Heating station equipment health state monitoring system and method

Abstract

The invention relates to the technical field of equipment state monitoring, in particular to a heating station equipment health state monitoring system and method. The method comprises the following steps: acquiring structural data of heating station equipment; carrying out topological structure analysis on the heating station based on the heating station equipment structure data to generate heating station equipment topological data; carrying out virtual simulation modeling on the structural data of the heating station equipment by utilizing the topological data of the heating station equipment to generate a three-dimensional model of the heating station equipment; extracting a heat exchanger area of the three-dimensional model of the heating station equipment, and performing heat exchange pipeline path analysis on the heat exchanger area to generate heat exchange circulation data; and surface acoustic wave sensor data acquisition is carried out based on the heat exchanger area to obtain heat exchange surface wave group speed change data. According to the method, through structural topology modeling, fine heat exchange area monitoring, dynamic damage accumulation analysis and closed-loop operation optimization, the accurate monitoring and risk early warning capability of the health state of the heating station equipment is comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment status monitoring, and in particular to a system and method for monitoring the health status of thermal power station equipment. Background Art

[0002] In the early days, maintenance of thermal power station equipment relied primarily on regular manual inspections and empirical judgment, resulting in monitoring blind spots and delayed responses. With the advancement of sensor technology, real-time collection of parameters such as temperature, pressure, and vibration has become possible, gradually enriching the data base for equipment operating status. In the information age, while traditional threshold-based monitoring methods can provide basic alerts, they struggle to accurately reflect the overall health of the equipment, prone to false alarms and missed alerts. With the rise of big data and machine learning technologies, thermal power station equipment health monitoring has entered an intelligent phase. By building multidimensional data models of equipment operation and employing algorithms for condition assessment, fault diagnosis, and predictive maintenance, comprehensive assessments of equipment health and early warnings are achieved. However, existing technologies often struggle with fine-grained monitoring of key components, such as heat exchangers, and lack detailed analysis of heat exchange piping paths. Furthermore, assessments of thermal stress and damage often rely on empirical or static indicators, which fail to reflect non-steady-state dynamic processes. This results in limited capabilities for accurate monitoring of thermal power station equipment health and risk warnings. Summary of the Invention

[0003] Based on this, it is necessary to provide a thermal power station equipment health status monitoring system and method to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for monitoring the health status of thermal power station equipment is provided, the method comprising the following steps: Step S1: Acquire the thermal power station equipment structure data; perform a topological structure analysis on the thermal power station based on the thermal power station equipment structure data to generate the thermal power station equipment topology data; perform virtual simulation modeling on the thermal power station equipment structure data using the thermal power station equipment topology data to generate a three-dimensional model of the thermal power station equipment; Step S2: Extract the heat exchanger area of ​​the three-dimensional model of the thermal power station equipment, and perform heat exchange pipeline path analysis on the heat exchanger area to generate heat exchange flow data; perform surface acoustic wave sensor data acquisition based on the heat exchanger area to obtain heat exchange surface wave group velocity change data; Step S3: Calculate the transient thermal stress of the heat exchange surface wave group velocity change data; perform non-steady-state damage accumulation analysis on the transient thermal stress through the heat exchange flow data to generate heat exchanger micro-damage accumulation data; use the heat exchanger micro-damage accumulation data to optimize the heat exchange pipeline path to generate heat exchange optimization pipeline data; Step S4: Acquire the thermal power station operation data; extract the heat exchange start and stop data from the thermal power station operation data, and optimize the start and stop pipeline control of the heat exchange optimization pipeline data based on the heat exchange start and stop data to obtain the start and stop path that minimizes the cumulative damage; adjust the operation strategy based on the start and stop path that minimizes the cumulative damage, and feed back the adjustment results to the control system to achieve closed-loop monitoring of the health status of the thermal power station heat exchanger and damage risk warning operations.

[0005] Through topological structure analysis and virtual simulation modeling, this invention generates a highly reliable three-dimensional model of thermal power station equipment, providing a digital foundation for subsequent heat exchange pipeline analysis and sensor data mapping, effectively improving modeling efficiency and accuracy. Using surface acoustic wave sensors to collect surface wave group velocity data from the heat exchanger, and combining it with heat transfer characteristics to perform transient thermal stress and non-steady-state damage accumulation analysis, this system can identify minor structural damage and provide early warning of potential failures caused by thermal stress. Based on this accumulated micro-damage data, the heat exchange pipeline path is dynamically adjusted to generate optimal heat exchange optimization pipeline data, improving heat exchange efficiency while extending equipment life. This system exhibits high adaptability and autonomous optimization capabilities. By deeply mining start-stop data and optimizing pipeline control, the risk of fatigue damage to equipment during frequent starts and stops is effectively reduced, ensuring system operational stability and extending the service life of key components. By integrating simulation models, sensor data, operational data, and control feedback, a closed-loop monitoring system for the health status of heat exchangers is constructed, enabling a shift from "responsive maintenance" to "predictive maintenance" and improving equipment reliability and intelligent management. This method integrates structural modeling, sensor perception, data fusion, path optimization, and control feedback, boasting strong versatility and scalability. It provides technical support for the construction of smart energy systems and promotes the transformation and upgrade of thermal power station equipment from traditional management to intelligent operation and maintenance. Therefore, through structural topology modeling, precise heat exchange area monitoring, dynamic damage accumulation analysis, and closed-loop operation optimization, this invention comprehensively enhances the ability to accurately monitor the health status of thermal power station equipment and provide risk warnings.

[0006] Preferably, step S1 includes the following steps: Step S11: Acquire thermal power station equipment structure data; Step S12: Identify the structural components of the thermal power station equipment structure data to extract equipment unit data; construct an equipment connection relationship diagram based on the equipment unit data to generate an initial thermal power station structure diagram; Step S13: Performing graph structure analysis on the initial structure diagram of the thermal power station, extracting node connection relationships, and generating thermal power station equipment topology data; using the thermal power station equipment topology data, performing spatial correlation modeling on the equipment unit data, and generating structure mapping data; Step S14: Execute virtual simulation modeling operations based on the structural mapping data to generate an initial three-dimensional structural model of the thermal power station equipment; perform component geometry correction and topological closure processing on the initial three-dimensional structural model of the thermal power station equipment to generate a three-dimensional model of the thermal power station equipment.

[0007] This invention constructs a high-fidelity 3D model of the thermal power station structure through a comprehensive process from structural data acquisition, unit extraction, connection identification, to spatial modeling and geometric closure. This effectively avoids component disconnection, topological errors, and geometric incompleteness that can occur during structural modeling, ensuring the accuracy of subsequent simulation and analysis. By identifying structural components and extracting device unit data, a fine-grained decomposition and classification of the complex equipment system of the thermal power station is achieved, improving the model's operability and maintainability, and providing reliable data support for the modeling and optimization of structural logical relationships. An initial structural diagram is constructed using device connection relationships, and device topology data is generated through graph structure analysis. This accurately describes the spatial and functional relationships between device units, providing a logical constraint foundation for subsequent applications such as path planning and heat flow simulation. Spatial correlation modeling using structural mapping data ensures high consistency between device logical relationships and physical structures, enhancing the model's expressiveness and interactivity, and supporting simulation and system integration operations in multiple scenarios. Component geometry correction and topological closure after 3D modeling effectively address issues such as broken boundaries and misaligned voids that arise during initial modeling, significantly improving the integrity, accuracy, and visualization quality of the structural model. The high-quality three-dimensional structural model provides a reliable foundation for precise regional positioning, structural feature extraction, sensor data mapping and analysis model construction in subsequent steps, building an integrated technical path from "structural understanding" to "functional analysis".

[0008] Preferably, step S2 includes the following steps: Step S21: performing regional segmentation on the three-dimensional model of the thermal power station equipment to obtain heat exchanger regional structure data; identifying the heat exchange pipe network based on the heat exchanger regional structure data to obtain heat exchange pipe topology data; Step S22: performing path tracing analysis on the heat exchange pipeline topology data, calculating the fluid path length and distribution, and generating heat exchange flow data; Step S23: performing surface acoustic wave sensor layout simulation based on the heat exchanger regional structural data to generate sensor sampling layout data; performing surface acoustic wave acquisition control on the sensor sampling layout data to obtain surface acoustic wave original response data; Step S24: performing group velocity extraction and time drift correction on the original surface acoustic wave response data to generate heat exchange surface wave group velocity change data.

[0009] By segmenting the three-dimensional equipment model of a thermal power station and extracting heat exchanger regional structural data, this method can quickly and accurately locate key heat exchange component areas, providing a clear, structured regional model for subsequent analysis and improving modeling efficiency and accuracy. Heat exchange network identification based on regional structural data generates heat exchange pipeline topology data that fully reflects the spatial paths, connections, and structural hierarchy of fluid channels, providing a realistic and usable topological basis for heat exchange path analysis and optimization. By tracing the heat exchange pipeline topology and calculating the fluid path length and distribution, quantifiable and simulatable heat exchange flow data is obtained, providing basic parameter support for thermal stress analysis and dynamic simulation calculations. By simulating sensor layout in the heat exchanger area, generating an optimal sensor sampling layout, and controlling the surface acoustic wave sensor acquisition process, the scientific nature of sensor layout and the representativeness of response data are significantly improved, blind spots are reduced, and monitoring coverage is increased. Group velocity extraction and time drift correction are performed on the raw surface acoustic wave response data to effectively suppress system errors and environmental noise. The generated group velocity change data can more realistically reflect changes in the heat exchanger surface microstructure, laying a data foundation for micro-damage detection. This step integrates the multi-dimensional data of three-dimensional structure, topological path, flow parameters and sensor response into one, forming a multi-source coupling model data chain of the heat exchanger, providing systematic support for subsequent thermal stress analysis and path optimization.

[0010] Preferably, step S22 includes the following steps: Step S221: Filter the node connectivity of the heat exchange pipeline topology data, extract the effective heat exchange path segments, and generate path structure network data; perform geometric reconstruction and curvature analysis on the path structure network data, extract the path segment geometric constraint information, and generate heat exchange path geometric feature data; Step S222: performing spatial path expansion on the heat exchange path geometric characteristic data, and performing flow direction vector calculation on the expanded spatial path to generate an initial flow path vector field; Step S223: Measuring the resistance coefficient of the structure within the heat exchanger; weighting the initial flow path vector field by the resistance coefficient of the structure within the heat exchanger to generate an equivalent flow resistance path diagram; performing fluid path length integration and flow velocity dynamic simulation on the equivalent flow resistance path diagram, calculating the path-level fluid transmission delay, and generating flow delay matrix data; Step S224: performing path-level heat exchange efficiency estimation on the flow delay matrix data to generate heat exchange flow data.

