Boiler expansion monitoring method and device
By setting up a sensor group on the boiler to collect data in real time, perform filtering and compensation processing, and establishing an expansion trend prediction model, the real-time and accuracy of boiler expansion monitoring is solved, and real-time monitoring and abnormal evaluation of boiler expansion is realized.
Patent Information
- Application Number
- CN202510659513.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-21
- Publication Date
- 2025-08-08
AI Technical Summary
The existing boiler expansion monitoring methods lack real-time and accuracy, resulting in deformation or damage to boiler components, affecting the operation safety of power stations.
The sensor group is used to collect expansion displacement and environmental parameter data in real time, and an expansion trend prediction model is established after filtering and compensation processing, and the real-time expansion rate is calculated and compared to determine the expansion abnormality level.
Real-time monitoring and accurate evaluation of boiler expansion are realized, the accuracy of expansion monitoring is improved, and missed detection and misjudgment of expansion abnormalities are avoided.
Smart Images
Figure CN120445129A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of boiler monitoring, and in particular to a boiler expansion monitoring method and device. Background Art
[0002] During the operation of a power plant boiler, the boiler expands when it starts and contracts when it stops. During this process, if there is abnormal expansion or the working fluid ages, it can cause deformation or even cracking of boiler components, seriously affecting the safe operation of the power plant.
[0003] Currently, the main method of detecting boiler expansion is for power plant personnel to read and record the boiler expansion indicators at various monitoring points to achieve boiler monitoring. However, due to the scattered distribution of boiler expansion indicators, this method lacks real-time performance. At the same time, manual monitoring records are also prone to omissions, resulting in low monitoring accuracy.
[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention
[0005] The main purpose of the present invention is to provide a boiler expansion monitoring method, device, equipment and storage medium, aiming to solve the technical problems of poor real-time performance and low accuracy in boiler monitoring.
[0006] To achieve the above object, the present invention provides a boiler expansion monitoring method, which comprises the following steps:
[0007] Real-time collection of expansion displacement data and environmental parameter data from each sensor group, where multiple sensor groups are arranged axially and circumferentially on the outer surface of the boiler pressure-bearing component;
[0008] performing filtering processing on the expansion displacement data and compensating processing on the environmental parameter data;
[0009] establishing an expansion trend prediction model based on the processed data, and calculating the real-time expansion rate of the boiler using the expansion trend prediction model;
[0010] The real-time expansion rate is compared with a preset expansion rate to determine the expansion abnormality level of the boiler.
[0011] In some embodiments, filtering the expansion displacement data includes:
[0012] Based on the current real-time load rate of the boiler, the adaptive wavelet packet decomposition algorithm is used to determine the target decomposition level;
[0013] Decomposing the expansion displacement data based on the target decomposition level;
[0014] Threshold denoising is performed on the high-frequency components in the decomposed expansion displacement data, and time-domain matched filtering is performed on the low-frequency components in the decomposed expansion displacement data to obtain filtered expansion displacement data.
[0015] In some embodiments, the compensating the environmental parameter data includes:
[0016] Based on the historical temperature sensor temperature and the historical pipe wall temperature, the nonlinear relationship between the temperature rise gradient and the displacement error is fitted by the least square method to establish the initial compensation equation;
[0017] Correcting the compensation coefficient of the compensation equation by using Kalman filtering to obtain a corrected compensation equation;
[0018] The environmental parameter data is input into the revised compensation equation.
[0019] In some embodiments, establishing an expansion trend prediction model based on the processed data includes:
[0020] Determine a hybrid neural network architecture, where the input layer receives displacement, temperature, and pressure data with a time window length of 10 minutes. The first branch uses a bidirectional LSTM module to extract time series features, with 64 hidden layer nodes. The second branch uses a graph convolutional network (GCN) to model the spatial correlation between sensor nodes, and the adjacency matrix is generated based on the tube-screen structure topology.
[0021] Model training is performed based on the hybrid neural network architecture. The model training process involves loading a historical dataset with abnormal operating condition samples containing crack propagation and creep acceleration. A transfer learning strategy is employed, with simulation data used in the pre-training phase and field data used in the fine-tuning phase. The loss function combines the mean square error and the pipe yield strength constraint, with a weighting ratio of 2:1.
