. This represents the iron ion concentration.

[0042] The physical model of corrosion rate is based on the physical principle that the migration of corrosion products is driven by concentration difference. It dynamically calculates the real-time corrosion rate of the pipeline by predicting the concentration of iron ions.

[0043] Step S207: Based on the relationship between the real-time corrosion rate and the preset corrosion rate threshold, the monitoring result is obtained; In this embodiment, the corrosion rate threshold is a safe upper limit for the corrosion rate determined based on the safety and lifespan requirements of the pipeline material. The real-time corrosion rate calculated in step S206 is compared with this corrosion rate threshold to obtain the monitoring result.

[0044] Step S208: When the monitoring result shows that the real-time corrosion rate exceeds the corrosion rate threshold, the corresponding unit operating parameters are adjusted in reverse order according to the optimal weight coefficient from high to low, until the real-time corrosion rate falls back to within the corrosion rate threshold.

[0045] In this embodiment, when the monitoring results show that the real-time corrosion rate exceeds the corrosion rate threshold, the operating parameters of the unit with the greatest impact are preferentially adjusted in reverse order according to the optimal weight coefficient from high to low. For example, if the pH value has the highest weight coefficient and is negative, the system will automatically increase the pH value (reverse operation) when the corrosion rate exceeds the standard, so as to suppress the corrosion reaction in the most effective way.

[0046] In practice, this control action alters the unit's operating state. New unit operating parameters are collected in real time and recalculated and judged using the process starting from S205. Through continuous reverse adjustment, the real-time corrosion rate falls back to within the corrosion rate threshold, thereby achieving online, intelligent closed-loop control of pipeline corrosion.

[0047] The present invention provides a method for controlling pipeline corrosion in generator sets, comprising: performing feature normalization processing on the acquired raw dataset to obtain a target dataset; constructing an iron ion concentration prediction model based on the iron ion concentration and generator operating parameters in the target dataset; calculating the predicted iron ion concentration using the iron ion concentration prediction model and real-time generator operating parameters acquired at a preset frequency; calculating the real-time corrosion rate using a preset corrosion rate physical model and the predicted iron ion concentration; and obtaining monitoring results based on the relationship between the real-time corrosion rate and a preset corrosion rate threshold.

[0048] By leveraging a sensor network deployed at key nodes of the boiler steam-water system, data is collected in real time at a sampling frequency of no less than 1Hz, with a data transmission delay of ≤1s. This enables real-time and dynamic monitoring of corrosion changes, overcoming the shortcomings of traditional periodic sampling and detection methods, which have long cycles and significant lag.

[0049] By constructing an iron ion concentration prediction model, and based on the iron ion concentration, a corrosion coupling model is built to calculate the corrosion rate of the entire pipeline in the steam-water circulation system. This model can accurately and comprehensively correlate the complex relationship between unit operating parameters, corrosion product migration behavior, and wall corrosion status, and automatically identify key influencing characteristics, thereby achieving precise judgment and control of corrosion.

[0050] By setting a corrosion safety threshold and prioritizing the control of the operating parameters with the greatest impact, corrosion can be effectively reduced by addressing the root causes of corrosion reactions and blocking the physical nature of oxide scale corrosion, thus ensuring the safe and stable operation of the boiler and extending its service life.

[0051] Because it can accurately judge and control the corrosion of pipelines, it can avoid the situation where corrosion is aggravated due to improper regulation, reduce the number of boiler repairs and replacements, and thus reduce maintenance costs.

[0052] Example 3 Please see Figure 5 , Figure 5 This is a structural block diagram of an embodiment of a generator set pipeline corrosion control device according to the present invention. The device includes: The data preprocessing module 301 is used to perform feature normalization processing on the acquired raw dataset to obtain the target dataset; The model building module 302 is used to build an iron ion concentration prediction model based on the iron ion concentration and unit operating parameters in the target dataset. The concentration prediction module 303 is used to calculate the predicted iron ion concentration by using the iron ion concentration prediction model and combining it with the real-time unit operating parameters obtained at a preset frequency. The corrosion rate calculation module 304 is used to calculate the real-time corrosion rate using a preset corrosion rate physical model and the predicted iron ion concentration. The monitoring module 305 is used to obtain monitoring results based on the relationship between the real-time corrosion rate and the preset corrosion rate threshold. The adjustment module 306 is used to reverse the adjustment of the unit operating parameters when the monitoring result shows that the real-time corrosion rate exceeds the corrosion rate threshold, until the real-time corrosion rate falls back to within the corrosion rate threshold.

[0053] In an optional embodiment, the model building module 302 includes: The model building submodule is used to build a linear regression model with the iron ion concentration as the dependent variable and the unit operating parameters as the independent variables. The weight coefficient determination submodule is used to determine the optimal weight coefficients of the unit operating parameters that minimize the prediction error of the linear regression model using the least squares method. The model building submodule is used to build the iron ion concentration prediction model based on the unit operating parameters and the corresponding optimal weight coefficients.

[0054] In an optional embodiment, the adjustment module 306 is specifically used for: When the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold, the corresponding unit operating parameters are adjusted in reverse order according to the optimal weight coefficient from high to low, until the real-time corrosion rate falls back to within the corrosion rate threshold.

