Construction method and system of power plant equipment health assessment model

Abstract

The invention relates to the technical field of equipment health assessment, in particular to a power plant equipment health assessment model construction method and system. The method comprises the following steps: acquiring station information data of power plant equipment; site equipment data transmission channel configuration is carried out on the power plant equipment site information data, and a site equipment data transmission channel is generated; carrying out information integration on the power plant equipment station information data by utilizing the station equipment data transmission channel to generate a power plant equipment operation data integration platform; performing power plant equipment operation monitoring on the power plant equipment operation data integration platform to obtain power plant equipment operation monitoring data; and performing equipment multi-working-condition trend fluctuation calculation on the power plant equipment operation monitoring data to obtain equipment working condition trend fluctuation data. Through data integration, refined working condition analysis, unsteady state abnormal state transition analysis and dynamic loss assessment, the precision of the power plant equipment health assessment model is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment health assessment, and in particular to a method and system for constructing a power plant equipment health assessment model. Background Art

[0002] At first, the health assessment of power plant equipment relied on experience and regular manual inspections, which had the problems of poor timeliness, low accuracy and failure to warn of potential faults. With the development of sensor technology, Internet of Things technology and data acquisition systems, real-time monitoring of power plant equipment has become possible. By installing sensors, the operating data of the equipment (such as temperature, pressure, vibration, etc.) can be collected in real time to provide basic data for health assessment. The rapid development of machine learning and artificial intelligence technology has provided new solutions for the health assessment of power plant equipment. Data-based health assessment models have gradually shifted from traditional statistical methods (such as fault tree analysis, Bayesian networks, etc.) to more intelligent algorithm models, such as deep learning, support vector machines (SVM) and decision trees, which can predict the health status of equipment and diagnose faults through historical operating data, sensor data and fault cases. However, the current traditional assessment methods fail to make full use of the changing trends of equipment under different operating conditions for accurate analysis, and ignore the abnormal state of equipment during non-steady-state operation, which leads to low accuracy of the health assessment model of power plant equipment. Summary of the invention

[0003] Based on this, it is necessary to provide a method and system for constructing a power plant equipment health assessment model to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for constructing a power plant equipment health assessment model is provided, the method comprising the following steps:

[0005] Step S1: Acquire power plant equipment site information data; configure the site equipment data transmission channel for the power plant equipment site information data to generate the site equipment data transmission channel; integrate the power plant equipment site information data using the site equipment data transmission channel to generate a power plant equipment operation data integration platform;

[0006] Step S2: monitoring the operation of power plant equipment on the power plant equipment operation data integration platform, thereby obtaining the power plant equipment operation monitoring data; performing equipment multi-condition trend fluctuation calculation on the power plant equipment operation monitoring data, thereby obtaining the equipment condition trend fluctuation data; dividing the power plant equipment operation monitoring data into equipment operation modes according to the equipment condition trend fluctuation data, thereby generating the equipment steady-state operation mode and the equipment non-steady-state operation mode; performing equipment abnormal state transition analysis based on the equipment non-steady-state operation mode, thereby generating the power plant equipment non-steady-state abnormal state transition probability data;

[0007] Step S3: Acquire rated life data of power plant equipment; perform equipment loss analysis on the rated life data of power plant equipment based on the steady-state operation mode of the equipment to generate steady-state operation mode loss data of power plant equipment; construct a health assessment model based on the non-steady-state abnormal state transition probability data of power plant equipment and the steady-state operation mode loss data of power plant equipment to generate a health assessment model for power plant equipment;

[0008] Step S4: Import the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment into the power plant equipment health assessment model for comprehensive health assessment, and generate a power plant equipment health assessment report; construct equipment repair decisions based on the power plant equipment health assessment report to perform power plant equipment health operations.

[0009] The present invention ensures that the operation data of power plant equipment can be seamlessly transmitted and integrated by configuring the site equipment data transmission channel, eliminates the data island phenomenon, and realizes the real-time sharing of equipment information, which provides a unified data platform for subsequent monitoring, analysis and evaluation, ensures the accuracy, completeness and timeliness of data, and thus improves the reliability of health assessment. Through multi-condition trend fluctuation calculation, the operation fluctuation of the equipment under different working conditions can be fully captured, and then the steady-state and non-steady-state operation modes of the equipment can be accurately divided. This analysis helps to identify abnormal changes or hidden faults of the equipment, making the health assessment more detailed and accurate. At the same time, through the abnormal state transition analysis based on the non-steady-state operation mode, the potential risks of the equipment can be revealed, the occurrence of faults can be warned in advance, and the safety and reliability of the equipment can be improved. The loss analysis based on the steady-state operation mode of the equipment provides the loss data generated during the operation of the equipment, which helps to predict the wear of the equipment in long-term operation. Combined with the non-steady-state abnormal state transition probability data, the health status of the equipment can be comprehensively evaluated, not only based on the static rated life, but also dynamically considering the actual performance of the equipment under different working conditions, thereby providing an accurate basis for the maintenance and replacement decision of the equipment, avoiding the economic losses caused by excessive maintenance or delayed maintenance. By combining the data of steady-state and non-steady-state operating modes, a comprehensive equipment health assessment report is generated, which not only provides the current health status of the equipment, but also predicts the future failure risks. This comprehensive assessment helps to optimize maintenance strategies, formulate more targeted repair decisions, reduce unnecessary downtime, and improve the operating efficiency of power plants. In addition, the equipment repair decision-making based on the health assessment report can formulate maintenance priorities according to the specific conditions of the equipment, thereby optimizing resource allocation, reducing maintenance costs, and extending the service life of the equipment. Therefore, the present invention improves the accuracy of the power plant equipment health assessment model through data integration, refined operating condition analysis, non-steady-state abnormal state transfer analysis, and dynamic loss evaluation.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire power plant equipment site information data;

[0012] Step S12: performing data preprocessing on the power plant equipment site information data to generate standard power plant equipment site information data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0013] Step S13: configuring a site equipment data transmission channel for the standard power plant equipment site information data to generate a site equipment data transmission channel;

[0014] Step S14: Use the site equipment data transmission channel to deploy the edge perception computing gateway for the standard power plant equipment site information data to generate edge perception computing gateway deployment data; integrate the standard power plant equipment site information data based on the edge perception computing gateway deployment data to generate a power plant equipment operation data integration platform.

[0015] The present invention ensures the accuracy and consistency of power plant equipment information through data preprocessing and standardization, which provides a reliable basis for subsequent analysis and prediction, and reduces misjudgments and errors caused by data quality problems. By accurately configuring the transmission channel of site equipment data, the stability and speed of data transmission are optimized, which ensures that the power plant equipment data can be transmitted to the central processing system or edge computing node in real time, providing support for rapid response and decision-making. The deployment of the edge perception computing gateway can directly process part of the data on the power plant site, reduce the burden of data transmission, and improve the real-time response capability of the system. Through preliminary data analysis on site, delays can be reduced and equipment anomalies can be responded to more quickly. Through the construction of an information integration platform, data from different power plant equipment is centrally managed and analyzed, and comprehensive monitoring of equipment status is achieved, which helps to discover potential faults and anomalies, improve the operating efficiency of equipment, and reduce downtime. The combination of the integrated platform and the edge computing gateway helps to build an intelligent and automated equipment monitoring system that can automatically detect anomalies and respond quickly, which not only improves the equipment management efficiency of the power plant, but also enhances the overall safety and reliability. Through the integrated data platform, the system can provide power plant managers with real-time equipment operating status, and issue early warnings by analyzing historical data, equipment trends, etc., to assist managers in making scientific decisions.

[0016] Preferably, the method for constructing a power plant equipment health assessment model includes:

[0017] Based on the edge perception computing gateway deployment data, the standard power plant equipment site information data is uploaded to the edge perception computing gateway for data spatiotemporal alignment to generate power plant equipment site spatiotemporal alignment data;

[0018] Perform data characteristic analysis on the spatiotemporal alignment data of power plant equipment sites to generate data characteristics of power plant equipment sites; perform weighted fusion of associated data on the spatiotemporal alignment data of power plant equipment sites according to the data characteristics of power plant equipment sites to generate associated fusion data of power plant equipment sites;

[0019] The associated integrated data of power plant equipment sites are connected to the cloud platform to generate a power plant equipment operation data integration platform.

[0020] The present invention enables the equipment data to be quickly uploaded and preliminarily processed on site through the deployment of edge perception computing gateway, reduces data transmission delay, and can obtain the equipment health status in real time, providing timely decision support for managers. Data characteristic analysis and weighted fusion steps help to accurately evaluate the health status of the equipment, and improve the accuracy and reliability of health assessment by fusing different types of data. By establishing benchmarks and prediction models, it is possible to timely discover health changes of equipment and warn potential equipment failures or degradation trends in advance. The combination of weighted fusion and cloud platform helps to comprehensively analyze various performance data of the equipment, thereby providing multi-dimensional support for equipment health assessment and ensuring the comprehensiveness and accuracy of the assessment results. Based on data analysis of edge computing and cloud platform, power plants can quickly detect equipment anomalies and intervene in time. This intelligent monitoring and early warning mechanism can effectively reduce equipment failure rate, reduce unexpected downtime, and improve the operating efficiency of power plants. Through real-time monitoring and health assessment, power plants can optimize maintenance plans according to the health status of equipment and implement accurate preventive maintenance, which can not only extend the service life of equipment, but also effectively reduce unnecessary maintenance costs and downtime.

