Method and system for dynamically monitoring and early warning state of boiler high-temperature pipeline support hanger
By constructing a network of monitoring points and a network of risk coefficients for support and hangers, and conducting a two-dimensional risk integration analysis of load and displacement changes, the problem of low timeliness and accuracy of dynamic risk early warning response in existing technologies is solved, and the optimal allocation and accurate early warning of support and hanger condition monitoring resources are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-15
- Publication Date
- 2026-04-14
AI Technical Summary
Existing technologies cannot make comprehensive judgments based on multiple factors, resulting in low timeliness and accuracy of dynamic risk warning response for boiler high-temperature pipe supports and hangers, and difficulty in identifying potential faults caused by factors such as thermal expansion linkage and structural coupling.
By acquiring the distribution map of high-temperature pipelines, a distribution network of support and hanger monitoring points is constructed. A two-dimensional risk integration analysis of load change and displacement change is performed to determine the risk coefficient distribution network of support and hanger monitoring points. Based on the nearest neighbor risk coefficient and matrix, resource reallocation and dynamic status monitoring and early warning are carried out.
It enables comprehensive judgment based on multiple factors, improving the optimal allocation of support and hanger condition monitoring resources and the timeliness and accuracy of precise dynamic risk early warning response.
Smart Images
Figure CN121854835A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of boiler monitoring and early warning technology, and in particular to a method and system for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers. Background Technology
[0002] In large coal-fired power generation boiler systems, high-temperature and high-pressure pipelines such as main steam and reheat hot sections undergo drastic thermal expansion and contraction during operation, causing pipeline supports to bear continuously changing loads and displacements. The stability and responsiveness of the supports are directly related to the overall stress distribution and structural safety of the pipeline system.
[0003] To ensure the reliable operation of the pipeline system under various operating conditions such as start-up, shutdown, and load changes, the conventional practice is to conduct condition checks and maintenance on the supports and hangers through regular inspections and local monitoring to avoid risks such as support and hanger jamming, imbalance, and fatigue failure.
[0004] Existing support and hanger condition monitoring methods mostly employ a single-point, decentralized deployment approach, which cannot systematically screen and dynamically monitor support and hanger distribution based on the overall thermal stress behavior of the piping system. Furthermore, monitoring data processing primarily relies on single-dimensional judgments (such as abnormal loads or sudden displacements), lacking a comprehensive assessment of the correlation and regional coupling effects between multiple high-risk supports and hangers. This makes it difficult to identify potential regional faults caused by factors such as thermal expansion linkages, structural coupling, or spatial interference, resulting in low timeliness and accuracy of dynamic risk warning responses. Summary of the Invention
[0005] The purpose of this application is to provide a method and system for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports, in order to solve the technical problems of existing technologies that cannot make comprehensive judgments based on multiple factors, and have low timeliness and accuracy of dynamic risk early warning response.
[0006] Firstly, this application provides a method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports, comprising: Step S100: Obtain the high-temperature pipeline distribution map of the target boiler, and collect support and hanger monitoring points from three dimensions: the degree of influence of thermal expansion, stress concentration and spatial layout complexity, and construct a support and hanger monitoring point distribution network. Step S200: Traverse the distribution network of support and hanger monitoring points to perform a two-dimensional risk integration analysis of load change and displacement change, and determine the risk coefficient distribution network of support and hanger monitoring points; Step S300: Based on the risk coefficient distribution network of the support and hanger monitoring points, the monitoring matrix of the support and hanger monitoring point distribution network is divided to determine M nearest neighbor risk monitoring matrices and M nearest neighbor risk coefficients, where M is a positive integer; Step S400: Based on the M nearest neighbor risk coefficients and the M nearest neighbor risk monitoring matrices, resource reallocation is performed on the support and hanger status monitoring unit of the target boiler to obtain M support and hanger status monitoring sub-units and M support and hanger status early warning thresholds; Step S500: The M support and hanger status monitoring subunits are used to perform dynamic status monitoring and early warning on the M neighbor risk monitoring matrices based on the M support and hanger status early warning thresholds.