[0011] The present invention uses node connectivity screening and geometric reconstruction analysis, and step S221 can eliminate invalid or redundant pipeline sections, extract real and effective heat exchange paths, and generate complete path structure network data and geometric feature information in combination with curvature analysis, providing a solid structural foundation for accurate modeling and subsequent simulation. Expanding the geometric path to a spatial scale and calculating the initial flow direction vector in combination with the path direction information can reflect the true direction and flow trend of each fluid path in the heat exchange system, laying a physical basis for flow behavior modeling and heat conduction simulation. By measuring the resistance coefficient of the heat exchanger structure and weighting the flow direction vector field, an equivalent flow resistance path diagram is generated, which truly reflects the flow impedance differences of different path segments, and helps to identify flow bottlenecks and inefficient areas in the thermal power station. Based on the equivalent flow resistance diagram, the fluid path length integration and flow velocity simulation are performed, which can dynamically calculate the fluid transmission delay on each path segment and generate flow delay matrix data, providing key time variable support for subsequent thermal efficiency evaluation and start-stop strategies. By estimating the heat exchange efficiency based on the time delay matrix, the differences in heat exchange efficiency can be quantitatively evaluated according to the path dimension, thereby identifying inefficient heat exchange pathways in the structure and providing a powerful technical reference for optimized design and local modification.

[0012] Preferably, step S222 includes the following steps: Step S2221: Perform three-dimensional structural denoising and projection on the geometric feature data of the heat exchange path to eliminate high-order micro-curvature interference and generate a path principal axis fitting line group; perform piecewise spline reconstruction and expansion based on the path principal axis fitting line group to convert the complex spatial path into a regularized path segment sequence and generate a spatial expansion path set; Step S2222: performing geometric continuity weight assignment on the spatially expanded path set, calibrating the directional consistency and structural influence coefficient of each micro-segment, and generating a path direction weighting matrix; Step S2223: performing directional flow vector decomposition based on the path direction weighted matrix, extracting the mainstream vector and disturbance vector of the path element unit, and generating a local flow direction distribution map; Step S2224: reconstruct the local flow direction distribution map at the full path scale to generate a unified initial flow path vector field.

[0013] The present invention can effectively remove the disturbance information caused by high-order micro-curvature and eliminate errors caused by microstructures such as warping and bumps of pipeline components through three-dimensional structural denoising projection and path principal axis fitting line generation; it can also significantly improve the consistency of geometric modeling and the stability of numerical calculations by converting complex paths into regularized segment sequences through spline reconstruction. The geometric continuity weight distribution quantifies the directional consistency and geometric structure influence of each micro-segment to establish a path direction weighted matrix; this matrix can truly express the contribution of each path segment to the consistency of the overall flow direction, effectively improving the local accuracy and global coherence of subsequent vector field modeling. The directional flow vector decomposition performed can decompose the flow trend of each path micro-element unit into mainstream vectors and disturbance vectors; the generated local flow distribution map provides key physical support for analyzing the influence of local structure on flow deflection, vortex or turbulence formation, and has high-resolution modeling capabilities. By splicing local flow maps to generate a unified flow path vector field, seamless connection between local structural changes and global flow trends is achieved; the final generated vector field has good physical consistency, directional continuity and structural correlation, providing a solid foundation for subsequent fluid simulation, resistance analysis and heat exchange efficiency calculation.

[0014] Preferably, step S3 includes the following steps: Step S31: performing multi-scale thermal inversion on the heat exchange surface wave group velocity change data to generate transient thermal gradient distribution data; performing material thermal response modeling on the transient thermal gradient distribution data to calculate the corresponding transient thermal stress data; Step S32: performing unsteady-state boundary modeling on the heat exchange flow data to generate dynamic boundary condition data for the heat exchange process; performing coupling analysis on the transient thermal stress data and the dynamic boundary condition data, implementing unsteady-state damage accumulation modeling, and generating micro-damage evolution curve data; Step S33: performing regional clustering on the micro-damage evolution curve data, and extracting the damage accumulation threshold value of the clustered area to generate heat exchanger micro-damage accumulation data; Step S34: Based on the cumulative data of heat exchanger micro-damage, a path loss sensitivity analysis is performed on the heat exchange pipeline path, high-risk path segments are identified, and a set of candidate paths for heat exchange pipeline improvement is generated; flow efficiency reconstruction and heat exchange performance evaluation are performed on the candidate paths for heat exchange pipeline improvement to generate heat exchange optimized pipeline data.

[0015] The present invention performs multi-scale thermal inversion on group velocity change data to obtain transient thermal gradient distribution, and then combines it with the material thermal response model to calculate high-precision transient thermal stress data, achieving precise quantitative modeling from response data to thermal behavior, providing a scientific basis for damage analysis. Unsteady-state boundary modeling is performed in conjunction with heat transfer flow data to obtain dynamic boundary conditions, and coupled with thermal stress data to establish an unsteady-state damage accumulation model, effectively improving the simulation and prediction capabilities of the micro-damage evolution process under actual working conditions. By constructing micro-damage evolution curves and regional clustering analysis, the local and global damage change trends of the heat exchanger structure under thermal stress can be intuitively displayed, and high-damage areas can be identified accordingly, providing support for structural risk assessment. By extracting damage accumulation thresholds from clustered areas, quantifiable heat exchanger micro-damage accumulation data is obtained, providing digital input conditions for decision-making and control systems, and promoting data-driven damage warning and maintenance strategy formulation. Path loss sensitivity analysis based on damage data can accurately locate high-risk pipeline sections, generate targeted improved candidate path sets, avoid invalid optimization, and significantly improve the targeted nature of path reconstruction. Based on the improved candidate path set, flow efficiency reconstruction and heat exchange performance evaluation are carried out to generate the final heat exchange optimization pipeline data, achieving dual optimization of structural health and system performance, and promoting the improvement of heat exchange efficiency and extension of life of thermal power stations.

[0016] Preferably, in step S34, reconstructing the flow efficiency and evaluating the heat exchange performance of the heat exchange pipeline improvement candidate path set includes: Finite volume fluid simulation is performed on the candidate path set for heat exchange pipeline improvement to generate path flow velocity distribution data. Based on the path flow velocity distribution data, the turbulent structure of the candidate path set for heat exchange pipeline improvement is identified and pressure drop calculation is performed to generate a flow resistance distribution map. The flow resistance distribution map is combined with the thermal boundary conditions to perform local heat transfer coefficient inversion to generate heat transfer efficiency distribution data. The heat transfer efficiency distribution data is used to perform inter-path thermal performance comparison analysis, screen high-performance path units, and generate a path performance optimization set. The optimal path performance set is combined with micro-damage accumulation data to conduct a structural safety review, eliminate potential fatigue sections, and generate a structural safety optimized path set; Multi-objective thermal-mechanical collaborative optimization calculations are performed on the structural safety optimization path set to comprehensively evaluate thermal efficiency, structural integrity, and flow stability, ultimately generating heat exchange optimization pipeline data.

[0017] This invention applies finite volume method (FVM) fluid simulation to the improved path set, generating fine-grained path velocity distribution data. This provides realistic boundary conditions for subsequent turbulent structure identification and pressure drop calculation, achieving a refined mapping from geometric paths to physical flow fields. Based on the velocity distribution data, local turbulent structure characteristics are automatically identified and pressure drop distribution is quantified, forming a flow resistance distribution map. This comprehensively reveals flow bottlenecks and resistance gradients in the pipeline, providing a decision-making basis for fluid dynamics performance optimization. Combining the flow resistance map with boundary conditions, the local heat transfer coefficient field is inverted and further constructed into heat transfer efficiency distribution data. This enables spatial distribution modeling of the heat transfer capacity of different paths, providing a quantitative basis for path thermal performance evaluation. By performing inter-path performance comparison analysis on the heat transfer efficiency distribution data, high thermal efficiency regions are screened and an optimized path performance set is constructed. This enables efficient path selection based on thermal performance indicators, improving energy efficiency. The optimized path performance set is coupled with microdamage accumulation data to identify and eliminate potential fatigue segments, resulting in a structurally safe optimized path set. This ensures that path optimization balances efficiency with structural reliability and lifespan safety. Based on a set of structural safety optimization paths, a multi-objective collaborative optimization algorithm is executed, comprehensively considering the three factors of maximizing thermal efficiency, maintaining structural integrity, and enhancing flow stability. This generates a globally optimal heat exchange path structure, achieving system-level collaborative improvement. The resulting optimized heat exchange piping data is highly feasible, energy-efficient, and safe, driving the thermal system towards a highly reliable and efficient system driven by digital twins, thereby improving the operating life and maintenance cost-effectiveness of the heat exchange system.

[0018] Preferably, step S4 includes the following steps: Step S41: Acquire thermal power station operation data; Step S42: extracting the heat exchange start-stop cycle and transient load changes from the thermal power station operation data to obtain start-stop behavior sequence data; performing fluctuation frequency analysis and startup peak statistics on the start-stop behavior sequence data to generate start-stop stress characteristic data; Step S43: performing time-series coupling simulation on the start-stop stress characteristic data and the heat exchange optimization pipeline data, analyzing the stress response distribution of different paths, and generating a start-stop path stress distribution diagram; Step S44: Based on the start-stop path stress distribution diagram, the damage accumulation function of each candidate path is calculated, the path with the minimum damage growth rate is selected, and the start-stop path with the minimum cumulative damage is generated; the start-stop path with the minimum cumulative damage is used to optimize the start-stop control of the heat exchanger area of ​​the thermal power station and generate operation strategy adjustment parameters; Step S45: Input the operation strategy adjustment parameters into the three-dimensional model of the thermal power station equipment to perform closed-loop monitoring of the equipment health status, and perform damage risk threshold judgment on the monitored equipment health status to perform damage risk warning operations for the thermal power station heat exchanger.