[0021] Preferably, step S2 comprises the following steps:

[0022] Step S21: monitoring the operation of power plant equipment on the power plant equipment operation data integration platform, thereby obtaining the power plant equipment operation monitoring data; performing multi-dimensional graph conversion on the power plant equipment operation monitoring data, and generating a multi-dimensional graph of the power plant equipment operation;

[0023] Step S22: performing comparative analysis of equipment multi-operating condition related trends on the power plant equipment operation monitoring data according to the multi-dimensional graph of power plant equipment operation, and generating equipment multi-operating condition trend comparative analysis data;

[0024] Step S23: performing trend fluctuation calculation on the equipment multi-operating condition trend comparison analysis data to obtain equipment operating condition trend fluctuation data; dividing the power plant equipment operation monitoring data into equipment operation modes according to the equipment operating condition trend fluctuation data to generate equipment steady-state operation mode and equipment non-steady-state operation mode;

[0025] Step S24: Based on the non-steady-state operation mode of the equipment, the multi-dimensional graph of the power plant equipment operation is monitored and early-warning data is screened to obtain non-steady-state early-warning data of the power plant equipment; abnormal state transfer analysis is performed on the non-steady-state early-warning data of the power plant equipment to generate non-steady-state abnormal state transfer probability data of the power plant equipment.

[0026] Through multi-dimensional graphs and trend fluctuation analysis, the present invention enables power plants to understand the operating status of equipment in real time, discover potential faults in time, and make early warnings. This process not only improves the early identification capability of faults, but also prevents large-scale faults of equipment during operation, and reduces sudden downtime and maintenance costs. The comparative analysis of multi-operating condition trends of equipment provides important support for the operation optimization of equipment. It can reasonably schedule equipment operation and load distribution according to the performance of equipment under different operating conditions, thereby extending the service life of equipment and improving its operating efficiency. Through the division of non-steady-state operation modes of equipment and abnormal state transition analysis, power plants can deeply understand the health status of equipment and discover equipment abnormalities in time. Abnormal state transition probability data helps managers scientifically predict problems with equipment, make adjustments and maintenance in time, and reduce the risk of equipment failure and downtime. Through early warning, accurate fault detection and intelligent state transition analysis, power plants can optimize maintenance plans, reduce excessive maintenance and repair costs, and improve the operating safety of equipment. Comprehensive monitoring, data analysis and intelligent early warning of equipment make power plant management more refined, avoid human errors and the inefficiency of traditional maintenance methods, thereby improving overall operational efficiency. By optimizing operating modes and adjusting equipment loads, power plants can maximize the use of existing equipment resources and improve production efficiency.

[0027] Preferably, performing multi-dimensional graph conversion on the power plant equipment operation monitoring data includes:

[0028] Perform power plant equipment operation signal conversion on power plant equipment operation monitoring data to generate power plant equipment operation signals; perform waveform conversion on power plant equipment operation signals to generate power plant equipment operation signal waveforms; perform time domain analysis on power plant equipment operation signal waveforms to generate power plant equipment time domain signal waveforms;

[0029] Perform order ratio analysis on the time domain signal waveform of power plant equipment to generate an order ratio diagram of power plant equipment;

[0030] Perform signal waveform extraction on the time domain signal waveform of power plant equipment to obtain the time domain signal waveform curve of power plant equipment; perform FFT transformation on the time domain signal waveform curve of power plant equipment to generate the frequency domain waveform curve of power plant equipment; perform power spectrum analysis on the frequency domain waveform curve of power plant equipment to generate the power spectrum diagram of power plant equipment;

[0031] Extract equipment influencing parameters from the power spectrum of power plant equipment to obtain power influencing parameters of power plant equipment; perform waterfall chart analysis on the power spectrum of power plant equipment based on the power influencing parameters of power plant equipment to generate a waterfall chart of power plant equipment;

[0032] The time domain signal waveform diagram of power plant equipment, the order ratio diagram of power plant equipment, the power spectrum diagram of power plant equipment and the waterfall diagram of power plant equipment are integrated to generate a multi-dimensional diagram of the power plant equipment operation.

[0033] The present invention can perform fault diagnosis on equipment from multiple angles by comprehensively analyzing data of different dimensions such as time domain, frequency domain and power spectrum. For example, the fluctuation of equipment is identified by time domain signal analysis, and potential mechanical failure or electrical problems are found by frequency domain analysis, and finally the problems in long-term operation of equipment are predicted by waterfall chart analysis. Through the integration of multi-dimensional graphs, power plants can comprehensively evaluate equipment performance, including key indicators such as vibration, load, and energy distribution, which provides an accurate basis for long-term health management, performance optimization and load scheduling of equipment. Frequency domain and power spectrum analysis of power plant equipment can reveal early signs of failure such as frequency anomalies and mechanical wear, thereby providing data support for equipment maintenance decisions. Through waterfall chart analysis, potential problems of equipment under different loads can be discovered in advance, troubleshooting or maintenance can be carried out in advance, and the risk of sudden failure can be reduced. Through the integration of graphs, power plant managers can obtain a clear equipment health status diagram, which is convenient for quick decision-making. The graph can not only reflect the current state, but also predict the possibility of future failures through the analysis of historical data, making the operation of the power plant more intelligent and scientific. Based on the accurate fault diagnosis and performance analysis of multi-dimensional maps, power plants can formulate more reasonable maintenance strategies to avoid excessive maintenance and misdiagnosis. By optimizing maintenance plans, reducing equipment downtime, improving equipment operating efficiency, and ultimately reducing maintenance costs and production interruption losses.

[0034] Preferably, dividing the equipment operation mode of the power plant equipment operation monitoring data according to the equipment operating condition trend fluctuation data includes:

[0035] Based on a preset time range, the equipment operating condition trend fluctuation data is segmented into adjacent fluctuation curve segments to obtain a first equipment operating condition trend fluctuation curve segment and a second equipment operating condition trend fluctuation curve segment; trend fluctuation peak values ​​are calculated for the first equipment operating condition trend fluctuation curve segment and the second equipment operating condition trend fluctuation curve segment to obtain a first fluctuation curve peak value and a second fluctuation curve peak value;

[0036] Calculate the frequency domain signal ratio of the first fluctuation curve peak value and the second fluctuation curve peak value to obtain the first fluctuation curve frequency domain signal ratio data and the second fluctuation curve frequency domain signal ratio data, wherein the frequency domain signal includes a low-frequency signal and a high-frequency signal; perform frequency characteristic analysis based on the first fluctuation curve frequency domain signal ratio data and the first fluctuation curve peak value to generate first frequency fluctuation characteristic data; perform frequency characteristic analysis based on the second fluctuation curve frequency domain signal ratio data and the second fluctuation curve peak value to generate second frequency fluctuation characteristic data;

[0037] The first frequency fluctuation characteristic data and the second frequency fluctuation characteristic data are calculated for similarity to obtain frequency fluctuation characteristic similarity data; the frequency fluctuation characteristic similarity data is compared with a preset standard similarity threshold; when the frequency fluctuation characteristic similarity data is greater than or equal to the preset standard similarity threshold, the power plant equipment corresponding to the equipment operating condition trend fluctuation data is marked as a steady-state operation mode; when the frequency fluctuation characteristic similarity data is less than the preset standard similarity threshold, the power plant equipment corresponding to the equipment operating condition trend fluctuation data is marked as a non-steady-state operation mode.

[0038] The present invention can accurately capture the slight changes in the operation of the equipment by segmenting the fluctuation curve segments, calculating the fluctuation peak value and the frequency domain signal ratio. This meticulous trend analysis helps to accurately identify the operating status of the equipment. The similarity calculation based on the frequency characteristic analysis can effectively distinguish whether the equipment is in a steady state or a non-steady state mode. The steady state mode indicates that the equipment is running stably, while the non-steady state mode indicates that the equipment has potential failures or abnormalities. By comparing the frequency fluctuation characteristic similarity data and the standard similarity threshold, the system can timely mark the equipment with abnormal operation and issue a warning, thereby helping the operator to take measures in advance to prevent the occurrence of dangerous events such as equipment failure or fire. Combined with the real-time data of equipment operation, intelligent decision support can be provided for power plant management. After identifying the non-steady state operation mode, the operator can perform targeted maintenance or adjustment to optimize the equipment operation efficiency. By timely monitoring the operating status of the equipment and making accurate operation mode divisions, sudden failures caused by unclear equipment operation status are avoided, and the long-term reliability and stability of power plant equipment are improved.