[0007] Furthermore, step S100 includes: Step S110: Identify the distribution of supports and hangers based on the high-temperature pipeline distribution map to obtain the support and hanger distribution map; Step S121: Based on the degree of influence of thermal expansion, filter the support and hanger distribution map and the high-temperature pipeline distribution map to obtain the first set of support and hanger monitoring points; Step S122: Based on the stress concentration, filter the support and hanger distribution map and the high-temperature pipeline distribution map to obtain a second set of support and hanger monitoring points; Step S123: Based on the spatial layout complexity, filter the support and hanger distribution map and the high-temperature pipeline distribution map to obtain a third set of support and hanger monitoring points; Step S130: Perform the union of the first set of support bracket monitoring points, the second set of support bracket monitoring points, and the third set of support bracket monitoring points, and construct the support bracket monitoring point distribution network by combining the location of each support bracket monitoring point.
[0008] Furthermore, step S121 includes: Extract the pipeline paths of the main steam pipeline, reheat hot section pipeline, reheat cold section pipeline, and high-pressure water supply pipeline from the high-temperature pipeline distribution map to obtain a set of high-temperature pipeline paths; Extract the set of support and hanger locations from the support and hanger distribution map; Based on the characteristics of pipeline materials, structural parameters, and design operating temperature, high thermal expansion risk areas are identified in the set of high-temperature pipeline paths to obtain a set of high thermal expansion risk areas. Based on the set of support and hanger locations, the set of high thermal expansion risk areas is matched according to preset risk locations to obtain the first set of support and hanger monitoring points.
[0009] Furthermore, the preset risk locations include the fixed end, the compensator, the device interface, and both ends of the long straight section.
[0010] Furthermore, in step S122, the thermal displacement trend of the long-distance main steam pipeline or reheat hot section pipeline is analyzed, and the expansion path end, fixed end and guide section of the support and hanger that are sensitive to thermal deformation are selected. The second set of support and hanger monitoring points is determined by identifying the structurally vulnerable areas of the support and hanger. The structurally vulnerable areas include the connection points and compensators of the local stress concentration areas. In step S123, by analyzing whether there are adjustment difficulties and layout interference in the space where the support and hanger are located, the support and hanger in unfavorable spatial environments are marked in order to determine the set of monitoring points for the third support and hanger.
[0011] Furthermore, step S200 includes: The load and displacement of the support and hanger monitoring point distribution network are monitored according to the preset monitoring frequency to obtain the load monitoring data sequence distribution network and the displacement monitoring data sequence distribution network. By utilizing the load change feature extraction branch, feature extraction is performed on the load monitoring data sequence distribution network to obtain the load change feature distribution network. By utilizing the displacement monitoring feature extraction branch, feature extraction is performed on the displacement monitoring data sequence distribution network to obtain the displacement change feature distribution network. By performing a weighted analysis on the load change characteristic distribution network and the displacement change characteristic distribution network, the risk coefficient distribution network of the support and hanger monitoring points is obtained.
[0012] Furthermore, multiple sample load monitoring data sequences and corresponding multiple sample load change features are obtained as training data to supervise the training of the framework built on the neural network until the training converges, thus obtaining the load change feature extraction branch after training is completed.
[0013] Furthermore, step S300 includes: After arranging the risk coefficients of the support and hanger monitoring points in the risk coefficient distribution network from largest to smallest, the risk coefficients of the support and hanger monitoring points located in the top M positions are extracted as the M nearest neighbor centers. The risk coefficient distribution network of the support and hanger monitoring points is divided based on the M nearest neighbor centers to obtain the risk coefficient set of the M nearest neighbor support and hanger monitoring points; Each of the M nearest neighbor support and hanger monitoring points is used as a monitoring matrix to obtain M nearest neighbor risk monitoring matrices. Calculate the mean of the risk coefficient set of the M nearest neighbor support monitoring points to obtain the M nearest neighbor risk coefficients.
[0014] Furthermore, the risk coefficient of each monitoring point in the risk coefficient distribution network of the support and hanger monitoring points is added to the set of risk coefficients of the nearest neighbor monitoring points corresponding to the nearest neighbor center, to obtain the M sets of risk coefficients of the nearest neighbor monitoring points.
[0015] Secondly, this application provides a dynamic monitoring and early warning system for the status of boiler high-temperature pipe supports, which applies the dynamic monitoring and early warning method for the status of boiler high-temperature pipe supports described in any one of the preceding claims. The system includes: The system includes a hanging support monitoring point distribution network construction module, a risk coefficient distribution network determination module, a nearest neighbor risk coefficient determination module, a support and hanger status early warning threshold module, and a status dynamic monitoring and early warning module.