[0019] The present invention extracts the heat exchange start-stop cycle and transient load changes by analyzing the operating data of the thermal power station, constructs a start-stop behavior sequence data model, and converts the original operating information into structured data for time series analysis, providing a data basis for dynamic stress modeling. By performing fluctuation frequency analysis and startup peak statistics on the start-stop behavior sequence data, the start-stop stress characteristic data including frequency, amplitude, and duration are obtained, revealing the transient mechanical and thermal shock law caused by the start-stop operation on the heat exchange pipeline, and providing physical driving quantity for subsequent damage analysis. The start-stop stress characteristic data and the heat exchange optimization pipeline data are subjected to time-series coupling simulation to generate a start-stop path stress distribution diagram, realize path-level stress response modeling, and support stress-path structure integrated dynamic analysis. Based on the start-stop path stress distribution diagram, a path damage accumulation function model is constructed to evaluate the life decay trend of different paths under the start-stop cycle, screen out the path with the smallest damage growth rate, and improve the reliability and fatigue suppression capability of the system start-stop operation. Based on the identification of minimized damage paths, operational strategy adjustment parameters (such as start-stop rhythm, power ramp coefficient, and temperature slope) are inferred. This optimizes intelligent start-stop control in the heat exchanger area of ​​the thermal power station and reduces the probability of fatigue triggering. These operational strategy adjustment parameters are fed back into the three-dimensional model of the thermal power station equipment. Combined with real-time operational data, virtual sensor-driven closed-loop health status monitoring is implemented, along with trend tracking and status assessment of multi-dimensional indicators.

[0020] Preferably, in step S44, optimizing the start-stop control of the heat exchanger area of ​​the thermal power station by using the start-stop path that minimizes cumulative damage includes: Using the start-stop path that minimizes cumulative damage, high-frequency start-stop sections are identified in the heat exchanger area of ​​the thermal power station, thereby obtaining high-frequency start-stop section data; Performing start-stop preheating optimization on the start-stop path that minimizes cumulative damage based on high-frequency start-stop segment data to generate start-stop path preheating optimization data; setting a dynamic control temperature difference threshold based on the start-stop path preheating optimization data, and performing a first start-stop control optimization on the start-stop path that minimizes cumulative damage using the dynamic control temperature difference threshold to generate first start-stop control optimization data; Based on the start-stop path that minimizes cumulative damage, the static path of the heat exchanger area of ​​the thermal power station is screened to obtain a long static start-stop path. Low-flow rate start control optimization is performed on the long static start-stop path to generate the second start-stop control optimization data. The first start-stop control optimization data and the second start-stop control optimization data are integrated into the operation strategy adjustment parameters.

[0021] This invention applies a high-frequency start-stop segment identification algorithm to a start-stop path designed to minimize cumulative damage. This algorithm accurately extracts time periods with abnormally high start-stop frequency, generating high-frequency start-stop segment data for subsequent differentiated control strategy deployment, effectively mitigating the rapid accumulation of thermal fatigue induced by frequent operation. Based on this high-frequency start-stop segment data, preheating control optimization is implemented on the start-stop path, generating start-stop path preheating optimization data. This controls the initial temperature gradient and thermal stress abruptness during the start-stop process, significantly reducing the initial amplitude of stress fluctuations and delaying the spread of structural damage. Based on this start-stop path preheating optimization data, a dynamic temperature difference threshold model is constructed to automatically adjust the permissible start-up temperature difference range within the heat exchanger region, implementing a three-dimensional "temperature difference-path-stress" linkage adjustment mechanism. This generates first-level start-stop control optimization data, enhancing the intelligent control system. A static path screening mechanism is implemented for areas of the start-stop path that have been inactive for extended periods, extracting long static start-stop paths. A low-flow rate start-up control optimization mechanism is then introduced for these paths to control fluid shear force and thermal shock rate during the initial startup phase, generating second-level start-stop control optimization data to mitigate the "cold start stress concentration" effect. By integrating the first start-stop control optimization data and the second start-stop control optimization data, an operation strategy adjustment parameter set is formed that covers high-frequency sections and static paths, supporting multi-path, multi-state, and adaptive scheduling control logic during the start-stop process, and improving the system's safety throughout its life cycle.

[0022] In this specification, a thermal power station equipment health status monitoring system is provided, which is used to execute the above-mentioned thermal power station equipment health status monitoring method. The thermal power station equipment health status monitoring system includes: The simulation modeling module is used to obtain the structural data of the thermal power station equipment; perform topological structure analysis on the thermal power station based on the thermal power station equipment structural data to generate the thermal power station equipment topology data; use the thermal power station equipment topology data to perform virtual simulation modeling on the thermal power station equipment structural data to generate a three-dimensional model of the thermal power station equipment; The heat exchange analysis module is used to extract the heat exchanger area of ​​the three-dimensional model of the thermal power station equipment, analyze the heat exchange pipeline path in the heat exchanger area, and generate heat exchange flow data; based on the heat exchanger area, surface acoustic wave sensor data is collected to obtain heat exchange surface wave group velocity change data; The heat exchange path analysis module is used to calculate the transient thermal stress of the heat exchange surface wave group velocity change data; perform non-steady-state damage accumulation analysis on the transient thermal stress through heat exchange flow data to generate heat exchanger micro-damage accumulation data; use the heat exchanger micro-damage accumulation data to optimize the heat exchange pipeline path and generate heat exchange optimization pipeline data; The health assessment module is used to obtain the operating data of the thermal power station; extract the heat exchange start and stop data of the thermal power station operating data, and optimize the start and stop pipeline control of the heat exchange optimization pipeline data based on the heat exchange start and stop data to obtain the start and stop path that minimizes cumulative damage; adjust the operating strategy based on the start and stop path that minimizes cumulative damage, and feed back the adjustment results to the control system to realize closed-loop monitoring of the health status of the thermal power station heat exchanger and damage risk early warning operations.

[0023] The beneficial effect of the present invention is that the simulation modeling module is used to perform topological analysis and virtual modeling on the structural data of the thermal power station equipment, and a three-dimensional digital twin model with precise physical semantics and spatial layout is generated, which provides a structured basis for subsequent heat exchange analysis and damage simulation, and effectively improves the modeling efficiency and model accuracy. The surface wave group velocity changes in the heat exchanger area are collected in real time by means of a surface acoustic wave sensor, and the heat exchange process is dynamically visualized and reconstructed in combination with the path analysis results, providing an accurate physical thermal response basis and enhancing the real-time and sensitivity of micro-damage identification. The heat exchange flow data and the wave group thermal stress calculation results are coupled and analyzed to construct a non-steady-state damage accumulation model, systematically depicting the dynamic evolution process of micro-damage under the combined action of thermal shock and flow disturbance, and significantly improving the accuracy of early damage identification. Based on the micro-damage accumulation data and flow characteristics, path reconstruction and thermal efficiency optimization are implemented to generate heat exchange optimization pipeline data, realize efficient path screening and low fatigue section matching, effectively suppress fatigue concentration, and improve overall thermal efficiency and operating life. The start-stop behavior characteristics are extracted using operating data and coupled with the thermodynamic performance of the heat exchange path to construct a start-stop path control optimization model, obtaining a start-stop path that minimizes cumulative damage, effectively slowing down the fatigue degradation rate and improving the start-stop robustness. The operating strategy adjustment parameters are fed back to the control system through the health assessment module, forming a closed-loop health monitoring system with micro-damage perception, path optimization and control, and health status discrimination as the core, realizing predictive maintenance and intelligent early warning of the equipment operation status. Therefore, the present invention comprehensively improves the accurate monitoring and risk early warning capabilities of the health status of thermal power station equipment through structural topology modeling, fine heat exchange area monitoring, dynamic damage accumulation analysis and closed-loop operation optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic flow chart of the steps of a method for monitoring the health status of thermal power station equipment; Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG. Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. 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

[0025] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0027] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 3 A method for monitoring the health status of thermal power station equipment comprises the following steps: Step S1: Acquire the thermal power station equipment structure data; perform a topological structure analysis on the thermal power station based on the thermal power station equipment structure data to generate the thermal power station equipment topology data; perform virtual simulation modeling on the thermal power station equipment structure data using the thermal power station equipment topology data to generate a three-dimensional model of the thermal power station equipment; Step S2: Extract the heat exchanger area of ​​the three-dimensional model of the thermal power station equipment, and perform heat exchange pipeline path analysis on the heat exchanger area to generate heat exchange flow data; perform surface acoustic wave sensor data acquisition based on the heat exchanger area to obtain heat exchange surface wave group velocity change data; Step S3: Calculate the transient thermal stress of the heat exchange surface wave group velocity change data; perform non-steady-state damage accumulation analysis on the transient thermal stress through the heat exchange flow data to generate heat exchanger micro-damage accumulation data; use the heat exchanger micro-damage accumulation data to optimize the heat exchange pipeline path to generate heat exchange optimization pipeline data; Step S4: Acquire the thermal power station operation data; extract the heat exchange start and stop data from the thermal power station operation data, and optimize the start and stop pipeline control of the heat exchange optimization pipeline data based on the heat exchange start and stop data to obtain the start and stop path that minimizes the cumulative damage; adjust the operation strategy based on the start and stop path that minimizes the cumulative damage, and feed back the adjustment results to the control system to achieve closed-loop monitoring of the health status of the thermal power station heat exchanger and damage risk warning operations.

[0029] Through topological structure analysis and virtual simulation modeling, this invention generates a highly reliable three-dimensional model of thermal power station equipment, providing a digital foundation for subsequent heat exchange pipeline analysis and sensor data mapping, effectively improving modeling efficiency and accuracy. Using surface acoustic wave sensors to collect surface wave group velocity data from the heat exchanger, and combining it with heat transfer characteristics to perform transient thermal stress and non-steady-state damage accumulation analysis, this system can identify minor structural damage and provide early warning of potential failures caused by thermal stress. Based on this accumulated micro-damage data, the heat exchange pipeline path is dynamically adjusted to generate optimal heat exchange optimization pipeline data, improving heat exchange efficiency while extending equipment life. This system exhibits high adaptability and autonomous optimization capabilities. By deeply mining start-stop data and optimizing pipeline control, the risk of fatigue damage to equipment during frequent starts and stops is effectively reduced, ensuring system operational stability and extending the service life of key components. By integrating simulation models, sensor data, operational data, and control feedback, a closed-loop monitoring system for the health status of heat exchangers is constructed, enabling a shift from "responsive maintenance" to "predictive maintenance" and improving equipment reliability and intelligent management. This method integrates structural modeling, sensor perception, data fusion, path optimization, and control feedback, boasting strong versatility and scalability. It provides technical support for the construction of smart energy systems and promotes the transformation and upgrade of thermal power station equipment from traditional management to intelligent operation and maintenance. Therefore, through structural topology modeling, precise heat exchange area monitoring, dynamic damage accumulation analysis, and closed-loop operation optimization, this invention comprehensively enhances the ability to accurately monitor the health status of thermal power station equipment and provide risk warnings.

