Intelligent prediction method for fatigue damage of cold section of reheat steam pipeline of power station boiler

Abstract

The invention discloses a power station boiler reheat steam pipeline cold section fatigue damage intelligent prediction method, and relates to the field of power station boiler safety prevention and control, and the method comprises the steps: obtaining the operation condition data of a reheat steam pipeline cold section; preprocessing the operation condition data to obtain preprocessed data; constructing an operation condition prediction model based on a deep learning algorithm; inputting the preprocessed data into an operation condition prediction model to obtain an operation condition prediction result; acquiring material data, specification data and historical detection data of the cold section of the reheat steam pipeline; and realizing fatigue damage prediction of the cold section of the reheat steam pipeline based on the operation condition prediction result and the material data, specification data and historical detection data of the cold section of the reheat steam pipeline. According to the method, the prediction precision and efficiency of the fatigue damage of the cold section of the reheat steam pipeline can be improved, so that equipment faults can be effectively avoided.

Description

Technical Field

[0001] The present application relates to the field of safety prevention and control of power station boilers, and in particular to an intelligent prediction method for fatigue damage of a cold section of a reheat steam pipeline of a power station boiler. Background Art

[0002] A power plant boiler is a device that uses thermal energy such as coal and gas to heat water or other media into steam for power generation. It has been in service for a long time under high temperature and high pressure environments. Under the condition of constant fluctuations in stress loads, it will inevitably produce local fatigue and other damage, causing equipment failure. The cold section of the reheat steam pipeline is an important pressure-bearing component of the power plant boiler. It is prone to fatigue damage. Once a failure occurs, it will not only reduce production efficiency and increase the operation and maintenance costs of the power plant, but also cause casualties. However, there is currently no public technology for predicting fatigue damage in the cold section of the reheat steam pipeline. Summary of the invention

[0003] The purpose of this application is to provide an intelligent prediction method for fatigue damage of the cold section of the reheat steam pipeline of a power station boiler, which can improve the prediction accuracy and efficiency of fatigue damage of the cold section of the reheat steam pipeline, thereby effectively avoiding the occurrence of equipment failure.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] The present application provides an intelligent prediction method for fatigue damage of a cold section of a power plant boiler reheat steam pipeline, comprising:

[0006] Acquire the operating condition data of the cold section of the reheat steam pipeline; the operating condition data includes: temperature data and pressure data;

[0007] Preprocessing the operating condition data to obtain preprocessed data;

[0008] Build an operating condition prediction model based on deep learning algorithms;

[0009] Inputting the preprocessed data into the operating condition prediction model to obtain an operating condition prediction result;

[0010] Obtaining material data, specification data and historical test data of the cold section of the reheat steam pipeline; the material data includes the brand of the material used in the cold section of the reheat steam pipeline and the material performance data; the specification data includes the outer diameter and inner wall thickness of the cold section of the reheat steam pipeline; the historical test data includes the historical pipe wall thickness test data of the cold section of the reheat steam pipeline;

[0011] Fatigue damage prediction of the cold section of the reheat steam pipeline is achieved based on the operating condition prediction results and the material data, specification data and historical detection data of the cold section of the reheat steam pipeline.

[0012] Optionally, an Informer algorithm is used as the deep learning algorithm to construct the operating condition prediction model.

[0013] Optionally, an Informer algorithm is used as the deep learning algorithm to construct the operating condition prediction model, including:

[0014] Constructing a data set, and dividing the data set into a training set, a validation set, and a test set according to a set ratio;

[0015] Using the Informer algorithm to build a neural network model;

[0016] The training set, the validation set and the test set are used to train and optimize the neural network model until the output error of the trained neural network model meets the set error constraint, and the trained neural network model is used as the operating condition prediction model.

[0017] Optionally, constructing a dataset includes:

[0018] Acquire historical operating condition time series data of the low-temperature superheater of the power station boiler; the historical operating condition time series data includes: historical temperature time series data and historical pressure time series data;

[0019] The historical operating condition time series data is preprocessed to obtain the data set.