[0016] Compared with existing technologies, the method and system for dynamic monitoring and early warning of the status of high-temperature pipeline supports and hangers provided in this application acquires a high-temperature pipeline distribution map of the target boiler, collects support and hanger monitoring points from three dimensions: the degree of influence of thermal expansion, stress concentration, and spatial layout complexity, and constructs a support and hanger monitoring point distribution network. Then, it traverses the support and hanger monitoring point distribution network to perform a two-dimensional risk integration analysis of load change and displacement change, determines the risk coefficient distribution network of support and hanger monitoring points, and then divides the support and hanger monitoring point distribution network into monitoring matrices based on the risk coefficient distribution network of support and hanger monitoring points to determine M nearest neighbor risk monitoring matrices and M nearest neighbor risk coefficients. Then, based on the M nearest neighbor risk coefficients and M nearest neighbor risk monitoring matrices, it reallocates resources for the support and hanger status monitoring units of the target boiler to obtain M support and hanger status monitoring sub-units and M support and hanger status early warning thresholds. Finally, it uses the M support and hanger status monitoring sub-units to perform dynamic status monitoring and early warning of the M nearest neighbor risk monitoring matrices based on the M support and hanger status early warning thresholds.
[0017] This enables comprehensive judgment based on multiple factors, achieves optimal allocation of support and hanger status monitoring resources, and provides accurate dynamic status monitoring and risk warning, thereby improving the timeliness and accuracy of dynamic risk warning response. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0019] Figure 1 This is a flowchart illustrating the dynamic monitoring and early warning method for the status of boiler high-temperature pipe supports provided in this application embodiment; Figure 2 This is a schematic diagram of the structure of the dynamic monitoring and early warning system for the status of boiler high-temperature pipe supports provided in this application embodiment.
[0020] Figure label: 10 - Construction module for the distribution network of hanger monitoring points; 20 - Module for determining the distribution network of risk coefficients; 30 - Module for determining the risk coefficients of neighboring countries; 40 - Module for early warning threshold of hanger status; 50 - Module for dynamic monitoring and early warning of status. Detailed Implementation
[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.
[0022] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.
[0023] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0024] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this application is in use. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. In addition, the terms "first," "second," and "third," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0025] Furthermore, terms such as "horizontal," "vertical," and "sag" do not imply that components must be absolutely horizontal or suspended, but rather that they can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal relative to "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.
[0026] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0027] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.
[0028] like Figure 1 and Figure 2 As shown, this application provides a method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers, and a system for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers using the method. The system includes a support monitoring point distribution network construction module 10, a risk coefficient distribution network determination module 20, a nearest neighbor risk coefficient determination module 30, a support status early warning threshold module 40, and a status dynamic monitoring and early warning module 50.
[0029] like Figure 1 As shown in the embodiment of this application, the method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers includes: Step S100: The high-temperature pipeline distribution map of the target boiler can be obtained through the hanger monitoring point distribution network construction module 10. The high-temperature pipeline distribution map is collected from three dimensions: the degree of influence of thermal expansion, stress concentration and spatial layout complexity, and the support and hanger monitoring points are collected to construct the support and hanger monitoring point distribution network. The high-temperature pipeline distribution diagram refers to the information drawing that describes the layout path, connection relationship, and support and hanger installation position of high-temperature operating pipelines such as main steam pipelines, reheat pipelines, and high-pressure feedwater in the boiler system between the boiler body and auxiliary equipment. Specifically, it may include two-dimensional design drawings, BIM models, and point cloud modeling diagrams.
[0030] The degree of influence of thermal expansion refers to the magnitude of geometric dimensional changes caused by material thermal expansion during pipeline operation, especially in long straight sections and paths with large temperature differences, which directly affects the load and displacement behavior of supports and hangers.
[0031] Stress concentration is a characterization of the local stress distribution level at pipeline structures due to geometric changes (such as tees, elbows, compensators, welded joints, etc.) or operational boundary conditions (such as fixed ends). These areas are prone to complex stress on supports and hangers.