[0030] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart showing the steps of a method for monitoring the health status of thermal power station equipment according to the present invention. In this example, the method for monitoring the health status of thermal power station equipment includes the following steps: Step S1: Acquire the thermal power station equipment structure data; perform a topological structure analysis on the thermal power station based on the thermal power station equipment structure data to generate the thermal power station equipment topology data; perform virtual simulation modeling on the thermal power station equipment structure data using the thermal power station equipment topology data to generate a three-dimensional model of the thermal power station equipment; Step S2: Extract the heat exchanger area of ​​the three-dimensional model of the thermal power station equipment, and perform heat exchange pipeline path analysis on the heat exchanger area to generate heat exchange flow data; perform surface acoustic wave sensor data acquisition based on the heat exchanger area to obtain heat exchange surface wave group velocity change data; Step S3: Calculate the transient thermal stress of the heat exchange surface wave group velocity change data; perform non-steady-state damage accumulation analysis on the transient thermal stress through the heat exchange flow data to generate heat exchanger micro-damage accumulation data; use the heat exchanger micro-damage accumulation data to optimize the heat exchange pipeline path to generate heat exchange optimization pipeline data; Step S4: Acquire the thermal power station operation data; extract the heat exchange start and stop data from the thermal power station operation data, and optimize the start and stop pipeline control of the heat exchange optimization pipeline data based on the heat exchange start and stop data to obtain the start and stop path that minimizes the cumulative damage; adjust the operation strategy based on the start and stop path that minimizes the cumulative damage, and feed back the adjustment results to the control system to achieve closed-loop monitoring of the health status of the thermal power station heat exchanger and damage risk warning operations.

[0031] In this embodiment of the present invention, the geometric dimensions, connection relationships, and material parameters of each device in the thermal power station are collected using sensors, CAD drawings, or a BIM system. The number of devices is 100, primarily 20 heat exchangers, with a total pipeline length of approximately 500 meters and a pipe diameter range of 20 to 200 mm. The collected device data is mapped between nodes and edges to form a topological graph. Graph theory algorithms (such as depth-first search (DFS)) are used to identify the connectivity between the heat exchangers and pipelines, generating a topological matrix. A 20×20 adjacency matrix is ​​constructed to represent the direct connections between the heat exchangers. Using this topological data and the device's geometric parameters, a 3D model is created in simulation software (such as ANSYS or COMSOL). The model includes detailed structures such as the heat exchanger shell, heat exchange pipelines, and connecting flanges, with a dimensional accuracy of ±1 mm. The 3D model is exported in a file format (such as STEP or IGES) for subsequent analysis. The main heat exchanger area is identified from the 3D model, and the heat exchanger path area is selected. Use geometric segmentation algorithms (such as regional segmentation based on surface curvature) to accurately locate the heat exchanger tube path of the heat exchanger with an error of ≤2mm. Use path planning algorithms (such as Dijkstra or A* algorithms) to analyze the flow path of the heat exchange medium and the fluid resistance to generate heat exchange flow data, including pipe length, pressure loss, and flow velocity distribution. The longest pipe length is 80 meters, the average flow velocity is 1.5m / s, and the pressure loss is 0.12MPa. Surface acoustic wave sensors (10 in number, with a spacing of approximately 8 meters) are arranged at key points along the heat exchange tube path to collect changes in the group velocity of the pipe wall. The sampling frequency is 100kHz, and the data time resolution is 10ms. The collected data includes a dynamic change curve of the group velocity over time, ranging from 0.5 to 5km / s. Based on the group velocity change data, the transient thermal stress σ(t) is calculated using a thermoelastic mechanics model, using the following formula: ;in, is the elastic modulus (2×10^11Pa), is the coefficient of thermal expansion (12×10^-6 / °C), The instantaneous temperature change is obtained by inverting the group velocity change. The calculated result is the maximum thermal stress peak σ_max≈80MPa, which lasts for 10 seconds. The cumulative value of micro-damage of the heat exchanger is calculated using the Miner damage accumulation method. : ;in is the actual number of cycles, =The number of cycles of material fatigue life, determined based on the thermal stress spectrum. The accumulated microdamage D = 0.035 (less than 1, indicating the equipment has not yet failed). Based on the accumulated microdamage data, the pipeline routing was adjusted to reduce flow in stress-concentrated sections and distribute the heat load. A genetic algorithm was used to optimize pipeline flow rate distribution, with the objective function minimizing accumulated damage. After optimization, pipeline pressure loss was reduced by 10%, and the damage value dropped to D = 0.025. Real-time data such as temperature, pressure, and flow were collected, with particular attention paid to heat exchanger start and stop signals. The sampling period was 1 second, and historical data was stored for 6 months. The number of heat exchanger starts and stops, their duration, and time intervals were counted. The average start and stop cycle was 4 hours, with an average of 12 starts and stops per day. A start and stop path control model was constructed based on the heat exchanger optimization pipeline data and combined with the start and stop data. The objective function was to minimize the accumulated damage of the heat exchanger pipeline, constraining start and stop frequency and thermal efficiency. A dynamic programming algorithm was used to solve the optimal start and stop path. The optimal start and stop path was converted into control instructions and fed back to the PLC or DCS control system. After implementation, heat exchanger life was extended by 10% and unplanned equipment downtime was reduced by 30%. A closed-loop health monitoring system was established, triggering a risk warning if the cumulative micro-damage exceeds 0.05.

[0032] Preferably, step S1 includes the following steps: Step S11: Acquire thermal power station equipment structure data; Step S12: Identify the structural components of the thermal power station equipment structure data to extract equipment unit data; construct an equipment connection relationship diagram based on the equipment unit data to generate an initial thermal power station structure diagram; Step S13: Performing graph structure analysis on the initial structure diagram of the thermal power station, extracting node connection relationships, and generating thermal power station equipment topology data; using the thermal power station equipment topology data, performing spatial correlation modeling on the equipment unit data, and generating structure mapping data; Step S14: Execute virtual simulation modeling operations based on the structural mapping data to generate an initial three-dimensional structural model of the thermal power station equipment; perform component geometry correction and topological closure processing on the initial three-dimensional structural model of the thermal power station equipment to generate a three-dimensional model of the thermal power station equipment.

[0033] In this embodiment of the present invention, on-site laser scanners are used to collect equipment point cloud data, obtaining high-precision spatial coordinates and surface morphology. Design drawings, construction blueprints, and manufacturer CAD models (common formats such as STEP, IGES, and DWG) are acquired. Data from equipment sensors and smart tags is read to obtain equipment identification information, status, and location. Historical maintenance records and equipment specifications are integrated to assist in confirming equipment type and parameters. Multi-source, heterogeneous data is converted into a unified structured format (e.g., point cloud to mesh, CAD file to standard model format). Point cloud data is filtered to remove environmental noise and scanning errors. Scanning blind spots and missing data are filled using interpolation or shape completion techniques. The equipment list is compared to confirm that all equipment has been collected and that data is complete. A structured, standardized raw data set of thermal power station equipment is output. Point cloud clustering algorithms (e.g., DBSCAN) or deep learning-based semantic segmentation models are used to segment the point cloud / mesh data and identify different equipment components. Equipment unit classification (e.g., pump, valve, pipe segment) is achieved by combining part numbers and attribute tags from the CAD model. Outputs a device unit data table containing device ID, spatial location, dimensions, and functional attributes. Based on spatial proximity and design specifications, physical connections between devices (such as pipe interfaces and mechanical connections) are determined. Pipeline flow directions and signal paths are analyzed to generate directed connection edges. Connection validity is verified, eliminating abnormal or indirect connections. Device units are treated as graph nodes, and connections as graph edges, forming a device connection diagram. The structure diagram is visualized and supports querying node and connection attributes. Outputs a device unit data table plus a device connection diagram (initial structure diagram). Calculates metrics such as degree centrality and betweenness centrality for each node to identify key devices and bottleneck nodes. Uses graph traversal algorithms to detect connected components and ensure the integrity of the overall network. Applying loop detection algorithms, locates circular flow paths and optimizes the topology. Generates a topological matrix or adjacency table describing node connectivity. Node attributes (device function, operating status) and edge attributes (connection type, flow direction) are recorded. Topological data is associated with the 3D spatial coordinates of the device units, achieving dual spatial and topological mapping. Evaluates spatial distances, azimuths, and interference zones between devices. Output structural mapping data, which includes comprehensive information on the three-dimensional position and topological connection of the equipment. Output the topological data + structural mapping data of the thermal power station equipment. Import the structural mapping data into a three-dimensional modeling platform (such as Revit, SolidWorks, CATIA). Construct the skeleton structure of the overall three-dimensional model of the thermal power station according to the spatial position and topological connection of the equipment units. Gradually refine the equipment components and add structural details (support frames, interface flanges, etc.). Automatically detect geometric anomalies in the model (such as overlapping surfaces, voids, broken edges) and repair them. Use mesh reconstruction technology to optimize surface quality and improve model smoothness. Correct the model scale deviation to ensure consistency with the actual equipment size. Apply topology checking tools to ensure that the model has no open boundaries and non-manifold geometry.Close fluid channels and pipe interfaces to ensure continuity of the simulated fluid path. Verify the overall model's structural strength and connection stability, and generate 3D model files in standard formats (STL, OBJ, IFC) for subsequent simulation, virtual reality display, and maintenance management. Manage model versions and record modification history and metadata.