[0022] The confidence interval of the expansion amount within the preset time in the future is output according to the preset period. If the interval width exceeds the preset width, the model is retrained.
[0023] In some embodiments, calculating the real-time expansion rate of the boiler using the expansion trend prediction model includes:
[0024] Setting a sliding time window at the output end of the expansion trend prediction model and calculating the first-order derivative of the displacement within the sliding time window as the instantaneous rate;
[0025] calculating a sliding standard deviation of the instantaneous rate;
[0026] When the sliding standard deviation exceeds twice the historical mean for three consecutive times, it is determined to be a transient disturbance;
[0027] When transient disturbances exist, the DBSCAN clustering algorithm is used to identify abnormal rate clusters. After removing outliers, the average rate is calculated and used as the real-time expansion rate of the boiler.
[0028] In some embodiments, comparing the real-time expansion rate with a preset expansion rate to determine the expansion abnormality level of the boiler includes:
[0029] If the real-time expansion rate exceeds the preset expansion rate, the corresponding abnormal area is located, and the expansion amount collected by the sensor in the abnormal area and the temperature gradient of the abnormal area are obtained;
[0030] Calculating a diffusion index of the abnormal area according to the expansion amount and the temperature gradient;
[0031] The expansion abnormality level of the boiler is determined according to the abnormal diffusion index.
[0032] In some embodiments, determining the expansion abnormality level of the boiler according to the abnormal diffusion index includes:
[0033] If the abnormal diffusion index is less than or equal to the first index threshold, determining that the expansion abnormality level of the boiler is a locally controllable abnormality level;
[0034] If the abnormal diffusion index is greater than the first index threshold and less than or equal to the second index threshold, determining that the expansion abnormality level of the boiler is the regional expansion abnormality level;
[0035] If the abnormal diffusion index is greater than the second index threshold, the expansion abnormality level of the boiler is determined to be a systemic risk abnormality level.
[0036] In addition, to achieve the above-mentioned purpose, the present invention further provides a boiler expansion monitoring device, the boiler expansion monitoring device comprising:
[0037] An acquisition module is used to collect expansion displacement data and environmental parameter data of each sensor group in real time, wherein a plurality of sensor groups are arranged at intervals along the axial direction and the circumferential direction on the outer surface of the boiler pressure-bearing component;
[0038] a processing module, configured to filter the expansion displacement data and compensate the environmental parameter data;
[0039] a calculation module, configured to establish an expansion trend prediction model based on the processed data, and calculate the real-time expansion rate of the boiler using the expansion trend prediction model;
[0040] The determination module is configured to compare the real-time expansion rate with a preset expansion rate to determine an expansion abnormality level of the boiler.
[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a boiler expansion monitoring device, which includes: a memory, a processor, and a boiler expansion monitoring program stored in the memory and executable on the processor, wherein the boiler expansion monitoring program is configured to implement the steps of the boiler expansion monitoring method described above.
[0042] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a boiler expansion monitoring program is stored. When the boiler expansion monitoring program is executed by a processor, the steps of the boiler expansion monitoring method described above are implemented.
[0043] The present invention collects expansion displacement data and environmental parameter data from each sensor group in real time. Multiple sensor groups are arranged axially and circumferentially on the outer surface of the boiler's pressure-bearing components. The expansion displacement data is filtered, and the environmental parameter data is compensated. An expansion trend prediction model is established based on the processed data, and the real-time expansion rate of the boiler is calculated using the expansion trend prediction model. This real-time expansion rate is compared with a preset expansion rate to determine the boiler's expansion anomaly level. This method allows for real-time monitoring of the boiler's expansion displacement, while simultaneously obtaining a real-time expansion rate using the expansion trend prediction model. The expansion anomaly level is then assessed based on the real-time expansion rate, improving the accuracy of boiler expansion monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 This is a flow chart of a first embodiment of a method for monitoring boiler expansion according to the present invention;
[0045] Figure 2 This is a structural block diagram of the first embodiment of the boiler expansion monitoring device of the present invention.
[0046] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION
[0047] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0048] The embodiment of the present invention provides a boiler expansion monitoring method, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of a boiler expansion monitoring method according to the present invention.