[0032] The spatial layout complexity describes the geometric spatial difficulty of the support and hanger installation environment, such as interference with other equipment, limited adjustment space, different installation directions, and restricted layout due to structural limitations, which affect the accuracy of sensor deployment and status acquisition.
[0033] The network of support and hanger monitoring points is a data structure and physical layout system built for structural risk management. Its nodes are the selected support and hanger monitoring points, and the edges represent the spatial / thermal / stress coupling relationships between the points, which are used for subsequent dynamic monitoring point deployment and strategy configuration.
[0034] In step S200, the risk coefficient distribution network determination module 20 can traverse the support and hanger monitoring point distribution network to perform a two-dimensional risk integration analysis of load change and displacement change, and determine the support and hanger monitoring point risk coefficient distribution network. In step S300, the nearest neighbor risk coefficient determination module 30 can divide the support and hanger monitoring point distribution network into monitoring matrices based on the risk coefficient distribution network of the support and hanger monitoring points, and determine M nearest neighbor risk monitoring matrices and M nearest neighbor risk coefficients, where M is a positive integer; In step S400, the support and hanger status early warning threshold module 40 can reallocate resources of the support and hanger status monitoring unit of the target boiler based on M nearest neighbor risk coefficients and M nearest neighbor risk monitoring matrices to obtain M support and hanger status monitoring sub-units and M support and hanger status early warning thresholds. In step S500, the dynamic status monitoring and early warning module 50 can use M support and hanger status monitoring sub-units to perform dynamic status monitoring and early warning on M neighbor risk monitoring matrices based on the M support and hanger status early warning thresholds.
[0035] With this configuration, the boiler high-temperature pipeline support and hanger status dynamic monitoring and early warning method and system provided in this application embodiment achieves comprehensive judgment based on multiple factors, and achieves the optimal configuration effect of support and hanger status monitoring resources and the effect of accurate status dynamic monitoring risk early warning, thereby improving the timeliness and accuracy of dynamic risk early warning response.
[0036] Furthermore, step S100 may also include: Step S110: Identify the distribution of supports and hangers based on the high-temperature pipeline distribution map to obtain the support and hanger distribution map; Step S121: Screen the support and hanger monitoring points based on the degree of thermal expansion effect on the support and hanger distribution map and the high-temperature pipeline distribution map to obtain the first set of support and hanger monitoring points; This may further include: extracting the pipeline paths of the main steam pipeline, reheat hot section pipeline, reheat cold section pipeline, and high-pressure water supply pipeline from the high-temperature pipeline distribution map to obtain a set of high-temperature pipeline paths; extracting the set of support and hanger locations from the support and hanger distribution map; identifying high thermal expansion risk areas in the high-temperature pipeline path set based on pipeline material characteristics, structural parameters, and design operating temperature to obtain a set of high thermal expansion risk areas; and matching the set of high thermal expansion risk areas with the set of support and hanger locations according to preset risk locations to obtain the first set of support and hanger monitoring points. The preset risk locations include fixed ends, compensators, equipment interfaces, and both ends of long straight sections.
[0037] Step S122: Screen the support and hanger monitoring points based on the stress concentration of the support and hanger distribution map and the high-temperature pipeline distribution map to obtain the second set of support and hanger monitoring points; Specifically, by analyzing the thermal displacement trend of long-distance main steam pipelines or reheat hot section pipelines, the expansion path ends, fixed ends, and guide sections of supports and hangers that are sensitive to thermal deformation can be selected, and the set of monitoring points for the second support and hanger can be determined by identifying the structurally vulnerable areas of the supports and hangers. These structurally vulnerable areas include local stress concentration areas such as connection points and compensators.
[0038] Step S123: Based on the spatial layout complexity, filter the support and hanger distribution map and the high-temperature pipeline distribution map to obtain the third set of support and hanger monitoring points; Specifically, the set of monitoring points for the third support can be determined by analyzing whether there are difficulties in adjusting the space where the support is located and interference in the layout, and by highlighting the support in unfavorable spatial environments.
[0039] Step S130: Find the union of the three sets of monitoring points (first, second, and third support brackets) and construct a distribution network of support bracket monitoring points based on the location of each support bracket monitoring point. This lays the structural foundation for subsequent dynamic status assessment and intelligent monitoring resource allocation.