[0034] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: performing regional segmentation on the three-dimensional model of the thermal power station equipment to obtain heat exchanger regional structure data; identifying the heat exchange pipe network based on the heat exchanger regional structure data to obtain heat exchange pipe topology data; Step S22: performing path tracing analysis on the heat exchange pipeline topology data, calculating the fluid path length and distribution, and generating heat exchange flow data; Step S23: performing surface acoustic wave sensor layout simulation based on the heat exchanger regional structural data to generate sensor sampling layout data; performing surface acoustic wave acquisition control on the sensor sampling layout data to obtain surface acoustic wave original response data; Step S24: performing group velocity extraction and time drift correction on the original surface acoustic wave response data to generate heat exchange surface wave group velocity change data.

[0035] In this embodiment of the present invention, a 3D model of the thermal power station equipment is input (output from step S14). A 3D image segmentation algorithm based on geometric features and material properties (such as voxel clustering or graph cuts) is used to identify the spatial extent of the heat exchanger. CAD metadata and equipment function labels are combined to assist in confirming the boundaries of the heat exchanger components. Heat exchanger regional structural data is output, including the heat exchanger's geometric shape, spatial location, and component information. Based on this heat exchanger regional structural data, the geometric form of the heat exchange piping (such as pipe diameter, bends, and branches) is detected using point cloud or mesh details. Node and segment information for the heat exchange piping is automatically extracted by combining connection point features and interface shapes. A heat exchange piping topology graph is constructed, with nodes representing pipe connection points and edges representing pipe segments, including flow direction information. The heat exchange piping topology data is output to prepare for subsequent fluid path analysis. Input the heat exchange piping topology data (output from step S21). A graph traversal algorithm (such as depth-first search (DFS) or breadth-first search (BFS)) is used to identify all fluid paths. The fluid path length is calculated for each path, and the lengths of each segment are accumulated. Based on pipe diameters and branch points, simulate fluid flow distribution and pressure distribution. Combined with actual operating parameters (such as flow rate, pressure, and temperature), calculate the fluid residence time and heat exchange efficiency in each path. This generates a heat exchange flow data set containing key indicators such as path length, flow distribution, and fluid residence time. This heat exchange flow data is output to support subsequent performance evaluation and design optimization. Input the heat exchanger's regional structural data (output from step S21). Using the heat exchanger's geometric model and acoustic wave propagation characteristics, simulate the propagation path of surface acoustic waves on the heat exchanger's surface. Based on acoustic wave coverage and sensitivity requirements, design a sensor layout plan, determining the sensor location, number, and spacing. Output sensor sampling layout data, including the spatial coordinates and coverage area of ​​each sensor. Based on this sensor sampling layout data, control the surface acoustic wave sensor acquisition module and initiate the signal acquisition process. Collect raw response signals from the acoustic wave propagation process, including multi-dimensional data such as waveform, time delay, and amplitude. Simultaneously collect environmental parameters (such as temperature and humidity) for calibration reference. Output the raw surface acoustic wave response data to prepare for subsequent signal processing. Input the raw surface acoustic wave response data (output from step S23). Use time-frequency analysis methods (such as wavelet transform and short-time Fourier transform (STFT)) to extract the group velocity characteristics of the acoustic wave signal. Calculate the acoustic wave group velocity variation curve to reflect the surface structure and material state of the heat exchanger. Analyze the time delay drift of environmental parameters and acquisition equipment to establish a time drift model. Apply a correction algorithm (such as dynamic time warping (DTW)) to correct the time drift error in the group velocity curve. Ensure that the extracted group velocity variation data accurately reflects actual physical changes. This creates a high-precision, real-time group velocity variation dataset that reflects the surface wave propagation state of the heat exchanger. The output data is used for heat exchanger status monitoring, fault diagnosis, and health assessment.

[0036] Preferably, step S22 includes the following steps: Step S221: Filter the node connectivity of the heat exchange pipeline topology data, extract the effective heat exchange path segments, and generate path structure network data; perform geometric reconstruction and curvature analysis on the path structure network data, extract the path segment geometric constraint information, and generate heat exchange path geometric feature data; Step S222: performing spatial path expansion on the heat exchange path geometric characteristic data, and performing flow direction vector calculation on the expanded spatial path to generate an initial flow path vector field; Step S223: Measuring the resistance coefficient of the structure within the heat exchanger; weighting the initial flow path vector field by the resistance coefficient of the structure within the heat exchanger to generate an equivalent flow resistance path diagram; performing fluid path length integration and flow velocity dynamic simulation on the equivalent flow resistance path diagram, calculating the path-level fluid transmission delay, and generating flow delay matrix data; Step S224: performing path-level heat exchange efficiency estimation on the flow delay matrix data to generate heat exchange flow data.

[0037] In an embodiment of the present invention, graph theory algorithms (such as depth-first search (DFS) or breadth-first search (BFS)) are used to screen valid connected paths using the topological data of the heat exchange pipeline (typically a graph structure of node-pipeline connections). Isolated points, dead ends, or invalid loops are removed to extract the path segments that actually participate in the heat exchange fluid flow and construct path structure network data. Each path segment in the path structure network is mapped to its spatial coordinates (such as path lines in a 3D point cloud or CAD model). Curvature analysis is performed on the path: the curvature value of each point on the path is calculated to determine the degree of pipeline curvature. Key curvature points are selected using a curvature threshold to generate geometric constraints for the path segment (such as maximum curvature and local curvature distribution), which are used for geometric constraints in subsequent flow simulations. The output "heat exchange path geometric feature data" includes the coordinates of the path segment's start and end nodes, pipe diameter information, curvature parameters, and connection relationships. The three-dimensional path is unfolded into a two-dimensional or computationally convenient spatial coordinate system to facilitate subsequent flow direction analysis. This unfolding method can be "flattened" based on the pipeline's direction, preserving length and connection order. This process can be implemented using geometric projection or path parameterization. Based on the fluid flow direction, a unit flow vector is calculated for each segment along the path, typically a unit vector in the direction of the path tangent. The vector field data structure includes the position vector and the corresponding flow direction unit vector for each sampling point along the path. This generated "initial flow path vector field" serves as the basis for subsequent flow resistance weighting and dynamic simulation. Local resistance coefficients corresponding to different structures within the heat exchanger (such as tube wall roughness, elbows, and joints) are obtained through experimental measurements or literature review. Resistance coefficient data can be in scalar or matrix form, encompassing the characteristics of different path segments. Resistance coefficients are assigned to the corresponding path segments in the initial flow path vector field to form a weighted equivalent flow resistance path map. The equivalent resistance of each path segment is calculated, reflecting the difficulty of fluid passage through that segment. A path length integral is performed on the equivalent flow resistance path map to account for the effect of resistance on fluid velocity. Numerical simulation (such as CFD simulation or a simplified flow velocity dynamic model) is used to calculate the flow velocity variation along the path and obtain the fluid transmission delay. A "flow delay matrix data" is formed, where the rows and columns of the matrix correspond to the path nodes, and the elements represent the path transmission delay. Based on the flow delay matrix and the geometric and physical characteristics of the path, a heat transfer efficiency estimation model is established. The model can refer to the basic principles of heat transfer, such as the relationship between the convective heat transfer coefficient, heat transfer area, temperature difference and fluid residence time. For each path, the heat exchange efficiency of the path is estimated based on the flow delay (reflecting the fluid residence time). The efficiency can be calculated using empirical formulas or numerical simulations, and the path heat exchange efficiency value is output in combination with the path heat transfer characteristics. The heat exchange efficiencies of all paths are summarized to form the overall "heat transfer flow data" to guide pipeline design optimization and performance evaluation.

[0038] Preferably, step S222 includes the following steps: Step S2221: Perform three-dimensional structural denoising and projection on the geometric feature data of the heat exchange path to eliminate high-order micro-curvature interference and generate a path principal axis fitting line group; perform piecewise spline reconstruction and expansion based on the path principal axis fitting line group to convert the complex spatial path into a regularized path segment sequence and generate a spatial expansion path set; Step S2222: performing geometric continuity weight assignment on the spatially expanded path set, calibrating the directional consistency and structural influence coefficient of each micro-segment, and generating a path direction weighting matrix; Step S2223: performing directional flow vector decomposition based on the path direction weighted matrix, extracting the mainstream vector and disturbance vector of the path element unit, and generating a local flow direction distribution map; Step S2224: reconstruct the local flow direction distribution map at the full path scale to generate a unified initial flow path vector field.

[0039] In an embodiment of the present invention, the geometric characteristic data of the heat exchange path (including the point set of the path in three-dimensional space and its curvature information) is input. A spatial filtering algorithm (such as Gaussian filtering and wavelet denoising) is used to eliminate high-order micro-curvature interference from the curvature data and remove noise caused by measurement errors or local microstructures. The path point cloud is projected in the main direction, and principal component analysis (PCA) is used to extract the main axis direction of the path to obtain a vector set of the main axis direction of the path. Based on the main axis direction, the path point set is fitted, and a multi-segment Bezier curve or B-spline curve is used to fit the main axis of the path to generate a fitting line group. During the fitting process, the curve is ensured to be smooth and the fitting error is minimized. The order of the fitting curve is appropriately controlled to avoid overfitting or underfitting. The fitting line group is segmented into several regular path segments, and a segmented spline curve expansion algorithm (such as a uniformly parameterized B-spline) is used to convert the complex spatial path into a regular, continuous sequence of path segments. Each path segment maintains uniform length and curvature to facilitate subsequent flow vector calculations. This generates a spatially unfolded path set, consisting of a sequence of piecewise spline paths and their spatial coordinate data. For each path micro-segment in the spatially unfolded path set, the angle between its tangent direction and that of its adjacent micro-segments is calculated to assess directional consistency. Smaller angles indicate a higher directional consistency weight, while smaller angles indicate a lower weight. Structural influence coefficients are assigned based on path geometric characteristics (such as curvature, segment length, and local curvature complexity). Segments with greater curvature have a relatively larger structural influence coefficient, reflecting their impact on flow disturbances. The directional consistency weight and the structural influence coefficient are weighted together to form a comprehensive weight for each path micro-segment. The weights of all micro-segments are aggregated to construct a path direction weighting matrix, whose elements represent the strength of directional relationships and influence weights between micro-segments. Based on the path direction weighting matrix, the flow direction vector of each path micro-element is decomposed using vector decomposition methods (such as principal component analysis (PCA) or singular value decomposition (SVD)). This decomposition is performed into two components: a mainstream vector (representing the main flow direction of the path) and a disturbance vector (representing local deviations from the flow direction). The mainstream vectors and disturbance vectors of all path elements are spatially mapped to form a local flow distribution map. Each point in the flow distribution map contains vector information that describes the directionality of the fluid motion and the magnitude of the disturbance at that point. The micro-segment vectors on the local flow distribution map are continuously spliced ​​in path order to ensure directional continuity and a smooth transition of the vector field. The vector directions at the splicing points are interpolated to eliminate breakpoints or directional mutations caused by segmentation. Through splicing and reconstruction, a unified initial flow path vector field at the full path scale is formed. This vector field describes the initial motion trend of the fluid on the heat exchange path and serves as the basic data for subsequent flow resistance weighting and simulation.