[0055] In an optional embodiment, the data preprocessing module 301 includes: The outlier removal submodule is used to detect and remove outliers in the iron ion concentration and the unit operating parameters using the 3σ criterion. The filling submodule is used to fill the iron ion concentration and the unit operating parameters by linear interpolation or K-nearest neighbor interpolation. The normalization submodule is used to perform Min-Max feature normalization processing on the filled iron ion concentration and the unit operating parameters to obtain the target dataset.

[0056] In an optional embodiment, the weight coefficient determination submodule includes: The total error function construction unit is used to construct a total error function with the weighting coefficients of the operating parameters of each unit as variables; The optimal weight coefficient determination unit is used to calculate the optimal weight coefficients of each of the unit operating parameters that minimize the error by minimizing the total error function.

[0057] In an optional embodiment, the physical model for the corrosion rate is: ; in, The rate of mass change of corrosion products in the working fluid. The mass transfer coefficient is . This represents the concentration of iron ions near the metal-matrix interface, which is approximately equal to the saturation concentration. This represents the iron ion concentration.

[0058] Example 4 This invention also provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a generator set pipeline corrosion control method according to any embodiment.

[0059] Example 5 This invention also provides a computer storage medium storing a computer program thereon, which, when executed by the processor, implements the steps of a generator set pipeline corrosion control method according to any embodiment.

[0060] Example 6 This invention also provides a computer program product storing a computer program, which, when executed by the processor, implements the steps of a generator set pipeline corrosion control method according to any embodiment.

[0061] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0062] In the several embodiments provided in this application, it should be understood that the methods, apparatuses, electronic devices, and storage media disclosed in this invention can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0063] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0064] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0065] If the integrated unit is implemented as 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 all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling corrosion of generator set pipelines, characterized in that, include: The original dataset is subjected to feature normalization to obtain the target dataset; A model for predicting iron ion concentration is constructed using the iron ion concentration and unit operating parameters in the target dataset. The predicted iron ion concentration is calculated using the iron ion concentration prediction model and real-time unit operating parameters obtained at a preset frequency. The real-time corrosion rate is calculated using a preset physical model of corrosion rate and the predicted iron ion concentration. The monitoring results are obtained based on the relationship between the real-time corrosion rate and the preset corrosion rate threshold. When the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold, the unit operating parameters are adjusted in the opposite direction until the real-time corrosion rate falls back to within the corrosion rate threshold.

2. The method for controlling corrosion of generator set pipelines according to claim 1, characterized in that, Using the iron ion concentration and unit operating parameters in the target dataset, a model for predicting iron ion concentration is constructed, including: A linear regression model was established with the iron ion concentration as the dependent variable and the unit operating parameters as the independent variables. The optimal weighting coefficients of the unit operating parameters that minimize the prediction error of the linear regression model are determined by the least squares method. Based on the unit operating parameters and the corresponding optimal weighting coefficients, the iron ion concentration prediction model is constructed.

3. The method for controlling corrosion of generator set pipelines according to claim 2, characterized in that, The step of adjusting the unit operating parameters in reverse until the real-time corrosion rate falls back to within the corrosion rate threshold when the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold is specifically as follows: When the monitoring result indicates that the real-time corrosion rate exceeds the corrosion rate threshold, the corresponding unit operating parameters are adjusted in reverse order according to the optimal weight coefficient from high to low, until the real-time corrosion rate falls back to within the corrosion rate threshold.

4. The method for controlling corrosion of generator set pipelines according to claim 1, characterized in that, The acquired raw dataset is subjected to feature normalization to obtain the target dataset, which includes: The 3σ criterion was used to detect and eliminate outliers in the iron ion concentration and the unit operating parameters. Linear interpolation or K-nearest neighbor interpolation is performed to fill in the iron ion concentration and the unit operating parameters; The iron ion concentration and the unit operating parameters after filling were subjected to Min-Max feature normalization to obtain the target dataset.

5. The method for controlling corrosion of generator set pipelines according to claim 2, characterized in that, The optimal weighting coefficients of the unit operating parameters that minimize the prediction error of the linear regression model are determined using the least squares method, including: Construct a total error function with the weighting coefficients of the operating parameters of each unit as variables; By minimizing the total error function, the optimal weighting coefficients of each unit operating parameter that minimizes the error are calculated.

6. The method for controlling corrosion of generator set pipelines according to claim 2, characterized in that, The physical model for the corrosion rate is as follows: ； in, The rate of mass change of corrosion products in the working fluid. The mass transfer coefficient is . This represents the concentration of iron ions near the metal-matrix interface, which is approximately equal to the saturation concentration. This represents the iron ion concentration.

7. A device for controlling corrosion of generator set pipelines, characterized in that, include: The data preprocessing module is used to perform feature normalization on the acquired raw dataset to obtain the target dataset; The model building module is used to build an iron ion concentration prediction model based on the iron ion concentration and unit operating parameters in the target dataset. The concentration prediction module is used to calculate the predicted iron ion concentration by using the iron ion concentration prediction model and combining it with the real-time unit operating parameters obtained at a preset frequency. The corrosion rate calculation module is used to calculate the real-time corrosion rate using a preset physical model of corrosion rate and the predicted iron ion concentration. The monitoring module is used to obtain monitoring results based on the relationship between the real-time corrosion rate and the preset corrosion rate threshold. The adjustment module is used to reverse the adjustment of the unit operating parameters when the monitoring result shows that the real-time corrosion rate exceeds the corrosion rate threshold, until the real-time corrosion rate falls back to within the corrosion rate threshold.

8. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the method as described in any one of claims 1-6.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it performs the method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1-6.

Images