[0040] A preferred embodiment involves first extracting complete path information for the four types of high-temperature pipelines involved in the target boiler from the pipeline layout diagram to form a high-temperature pipeline path set; second, extracting the location, number, and type of each support from the support and hanger distribution diagram to form a support and hanger location set; then, calculating or analyzing the expansion trend of each pipe segment using parameters such as material thermal expansion characteristics, path length, and support boundary conditions, screening out pipe segments significantly affected by thermal deformation, and establishing a high thermal expansion risk area set; finally, spatially matching the high thermal expansion risk area set with the support and hanger locations, retaining only the supports and hangers located at preset risk positions as the first batch of key monitoring targets, forming the first support and hanger monitoring point set.
[0041] By selecting monitoring points based on thermal characteristics and eliminating areas with small thermal strain effects and gradual structural changes, the efficiency of point selection and the accuracy of risk identification are significantly improved, laying the foundation for subsequent condition monitoring.
[0042] Furthermore, step S200 may also include: performing load monitoring and displacement monitoring on the distribution network of monitoring points of the support and hanger according to a preset monitoring frequency, and obtaining a load monitoring data sequence distribution network and a displacement monitoring data sequence distribution network. The preset monitoring frequency refers to the sensor data acquisition cycle set by the system before operation based on the boiler operating characteristics, support and hanger response speed and risk warning requirements, such as 5~10 minutes / time. By utilizing the load change feature extraction branch, feature extraction is performed on the load monitoring data sequence distribution network. Specifically, the load change data of each monitoring point in the load monitoring data sequence distribution network is processed to extract load features that reflect structural instability, such as mean change rate, maximum peak value, and short-term mutation, and the load change feature distribution network is obtained. By utilizing the displacement monitoring feature extraction branch, feature extraction is performed on the displacement monitoring data sequence distribution network, specifically extracting dynamic indicators such as abnormal slip, over-limit displacement, and vibration amplitude, and obtaining the displacement change feature distribution network. Weighted analysis is performed on the load change characteristic distribution network and the displacement change characteristic distribution network. The load characteristics and displacement characteristics of each monitoring point are synthesized according to the set rules to form a normalized risk coefficient. The risk coefficient distribution network of the support and hanger monitoring points is obtained by summarizing the data. The load monitoring data sequence distribution network and the displacement monitoring data sequence distribution network reflect the changes in the monitoring data of load and displacement, respectively.
[0043] In a preferred embodiment, multiple sample load monitoring data sequences and corresponding multiple sample load change features are acquired as training data, and the framework constructed based on the neural network is subjected to supervised training until the training converges, thereby obtaining the load change feature extraction branch after training is completed.
[0044] For example, data from approximately 2000 support and hanger monitoring points were collected from 10 in-service supercritical coal-fired power units. Each point was collected over a 1-hour period at a monitoring frequency of 1 Hz, resulting in 3600 data points per point. These sequences were manually or semi-automatically labeled into categories such as "stable," "fluctuating," "abrupt," "rising trend," and "falling trend," forming a training dataset. The cross-entropy loss function was used to analyze the training process. After 100 training iterations, the loss decreased to 0.02, and the accuracy improved to over 95%. The model eventually converged, yielding a load change feature extraction branch. Based on the same principle used in training the load change feature extraction branch, a displacement monitoring feature extraction branch was obtained.
[0045] Furthermore, step S300 may further include: arranging the risk coefficients of the support and hanger monitoring points in the risk coefficient distribution network in descending order, and extracting the risk coefficients of the top M support and hanger monitoring points as M nearest neighbor centers; dividing the support and hanger monitoring point risk coefficient distribution network based on the M nearest neighbor centers to obtain M sets of nearest neighbor support and hanger monitoring point risk coefficients; taking the support and hanger monitoring points corresponding to the M sets of nearest neighbor support and hanger monitoring point risk coefficients as a monitoring matrix to obtain M nearest neighbor risk monitoring matrices; and calculating the mean of the M sets of nearest neighbor support and hanger monitoring point risk coefficients to obtain M nearest neighbor risk coefficients.
[0046] In the aforementioned embodiments, the risk coefficient of each monitoring point in the risk coefficient distribution network of the support and hanger monitoring points can be added to the set of risk coefficients of the nearest neighboring support and hanger monitoring points corresponding to the nearest neighboring center, thereby obtaining M sets of risk coefficients of the nearest neighboring support and hanger monitoring points.