[0049] In this embodiment, the boiler expansion monitoring method includes the following steps:
[0050] Step S10: collecting expansion displacement data and environmental parameter data of each sensor group in real time.
[0051] In this embodiment, the executor of this embodiment is a boiler expansion monitoring device, wherein the boiler expansion monitoring device has functions such as data processing, data communication and program running. The boiler expansion monitoring device can be a computer terminal device or other network device, and of course it can also be other devices with similar functions. This embodiment does not limit this.
[0052] It should be noted that during the operation of a power plant boiler, the boiler will expand when it is started and contract when it stops working. During this expansion and contraction process, if there is abnormal expansion or the working fluid ages, it will cause the boiler components to deform or even crack and break, seriously affecting the operational safety of the power plant. Currently, the main method of detecting boiler expansion is to have power plant personnel read and record the boiler expansion indicators at various monitoring points to achieve boiler monitoring. However, due to the scattered distribution of boiler expansion indicators, this method lacks real-time performance. At the same time, manual monitoring records are often missed, resulting in low monitoring accuracy.
[0053] To address the above technical issues, this embodiment collects expansion displacement data and environmental parameter data from each sensor group in real time. Multiple sensor groups are arranged axially and circumferentially on the outer surface of the boiler's pressure-bearing components. The expansion displacement data is filtered and the environmental parameter data is compensated. An expansion trend prediction model is established based on the processed data, and the real-time expansion rate of the boiler is calculated using the expansion trend prediction model. The real-time expansion rate is compared with a preset expansion rate to determine the boiler's expansion anomaly level. This method allows for real-time monitoring of the boiler's expansion displacement, while simultaneously obtaining a real-time expansion rate using the expansion trend prediction model. The expansion anomaly level is then assessed based on the real-time expansion rate, improving the accuracy of boiler expansion monitoring. Specifically, this can be achieved as follows.
[0054] In this embodiment, multiple sensor groups are arranged axially and circumferentially on the outer surface of the boiler's pressure-bearing components. These sensors then collect expansion displacement data and environmental parameter data in real time. It's important to note that current boiler expansion monitoring systems often use single-point or linearly arranged sensors, which cannot fully capture abnormal axial and circumferential expansion characteristics of pressure-bearing components. This is particularly true in areas with sudden changes in tube panel thickness and weld stress concentrations, which can easily create monitoring blind spots and lead to missed detection of localized abnormal expansion. Therefore, this embodiment arranges sensors axially and circumferentially to avoid missed detection of abnormal expansion.
[0055] Step S20: filtering the expansion displacement data and compensating the environmental parameter data.
[0056] It should be noted that after the above data is collected, in order to improve the accuracy of detection, the present embodiment further processes the data, specifically filtering the expansion displacement data and performing compensation processing based on the environmental parameter data.
[0057] In a specific implementation, the process of filtering the expansion displacement data is as follows: determining the target decomposition layer number by using an adaptive wavelet packet decomposition algorithm based on the current real-time load rate of the boiler; decomposing the expansion displacement data based on the target decomposition layer number; performing threshold denoising on the high-frequency components in the decomposed expansion displacement data; and performing time-domain matched filtering on the low-frequency components in the decomposed expansion displacement data to obtain the filtered expansion displacement data.
[0058] It should be noted that if the current real-time load rate is less than or equal to 50%, the target decomposition layer number is 4 layers. If the current real-time load rate is greater than 50%, the target decomposition layer number is 6 layers. Then, the expansion displacement data is decomposed into high-frequency components and low-frequency components according to the decomposition layer number. For the high-frequency components, threshold denoising is performed in this embodiment. The specific threshold expression is: where σ j is the noise standard deviation of the jth layer, N j is the coefficient length, retaining the frequency T j High-frequency components in the range of 0.1Hz-5Hz. For low-frequency components, this embodiment performs time-domain matched filtering, specifically by constructing a reference template: During the cold start-up phase of the boiler, the expansion displacement curve under interference-free conditions is collected to generate a reference template signal Sref(t). Cross-correlation matching: The cross-correlation function between the low-frequency component Sraw(t) and the template Sref(t) is calculated:
[0059] R(τ)=∫S raw (t)S ref (t-τ)dt
[0060] The phase of the low-frequency component is aligned with the phase of the reference template signal through the above function to complete the filtering.