[0039] Preferably, performing abnormal state transition analysis on non-steady-state warning data of power plant equipment includes:

[0040] Extract warning parameters from the non-steady-state warning data of power plant equipment to obtain non-steady-state warning parameters of power plant equipment; confirm warning timestamps for non-steady-state warning parameters of power plant equipment to obtain non-steady-state warning timestamps of power plant equipment;

[0041] Dynamically screen the warning parameters of the non-steady-state warning parameters of the power plant equipment with adjacent timestamps through the non-steady-state warning timestamps of the power plant equipment to obtain warning correlation parameters; use the warning correlation parameters to perform abnormal state correlation analysis on the non-steady-state warning parameters of the power plant equipment to generate non-steady-state abnormal state correlation data of the power plant equipment;

[0042] The Markov chain is constructed for the non-steady-state abnormal state correlation data of the power plant equipment to generate the power plant equipment state transition diagram; the edge distance of the power plant equipment state transition diagram is calculated to generate the non-steady-state abnormal state transition probability data of the power plant equipment.

[0043] The present invention can extract key warning parameters closely related to equipment failure from a large amount of monitoring data by performing parameter extraction and dynamic screening on non-steady-state warning data of power plant equipment. This screening can reduce redundant information and improve the accuracy of analysis. By confirming the warning timestamp and dynamically screening the warning parameters, the abnormal changes of the equipment within a certain period of time can be clearly identified, and the relevant parameters can be timely associated to help quickly identify problems with the equipment. For example, time windows of multiple abnormal states can provide a more accurate time range for fault prediction. By performing abnormal state association analysis on warning-related parameters, the inherent connection between different states of the equipment can be revealed, and potential systemic failure modes can be identified, so that the working state of the equipment can be understood as a whole and misdiagnosis caused by a single factor can be avoided. The state transition process of the equipment is modeled using the Markov chain model, and the transfer law of the equipment state can be accurately described. By generating a state transition diagram of power plant equipment, the future state changes of the equipment can be predicted, providing data support for subsequent maintenance and management. By calculating the edge distance of the equipment state transition diagram, the transition probability of the non-steady-state abnormal state of the power plant equipment can be obtained, which enables the future state of the equipment to be described probabilistically, provides a scientific basis for formulating equipment maintenance and optimization plans, and further improves the safety and reliability of the equipment.

[0044] Preferably, step S3 comprises the following steps:

[0045] Step S31: Acquire rated life data of power plant equipment;

[0046] Step S32: performing a power plant equipment operation load analysis on the multi-dimensional graph of power plant equipment operation based on the steady-state operation mode of the equipment to generate steady-state operation power plant equipment operation load data; performing an equipment loss analysis on the rated life data of the power plant equipment based on the steady-state operation power plant equipment operation load data to generate steady-state operation mode loss data of the power plant equipment;

[0047] Step S33: dividing the data set of the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment to generate a model training set and a model test set;

[0048] Step S34: Perform model training on the model training set through a feedforward neural network algorithm to generate a power plant equipment health assessment pre-model; perform model optimization iteration on the power plant equipment health assessment pre-model using the model test set to generate a power plant equipment health assessment model.

[0049] The present invention can comprehensively evaluate the actual working conditions of power plant equipment, including load conditions, operating efficiency, etc., by analyzing the operating load based on the steady-state operation mode of the equipment, and help identify whether the equipment is in the best operating state. In the steady-state operation mode, the operating load and rated life of the equipment are analyzed, and the loss of the equipment can be accurately evaluated, thereby providing a reference basis for later maintenance, overhaul and replacement. The loss data generation in the steady-state operation mode helps to reveal the problems of physical loss, fatigue damage and reduced efficiency of the equipment in long-term operation, and helps managers to clarify the current health status of the equipment. This analysis can provide data support for the service life prediction of the equipment, thereby providing a more accurate maintenance and replacement plan for the power plant. By reasonably dividing the non-steady-state abnormal state transition probability data and the steady-state operation mode loss data, a training set and a test set are generated to ensure the representativeness and accuracy of the training data. This step can avoid overfitting or underfitting and improve the prediction ability of the model. The feedforward neural network algorithm is used for training, which can not only use the advantages of deep learning to process large-scale data, but also learn complex equipment health assessment models. The model is optimized and iterated using the test set, which can further improve the accuracy and stability of the power plant equipment health assessment model. The iterative optimization process can help capture subtle differences in equipment health status changes, thereby improving the accuracy of the model and its practical application value. This method combines steady-state operation analysis and non-steady-state abnormal state transfer data to provide comprehensive data support for the health assessment of power plant equipment. Through the training of the neural network model, it can intelligently identify potential equipment failures, provide early warnings, avoid sudden equipment failures, and improve the level of intelligent equipment management.

[0050] Preferably, step S4 comprises the following steps:

[0051] Step S41: Importing the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment into the power plant equipment health assessment model to perform a comprehensive health assessment and generate power plant equipment health assessment data;

[0052] Step S42: Visualize the power plant equipment health assessment data to generate a power plant equipment health assessment report; construct equipment repair decisions based on the power plant equipment health assessment report to perform power plant equipment health operations.

[0053] The present invention can comprehensively evaluate the health status of power plant equipment by inputting the non-steady-state abnormal state transition probability data and the steady-state operation mode loss data of power plant equipment into the health assessment model. This comprehensive analysis method can consider the health changes of equipment under different operation modes and provide more accurate health assessment data. The data of comprehensive health assessment can not only reflect the current operating status of the equipment, but also predict its future failure or damage, helping managers to make corresponding maintenance or replacement decisions in advance to avoid the impact of equipment failure. Visualizing the health assessment data of power plant equipment can convert complex technical data into intuitive and easy-to-understand charts and reports, which helps managers, engineers and decision makers to understand the health status, risk level and potential problems of equipment more quickly and accurately. The visualization report can not only display the results of the health assessment, but also highlight key risk points and early warning information, helping power plant personnel to quickly respond to equipment problems and reduce the probability of failure. Based on the health assessment report, a scientific basis can be provided for equipment repair or replacement. Through an intelligent decision support system, an optimized repair plan can be formulated according to the health status and risk assessment of the equipment to improve the pertinence and efficiency of the repair work. Through the automation of equipment repair decisions, human judgment errors can be reduced and the accuracy of repair decisions can be improved. At the same time, properly arranging maintenance and replacement time can help reduce equipment downtime and avoid impact on power plant production.

[0054] In this specification, a system for constructing a power plant equipment health assessment model is provided, which is used to execute the above-mentioned method for constructing a power plant equipment health assessment model. The system for constructing a power plant equipment health assessment model includes:

[0055] The data integration module is used to obtain the site information data of the power plant equipment; configure the site equipment data transmission channel for the site information data of the power plant equipment to generate the site equipment data transmission channel; integrate the site information data of the power plant equipment using the site equipment data transmission channel to generate the power plant equipment operation data integration platform;

[0056] The operating condition analysis module is used to monitor the operation of power plant equipment on the power plant equipment operation data integration platform, so as to obtain the power plant equipment operation monitoring data; perform equipment multi-operating condition trend fluctuation calculation on the power plant equipment operation monitoring data to obtain equipment operating condition trend fluctuation data; divide the power plant equipment operation monitoring data into equipment operation modes according to the equipment operating condition trend fluctuation data, and generate equipment steady-state operation mode and equipment non-steady-state operation mode; perform equipment abnormal state transfer analysis based on the equipment non-steady-state operation mode, and generate power plant equipment non-steady-state abnormal state transfer probability data;

[0057] The health prediction module is used to obtain the rated life data of power plant equipment; perform equipment loss analysis on the rated life data of power plant equipment based on the steady-state operation mode of the equipment to generate the steady-state operation mode loss data of the power plant equipment; construct a health assessment model based on the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment to generate the power plant equipment health assessment model;

[0058] The evaluation and decision-making module is used to import the non-steady-state abnormal state transition probability data of power plant equipment and the steady-state operation mode loss data of power plant equipment into the power plant equipment health assessment model to conduct a comprehensive health assessment and generate a power plant equipment health assessment report; based on the power plant equipment health assessment report, equipment repair decision-making is constructed to execute power plant equipment health operations.

[0059] The beneficial effect of the present invention is that through the configuration of the site equipment data transmission channel and the establishment of the power plant equipment operation data integration platform, the efficient integration and real-time data transmission of multi-site equipment information can be achieved, ensuring the integrity and accuracy of the data. The use of the integrated platform simplifies the data management process, provides unified data support for the real-time monitoring and subsequent analysis of the equipment status, and improves the overall operation efficiency. The equipment operation monitoring combined with the multi-condition trend fluctuation calculation can fully capture the dynamic changes of the equipment operation status and accurately identify the steady-state and non-steady-state operation modes. Through the division of the operation mode, the normal and abnormal equipment operation states can be effectively distinguished, providing a basis for subsequent abnormal analysis and health assessment. The abnormal state transition probability analysis using the non-steady-state operation mode data can quantify the possibility of the equipment transferring from one state to another. The Markov chain analysis model provides a scientific basis for the prediction of equipment operation, helping managers to identify potential risks in advance and take preventive measures. Based on the equipment steady-state operation mode and the non-steady-state abnormal state transition probability data, the equipment loss and abnormal state are comprehensively considered to construct a health assessment model. This assessment method can comprehensively quantify the health status of the equipment. The construction of the health assessment model provides a scientific equipment status diagnostic tool that can accurately evaluate the current operating status and remaining life of the equipment. The health assessment report provides a clear scientific basis for equipment repair or replacement by visually displaying the operation and health status of the equipment. The construction of repair decisions combined with health assessment data can dynamically adjust the maintenance plan, avoid blind maintenance, and optimize resource allocation. Therefore, the present invention improves the accuracy of the power plant equipment health assessment model through data integration, refined operating condition analysis, non-steady-state abnormal state transfer analysis, and dynamic loss assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of the steps of a method for constructing a power plant equipment health assessment model;