[0047] One specific implementation involves sorting all monitoring points by risk coefficient in descending order and extracting the top M points as nearest neighbor centers. These points are considered the weakest or most dangerous critical nodes at present. All other monitoring points are assigned to a set based on their distance from the nearest neighbor center (which can be geometric distance, topological path length, or thermal stress path weight). Each point is assigned to the set corresponding to the nearest center, forming M sets of risk coefficients for nearest neighbor support monitoring points.
[0048] Each set contains monitoring points as an independent monitoring matrix, which facilitates subsequent resource allocation (such as data bandwidth, computing power, and monitoring frequency adjustment) by region; the risk coefficient of each set is averaged to obtain the nearest neighbor risk coefficient, which represents the overall risk level of the matrix. This value will be used in the next step to set the early warning level and resource priority.
[0049] For example, consider a boiler system with 200 support and hanger monitoring points. Five nearest-neighbor center points (with risk values such as 0.92, 0.87, etc.) are selected based on risk coefficient ranking. The remaining 195 points are then assigned to these five centers based on spatial thermal distance, with average risk values of 0.78, 0.65, 0.50, 0.45, and 0.40 for each set. These form five nearest-neighbor risk monitoring matrices, each with its own independent monitoring frequency and alarm threshold settings.
[0050] In step 500, one optional embodiment is that monitoring resources of different levels can be allocated according to the neighbor risk coefficients of the M neighbor risk monitoring matrices.
[0051] For example, sub-units with a risk coefficient > 0.8 are designated as Level 1 key monitoring areas, allocated higher sampling frequencies, more frequent status assessment cycles, and stricter threshold standards. Each sub-unit is internally bound to support and hanger monitoring points, resource allocation strategies, operational data channels, and local threshold models, thereby constructing a monitoring structure with clear boundaries, independent states, and parallel management capabilities. Those skilled in the art, combining historical data, design values, and real-time fluctuation trends, set early warning thresholds for each support and hanger status monitoring sub-unit, thus obtaining the M support and hanger status early warning thresholds. These thresholds include fluctuation frequency thresholds, abnormal change trigger times, and load anomaly tolerance.
[0052] M support and hanger status monitoring sub-units are used to monitor the data of the M nearest neighbor risk monitoring matrices respectively, and the monitored data are judged by the M support and hanger status early warning thresholds. When any support and hanger status index (such as instantaneous load jump, continuous displacement deviation) exceeds its threshold, an early warning is triggered.
[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
Claims
1. A method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports, characterized in that, include: Step S100: Obtain the high-temperature pipeline distribution map of the target boiler, and collect support and hanger monitoring points from three dimensions: the degree of influence of thermal expansion, stress concentration and spatial layout complexity, and construct a support and hanger monitoring point distribution network. Step S200: Traverse the distribution network of support and hanger monitoring points to perform a two-dimensional risk integration analysis of load change and displacement change, and determine the risk coefficient distribution network of support and hanger monitoring points; Step S300: Based on the risk coefficient distribution network of the support and hanger monitoring points, the monitoring matrix of the support and hanger monitoring point distribution network is divided to determine M nearest neighbor risk monitoring matrices and M nearest neighbor risk coefficients, where M is a positive integer; Step S400: Based on the M nearest neighbor risk coefficients and the M nearest neighbor risk monitoring matrices, resource reallocation is performed on the support and hanger status monitoring unit of the target boiler to obtain M support and hanger status monitoring sub-units and M support and hanger status early warning thresholds; Step S500: The M support and hanger status monitoring subunits are used to perform dynamic status monitoring and early warning on the M neighbor risk monitoring matrices based on the M support and hanger status early warning thresholds.
2. The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to claim 1, characterized in that, Step S100 includes: Step S110: Identify the distribution of supports and hangers based on the high-temperature pipeline distribution map to obtain the support and hanger distribution map; Step S121: Based on the degree of influence of thermal expansion, filter the support and hanger distribution map and the high-temperature pipeline distribution map to obtain the first set of support and hanger monitoring points; Step S122: Based on the stress concentration, filter the support and hanger distribution map and the high-temperature pipeline distribution map to obtain a second set of support and hanger monitoring points; Step S123: Based on the spatial layout complexity, filter the support and hanger distribution map and the high-temperature pipeline distribution map to obtain a third set of support and hanger monitoring points; Step S130: Perform the union of the first set of support bracket monitoring points, the second set of support bracket monitoring points, and the third set of support bracket monitoring points, and construct the support bracket monitoring point distribution network by combining the location of each support bracket monitoring point.