[0061] Furthermore, the process of compensating the environmental parameter data is to fit the nonlinear relationship between the temperature rise gradient and the displacement error through the least squares method based on the historical temperature sensor temperature and the historical pipe wall temperature to establish an initial compensation equation; correct the compensation coefficient of the compensation equation through Kalman filtering to obtain a corrected compensation equation; and input the environmental parameter data into the corrected compensation equation.
[0062] It should be noted that the compensation equation is:
[0063]
[0064] Among them, α is the temperature rise coupling coefficient, and β is the thermal inertia correction factor. Then, alphaα and betaβ are updated through Kalman filtering to ensure that the deviation between the compensated displacement and the laser reference value is ≤0.05mm. After the correction is completed, environmental parameters such as the combustion chamber flue gas temperature field distribution and steam pressure fluctuation frequency are input into the compensation model.
[0065] Step S30: establishing an expansion trend prediction model based on the processed data, and calculating the real-time expansion rate of the boiler using the expansion trend prediction model.
[0066] In a specific implementation, the process of establishing an expansion trend prediction model is to determine a hybrid neural network architecture, perform model training based on the hybrid neural network architecture, and output a confidence interval of the expansion amount within a preset time in the future according to a preset period. If the interval width exceeds the preset width, the model is retrained.
[0067] It should be noted that the hybrid neural network architecture has an input layer that receives displacement, temperature, and pressure data with a 10-minute time window. The first branch uses a bidirectional LSTM module to extract time series features, with 64 hidden layer nodes. The second branch uses a graph convolutional network (GCN) to model the spatial correlation between sensor nodes. The adjacency matrix is generated based on the pipe-panel structural topology. The specific process of model training involves loading a historical dataset containing abnormal operating condition samples of crack propagation and creep acceleration. A transfer learning strategy is adopted, with simulation data used in the pre-training phase and field data used in the fine-tuning phase. The loss function combines the mean square error and the pipe yield strength constraint, with a weight ratio of 2:1. A confidence interval for the future expansion within a preset time period is output at a preset period. If the interval width exceeds the preset width, the model is retrained. For example, a 95% confidence interval for the expansion within the next 15 minutes is output every 30 seconds, and model retraining is triggered when the interval width exceeds 2 mm. The above parameter settings are for illustration only and can be adjusted according to actual conditions in the specific implementation. This is not limited in this embodiment.
[0068] Furthermore, the real-time expansion rate calculation process is to set a sliding time window at the output end of the expansion trend prediction model, and calculate the first-order derivative of the displacement within the sliding time window as the instantaneous rate; calculate the sliding standard deviation of the instantaneous rate; when the sliding standard deviation exceeds twice the historical mean for three consecutive times, it is determined to be a transient disturbance; when a transient disturbance exists, the DBSCAN clustering algorithm is used to identify abnormal rate clusters, and after eliminating outliers, the average rate is calculated, and the average rate is used as the real-time expansion rate of the boiler.
[0069] Step S40: Compare the real-time expansion rate with a preset expansion rate to determine the expansion abnormality level of the boiler.
[0070] In a specific implementation, the real-time expansion rate is compared with a preset expansion rate. If the real-time expansion rate exceeds the preset expansion rate, the abnormal area can be determined according to the position of the corresponding sensor. Then, the expansion amount collected by the sensor in the abnormal area and the temperature gradient of the abnormal area are obtained. According to the expansion amount and the temperature gradient, the diffusion index of the abnormal area can be calculated. The calculation formula of the diffusion index is:
[0071]
[0072] where, ΔL i represents the expansion amount, and ΔT i represents the temperature gradient.
[0073] Furthermore, if the abnormal diffusion index is less than or equal to the first index threshold, it is determined that the expansion abnormal level of the boiler is the local controllable abnormal level; if the abnormal diffusion index is greater than the first index threshold and less than or equal to the second index threshold, it is determined that the expansion abnormal level of the boiler is the regional expansion abnormal level; if the abnormal diffusion index is greater than the second index threshold, it is determined that the expansion abnormal level of the boiler is the systemic risk abnormal level. For example, when D ≤ 0.3, it is determined as the local controllable abnormal level; when 0.3 < D ≤ 0.6, it is determined as the regional expansion abnormal level; when D > 0.6, it is determined as the systemic risk abnormal level. 0.3 is the first index threshold, and 0.6 is the second index threshold. The settings of the first index threshold and the second index threshold are only for illustrative purposes and can be adjusted according to the actual situation in specific implementations. This embodiment does not limit this.