[0061] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0062] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0063] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0064] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0065] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0066] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0067] To achieve this, please refer to Figures 1 to 3 A method for constructing a power plant equipment health assessment model, the method comprising the following steps:

[0068] Step S1: Acquire power plant equipment site information data; configure the site equipment data transmission channel for the power plant equipment site information data to generate the site equipment data transmission channel; integrate the power plant equipment site information data using the site equipment data transmission channel to generate a power plant equipment operation data integration platform;

[0069] Step S2: monitoring the operation of power plant equipment on the power plant equipment operation data integration platform, thereby obtaining the power plant equipment operation monitoring data; performing equipment multi-condition trend fluctuation calculation on the power plant equipment operation monitoring data, thereby obtaining the equipment condition trend fluctuation data; dividing the power plant equipment operation monitoring data into equipment operation modes according to the equipment condition trend fluctuation data, thereby generating the equipment steady-state operation mode and the equipment non-steady-state operation mode; performing equipment abnormal state transition analysis based on the equipment non-steady-state operation mode, thereby generating the power plant equipment non-steady-state abnormal state transition probability data;

[0070] Step S3: Acquire rated life data of power plant equipment; perform equipment loss analysis on the rated life data of power plant equipment based on the steady-state operation mode of the equipment to generate steady-state operation mode loss data of power plant equipment; construct a health assessment model based on the non-steady-state abnormal state transition probability data of power plant equipment and the steady-state operation mode loss data of power plant equipment to generate a health assessment model for power plant equipment;

[0071] Step S4: Import the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment into the power plant equipment health assessment model for comprehensive health assessment, and generate a power plant equipment health assessment report; construct equipment repair decisions based on the power plant equipment health assessment report to perform power plant equipment health operations.

[0072] The present invention ensures that the operation data of power plant equipment can be seamlessly transmitted and integrated by configuring the site equipment data transmission channel, eliminates the data island phenomenon, and realizes the real-time sharing of equipment information, which provides a unified data platform for subsequent monitoring, analysis and evaluation, ensures the accuracy, completeness and timeliness of data, and thus improves the reliability of health assessment. Through multi-operating condition trend fluctuation calculation, the operation fluctuation of the equipment under different operating conditions can be fully captured, and then the steady-state and non-steady-state operation modes of the equipment can be accurately divided. This analysis helps to identify abnormal changes or potential faults of the equipment, making the health assessment more detailed and accurate. At the same time, through the abnormal state transition analysis based on the non-steady-state operation mode, the potential risks of the equipment can be revealed, the occurrence of faults can be warned in advance, and the safety and reliability of the equipment can be improved. The loss analysis based on the steady-state operation mode of the equipment provides the loss data generated during the operation of the equipment, which helps to predict the wear of the equipment in long-term operation. Combined with the non-steady-state abnormal state transition probability data, the health status of the equipment can be comprehensively evaluated, not only based on the static rated life, but also dynamically considering the actual performance of the equipment under different operating conditions, thereby providing an accurate basis for the maintenance and replacement decision of the equipment, avoiding the economic losses caused by excessive maintenance or delayed maintenance. By combining the data of steady-state and non-steady-state operating modes, a comprehensive equipment health assessment report is generated, which not only provides the current health status of the equipment, but also predicts the future failure risks. This comprehensive assessment helps to optimize maintenance strategies, formulate more targeted repair decisions, reduce unnecessary downtime, and improve the operating efficiency of power plants. In addition, the equipment repair decision-making based on the health assessment report can formulate maintenance priorities according to the specific conditions of the equipment, thereby optimizing resource allocation, reducing maintenance costs, and extending the service life of the equipment. Therefore, the present invention improves the accuracy of the power plant equipment health assessment model through data integration, refined operating condition analysis, non-steady-state abnormal state transfer analysis, and dynamic loss evaluation.

[0073] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of a step flow chart of a method for constructing a power plant equipment health assessment model according to the present invention. In this example, the method for constructing a power plant equipment health assessment model includes the following steps:

[0074] Step S1: Acquire power plant equipment site information data; configure the site equipment data transmission channel for the power plant equipment site information data to generate the site equipment data transmission channel; integrate the power plant equipment site information data using the site equipment data transmission channel to generate a power plant equipment operation data integration platform;

[0075] In an embodiment of the present invention, real-time equipment data is obtained from each equipment site of the power plant, including but not limited to temperature, pressure, flow, equipment operating status, fault information, maintenance records, etc. These data are usually collected through sensors and equipment interfaces and stored in a local database or a remote cloud platform. Data interface docking with a power plant management system (such as a SCADA system) or an equipment automation system (such as a PLC system) can be performed to ensure that data can be obtained in real time or regularly. According to the network environment and equipment types of the power plant, a suitable communication protocol and data transmission method are designed. For example, protocols such as OPC (OLE for Process Control), Modbus, MQTT, REST API, etc. are used to establish a real-time data transmission channel between the device and the central platform. Parameters of the data transmission channel are configured, such as data transmission frequency, bandwidth, error checking and retransmission mechanism, to ensure data stability and security. A VPN (virtual private network) or encrypted channel needs to be established to improve the security of data transmission. Ensure that the data formats collected by different devices are consistent, and use a unified format (such as JSON, XML or CSV) to transmit data to facilitate subsequent data processing and integration. Through the configured data transmission channel, the equipment operation data of each site is obtained in real time and imported into the data integration platform. The data integration platform can automatically identify the data formats of different sites and different equipment, and perform format conversion to ensure that data from different sources can be uniformly displayed and analyzed on the same platform. The collected equipment data is integrated through algorithms, such as processing the timeliness of data through time series analysis, using data cleaning technology to remove noise and invalid data, and using missing value filling methods to supplement missing data. Based on the integrated data, a power plant equipment operation data integration platform can be built. The platform can use data visualization technology to display the data of different equipment in real time, support charts, reports, trend analysis and other display methods, and help operation and maintenance personnel to promptly discover equipment failures or potential problems. The integration platform should have intelligent analysis capabilities, and analyze equipment data through machine learning and data mining technologies, such as fault prediction, remaining life estimation, performance optimization suggestions, etc. The platform should support data exchange and interface docking with other management systems (such as ERP, CMMS, EAM, etc.) to form a complete equipment management system.

[0076] Step S2: monitoring the operation of power plant equipment on the power plant equipment operation data integration platform, thereby obtaining the power plant equipment operation monitoring data; performing equipment multi-condition trend fluctuation calculation on the power plant equipment operation monitoring data, thereby obtaining the equipment condition trend fluctuation data; dividing the power plant equipment operation monitoring data into equipment operation modes according to the equipment condition trend fluctuation data, thereby generating the equipment steady-state operation mode and the equipment non-steady-state operation mode; performing equipment abnormal state transition analysis based on the equipment non-steady-state operation mode, thereby generating the power plant equipment non-steady-state abnormal state transition probability data;

[0077] In the embodiment of the present invention, in the power plant equipment operation data integration platform, it is first necessary to clearly define the key indicators to be monitored, such as equipment temperature, pressure, speed, vibration, power consumption, etc. These data are collected by real-time sensors and transmitted to the integration platform through data transmission channels. The platform uses real-time data stream processing technology to continuously monitor the operation data of various types of equipment. For example, a time series database (such as InfluxDB) is used to store equipment operation data, and a real-time monitoring system (such as Grafana) is used to display data and alarm. When the equipment parameters exceed the preset normal range, the platform triggers an alarm to notify the operation and maintenance personnel. The machine learning model can be combined to identify early signals of equipment abnormalities. When the equipment is running under different working conditions, its data performance will be different. For example, working condition parameters such as load and speed will directly affect the operating status of the equipment. Based on the historical data of the equipment, a clustering algorithm (such as K-means or DBSCAN) is used to identify multiple working condition modes and divide different working condition categories. For each working condition category, time series analysis (such as Fourier transform, wavelet analysis, etc.) is used to calculate the fluctuation trend of equipment operation data. The following methods can be used: remove short-term fluctuations and retain long-term trends through trend analysis methods (such as Hodrick-Prescott filter); use volatility analysis methods (such as standard deviation, root mean square error, etc.) to quantify the fluctuation amplitude of the equipment under different working conditions. According to the fluctuation data under different working conditions, the equipment working condition trend fluctuation data is obtained, which will be used for subsequent mode division and state prediction. Based on the equipment working condition trend fluctuation data, the operating state of the equipment is classified by pattern recognition algorithm. Generally speaking, the steady-state mode refers to the stable operation of the equipment with small fluctuation amplitude; the non-steady-state mode refers to the large fluctuation or abnormal behavior of the equipment. Under normal operation, the equipment has small performance fluctuations, stable operation, and meets the equipment design parameters. Use methods such as mean-standard deviation analysis and root mean square error to determine. The equipment is in an abnormal state or has a fault during operation, resulting in unstable operation. The period of severe fluctuation can be identified by setting a fluctuation threshold or based on trend analysis. Using classification algorithms such as support vector machine (SVM) or decision tree, the equipment operation data is divided into steady-state and non-steady-state operation modes according to the fluctuation trend. When the equipment is in non-steady-state mode, its operating state will change, such as from normal to fault, or from minor fault to major fault. First, build a state transition model of the equipment based on historical data, which can use Markov process modeling to model the state transition of the equipment. Define different equipment states, such as "normal operation", "minor fault", "major fault", etc., and use the state transition matrix to describe the transition probability between different states. Based on the equipment operation data, calculate the transition probability between each state. For example, the transition probability of the equipment from "normal operation" to "minor fault", or the transition probability from "minor fault" to "major fault".Based on the historical equipment failure data, operating parameter fluctuations, etc., probability statistics methods (such as maximum likelihood estimation) are used to calculate the transition probability between states. Hidden Markov Model (HMM) can be used to implement dynamic transition analysis of abnormal equipment states. Through the equipment state transition model, combined with the operating trend fluctuation data and historical operation data, the transition probability data of the non-steady-state abnormal state of the power plant equipment is generated. This data represents the transition probability between different abnormal states of the equipment in the non-steady-state mode, and a matrix is ​​generated. Each row and column represents an equipment operating state, and each element in the matrix represents the transition probability from one state to another. Based on these transition probability data, operation and maintenance personnel can predict the development trend of equipment failures and provide a basis for maintenance decisions. Machine learning models can also combine these data to predict abnormal states and provide early warnings.