3. The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to claim 2, characterized in that, Step S121 includes: Extract the pipeline paths of the main steam pipeline, reheat hot section pipeline, reheat cold section pipeline, and high-pressure water supply pipeline from the high-temperature pipeline distribution map to obtain a set of high-temperature pipeline paths; Extract the set of support and hanger locations from the support and hanger distribution map; Based on the characteristics of pipeline materials, structural parameters, and design operating temperature, high thermal expansion risk areas are identified in the set of high-temperature pipeline paths to obtain a set of high thermal expansion risk areas. Based on the set of support and hanger locations, the set of high thermal expansion risk areas is matched according to preset risk locations to obtain the first set of support and hanger monitoring points.
4. The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to claim 3, characterized in that, The preset risk locations include the fixed end, the compensator, the device interface, and both ends of the long straight section.
5. The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to claim 4, characterized in that, In step S122, the thermal displacement trend of long-distance main steam pipeline or reheat hot section pipeline is analyzed, and the expansion path end, fixed end and guide section of the support and hanger that are sensitive to thermal deformation are selected. The second support and hanger monitoring point set is determined by identifying the structurally vulnerable areas of the support and hanger. The structurally vulnerable areas include the connection points and compensators of local stress concentration areas. In step S123, by analyzing whether there are adjustment difficulties and layout interference in the space where the support and hanger are located, the support and hanger in unfavorable spatial environments are marked in order to determine the set of monitoring points for the third support and hanger.
6. The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to claim 1, characterized in that, Step S200 includes: The load and displacement of the support and hanger monitoring point distribution network are monitored according to the preset monitoring frequency to obtain the load monitoring data sequence distribution network and the displacement monitoring data sequence distribution network. By utilizing the load change feature extraction branch, feature extraction is performed on the load monitoring data sequence distribution network to obtain the load change feature distribution network. By utilizing the displacement monitoring feature extraction branch, feature extraction is performed on the displacement monitoring data sequence distribution network to obtain the displacement change feature distribution network. By performing a weighted analysis on the load change characteristic distribution network and the displacement change characteristic distribution network, the risk coefficient distribution network of the support and hanger monitoring points is obtained.
7. The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to claim 6, characterized in that, Multiple sample load monitoring data sequences and corresponding sample load change features are acquired as training data. The framework based on the neural network is trained under supervision until the training converges, and the load change feature extraction branch is obtained after training is completed.
8. The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to claim 1, characterized in that, Step S300 includes: After arranging the risk coefficients of the support and hanger monitoring points in the risk coefficient distribution network from largest to smallest, the risk coefficients of the support and hanger monitoring points located in the top M positions are extracted as the M nearest neighbor centers. The risk coefficient distribution network of the support and hanger monitoring points is divided based on the M nearest neighbor centers to obtain the risk coefficient set of the M nearest neighbor support and hanger monitoring points; Each of the M nearest neighbor support and hanger monitoring points is used as a monitoring matrix to obtain M nearest neighbor risk monitoring matrices. Calculate the mean of the risk coefficient set of the M nearest neighbor support monitoring points to obtain the M nearest neighbor risk coefficients.
9. The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to claim 8, characterized in that, Each monitoring point risk coefficient in the support and hanger monitoring point risk coefficient distribution network is added to the set of neighboring support and hanger monitoring point risk coefficients corresponding to the nearest neighbor center, thus obtaining the M sets of neighboring support and hanger monitoring point risk coefficients.
10. A dynamic monitoring and early warning system for the status of boiler high-temperature pipe supports, characterized in that, The method for dynamic monitoring and early warning of the status of boiler high-temperature pipe supports and hangers according to any one of claims 1 to 9, wherein the system comprises: The system includes a hanging support monitoring point distribution network construction module, a risk coefficient distribution network determination module, a nearest neighbor risk coefficient determination module, a support and hanger status early warning threshold module, and a status dynamic monitoring and early warning module.