[0040] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: performing multi-scale thermal inversion on the heat exchange surface wave group velocity change data to generate transient thermal gradient distribution data; performing material thermal response modeling on the transient thermal gradient distribution data to calculate the corresponding transient thermal stress data; Step S32: performing unsteady-state boundary modeling on the heat exchange flow data to generate dynamic boundary condition data for the heat exchange process; performing coupling analysis on the transient thermal stress data and the dynamic boundary condition data, implementing unsteady-state damage accumulation modeling, and generating micro-damage evolution curve data; Step S33: performing regional clustering on the micro-damage evolution curve data, and extracting the damage accumulation threshold value of the clustered area to generate heat exchanger micro-damage accumulation data; Step S34: Based on the cumulative data of heat exchanger micro-damage, a path loss sensitivity analysis is performed on the heat exchange pipeline path, high-risk path segments are identified, and a set of candidate paths for heat exchange pipeline improvement is generated; flow efficiency reconstruction and heat exchange performance evaluation are performed on the candidate paths for heat exchange pipeline improvement to generate heat exchange optimized pipeline data.

[0041] In one embodiment of the present invention, transient thermal gradient distributions are calculated by inputting surface wave group velocity data (with multi-scale spatial and temporal resolution). A heat conduction inversion algorithm (e.g., a finite element or finite difference inverse problem solving method) is then employed to calculate the transient thermal gradient distribution. The inversion process combines the material's thermal diffusion equation and boundary conditions to perform spatial scale decomposition and capture local and macroscopic thermal gradient variations. A thermodynamic response model of the material is established based on its thermophysical parameters (such as thermal expansion coefficient, elastic modulus, and thermal conductivity). Transient thermal gradient data is input to calculate transient thermal stresses caused by temperature gradients. A thermoelastic model (linear or nonlinear elastic) is used to simulate the stress field, generating transient thermal gradient distribution data and corresponding transient thermal stress data. Based on the heat transfer flow data, a dynamic boundary condition model is established, taking into account time-varying boundary characteristics such as temperature, pressure, and flow rate. Time-varying boundary conditions are input into the thermodynamic model to generate dynamic boundary condition data for the heat transfer process. The transient thermal stress data and dynamic boundary condition data are coupled to construct a joint unsteady-state thermodynamic boundary problem. Damage mechanics models (such as continuous damage mechanics (CDM) or fracture mechanics models) are used to analyze the cumulative microdamage of materials under thermal stress. By integrating the damage variable over time and combining it with material fatigue life theory, the damage degree of the material over time is calculated. Microdamage evolution curve data is output to describe the temporal trend of damage. The spatial distribution of the microdamage evolution curve data is clustered (using algorithms such as K-means, DBSCAN, or hierarchical clustering) to identify regions with similar evolution trends. The clustering goal is to divide the damage evolution of different parts of the material into several typical regions. Statistical analysis is performed on the damage curves of each cluster region to extract key damage thresholds (such as critical damage thresholds and failure thresholds). These thresholds are set based on material failure criteria (for example, when the damage variable exceeds a certain value, the microdamage is considered severe). Cumulative microdamage data for the heat exchanger is generated, containing the cumulative damage level and corresponding threshold for each region. The combined microdamage data is then mapped to heat exchanger path segments. Sensitivity analysis methods (such as local sensitivity analysis and the Sobol index) are used to assess the contribution of each path segment to the overall damage impact. Identify high-risk path segments (i.e., pipeline segments with significant damage accumulation and impacting overall performance). Based on this information, design improvement strategies (such as path rerouting, adding supports, and replacing materials), generating a set of candidate paths for heat exchange piping improvements, including multiple optimization solutions. Perform flow simulations (using CFD software or a customized fluid dynamics model) for each candidate path, calculating flow efficiency. Evaluate heat exchange performance metrics (such as thermal efficiency, thermal resistance, and heat transfer capacity), and conduct a comprehensive evaluation based on structural safety. Generate optimized heat exchange piping data, including recommended piping solutions and performance comparisons.

[0042] Preferably, in step S34, reconstructing the flow efficiency and evaluating the heat exchange performance of the heat exchange pipeline improvement candidate path set includes: Finite volume fluid simulation is performed on the candidate path set for heat exchange pipeline improvement to generate path flow velocity distribution data. Based on the path flow velocity distribution data, the turbulent structure of the candidate path set for heat exchange pipeline improvement is identified and pressure drop calculation is performed to generate a flow resistance distribution map. The flow resistance distribution map is combined with the thermal boundary conditions to perform local heat transfer coefficient inversion to generate heat transfer efficiency distribution data. The heat transfer efficiency distribution data is used to perform inter-path thermal performance comparison analysis, screen high-performance path units, and generate a path performance optimization set. The optimal path performance set is combined with micro-damage accumulation data to conduct a structural safety review, eliminate potential fatigue sections, and generate a structural safety optimized path set; Multi-objective thermal-mechanical collaborative optimization calculations are performed on the structural safety optimization path set to comprehensively evaluate thermal efficiency, structural integrity, and flow stability, ultimately generating heat exchange optimization pipeline data.

[0043] In an embodiment of the present invention, flow efficiency reconstruction and heat exchange performance evaluation are performed on a set of candidate heat exchange pipeline improvements. Finite volume method numerical simulation techniques are first used, combined with the geometric model of the candidate heat exchange pipeline improvements and specific fluid inlet boundary conditions (such as flow velocity, pressure, and temperature), to accurately simulate the motion of the fluid within the path. Velocity distribution data for each spatial point within the path is obtained. During the simulation, appropriate turbulence models (such as the k-ε model, k-ω SST model, or large eddy simulation (LES)) are employed to accurately capture the complex turbulent structure within the pipeline. Subsequently, based on the calculated velocity field, the spatial distribution characteristics of the turbulent structure within the path are identified. Simultaneously, the pressure drop for each path segment is calculated based on the local flow state, thereby forming a complete flow resistance distribution map. This flow resistance distribution map is then combined with the thermal boundary conditions of the heat exchange process (including the wall temperature distribution and the heat transfer medium temperature field). Using the local heat transfer coefficient inversion method, the local heat transfer coefficient for each path segment is calculated using the coupled heat conduction and convection equations. This spatial distribution of heat transfer efficiency data is then obtained, thereby quantitatively describing the heat transfer performance of the heat exchange path. Based on the aforementioned heat transfer efficiency distribution data, a systematic inter-path thermal performance comparison analysis was conducted on each path in the candidate path set. Path units with excellent heat transfer performance were screened based on thermal efficiency indicators to form a path performance optimization set. Subsequently, combined with the previously obtained micro-damage accumulation data, a structural safety review was conducted on the path segments in the path performance optimization set, with a focus on eliminating those with potential fatigue failure risks to ensure the structural integrity and safety of the heat exchange pipeline in actual operation, thereby obtaining a structural safety optimized path set. Finally, a multi-objective thermal-mechanical collaborative optimization calculation method was used for this structural safety optimized path set, comprehensively evaluating and weighing the three performance indicators of maximizing thermal efficiency, ensuring structural integrity, and ensuring flow stability. Genetic algorithms, particle swarm optimization, or other advanced multi-objective optimization algorithms were used to collaboratively optimize the path geometry, fluid dynamic characteristics, and structural mechanical properties. Through iterative calculations and multi-dimensional performance indicator feedback, heat exchange optimized pipeline data was ultimately generated to meet the requirements of efficient heat transfer, structural safety and robustness, and stable flow, achieving comprehensive performance improvement and reliable operation of the pipeline.

[0044] Preferably, step S4 includes the following steps: Step S41: Acquire thermal power station operation data; Step S42: extracting the heat exchange start-stop cycle and transient load changes from the thermal power station operation data to obtain start-stop behavior sequence data; performing fluctuation frequency analysis and startup peak statistics on the start-stop behavior sequence data to generate start-stop stress characteristic data; Step S43: performing time-series coupling simulation on the start-stop stress characteristic data and the heat exchange optimization pipeline data, analyzing the stress response distribution of different paths, and generating a start-stop path stress distribution diagram; Step S44: Based on the start-stop path stress distribution diagram, the damage accumulation function of each candidate path is calculated, the path with the minimum damage growth rate is selected, and the start-stop path with the minimum cumulative damage is generated; the start-stop path with the minimum cumulative damage is used to optimize the start-stop control of the heat exchanger area of ​​the thermal power station and generate operation strategy adjustment parameters; Step S45: Input the operation strategy adjustment parameters into the three-dimensional model of the thermal power station equipment to perform closed-loop monitoring of the equipment health status, and perform damage risk threshold judgment on the monitored equipment health status to perform damage risk warning operations for the thermal power station heat exchanger.