[0078] Step S3: Acquire rated life data of power plant equipment; perform equipment loss analysis on the rated life data of power plant equipment based on the steady-state operation mode of the equipment to generate steady-state operation mode loss data of power plant equipment; construct a health assessment model based on the non-steady-state abnormal state transition probability data of power plant equipment and the steady-state operation mode loss data of power plant equipment to generate a health assessment model for power plant equipment;

[0079] In the embodiment of the present invention, by obtaining the rated life data of the power plant equipment, the rated life data of the power plant equipment is generally provided by the equipment manufacturer, or is calculated based on the operation history and design specifications of the equipment. The rated life generally refers to the maximum expected time for the equipment to operate without failure under specific working conditions. The obtained rated life data generally includes: the rated life of different equipment such as generators, transformers, boilers, etc. The operating time of the equipment under design conditions (for example, hours or years). The load value of the equipment under rated conditions. The regular maintenance requirements of the equipment during its rated life. In the steady-state operation mode, the operating parameters of the equipment change little and the performance is relatively stable. Therefore, in this mode, the loss of the equipment mainly comes from factors such as friction, wear, and aging during normal operation. By modeling the operating data of the equipment in the steady-state operation mode, the loss of each component of the equipment under long-term stable operation conditions is analyzed. This can be done in the following ways: For example, the energy loss of the generator during steady-state operation can be estimated by calculating the difference between the input power and the output power of the equipment. The loss of mechanical components caused by vibration, friction, etc. is usually evaluated by analyzing the operating parameters of the equipment (such as temperature, pressure, speed, etc.). The electrical loss of equipment such as transformers and generators is usually determined by parameters such as resistance, inductance, and capacity, which can be calculated using an electrical model. Based on information such as equipment operation time, load conditions, and operating conditions, the cumulative loss of the equipment in steady-state operation mode is calculated. For example, by integrating the various losses of the equipment, the loss value of the equipment in a specified period is obtained. Based on the above analysis results, the loss data of the equipment in steady-state operation mode is generated, including: Cumulative loss: the total loss value of the equipment in steady-state mode up to the current moment. Loss rate: the loss rate of the equipment per unit time in steady-state mode (for example, energy loss per hour). The purpose of the health assessment model is to evaluate the current health status of the equipment and its remaining life by combining the abnormal transition probability data of the equipment in non-steady-state mode with the loss data in steady-state mode. The model can be constructed based on the following steps: Calculate the health index of the equipment through the steady-state loss and non-steady-state abnormal state transition probability data of the equipment. The health index can evaluate the current health status of the equipment by integrating the steady-state loss and the risk of abnormal state transition. Calculate the remaining service life of the equipment based on the loss data and state transition probability of the equipment. Machine learning models (such as regression models and neural networks) can be used to predict the remaining life of the equipment. The Bayesian network model is used to represent the health status and state transition probability of the equipment, and the health status is inferred and evaluated in combination with the steady-state loss of the equipment. The steady-state loss data and non-steady-state state transition data of the equipment are used to estimate the health index and remaining life of the equipment through regression models (such as linear regression and support vector regression).Based on the deep learning neural network model, a health assessment model is trained through the equipment's historical operation data, loss data, and state transition data. It automatically calculates the equipment's health index and remaining lifespan, and generates regular assessment reports on the equipment's health status. The reports include the equipment's health index, remaining lifespan, and failure modes that require attention.

[0080] Step S4: Import the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment into the power plant equipment health assessment model for comprehensive health assessment, and generate a power plant equipment health assessment report; construct equipment repair decisions based on the power plant equipment health assessment report to perform power plant equipment health operations.

[0081] In an embodiment of the present invention, by converting the non-steady-state abnormal state transition probability data and the steady-state loss data according to a predetermined format, it is ensured that the two can be seamlessly connected in the health assessment model. Data cleaning is performed to remove noise and outliers, and standardized processing is performed so that the data meets the input requirements of the assessment model. An interface compatible with the power plant equipment health assessment model is developed to import the above data into the model. The interface can be a database interface, an API interface, or an automated data transmission system based on a cloud platform. The imported data (non-steady-state abnormal state transition probability data and steady-state loss data) is input into a preset health assessment model (such as a Bayesian network, a neural network, a support vector machine, etc.). The model will calculate the health index of the equipment based on these data and predict the remaining service life (RUL) of the equipment. Based on the non-steady-state abnormal state transition probability data, the probability and risk of abnormality of the equipment in the future period of time are evaluated, and a comprehensive analysis is performed in combination with the steady-state loss data. Through the steady-state loss data, the loss process of the equipment under normal working conditions is evaluated, which in turn affects the prediction of the health index and the remaining life, and a health assessment report of the equipment is generated based on the comprehensive evaluation results.

[0082] Preferably, step S1 comprises the following steps:

[0083] Step S11: Acquire power plant equipment site information data;

[0084] Step S12: performing data preprocessing on the power plant equipment site information data to generate standard power plant equipment site information data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0085] Step S13: configuring a site equipment data transmission channel for the standard power plant equipment site information data to generate a site equipment data transmission channel;

[0086] Step S14: Use the site equipment data transmission channel to deploy the edge perception computing gateway for the standard power plant equipment site information data to generate edge perception computing gateway deployment data; integrate the standard power plant equipment site information data based on the edge perception computing gateway deployment data to generate a power plant equipment operation data integration platform.

[0087] In the embodiment of the present invention, information is collected from various equipment sites of the power plant, involving data such as equipment type, location, operating status, maintenance log, energy consumption, etc. Through automated means such as sensors, monitoring systems, and Internet of Things devices, data from the site is collected in real time to ensure the integrity and timeliness of the data. Data from different sites and different devices are integrated to ensure a unified format and standard for data for subsequent processing. Duplicate data, erroneous data, or invalid data are removed to ensure data quality. Values ​​with obvious abnormalities are marked or deleted to avoid interference with analysis. Smoothing algorithms (such as moving average or Kalman filtering) are used to remove noise from sensor data. Signal processing technology is used to enhance data accuracy. For missing equipment data, mean filling, interpolation, or prediction model filling is used to ensure data integrity. Data of different dimensions (such as temperature, humidity, current, etc.) are standardized so that the data has consistent measurement units for subsequent analysis. Design a reasonable transmission channel based on the geographical location, network conditions, and equipment type of the equipment site. Wireless networks, wired networks, or hybrid networks are used to ensure efficient data transmission. Configure protocols suitable for data transmission at equipment sites, such as MQTT, HTTP / HTTPS, Modbus, etc. Set transmission frequency, bandwidth and other parameters to ensure smooth data transmission and avoid congestion. Test the configured transmission channel to ensure stability, reliability and efficiency. Adjust the transmission scheme according to the test results to ensure the real-time and integrity of the data. Select the appropriate edge computing gateway device according to the data volume, real-time requirements and computing requirements of the power plant site equipment. Deploy edge computing gateways at each equipment site to ensure that the gateway can receive equipment data in real time and perform preliminary processing. Configure the gateway to perform local data processing, such as data filtering, preprocessing, caching, real-time analysis, etc., to reduce data transmission pressure and improve efficiency. Configure the gateway's data storage, backup and recovery mechanism to ensure data reliability and security. Unify and integrate the data generated by different sites and different devices, and perform multi-level data fusion (for example, time fusion, space fusion). Ensure the compatibility of data from different sources through data cleaning and format conversion. Design and build an integrated platform that can receive data from each edge computing gateway. The platform should support the processing of multiple data sources and real-time data streams, and be highly scalable and flexible. Realize functions such as real-time monitoring, visualization, alarm mechanism, and historical data analysis of data. Provide intelligent functions such as equipment failure prediction, operation optimization and energy consumption analysis to improve the operation efficiency of power plants. Test the integrated platform at different sites to ensure the correctness of data and the stability of the platform. Optimize the platform based on test feedback to improve data processing capabilities and response speed.