[0074] In this embodiment, the expansion displacement data and the environmental parameter data of each sensor group are collected in real time. Among them, a plurality of sensor groups are arranged at intervals along the axial direction and the circumferential direction on the outer surface of the boiler pressure-bearing component; the expansion displacement data is filtered and the environmental parameter data is compensated; an expansion trend prediction model is established based on the processed data, and the real-time expansion rate of the boiler is calculated by using the expansion trend prediction model; the real-time expansion rate is compared with the preset expansion rate to determine the expansion abnormal level of the boiler. Through the above method, the expansion displacement of the boiler can be monitored in real time, and at the same time, the real-time expansion rate can be obtained by using the expansion trend prediction model, and the expansion abnormal level is evaluated based on the real-time expansion rate, which improves the accuracy of boiler expansion monitoring.
[0075] Refer to Figure 2 , Figure 2 which is the structural block diagram of the first embodiment of the boiler expansion monitoring device of the present invention.
[0076] As Figure 2 shown, the boiler expansion monitoring device proposed by the embodiment of the present invention includes:
[0077] The acquisition module 10 is used to collect the expansion displacement data and environmental parameter data of each sensor group in real time, wherein a plurality of sensor groups are arranged at intervals along the axial direction and the circumferential direction on the outer surface of the boiler pressure-bearing component;
[0078] A processing module 20 is configured to filter the expansion displacement data and compensate the environmental parameter data;
[0079] a calculation module 30 for establishing an expansion trend prediction model based on the processed data, and calculating the real-time expansion rate of the boiler using the expansion trend prediction model;
[0080] The determination module 40 is configured to compare the real-time expansion rate with a preset expansion rate to determine an expansion abnormality level of the boiler.
[0081] This embodiment collects expansion displacement data and environmental parameter data from each sensor group in real time. Multiple sensor groups are spaced axially and circumferentially on the outer surface of the boiler's pressure-bearing components. The expansion displacement data is filtered and the environmental parameter data is compensated. An expansion trend prediction model is established based on the processed data, and the real-time expansion rate of the boiler is calculated using the expansion trend prediction model. This real-time expansion rate is compared with a preset expansion rate to determine the boiler's expansion anomaly level. This method allows for real-time monitoring of the boiler's expansion displacement, while simultaneously obtaining a real-time expansion rate using the expansion trend prediction model. The expansion anomaly level is then assessed based on the real-time expansion rate, improving the accuracy of boiler expansion monitoring.
[0082] In some embodiments, the processing module 20 is configured to determine a target number of decomposition levels using an adaptive wavelet packet decomposition algorithm based on the current real-time load rate of the boiler;
[0083] Decomposing the expansion displacement data based on the target decomposition level;
[0084] Threshold denoising is performed on the high-frequency components in the decomposed expansion displacement data, and time-domain matched filtering is performed on the low-frequency components in the decomposed expansion displacement data to obtain filtered expansion displacement data.
[0085] In some embodiments, the processing module 20 is configured to fit the nonlinear relationship between the temperature rise gradient and the displacement error by the least square method based on the historical temperature sensor temperature and the historical pipe wall temperature, so as to establish an initial compensation equation;
[0086] Correcting the compensation coefficient of the compensation equation by using Kalman filtering to obtain a corrected compensation equation;
[0087] The environmental parameter data is input into the revised compensation equation.
[0088] In some embodiments, the computing module 30 is used to determine a hybrid neural network architecture, wherein the hybrid neural network architecture is an input layer receiving displacement, temperature, and pressure data with a time window length of 10 minutes, a first branch using a bidirectional LSTM module to extract time series features, and a hidden layer with 64 nodes, and a second branch using a graph convolutional network (GCN) to model the spatial correlation between sensor nodes, and an adjacency matrix is generated based on the tube-screen structure topology;
[0089] Model training is performed based on the hybrid neural network architecture. The model training process involves loading a historical dataset with abnormal operating condition samples containing crack propagation and creep acceleration. A transfer learning strategy is employed, with simulation data used in the pre-training phase and field data used in the fine-tuning phase. The loss function combines the mean square error and the pipe yield strength constraint, with a weighting ratio of 2:1.