[0045] In an embodiment of the present invention, a multidimensional time series thermal power station operation dataset is constructed by collecting operational monitoring data from the thermal power station site. This data includes, but is not limited to, the operating temperature, pressure, flow rate, heat exchange power, start / stop instruction records, and timestamp information of the heat exchanger. Feature extraction is performed on the collected thermal power station operation data to identify the time periods corresponding to the heat exchanger start / stop control instructions, and typical heat exchange start / stop cycles and corresponding load response curves are extracted. Furthermore, a fluctuation frequency analysis is performed on the start / stop behavior sequence using time series analysis to identify the frequency characteristics and periodic patterns of the start / stop behavior. Based on the peak response of the heat exchanger load changes during the start / stop cycle, key parameters such as the temperature sudden change rate and pressure transient rise rate at startup are extracted to generate start / stop stress characteristic data reflecting the stress characteristics caused by the start / stop process of the heat exchanger. Based on the aforementioned start / stop stress characteristic data and the obtained heat exchange optimization pipeline data, a coupled thermal-mechanical time series simulation model is constructed, and the start / stop excitation signals of the heat load are applied to different optimized path segments to conduct path-level transient stress response simulation. Using finite element methods and coupled multiphysics simulation, the stress distribution of each path segment under a specific start-stop cycle is determined. This leads to a stress distribution map for the start-stop path, which describes the time-varying stress concentration areas and dynamic stress amplitude distribution within the path segment. Based on the stress distribution map, a material fatigue model (such as the Miner linear cumulative damage model or a nonlinear fracture mechanics model) is used to calculate the damage accumulation function for each path segment under cyclic start-stop loads. The damage growth rates of all path segments are then compared and analyzed. Based on the principle of minimizing the damage growth rate, the path with the mildest structural response and longest life under the start-stop frequency is selected from multiple candidate paths to determine the start-stop path that minimizes cumulative damage. Subsequently, based on the thermal-mechanical response characteristics of this optimal path, the start-stop logic of the thermal power station heat exchanger is adjusted (e.g., adjusting the heating rate, pressure ramp curve, or start-stop cycle rhythm), forming a set of operational strategy adjustment parameters based on the structural protection mechanism. These operational strategy adjustment parameters are input into the thermal power station's three-dimensional digital twin model and combined with actual monitoring sensor data (such as strain gauges, temperature sensors, and flow meters) to implement real-time closed-loop monitoring of the equipment status. The system uses a health assessment algorithm to determine damage trends and health ratings for the current state of thermal equipment, establishing a time-series mapping relationship between equipment status and structural loads. Furthermore, the system sets a dynamically adjusted damage risk threshold, which, when compared with the monitored status, triggers damage risk warnings for heat exchangers. This provides thermal station operators with visual, quantifiable, and controllable start-up and shutdown control decision support, enabling intelligent operation and maintenance based on structural health awareness.

[0046] Preferably, in step S44, optimizing the start-stop control of the heat exchanger area of ​​the thermal power station by using the start-stop path that minimizes cumulative damage includes: Using the start-stop path that minimizes cumulative damage, high-frequency start-stop sections are identified in the heat exchanger area of ​​the thermal power station, thereby obtaining high-frequency start-stop section data; Performing start-stop preheating optimization on the start-stop path that minimizes cumulative damage based on high-frequency start-stop segment data to generate start-stop path preheating optimization data; setting a dynamic control temperature difference threshold based on the start-stop path preheating optimization data, and performing a first start-stop control optimization on the start-stop path that minimizes cumulative damage using the dynamic control temperature difference threshold to generate first start-stop control optimization data; Based on the start-stop path that minimizes cumulative damage, the static path of the heat exchanger area of ​​the thermal power station is screened to obtain a long static start-stop path. Low-flow rate start control optimization is performed on the long static start-stop path to generate the second start-stop control optimization data. The first start-stop control optimization data and the second start-stop control optimization data are integrated into the operation strategy adjustment parameters.

[0047] In this embodiment of the present invention, a time series analysis of the start-stop behavior experienced during the operation of a thermal power station, based on the start-stop paths obtained by the aforementioned screening to minimize cumulative damage, is performed to identify local sections of the paths frequently affected by start-stop operations. By statistically analyzing the start-stop frequency, duration, and corresponding temperature difference amplitude of the paths within an operating cycle, path regions experiencing frequent thermal excitation are delineated, generating data on high-frequency start-stop segments reflecting the vulnerability of these local regions. Subsequently, a start-stop preheat optimization process is performed on these high-frequency start-stop segments. This process mitigates the temperature surge in the high-frequency paths during the initial startup phase by adjusting parameters such as the temperature rise rate, starting flow rate, and preload power of the heat exchanger system during the start-stop process, reducing the magnitude of transient thermal stress. This process then generates start-stop path preheat optimization data, including a preheat curve, temperature adjustment rate, and operating tact. Based on this preheat optimization data, a dynamic control strategy for the start-stop paths is customized, setting a dynamic temperature difference control threshold. This temperature difference threshold is not a fixed value but is dynamically adjusted based on various factors, such as ambient temperature, historical start-stop records, and system load, to ensure that the transient thermal excitation experienced by the path segments does not exceed the thermal response limit of the material. This dynamic temperature difference threshold is applied to the start-stop control logic to generate the first start-stop control optimization data, which guides the activation conditions and rate control for each start-stop action during actual operation. Next, the start-stop path, designed to minimize cumulative damage, is analyzed for segments with extended periods of inactivity. These segments, known as long static start-stop paths, are identified. These segments are prone to fatigue cracking upon reactivation due to large temperature gradients and uneven internal stress release. Therefore, a low-flow rate start-up control strategy is employed. By limiting the flow rate and pressure fluctuation range during the initial cold start, the heat diffusion process is smoothed, mitigating the thermal-mechanical impact on the path structure. This generates the second start-stop control optimization data. Finally, the two sub-optimization data—the first start-stop control optimization data (dynamic temperature difference control) and the second start-stop control optimization data (low-speed cold start control)—are integrated into a complete set of operational strategy adjustment parameters encompassing the path selection strategy, start-stop timing, startup rate, and temperature control mechanism. This parameter set can be used to configure the automatic control system of the thermal power station, adjust the start-stop strategy to adapt to different seasons, load conditions and path states, and achieve full life cycle optimization control of the start-stop operations of the heat exchanger area, effectively reducing the risk of erosion of the structural integrity of critical path sections caused by frequent start-stops, and extending the service life of the equipment.

[0048] In this specification, a thermal power station equipment health status monitoring system is provided, which is used to execute the above-mentioned thermal power station equipment health status monitoring method. The thermal power station equipment health status monitoring system includes: The simulation modeling module is used to obtain the structural data of the thermal power station equipment; perform topological structure analysis on the thermal power station based on the thermal power station equipment structural data to generate the thermal power station equipment topology data; use the thermal power station equipment topology data to perform virtual simulation modeling on the thermal power station equipment structural data to generate a three-dimensional model of the thermal power station equipment; The heat exchange analysis module is used to extract the heat exchanger area of ​​the three-dimensional model of the thermal power station equipment, analyze the heat exchange pipeline path in the heat exchanger area, and generate heat exchange flow data; based on the heat exchanger area, surface acoustic wave sensor data is collected to obtain heat exchange surface wave group velocity change data; The heat exchange path analysis module is used to calculate the transient thermal stress of the heat exchange surface wave group velocity change data; perform non-steady-state damage accumulation analysis on the transient thermal stress through heat exchange flow data to generate heat exchanger micro-damage accumulation data; use the heat exchanger micro-damage accumulation data to optimize the heat exchange pipeline path and generate heat exchange optimization pipeline data; The health assessment module is used to obtain the operating data of the thermal power station; extract the heat exchange start and stop data of the thermal power station operating data, and optimize the start and stop pipeline control of the heat exchange optimization pipeline data based on the heat exchange start and stop data to obtain the start and stop path that minimizes cumulative damage; adjust the operating strategy based on the start and stop path that minimizes cumulative damage, and feed back the adjustment results to the control system to realize closed-loop monitoring of the health status of the thermal power station heat exchanger and damage risk early warning operations.

[0049] The beneficial effect of the present invention is that the simulation modeling module is used to perform topological analysis and virtual modeling on the structural data of the thermal power station equipment, and a three-dimensional digital twin model with precise physical semantics and spatial layout is generated, which provides a structured basis for subsequent heat exchange analysis and damage simulation, and effectively improves the modeling efficiency and model accuracy. The surface wave group velocity changes in the heat exchanger area are collected in real time by means of a surface acoustic wave sensor, and the heat exchange process is dynamically visualized and reconstructed in combination with the path analysis results, providing an accurate physical thermal response basis and enhancing the real-time and sensitivity of micro-damage identification. The heat exchange flow data and the wave group thermal stress calculation results are coupled and analyzed to construct a non-steady-state damage accumulation model, systematically depicting the dynamic evolution process of micro-damage under the combined action of thermal shock and flow disturbance, and significantly improving the accuracy of early damage identification. Based on the micro-damage accumulation data and flow characteristics, path reconstruction and thermal efficiency optimization are implemented to generate heat exchange optimization pipeline data, realize efficient path screening and low fatigue section matching, effectively suppress fatigue concentration, and improve overall thermal efficiency and operating life. The start-stop behavior characteristics are extracted using operating data and coupled with the thermodynamic performance of the heat exchange path to construct a start-stop path control optimization model, obtaining a start-stop path that minimizes cumulative damage, effectively slowing down the fatigue degradation rate and improving the start-stop robustness. The operating strategy adjustment parameters are fed back to the control system through the health assessment module, forming a closed-loop health monitoring system with micro-damage perception, path optimization and control, and health status discrimination as the core, realizing predictive maintenance and intelligent early warning of the equipment operation status. Therefore, the present invention comprehensively improves the accurate monitoring and risk early warning capabilities of the health status of thermal power station equipment through structural topology modeling, fine heat exchange area monitoring, dynamic damage accumulation analysis and closed-loop operation optimization.

[0050] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0051] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring the health status of thermal power station equipment, characterized in that: The following steps are involved: Step S1: Obtaining thermal power station equipment structure data; Perform topological structure analysis on the thermal power station based on the thermal power station equipment structure data to generate thermal power station equipment topology data; perform virtual simulation modeling on the thermal power station equipment structure data using the thermal power station equipment topology data to generate a three-dimensional model of the thermal power station equipment; Step S2: Extract the heat exchanger area of ​​the three-dimensional model of the thermal power station equipment, and perform heat exchange pipeline path analysis on the heat exchanger area to generate heat exchange flow data; perform surface acoustic wave sensor data acquisition based on the heat exchanger area to obtain heat exchange surface wave group velocity change data; Step S3: Calculate the transient thermal stress of the heat exchange surface wave group velocity change data; perform non-steady-state damage accumulation analysis on the transient thermal stress through the heat exchange flow data to generate heat exchanger micro-damage accumulation data; use the heat exchanger micro-damage accumulation data to optimize the heat exchange pipeline path to generate heat exchange optimization pipeline data; Step S4: Acquire the thermal power station operation data; extract the heat exchange start and stop data from the thermal power station operation data, and optimize the start and stop pipeline control of the heat exchange optimization pipeline data based on the heat exchange start and stop data to obtain the start and stop path that minimizes the cumulative damage; adjust the operation strategy based on the start and stop path that minimizes the cumulative damage, and feed back the adjustment results to the control system to achieve closed-loop monitoring of the health status of the thermal power station heat exchanger and damage risk warning operations.