[0088] Preferably, the method for constructing a power plant equipment health assessment model includes:

[0089] Based on the edge perception computing gateway deployment data, the standard power plant equipment site information data is uploaded to the edge perception computing gateway for data spatiotemporal alignment to generate power plant equipment site spatiotemporal alignment data;

[0090] Perform data characteristic analysis on the spatiotemporal alignment data of power plant equipment sites to generate data characteristics of power plant equipment sites; perform weighted fusion of associated data on the spatiotemporal alignment data of power plant equipment sites according to the data characteristics of power plant equipment sites to generate associated fusion data of power plant equipment sites;

[0091] The associated integrated data of power plant equipment sites are connected to the cloud platform to generate a power plant equipment operation data integration platform.

[0092] In an embodiment of the present invention, real-time operation data (such as temperature, pressure, vibration, power, etc.) are collected from each power plant equipment site, and these data usually have different timestamps and spatial distributions. The collected power plant equipment site information is uploaded to the edge computing gateway through the configured transmission channel. The edge computing gateway is responsible for local data processing and preliminary analysis. Since there is a deviation in the collection time of different devices and the spatial location of data collection is different, it is necessary to align the data of different devices in time and space, that is, to ensure that the data is compared and analyzed according to a unified time and space standard. For device data collected at different times, the timestamp is used to interpolate or synchronize the data to ensure that the data of each device has the same timestamp. Through geographic information system (GIS) technology, the device position is calibrated, and the device data of different sites are mapped to a unified spatial coordinate system to ensure the consistency of spatial data. The historical data of each device site is statistically analyzed to extract its basic statistical characteristics, such as mean, variance, maximum value, minimum value, etc. Through time series analysis, the long-term operation trend and change pattern of the equipment are analyzed, such as the gradual aging trend of the equipment, the load change trend, etc. Perform periodic analysis on the equipment operation data to identify its periodic change patterns (such as the day and night operation mode of the equipment, seasonal fluctuations, etc.). Use outlier detection algorithms (such as outlier detection based on box plots, Z-score algorithms, etc.) to identify abnormal fluctuations or deviations from the normal working range in the data. Through the above analysis, extract the core characteristics of the equipment data, such as the distribution of the equipment's working status, operation cycle, load changes, etc. Summarize these data characteristics into preliminary indicators of equipment health, including equipment efficiency, health status, potential failure risks, etc. Identify the correlation between the various equipment based on the different types, uses and their relationships with each other. For example, there is a high correlation between the operating status of wind turbines and generators. According to the different characteristics of the equipment (such as importance, accuracy, stability, etc.), assign different weights to various types of data. The health status of important equipment requires a higher weight, while the influence weight of auxiliary equipment can be appropriately reduced. Data fusion can be performed using methods such as weighted average method, principal component analysis (PCA) or factor analysis (FA). The spatiotemporal alignment data of each equipment site are weighted and fused according to the preset weights to generate associated data with comprehensive characteristics. These associated data can reflect the mutual influence between the various equipment and their overall operating status. Store the weighted fusion data locally or in the cloud to provide a comprehensive perspective for subsequent health assessments. Upload the generated power plant equipment site association fusion data to the cloud platform through the edge computing gateway. Configure the data transmission channel to ensure that the data can be uploaded from the edge computing gateway to the cloud platform stably and securely. HTTPS, MQTT and other protocols can be used for data transmission. After the cloud platform receives the equipment's association fusion data, it performs further data integration.The cloud platform should support efficient real-time data processing and historical data storage, and be able to handle a large number of data streams from different equipment sites. The platform design should include data storage, computing engine, visualization interface, alarm and report generation modules. The platform should be able to perform health assessment analysis, fault prediction, early warning system and other functions. Combined with cloud computing resources, the platform can perform large-scale computing and machine learning model training to improve the accuracy of equipment health assessment. Implement the equipment health assessment model on the cloud platform to visualize the health status, operating efficiency and other information of the equipment. Provide real-time monitoring, fault prediction, maintenance recommendations and other functions to support the power plant operation team to make more accurate decisions.

[0093] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0094] Step S21: monitoring the operation of power plant equipment on the power plant equipment operation data integration platform, thereby obtaining the power plant equipment operation monitoring data; performing multi-dimensional graph conversion on the power plant equipment operation monitoring data, and generating a multi-dimensional graph of the power plant equipment operation;

[0095] Step S22: performing comparative analysis of equipment multi-operating condition related trends on the power plant equipment operation monitoring data according to the multi-dimensional graph of power plant equipment operation, and generating equipment multi-operating condition trend comparative analysis data;

[0096] Step S23: performing trend fluctuation calculation on the equipment multi-operating condition trend comparison analysis data to obtain equipment operating condition trend fluctuation data; dividing the power plant equipment operation monitoring data into equipment operation modes according to the equipment operating condition trend fluctuation data to generate equipment steady-state operation mode and equipment non-steady-state operation mode;

[0097] Step S24: Based on the non-steady-state operation mode of the equipment, the multi-dimensional graph of the power plant equipment operation is monitored and early-warning data is screened to obtain non-steady-state early-warning data of the power plant equipment; abnormal state transfer analysis is performed on the non-steady-state early-warning data of the power plant equipment to generate non-steady-state abnormal state transfer probability data of the power plant equipment.

[0098] In an embodiment of the present invention, the operation status of the equipment is monitored by collecting the operation data (such as temperature, pressure, current, voltage, etc.) of each equipment in real time on the power plant equipment operation data integration platform. By configuring sensors and edge computing gateways, high-frequency data collection and transmission are achieved. The types of equipment monitored include generators, transformers, boilers, cooling systems, etc., covering the operation status of various core equipment in the power plant. The operation data of the equipment is converted from a single time series data to a multi-dimensional map, covering the relationship between multiple variables, such as the operation status, load, environmental factors, etc. of the equipment. Multi-dimensional visualization technology (such as radar charts, heat maps, three-dimensional charts, etc.) is used to display various health indicators of the equipment. Multi-dimensional maps help analyze the performance of the equipment under different working conditions and provide an intuitive view for subsequent analysis. The multi-dimensional operation data of each equipment in the power plant is compared and analyzed under multiple working conditions to identify the impact of different working conditions on the performance of the equipment. The working conditions include load changes, ambient temperature, operating time, etc. Correlation analysis and trend analysis are used to evaluate the behavior patterns of the equipment under different working conditions and reveal the performance degradation or abnormality of the equipment under specific working conditions. Compare the performance of the equipment under different working conditions to determine the optimal working conditions and performance bottlenecks of the equipment. Summarize and generate a set of trend comparison data of the equipment under multiple working conditions, which can be used for subsequent fault prediction and health assessment. Based on the trend comparison analysis data of multiple working conditions, the fluctuation characteristics of the equipment under different working conditions are obtained by calculating the fluctuation amplitude and change frequency of the equipment operation data. Use fluctuation analysis technology (such as Fourier transform, fluctuation amplitude analysis, etc.) to extract the fluctuation information of the equipment working conditions and evaluate its operating stability. According to the fluctuation data of the equipment, combined with a certain threshold judgment, distinguish the steady-state operation mode and the unsteady-state operation mode of the equipment. Steady-state operation mode: The equipment operates stably without obvious fluctuations or abnormalities, which usually indicates that the equipment is in a normal operating state. Unsteady-state operation mode: The equipment has large fluctuations or abnormalities in some cases, which are specifically temporary abnormalities caused by precursors to faults or external disturbances. Combined with the operating rules and trend fluctuation data of the equipment, the classification results of steady state and unsteady state are generated to provide a basis for subsequent health assessment and fault warning. Based on the unsteady-state operation mode of the equipment obtained in the previous step, the multi-dimensional map of the equipment is screened, focusing on those data that show abnormal or fluctuating characteristics. The screening process involves threshold checking and fluctuation identification of various indicators of the equipment, and marking the data that does not meet the steady-state conditions for further analysis. For the screened non-steady-state warning data, the state transition model (such as Markov chain, state machine model, etc.) is applied to analyze the transition process of the equipment from normal state to abnormal state. Analyze the different operating states that the equipment experiences during the non-steady state, such as the transition path from minor abnormality to serious failure.Based on abnormal state transition analysis, the transition probability of the equipment under different operating conditions is calculated to generate abnormal state transition probability data of the equipment. These transition probabilities can help predict the probability of equipment failure and provide important reference for equipment maintenance and scheduling.

[0099] Preferably, performing multi-dimensional graph conversion on the power plant equipment operation monitoring data includes:

[0100] Perform power plant equipment operation signal conversion on power plant equipment operation monitoring data to generate power plant equipment operation signals; perform waveform conversion on power plant equipment operation signals to generate power plant equipment operation signal waveforms; perform time domain analysis on power plant equipment operation signal waveforms to generate power plant equipment time domain signal waveforms;

[0101] Perform order ratio analysis on the time domain signal waveform of power plant equipment to generate an order ratio diagram of power plant equipment;

[0102] Perform signal waveform extraction on the time domain signal waveform of power plant equipment to obtain the time domain signal waveform curve of power plant equipment; perform FFT transformation on the time domain signal waveform curve of power plant equipment to generate the frequency domain waveform curve of power plant equipment; perform power spectrum analysis on the frequency domain waveform curve of power plant equipment to generate the power spectrum diagram of power plant equipment;

[0103] Extract equipment influencing parameters from the power spectrum of power plant equipment to obtain power influencing parameters of power plant equipment; perform waterfall chart analysis on the power spectrum of power plant equipment based on the power influencing parameters of power plant equipment to generate a waterfall chart of power plant equipment;

[0104] The time domain signal waveform diagram of power plant equipment, the order ratio diagram of power plant equipment, the power spectrum diagram of power plant equipment and the waterfall diagram of power plant equipment are integrated to generate a multi-dimensional diagram of the power plant equipment operation.