[0020] Optionally, the operating condition prediction model includes a temperature prediction model and a pressure prediction model.

[0021] Optionally, preprocessing the operating condition data to obtain preprocessed data includes:

[0022] Processing abnormal data in the operating condition data by numerical interpolation to obtain processed data;

[0023] The processed data is standardized to obtain the preprocessed data.

[0024] Optionally, the power station boiler reheat steam pipeline cold section fatigue damage intelligent prediction method further includes:

[0025] The process of realizing fatigue damage prediction of the cold section of the reheat steam pipeline based on the operating condition prediction result and the material data, specification data and historical detection data of the cold section of the reheat steam pipeline is programmed.

[0026] According to the specific embodiments provided in this application, this application has the following technical effects:

[0027] The present application provides an intelligent prediction method for fatigue damage of the cold section of the reheat steam pipeline of a power station boiler. By adopting a deep learning algorithm to construct an operating condition prediction model, based on the current operating condition data of the cold section of the reheat steam pipeline, accurate and rapid prediction of future operating conditions can be achieved. Based on the obtained operating condition prediction results, fatigue damage prediction calculation is performed to facilitate users to grasp the fatigue damage of the cold section of the reheat steam pipeline in real time, which can effectively avoid the occurrence of fatigue failure accidents in the cold section of the reheat steam pipeline, thereby enhancing the safety prevention and control capabilities of the power plant, improving production efficiency, and reducing the operation and maintenance costs of the power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 A schematic flow chart of an intelligent prediction method for fatigue damage of a cold section of a reheat steam pipeline of a power station boiler provided in one embodiment of the present application;

[0030] Figure 2 A schematic diagram of a neural network model structure provided in one embodiment of the present application;

[0031] Figure 3 A schematic diagram of the prediction effect of the cold section temperature of a reheat steam pipeline provided by another embodiment of the present application;

[0032] Figure 4 A schematic diagram of the cold section pressure prediction effect of a reheat steam pipeline provided in an embodiment of the present application;

[0033] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0035] Although there is no public fatigue damage prediction technology for pressure-bearing components of power plant boilers, there are some material fatigue damage assessment schemes in the fields of aircraft engines, ship transmission shaft systems, etc. For example, in the Chinese invention application CN112098247A known to the inventor, a method for estimating the remaining life of the inlet surge blades of an aircraft engine compressor is disclosed. This method is based on a linear cumulative damage method, and the composite fatigue damage is divided into two parts: high-cycle fatigue damage and low-cycle fatigue damage. The strain history of the surge phenomenon test is cycle counted using the measured blade dynamic strain data and static stress data, and fatigue damage is predicted for each cycle. The cumulative damage is calculated to estimate the remaining life of the blade. In the Chinese invention application CN113343528A known to the inventor, a method for predicting shaft fatigue damage based on the fusion of cross-point frequency response and dynamic response characteristics is disclosed. This method achieves rapid and accurate identification and prediction of faults of key ship transmission components through four steps. Among them, step 1: study the fatigue crack failure mechanism of transmission shaft system components; step 2: analyze the change law of the inherent characteristics of transmission shaft system components under different misalignment failures; step 3: quantitatively identify the cross-point frequency response characteristic parameters during the fatigue process of components; step 4: study the static and dynamic information fusion prediction method of fatigue damage cracks of shaft system components.

[0036] Although the known solutions given above can realize fatigue damage prediction, they cannot be applied to the field of power plant boiler safety control provided by this application.

[0037] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0038] In an exemplary embodiment, the present application provides an intelligent prediction method for fatigue damage of a cold section of a power plant boiler reheat steam pipeline. The method is executed by a computer device, specifically, it can be executed by a computer device such as a terminal or a server alone, or it can be executed by a terminal and a server together. In the present application embodiment, the method is applied to a server as an example for explanation. Figure 1 As shown, the method includes:

[0039] Step 100: Obtain operating condition data of the cold section of the reheat steam pipeline. The operating condition data includes: temperature data and pressure data.