2. The method for monitoring the health status of thermal power station equipment according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire thermal power station equipment structure data; Step S12: Identify the structural components of the thermal power station equipment structure data to extract equipment unit data; construct an equipment connection relationship diagram based on the equipment unit data to generate an initial structure diagram of the thermal power station; Step S13: Performing graph structure analysis on the initial structure diagram of the thermal power station, extracting node connection relationships, and generating thermal power station equipment topology data; using the thermal power station equipment topology data, performing spatial correlation modeling on the equipment unit data, and generating structure mapping data; Step S14: Execute virtual simulation modeling operations based on the structural mapping data to generate an initial three-dimensional structural model of the thermal power station equipment; perform component geometry correction and topological closure processing on the initial three-dimensional structural model of the thermal power station equipment to generate a three-dimensional model of the thermal power station equipment.

3. The method for monitoring the health status of thermal power station equipment according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing regional segmentation on the three-dimensional model of the thermal power station equipment to obtain heat exchanger regional structure data; identifying the heat exchange pipe network based on the heat exchanger regional structure data to obtain heat exchange pipe topology data; Step S22: performing path tracing analysis on the heat exchange pipeline topology data, calculating the fluid path length and distribution, and generating heat exchange flow data; Step S23: performing surface acoustic wave sensor layout simulation based on the heat exchanger regional structural data to generate sensor sampling layout data; performing surface acoustic wave acquisition control on the sensor sampling layout data to obtain surface acoustic wave original response data; Step S24: performing group velocity extraction and time drift correction on the original surface acoustic wave response data to generate heat exchange surface wave group velocity change data.

4. The method for monitoring the health status of thermal power station equipment according to claim 3, characterized in that: Step S22 includes the following steps: Step S221: Filter the node connectivity of the heat exchange pipeline topology data, extract the effective heat exchange path segments, and generate path structure network data; perform geometric reconstruction and curvature analysis on the path structure network data, extract the path segment geometric constraint information, and generate heat exchange path geometric feature data; Step S222: performing spatial path expansion on the heat exchange path geometric characteristic data, and performing flow direction vector calculation on the expanded spatial path to generate an initial flow path vector field; Step S223: Measuring the resistance coefficient of the structure within the heat exchanger; weighting the initial flow path vector field by the resistance coefficient of the structure within the heat exchanger to generate an equivalent flow resistance path diagram; performing fluid path length integration and flow velocity dynamic simulation on the equivalent flow resistance path diagram, calculating the path-level fluid transmission delay, and generating flow delay matrix data; Step S224: performing path-level heat exchange efficiency estimation on the flow delay matrix data to generate heat exchange flow data.

5. The method for monitoring the health status of thermal power station equipment according to claim 4, characterized in that: Step S222 includes the following steps: Step S2221: Perform three-dimensional structural denoising and projection on the geometric feature data of the heat exchange path to eliminate high-order micro-curvature interference and generate a path principal axis fitting line group; perform piecewise spline reconstruction and expansion based on the path principal axis fitting line group to convert the complex spatial path into a regularized path segment sequence and generate a spatial expansion path set; Step S2222: performing geometric continuity weight assignment on the spatially expanded path set, calibrating the directional consistency and structural influence coefficient of each micro-segment, and generating a path direction weighting matrix; Step S2223: performing directional flow vector decomposition based on the path direction weighted matrix, extracting the mainstream vector and disturbance vector of the path element unit, and generating a local flow direction distribution map; Step S2224: reconstruct the local flow direction distribution map at the full path scale to generate a unified initial flow path vector field.

6. The method for monitoring the health status of thermal power station equipment according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing multi-scale thermal inversion on the heat exchange surface wave group velocity change data to generate transient thermal gradient distribution data; performing material thermal response modeling on the transient thermal gradient distribution data to calculate the corresponding transient thermal stress data; Step S32: performing unsteady-state boundary modeling on the heat exchange flow data to generate dynamic boundary condition data for the heat exchange process; performing coupling analysis on the transient thermal stress data and the dynamic boundary condition data, implementing unsteady-state damage accumulation modeling, and generating micro-damage evolution curve data; Step S33: performing regional clustering on the micro-damage evolution curve data, and extracting the damage accumulation threshold value of the clustered area to generate heat exchanger micro-damage accumulation data; Step S34: Based on the cumulative data of heat exchanger micro-damage, a path loss sensitivity analysis is performed on the heat exchange pipeline path, high-risk path segments are identified, and a set of candidate paths for heat exchange pipeline improvement is generated; flow efficiency reconstruction and heat exchange performance evaluation are performed on the candidate paths for heat exchange pipeline improvement to generate heat exchange optimized pipeline data.

7. The method for monitoring the health status of thermal power station equipment according to claim 6, characterized in that: In step S34, the flow efficiency reconstruction and heat exchange performance evaluation of the heat exchange pipeline improvement candidate path set are performed, including: Finite volume fluid simulation is performed on the candidate path set for heat exchange pipeline improvement to generate path flow velocity distribution data. Based on the path flow velocity distribution data, the turbulent structure of the candidate path set for heat exchange pipeline improvement is identified and pressure drop calculation is performed to generate a flow resistance distribution map. The flow resistance distribution map is combined with the thermal boundary conditions to perform local heat transfer coefficient inversion to generate heat transfer efficiency distribution data. The heat transfer efficiency distribution data is used to perform inter-path thermal performance comparison analysis, screen high-performance path units, and generate a path performance optimization set. The optimal path performance set is combined with micro-damage accumulation data to conduct a structural safety review, eliminate potential fatigue sections, and generate a structural safety optimized path set; Multi-objective thermal-mechanical collaborative optimization calculations are performed on the structural safety optimization path set to comprehensively evaluate thermal efficiency, structural integrity, and flow stability, ultimately generating heat exchange optimization pipeline data.

8. The method for monitoring the health status of thermal power station equipment according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Acquire thermal power station operation data; Step S42: extracting the heat exchange start-stop cycle and transient load changes from the thermal power station operation data to obtain start-stop behavior sequence data; performing fluctuation frequency analysis and startup peak statistics on the start-stop behavior sequence data to generate start-stop stress characteristic data; Step S43: performing time-series coupling simulation on the start-stop stress characteristic data and the heat exchange optimization pipeline data, analyzing the stress response distribution of different paths, and generating a start-stop path stress distribution diagram; Step S44: Based on the start-stop path stress distribution diagram, the damage accumulation function of each candidate path is calculated, the path with the minimum damage growth rate is selected, and the start-stop path with the minimum cumulative damage is generated; the start-stop path with the minimum cumulative damage is used to optimize the start-stop control of the heat exchanger area of ​​the thermal power station and generate operation strategy adjustment parameters; Step S45: Input the operation strategy adjustment parameters into the three-dimensional model of the thermal power station equipment to perform closed-loop monitoring of the equipment health status, and perform damage risk threshold judgment on the monitored equipment health status to perform damage risk warning operations for the thermal power station heat exchanger.

9. The method for monitoring the health status of thermal power station equipment according to claim 8, characterized in that: In step S44, optimizing the start-stop control of the heat exchanger area of ​​the thermal power station by using the start-stop path that minimizes the cumulative damage includes: Using the start-stop path that minimizes cumulative damage, high-frequency start-stop sections are identified in the heat exchanger area of ​​the thermal power station, thereby obtaining high-frequency start-stop section data; Performing start-stop preheating optimization on the start-stop path that minimizes cumulative damage based on high-frequency start-stop segment data to generate start-stop path preheating optimization data; setting a dynamic control temperature difference threshold based on the start-stop path preheating optimization data, and performing a first start-stop control optimization on the start-stop path that minimizes cumulative damage using the dynamic control temperature difference threshold to generate first start-stop control optimization data; Based on the start-stop path that minimizes cumulative damage, the static path of the heat exchanger area of ​​the thermal power station is screened to obtain a long static start-stop path. Low-flow rate start control optimization is performed on the long static start-stop path to generate the second start-stop control optimization data. The first start-stop control optimization data and the second start-stop control optimization data are integrated into the operation strategy adjustment parameters.

10. A thermal power station equipment health status monitoring system, characterized in that: For executing the method for monitoring the health status of thermal power station equipment according to claim 1, the thermal power station equipment health status monitoring system comprises: The simulation modeling module is used to obtain the structural data of the thermal power station equipment; perform topological structure analysis on the thermal power station based on the thermal power station equipment structural data to generate the thermal power station equipment topology data; use the thermal power station equipment topology data to perform virtual simulation modeling on the thermal power station equipment structural data to generate a three-dimensional model of the thermal power station equipment; The heat exchange analysis module is used to extract the heat exchanger area of ​​the three-dimensional model of the thermal power station equipment, analyze the heat exchange pipeline path in the heat exchanger area, and generate heat exchange flow data; based on the heat exchanger area, surface acoustic wave sensor data is collected to obtain heat exchange surface wave group velocity change data; The heat exchange path analysis module is used to calculate the transient thermal stress of the heat exchange surface wave group velocity change data; perform non-steady-state damage accumulation analysis on the transient thermal stress through heat exchange flow data to generate heat exchanger micro-damage accumulation data; use the heat exchanger micro-damage accumulation data to optimize the heat exchange pipeline path and generate heat exchange optimization pipeline data; The health assessment module is used to obtain the operating data of the thermal power station; extract the heat exchange start and stop data of the thermal power station operating data, and optimize the start and stop pipeline control of the heat exchange optimization pipeline data based on the heat exchange start and stop data to obtain the start and stop path that minimizes cumulative damage; adjust the operating strategy based on the start and stop path that minimizes cumulative damage, and feed back the adjustment results to the control system to realize closed-loop monitoring of the health status of the thermal power station heat exchanger and damage risk early warning operations.

Images