[0105] In an embodiment of the present invention, key signal information is extracted from the original monitoring data (such as temperature, pressure, vibration, current, etc.) collected from the power plant equipment. The monitoring data is preliminarily processed, including data cleaning, denoising, etc., to ensure the accuracy of the collected signal, and the operation signal of the power plant equipment is generated, which usually includes a multi-parameter signal sequence of the equipment, such as equipment temperature, current fluctuation, etc. The operation signal of the power plant equipment is converted into a waveform diagram to show the change of the signal over time. The waveform diagram can intuitively display the dynamic behavior of the equipment in operation, such as the start-up, shutdown, load change, etc. of the equipment. The time domain waveform diagram can be used to preliminarily identify whether the equipment has abnormal fluctuations. The time domain analysis of the power plant equipment operation signal waveform diagram is performed, focusing on observing the change law of the signal on the time axis. The time domain analysis includes filtering and smoothing the signal to remove noise and highlight the real fluctuation of the equipment. The generated time domain signal waveform diagram can help detect periodic changes and sudden abnormalities in the operation of the equipment. The order ratio analysis of the time domain signal waveform diagram is performed, especially in the vibration signal analysis, the order ratio analysis can reveal the operation of the equipment at a specific operating frequency. The order ratio diagram shows the energy distribution corresponding to each order of the equipment (such as 1X, 2X, 3X and other frequency components), helping to discover potential mechanical problems such as imbalance and misalignment. Extract the signal waveform curve of a specific time period from the time domain signal waveform diagram. Signal waveform extraction can select key time windows or peak fluctuation areas to more finely analyze the operation of the equipment. Perform fast Fourier transform (FFT) on the time domain signal waveform curve of the power plant equipment and convert it to the frequency domain. FFT transformation can convert time domain signals into frequency components, help analyze the behavior of the equipment at different frequencies, identify frequency characteristics such as vibration and noise, and the generated frequency domain waveform curve shows the intensity distribution of the equipment in different frequency ranges. Perform power spectrum analysis on the frequency domain waveform curve of the power plant equipment to understand the power distribution of the signal. Power spectrum analysis can reveal the energy distribution of the equipment at different frequencies and identify abnormal frequency bands, such as peaks of certain specific frequencies that are related to equipment failures. Extract key parameters that affect the health and performance of the equipment from the power spectrum diagram, such as vibration amplitude and harmonic components. These parameters can reveal the performance of the equipment at specific frequencies and help analyze the health status of the equipment. Based on the power influencing parameters, a waterfall chart analysis is performed on the power spectrum of the equipment. The waterfall chart can show the process of the equipment frequency characteristics changing over time. The generated waterfall chart of the power plant equipment helps to reveal the changes in the frequency characteristics of the equipment during long-term operation, such as frequency drift during equipment aging. The previously generated time domain signal waveform chart, order ratio chart, power spectrum chart and waterfall chart are integrated to form a multi-dimensional equipment operation spectrum. After the multi-dimensional spectrum is integrated, it can provide a full range of perspectives for equipment health monitoring, including time changes, frequency analysis, signal strength and multi-level display of equipment status. The final generated multi-dimensional spectrum of power plant equipment operation provides support for subsequent equipment health assessment, fault prediction and maintenance decisions.

[0106] Preferably, dividing the equipment operation mode of the power plant equipment operation monitoring data according to the equipment operating condition trend fluctuation data includes:

[0107] Based on a preset time range, the equipment operating condition trend fluctuation data is segmented into adjacent fluctuation curve segments to obtain a first equipment operating condition trend fluctuation curve segment and a second equipment operating condition trend fluctuation curve segment; trend fluctuation peak values ​​are calculated for the first equipment operating condition trend fluctuation curve segment and the second equipment operating condition trend fluctuation curve segment to obtain a first fluctuation curve peak value and a second fluctuation curve peak value;

[0108] Calculate the frequency domain signal ratio of the first fluctuation curve peak value and the second fluctuation curve peak value to obtain the first fluctuation curve frequency domain signal ratio data and the second fluctuation curve frequency domain signal ratio data, wherein the frequency domain signal includes a low-frequency signal and a high-frequency signal; perform frequency characteristic analysis based on the first fluctuation curve frequency domain signal ratio data and the first fluctuation curve peak value to generate first frequency fluctuation characteristic data; perform frequency characteristic analysis based on the second fluctuation curve frequency domain signal ratio data and the second fluctuation curve peak value to generate second frequency fluctuation characteristic data;

[0109] The first frequency fluctuation characteristic data and the second frequency fluctuation characteristic data are calculated for similarity to obtain frequency fluctuation characteristic similarity data; the frequency fluctuation characteristic similarity data is compared with a preset standard similarity threshold; when the frequency fluctuation characteristic similarity data is greater than or equal to the preset standard similarity threshold, the power plant equipment corresponding to the equipment operating condition trend fluctuation data is marked as a steady-state operation mode; when the frequency fluctuation characteristic similarity data is less than the preset standard similarity threshold, the power plant equipment corresponding to the equipment operating condition trend fluctuation data is marked as a non-steady-state operation mode.

[0110] In an embodiment of the present invention, the fluctuation data in adjacent time periods are extracted from the equipment operating condition trend fluctuation data. The fluctuation data is segmented according to a preset time range to generate multiple independent fluctuation curve segments: a first equipment operating condition trend fluctuation curve segment. A second equipment operating condition trend fluctuation curve segment. Each curve segment represents the operation trend fluctuation of the equipment in a specific time period. The first equipment operating condition trend fluctuation curve segment is subjected to a peak analysis to extract the maximum value and generate a first fluctuation curve peak value. The second equipment operating condition trend fluctuation curve segment is subjected to the same peak analysis to extract the maximum value and generate a second fluctuation curve peak value. The first fluctuation curve peak value and the second fluctuation curve peak value are subjected to frequency domain conversion to decompose them into low-frequency signals and high-frequency signals. The proportion of signals in each frequency band is calculated to generate the following data: the first fluctuation curve frequency domain signal proportion data. The second fluctuation curve frequency domain signal proportion data. The frequency characteristic analysis is performed on the first fluctuation curve frequency domain signal proportion data and the first fluctuation curve peak value to identify the main frequency components and their change characteristics and generate the first frequency fluctuation characteristic data. The same frequency characteristic analysis is performed on the second fluctuation curve frequency domain signal proportion data and the second fluctuation curve peak value to generate the second frequency fluctuation characteristic data. Compare the first frequency fluctuation characteristic data and the second frequency fluctuation characteristic data, use a similarity algorithm to calculate the similarity between the two, and generate frequency fluctuation characteristic similarity data, which is used to measure the similarity between the two trend fluctuation curves in frequency characteristics. Compare the frequency fluctuation characteristic similarity data with the preset standard similarity threshold: if the frequency fluctuation characteristic similarity data ≥ the standard similarity threshold, the power plant equipment corresponding to the equipment condition trend fluctuation data is marked as a steady-state operation mode. If the frequency fluctuation characteristic similarity data < the standard similarity threshold, the power plant equipment corresponding to the equipment condition trend fluctuation data is marked as a non-steady-state operation mode.

[0111] Preferably, performing abnormal state transition analysis on non-steady-state warning data of power plant equipment includes:

[0112] Extract warning parameters from the non-steady-state warning data of power plant equipment to obtain non-steady-state warning parameters of power plant equipment; confirm warning timestamps for non-steady-state warning parameters of power plant equipment to obtain non-steady-state warning timestamps of power plant equipment;

[0113] Dynamically screen the warning parameters of the non-steady-state warning parameters of the power plant equipment with adjacent timestamps through the non-steady-state warning timestamps of the power plant equipment to obtain warning correlation parameters; use the warning correlation parameters to perform abnormal state correlation analysis on the non-steady-state warning parameters of the power plant equipment to generate non-steady-state abnormal state correlation data of the power plant equipment;

[0114] The Markov chain is constructed for the non-steady-state abnormal state correlation data of the power plant equipment to generate the power plant equipment state transition diagram; the edge distance of the power plant equipment state transition diagram is calculated to generate the non-steady-state abnormal state transition probability data of the power plant equipment.