[0040] Step 101: pre-process the operating condition data to obtain pre-processed data.

[0041] Step 102: construct an operating condition prediction model based on a deep learning algorithm. The operating condition prediction model includes a temperature prediction model and a pressure prediction model.

[0042] Step 103: Input the preprocessed data into the operating condition prediction model to obtain the operating condition prediction result.

[0043] Step 104: Obtain material data, specification data, and historical test data of the cold section of the reheat steam pipeline. The material data includes the grade of the material used in the cold section of the reheat steam pipeline and the material performance data. The specification data includes the outer diameter and inner wall thickness of the cold section of the reheat steam pipeline. The historical test data includes the historical pipe wall thickness test data of the cold section of the reheat steam pipeline.

[0044] Step 105: Fatigue damage prediction of the cold section of the reheat steam pipeline is implemented based on the operating condition prediction result and the material data, specification data and historical inspection data of the cold section of the reheat steam pipeline.

[0045] By implementing the above steps 100 to 105, the present application realizes the fatigue damage prediction of the cold section of the reheat steam pipeline of the power station boiler, so that the user can grasp the fatigue damage of the cold section of the reheat steam pipeline in advance and deal with it in advance, thereby reducing the occurrence of fatigue failure accidents of the cold section of the reheat steam pipeline, enhancing the safety prevention and control capabilities of the power plant, and helping to reduce the number of fault shutdowns, reduce the operation and maintenance costs of the power plant, and improve economic benefits.

[0046] In another exemplary embodiment of the present application, the Informer algorithm is used as a deep learning algorithm to construct an operating condition prediction model.

[0047] (1) Construct a dataset and divide it into training set, validation set, and test set according to the set ratio.

[0048] Step 1. Data collection: Collect historical operation data, material data, specification data, and historical test data of the low-temperature superheater of the power plant boiler to establish a basic database. The historical operation data includes the DCS temperature and DCS pressure data of the cold section of the reheat steam pipeline of the power plant boiler. The material data includes the brand and material performance data of the materials used in the cold section of the reheat steam pipeline. The specification data includes the outer diameter and inner wall thickness of the pipe in the cold section of the reheat steam pipeline. The historical test data mainly includes the historical test data of the wall thickness of the cold section of the reheat steam pipeline. For example, extract the historical temperature and pressure data of the cold section of the reheat steam pipeline in the past six months from the DCS control system of the power plant, in units of ℃ and MPa, respectively, and the time interval is controlled at 1min.

[0049] Step 2. Data processing: Process the abnormal data in the historical operation data to improve the data quality and ensure the prediction accuracy of the model. Data processing includes missing data processing and erroneous data processing.

[0050] Step 3. Dataset construction: First, standardize the data processed in Step 2 and save the standardization parameters. Then, create a dataset according to the training requirements and divide the dataset into training set, test set, and validation set according to the set ratio (for example, 7:2:1). The three sets are independent of each other.

[0051] Among them, after the processed data is standardized, the standardized parameters can be saved to ensure that the same standardized parameters can be used when the model is deployed.

[0052] (2) The Informer algorithm is used to build a neural network model. For example, the features parameter in the Informer algorithm is set to S, which means that a single input predicts a single output. The parameter seq_len is set to 96, which means that the data of the past 96 time nodes are used to predict the future data. The parameter pred_len is set to 24, which means predicting the data of the next 24 time nodes. The number of layers of the encoder and decoder are set to 2 and 1 respectively. The learning rate learning_rate is set to 0.0001, and the dimension of the fully connected network (FCN) is set to 2048. The structure of the obtained neural network model is as follows: Figure 2 As shown, Figure 2 In , e_layers and d_layers represent the number of layers of the encoder and decoder.