[0090] The confidence interval of the expansion amount within the preset time in the future is output according to the preset period. If the interval width exceeds the preset width, the model is retrained.
[0091] In some embodiments, the calculation module 30 is configured to set a sliding time window at the output end of the expansion trend prediction model and calculate the first-order derivative of the displacement within the sliding time window as the instantaneous rate;
[0092] calculating a sliding standard deviation of the instantaneous rate;
[0093] When the sliding standard deviation exceeds twice the historical mean for three consecutive times, it is determined to be a transient disturbance;
[0094] When transient disturbances exist, the DBSCAN clustering algorithm is used to identify abnormal rate clusters. After removing outliers, the average rate is calculated and used as the real-time expansion rate of the boiler.
[0095] In some embodiments, the determination module 40 is configured to locate a corresponding abnormal area if the real-time expansion rate exceeds a preset expansion rate, and obtain the expansion amount collected by the sensor in the abnormal area and the temperature gradient of the abnormal area;
[0096] Calculating a diffusion index of the abnormal area according to the expansion amount and the temperature gradient;
[0097] The abnormal expansion level of the boiler is determined according to the abnormal diffusion index.
[0098] In some embodiments, the determination module 40 is configured to determine that the expansion abnormality level of the boiler is a locally controllable abnormality level if the abnormal diffusion index is less than or equal to a first index threshold;
[0099] If the abnormal diffusion index is greater than the first index threshold and less than or equal to the second index threshold, determining that the expansion abnormality level of the boiler is the regional expansion abnormality level;
[0100] If the abnormal diffusion index is greater than the second index threshold, the expansion abnormality level of the boiler is determined to be a systemic risk abnormality level.
[0101] An embodiment of the present application also provides a boiler expansion monitoring device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, and the memory is used to store a boiler expansion monitoring program; the processor is used to implement the above-mentioned boiler expansion monitoring method when executing the program stored in the memory.
[0102] The communication bus mentioned in the above-mentioned boiler expansion monitoring device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc.
[0103] The communication interface is used for communication between the above-mentioned boiler expansion monitoring device and other devices.
[0104] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located remote from the processor.
[0105] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0106] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).
[0107] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.
[0108] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.
[0109] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.
[0110] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.
[0111] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.
[0112] In addition, for technical details not fully described in this embodiment, reference can be made to the boiler expansion monitoring method provided in any embodiment of the present invention, and will not be repeated here.
[0113] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.
[0114] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.
[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0116] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
[0117] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts of the above method.
Claims
1. A boiler expansion monitoring method, characterized in that: The boiler expansion monitoring method comprises: Real-time collection of expansion displacement data and environmental parameter data from each sensor group, where multiple sensor groups are arranged axially and circumferentially on the outer surface of the boiler pressure-bearing component; performing filtering processing on the expansion displacement data and compensating processing on the environmental parameter data; establishing an expansion trend prediction model based on the processed data, and calculating the real-time expansion rate of the boiler using the expansion trend prediction model; The real-time expansion rate is compared with a preset expansion rate to determine the expansion abnormality level of the boiler.
2. The boiler expansion monitoring method according to claim 1, characterized in that: The expansion displacement data is filtered, including: Based on the current real-time load rate of the boiler, the adaptive wavelet packet decomposition algorithm is used to determine the target decomposition level; Decomposing the expansion displacement data based on the target decomposition level; Threshold denoising is performed on the high-frequency components in the decomposed expansion displacement data, and time-domain matched filtering is performed on the low-frequency components in the decomposed expansion displacement data to obtain filtered expansion displacement data.
3. The boiler expansion monitoring method according to claim 1, characterized in that: The compensating process for the environmental parameter data includes: Based on the historical temperature sensor temperature and the historical pipe wall temperature, the nonlinear relationship between the temperature rise gradient and the displacement error is fitted by the least square method to establish the initial compensation equation; Correcting the compensation coefficient of the compensation equation by using Kalman filtering to obtain a corrected compensation equation; The environmental parameter data is input into the revised compensation equation.