[0053] (3) The neural network model is trained and optimized using a training set, a validation set, and a test set until the output error of the trained neural network model meets the set error constraint. The trained neural network model is used as an operating condition prediction model, and the operating condition prediction model is stored in a manner that the entire model is completely saved. During the training process, the prediction model file with the smallest error can also be saved.

[0054] Among them, the root mean square error is used as the evaluation index of the trained neural network model. The calculation formula of the root mean square error is expressed as:

[0055]

[0056] In the formula, R 2 is the root mean square error, y i,a is the operating condition monitoring value, y i,p is the predicted value of the operating condition, It is the average of the operating condition monitoring values.

[0057] Based on the above description, the implementation process of the above step 101 of the present application may include: processing the abnormal data in the operating condition data by means of numerical interpolation to obtain processed data. Standardizing the processed data to obtain preprocessed data. The abnormal data includes missing data and erroneous data. For example, erroneous characters such as bad, Bad, nan, and Nan appear.

[0058] Furthermore, in actual application, the operating condition prediction model and the standardized parameter file can be packaged and called to predict the future operating condition data of the cold section of the reheat steam pipeline. The calling process can be described as:

[0059] 1) The cold section temperature of the reheat steam pipeline is passed as input to the temperature standardization parameter file for standardization, and then the standardized temperature data is input into the temperature prediction model to achieve temperature prediction. Figure 3 shown.

[0060] 2) The cold section pressure of the reheat steam pipeline is passed as input to the standardized parameter file for standardization, and then the standardized pressure data is input into the pressure prediction model to realize the pressure prediction. Figure 4 shown.

[0061] In another exemplary embodiment of the present application, in order to improve the prediction efficiency, the temperature and pressure data of the cold section of the reheat steam pipeline monitored in real time by the power plant boiler DCS system can be standardized by loading the saved standardized parameter file and the prediction model file, and the model constructed in step 103 and the processing process performed in step 105 can be encapsulated into one function module for calling to realize fatigue damage prediction.

[0062] In another exemplary embodiment of the present application, in order to further improve the accuracy of fatigue damage prediction, the fatigue damage life assessment method of pressure-bearing components in the "Technical Guidelines for Life Assessment of Main Pressure-Bearing Components of Power Plant Boilers" (GB / T 30580-2022) can be combined to achieve fatigue damage prediction of the cold section of the reheat steam pipeline of the power plant boiler.

[0063] In actual application, the fatigue damage life assessment method of pressure-bearing components in the "Technical Guidelines for Life Assessment of Main Pressure-bearing Components of Power Plant Boilers" (GB / T30580-2022) can be written into a program, and then the historical operating condition monitoring data and prediction data of the cold section of the reheat steam pipeline can be imported into this program to calculate the fatigue damage amount of the cold section of the reheat steam pipeline in each period of time, and then calculate the cumulative amount of damage, and finally realize the fatigue damage prediction of the cold section of the reheat steam pipeline. Among them, the fatigue damage calculation process is as follows:

[0064]

[0065] In the formula, σ a is the hoop stress of the cold section pipe of the reheat steam pipeline. P1 and P2 are the peak or valley values ​​of the operating pressure of the cold section of the reheat steam pipeline, in MPa. D0 is the outer diameter of the pipe, in mm. S is the wall thickness of the pipe, in mm. E is the elastic modulus of the material, in MPa. Δεa 为 Strain amplitude, σ' f is the fatigue strength coefficient, N f is the number of fatigue cycles, b is the fatigue strength index, ε' f is the ductility coefficient of the material, c is the fatigue ductility index of the material, D Fstigue is the cumulative amount of fatigue damage, N fi is the number of cycles that can be cycled under the i-th condition of the cold section of the reheat steam pipeline, n i It is the half cycle number of the cold section of the reheat steam pipeline under the i-th operating condition.

[0066] In summary, this application introduces a deep learning algorithm to construct a time series prediction model for the operating conditions (temperature, pressure) of the cold section of the reheat steam pipeline of a power plant boiler. By calling this time series prediction model, the operating conditions (temperature, pressure) data of the cold section of the reheat steam pipeline in the future period are obtained. Combined with the fatigue damage life assessment method of pressure-bearing components in GB / T 30580-2022, the fatigue damage amount of the cold section of the reheat steam pipeline can be predicted, thereby reducing the occurrence of fatigue failure accidents in the cold section of the reheat steam pipeline, enhancing the safety prevention and control capabilities of power plants, reducing the operation and maintenance costs of power plants, and improving economic benefits.

[0067] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store fatigue damage prediction data of the cold section of the reheat steam pipeline. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent prediction method for fatigue damage of the cold section of the reheat steam pipeline of a power station boiler is implemented.

[0068] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0069] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0070] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0071] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0072] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0073] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0074] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0075] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. An intelligent prediction method for fatigue damage of cold section of reheat steam pipeline of power station boiler, characterized in that: The intelligent prediction method for fatigue damage of the cold section of the reheat steam pipeline of a power station boiler comprises: Acquire the operating condition data of the cold section of the reheat steam pipeline; the operating condition data includes: temperature data and pressure data; Preprocessing the operating condition data to obtain preprocessed data; Build an operating condition prediction model based on deep learning algorithms; Inputting the preprocessed data into the operating condition prediction model to obtain an operating condition prediction result; Obtaining material data, specification data and historical test data of the cold section of the reheat steam pipeline; the material data includes the brand of the material used in the cold section of the reheat steam pipeline and the material performance data; the specification data includes the outer diameter and inner wall thickness of the cold section of the reheat steam pipeline; the historical test data includes the historical pipe wall thickness test data of the cold section of the reheat steam pipeline; Fatigue damage prediction of the cold section of the reheat steam pipeline is achieved based on the operating condition prediction results and the material data, specification data and historical detection data of the cold section of the reheat steam pipeline.

2. The intelligent prediction method for fatigue damage of cold section of reheat steam pipeline of power station boiler according to claim 1 is characterized in that: The Informer algorithm is used as the deep learning algorithm to construct the operating condition prediction model.

3. The intelligent prediction method for fatigue damage of cold section of reheat steam pipeline of power station boiler according to claim 2 is characterized in that: The Informer algorithm is used as the deep learning algorithm to construct the operating condition prediction model, including: Constructing a data set, and dividing the data set into a training set, a validation set, and a test set according to a set ratio; Using the Informer algorithm to build a neural network model; The training set, the validation set and the test set are used to train and optimize the neural network model until the output error of the trained neural network model meets the set error constraint, and the trained neural network model is used as the operating condition prediction model.

4. The intelligent prediction method for fatigue damage of cold section of reheat steam pipeline of power station boiler according to claim 3 is characterized in that: Building a dataset includes: Acquire historical operating condition time series data of the low-temperature superheater of the power station boiler; the historical operating condition time series data includes: historical temperature time series data and historical pressure time series data; The historical operating condition time series data is preprocessed to obtain the data set.

5. The intelligent prediction method for fatigue damage of cold section of reheat steam pipeline of power station boiler according to claim 1 is characterized in that: The operating condition prediction model includes a temperature prediction model and a pressure prediction model.

6. The intelligent prediction method for fatigue damage of cold section of reheat steam pipeline of power station boiler according to claim 1 is characterized in that: Preprocessing the operating condition data to obtain preprocessed data includes: Processing abnormal data in the operating condition data by numerical interpolation to obtain processed data; The processed data is standardized to obtain the preprocessed data.

7. The intelligent prediction method for fatigue damage of cold section of reheat steam pipeline of power station boiler according to claim 1 is characterized in that: The intelligent prediction method for fatigue damage of the cold section of the reheat steam pipeline of the power station boiler also includes: The process of realizing fatigue damage prediction of the cold section of the reheat steam pipeline based on the operating condition prediction result and the material data, specification data and historical detection data of the cold section of the reheat steam pipeline is programmed.

Images