4. The boiler expansion monitoring method according to claim 1, characterized in that: The step of establishing an expansion trend prediction model based on the processed data includes: Determine a hybrid neural network architecture, where the input layer receives displacement, temperature, and pressure data with a time window length of 10 minutes. The first branch uses a bidirectional LSTM module to extract time series features, with 64 hidden layer nodes. The second branch uses a graph convolutional network (GCN) to model the spatial correlation between sensor nodes, and the adjacency matrix is generated based on the tube-screen structure topology. Model training is performed based on the hybrid neural network architecture. The model training process involves loading a historical dataset with abnormal operating condition samples containing crack propagation and creep acceleration. A transfer learning strategy is employed, with simulation data used in the pre-training phase and field data used in the fine-tuning phase. The loss function combines the mean square error and the pipe yield strength constraint, with a weighting ratio of 2:
1. The confidence interval of the expansion amount within the preset time in the future is output according to the preset period. If the interval width exceeds the preset width, the model is retrained.
5. The boiler expansion monitoring method according to claim 4, characterized in that: The method of calculating the real-time expansion rate of the boiler using the expansion trend prediction model includes: Setting a sliding time window at the output end of the expansion trend prediction model and calculating the first-order derivative of the displacement within the sliding time window as the instantaneous rate; calculating a sliding standard deviation of the instantaneous rate; When the sliding standard deviation exceeds twice the historical mean for three consecutive times, it is determined to be a transient disturbance; When transient disturbances exist, the DBSCAN clustering algorithm is used to identify abnormal rate clusters. After removing outliers, the average rate is calculated and used as the real-time expansion rate of the boiler.
6. The boiler expansion monitoring method according to claim 1, characterized in that: The comparing the real-time expansion rate with the preset expansion rate to determine the expansion abnormality level of the boiler includes: If the real-time expansion rate exceeds the preset expansion rate, the corresponding abnormal area is located, and the expansion amount collected by the sensor in the abnormal area and the temperature gradient of the abnormal area are obtained; Calculating a diffusion index of the abnormal area according to the expansion amount and the temperature gradient; The abnormal expansion level of the boiler is determined according to the abnormal diffusion index.
7. The boiler expansion monitoring method according to claim 6, characterized in that: Determining the expansion abnormality level of the boiler according to the abnormal diffusion index includes: If the abnormal diffusion index is less than or equal to the first index threshold, determining that the expansion abnormality level of the boiler is a locally controllable abnormality level; If the abnormal diffusion index is greater than the first index threshold and less than or equal to the second index threshold, determining that the expansion abnormality level of the boiler is the regional expansion abnormality level; If the abnormal diffusion index is greater than the second index threshold, the expansion abnormality level of the boiler is determined to be a systemic risk abnormality level.
8. A boiler expansion monitoring device, characterized in that: The boiler expansion monitoring device comprises: An acquisition module is used to collect expansion displacement data and environmental parameter data of each sensor group in real time, wherein a plurality of sensor groups are arranged at intervals along the axial direction and the circumferential direction on the outer surface of the boiler pressure-bearing component; a processing module, configured to filter the expansion displacement data and compensate the environmental parameter data; a calculation module, configured to establish an expansion trend prediction model based on the processed data, and calculate the real-time expansion rate of the boiler using the expansion trend prediction model; The determination module is configured to compare the real-time expansion rate with a preset expansion rate to determine an expansion abnormality level of the boiler.
9. The boiler expansion monitoring device according to claim 8, characterized in that: The processing module is used to determine the target decomposition level using an adaptive wavelet packet decomposition algorithm based on the current real-time load rate of the boiler; Decomposing the expansion displacement data based on the target decomposition level; Threshold denoising is performed on the high-frequency components in the decomposed expansion displacement data, and time-domain matched filtering is performed on the low-frequency components in the decomposed expansion displacement data to obtain filtered expansion displacement data.
10. The boiler expansion monitoring device according to claim 8, characterized in that: The processing module is used to fit the nonlinear relationship between the temperature rise gradient and the displacement error by the least square method based on the historical temperature sensor temperature and the historical pipe wall temperature, so as to establish an initial compensation equation; Correcting the compensation coefficient of the compensation equation by using Kalman filtering to obtain a corrected compensation equation; The environmental parameter data is input into the revised compensation equation.