[0115] In the embodiment of the present invention, by adding timestamp information to each warning parameter, recording the data generation time, forming time series data, and generating a non-steady-state warning timestamp for power plant equipment, the time characteristics of each abnormal state are identified. The non-steady-state warning timestamp of power plant equipment is used to select warning parameters in adjacent time periods to form a dynamic association. The screening algorithm is applied to filter invalid or noise parameters to ensure data accuracy, and the warning association parameters are generated to reflect the correlation between time adjacent states. Based on the warning association parameters, the non-steady-state warning parameters in different time periods are statistically analyzed to identify the association rules between them. The causal or co-occurrence relationship between abnormal states is constructed to generate non-steady-state abnormal state association data of power plant equipment to describe the relationship characteristics between abnormal states. The non-steady-state abnormal state association data of power plant equipment is modeled as a finite state set. Each abnormal state is defined as a node, and the transition relationship between states is established. Using the Markov chain theory, a state transition diagram of power plant equipment is generated to reflect the transition path of the abnormal state. The distance calculation is performed on the edges of the state transition diagram (i.e., the transition between abnormal states): considering factors such as the transition probability between states, the time interval, and the parameter change amplitude. The weighted formula is used for comprehensive calculation to generate the probability data of non-steady-state abnormal state transition of power plant equipment, describing the possibility and intensity of transition between various abnormal states.

[0116] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0117] Step S31: Acquire rated life data of power plant equipment;

[0118] Step S32: performing a power plant equipment operation load analysis on the multi-dimensional graph of power plant equipment operation based on the steady-state operation mode of the equipment to generate steady-state operation power plant equipment operation load data; performing an equipment loss analysis on the rated life data of the power plant equipment based on the steady-state operation power plant equipment operation load data to generate steady-state operation mode loss data of the power plant equipment;

[0119] Step S33: dividing the data set of the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment to generate a model training set and a model test set;

[0120] Step S34: Perform model training on the model training set through a feedforward neural network algorithm to generate a power plant equipment health assessment pre-model; perform model optimization iteration on the power plant equipment health assessment pre-model using the model test set to generate a power plant equipment health assessment model.

[0121] In an embodiment of the present invention, the rated life data of power plant equipment is obtained from the equipment operation manual, historical maintenance records or information provided by the manufacturer. The data includes the theoretical service life of the equipment, the rated working time, and the durability index of the relevant operating parameters. Based on the equipment time domain signal, frequency domain signal and power parameter in the multi-dimensional spectrum of power plant equipment operation, combined with the steady-state operation mode of the equipment, the equipment operation load is analyzed from multiple angles to generate the steady-state operation power plant equipment operation load data, which is used to reflect the actual operating conditions under the steady-state operation mode. Using the steady-state operation power plant equipment operation load data, the rated life data of the power plant equipment is analyzed for loss: the influence of the operation load on the life is evaluated, such as the life shortening rate caused by load overload. The equipment loss value per unit time is calculated to generate the steady-state operation mode loss data of the power plant equipment, which provides a basis for equipment health assessment. The non-steady-state abnormal state transition probability data of the power plant equipment is integrated with the steady-state operation mode loss data to form a comprehensive data set containing steady-state and non-steady-state operation information. The comprehensive data set is divided into a model training set and a model test set according to a certain ratio (e.g., 80% training set, 20% test set). Ensure the diversity and representativeness of the data set to avoid overfitting or underfitting during model training. Use the feedforward neural network algorithm (FFNN) and take the model training set as input to design a multi-layer neural network structure, including input layer, hidden layer and output layer: the input layer contains key features related to equipment health, such as operating load, loss rate, transition probability, etc. The hidden layer uses activation functions (such as ReLU or Sigmoid) for nonlinear transformation to capture complex feature relationships. The output layer generates equipment health scores or health status classification results to generate a preliminary power plant equipment health assessment pre-model. Use the model test set to perform performance testing on the power plant equipment health assessment pre-model to evaluate prediction accuracy and generalization ability. Optimize by: Adjusting the number of neural network layers and neurons. Using the cross entropy loss function or mean square error (MSE) for error feedback. Applying the Adam optimizer or SGD (stochastic gradient descent) to update weights. After multiple rounds of iterative optimization, a power plant equipment health assessment model with high accuracy and robustness is finally generated.

[0122] Preferably, step S4 comprises the following steps:

[0123] Step S41: Importing the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment into the power plant equipment health assessment model to perform a comprehensive health assessment and generate power plant equipment health assessment data;

[0124] Step S42: Visualize the power plant equipment health assessment data to generate a power plant equipment health assessment report; construct equipment repair decisions based on the power plant equipment health assessment report to perform power plant equipment health operations.

[0125] In an embodiment of the present invention, the non-steady-state abnormal state transition probability data of power plant equipment and the steady-state operation mode loss data of power plant equipment are imported into the power plant equipment health assessment model. The imported data is standardized to ensure that the weights of the two types of data in the model are balanced for comprehensive analysis. Using the power plant equipment health assessment model, a comprehensive assessment is performed through the following steps: the state stability score of the non-steady-state abnormal state transition probability data is scored. The cumulative loss rate and health risk of the equipment are calculated in combination with the steady-state operation mode loss data. Through the output layer of the health assessment model, the power plant equipment health assessment data (such as health score or health state classification) is generated. The comprehensive health assessment data reflects the current health state of the equipment and provides a basis for further operations. The equipment health assessment data is intuitively displayed as a power plant equipment health assessment report using chart tools (such as line charts, pie charts, heat maps, etc.). Based on the health status displayed in the assessment report, the following decision logic is constructed: Healthy state: no repair is required, only routine maintenance is performed. Sub-healthy state: formulate a preventive maintenance plan and arrange equipment optimization and adjustment. Fault state: generate a repair priority list and arrange emergency repair operations. Use a maintenance management system or intelligent scheduling platform to automatically generate equipment repair plans, including repair time, required resources, and operation steps. Re-enter the data after the repair is completed into the health assessment model to verify the repair effect and optimize the model's decision-making ability.

[0126] In this specification, a system for constructing a power plant equipment health assessment model is provided, which is used to execute the above-mentioned method for constructing a power plant equipment health assessment model. The system for constructing a power plant equipment health assessment model includes:

[0127] The data integration module is used to obtain the site information data of the power plant equipment; configure the site equipment data transmission channel for the site information data of the power plant equipment to generate the site equipment data transmission channel; integrate the site information data of the power plant equipment using the site equipment data transmission channel to generate the power plant equipment operation data integration platform;

[0128] The operating condition analysis module is used to monitor the operation of power plant equipment on the power plant equipment operation data integration platform, so as to obtain the power plant equipment operation monitoring data; perform equipment multi-operating condition trend fluctuation calculation on the power plant equipment operation monitoring data to obtain equipment operating condition trend fluctuation data; divide the power plant equipment operation monitoring data into equipment operation modes according to the equipment operating condition trend fluctuation data, and generate equipment steady-state operation mode and equipment non-steady-state operation mode; perform equipment abnormal state transfer analysis based on the equipment non-steady-state operation mode, and generate power plant equipment non-steady-state abnormal state transfer probability data;

[0129] The health prediction module is used to obtain the rated life data of power plant equipment; perform equipment loss analysis on the rated life data of power plant equipment based on the steady-state operation mode of the equipment to generate the steady-state operation mode loss data of the power plant equipment; construct a health assessment model based on the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment to generate the power plant equipment health assessment model;

[0130] The evaluation and decision-making module is used to import the non-steady-state abnormal state transition probability data of power plant equipment and the steady-state operation mode loss data of power plant equipment into the power plant equipment health assessment model to conduct a comprehensive health assessment and generate a power plant equipment health assessment report; based on the power plant equipment health assessment report, equipment repair decision-making is constructed to execute power plant equipment health operations.

[0131] The beneficial effect of the present invention is that through the configuration of the site equipment data transmission channel and the establishment of the power plant equipment operation data integration platform, the efficient integration and real-time data transmission of multi-site equipment information can be achieved, ensuring the integrity and accuracy of the data. The use of the integrated platform simplifies the data management process, provides unified data support for the real-time monitoring and subsequent analysis of the equipment status, and improves the overall operation efficiency. The equipment operation monitoring combined with the multi-condition trend fluctuation calculation can fully capture the dynamic changes of the equipment operation status and accurately identify the steady-state and non-steady-state operation modes. Through the division of the operation mode, the normal and abnormal equipment operation states can be effectively distinguished, providing a basis for subsequent abnormal analysis and health assessment. The abnormal state transition probability analysis using the non-steady-state operation mode data can quantify the possibility of the equipment transferring from one state to another. The Markov chain analysis model provides a scientific basis for the prediction of equipment operation, helping managers to identify potential risks in advance and take preventive measures. Based on the equipment steady-state operation mode and the non-steady-state abnormal state transition probability data, the equipment loss and abnormal state are comprehensively considered to construct a health assessment model. This assessment method can comprehensively quantify the health status of the equipment. The construction of the health assessment model provides a scientific equipment status diagnostic tool that can accurately evaluate the current operating status and remaining life of the equipment. The health assessment report provides a clear scientific basis for equipment repair or replacement by visually displaying the operation and health status of the equipment. The construction of repair decisions combined with health assessment data can dynamically adjust the maintenance plan, avoid blind maintenance, and optimize resource allocation. Therefore, the present invention improves the accuracy of the power plant equipment health assessment model through data integration, refined operating condition analysis, non-steady-state abnormal state transfer analysis, and dynamic loss assessment.

[0132] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0133] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for constructing a power plant equipment health assessment model, characterized in that: The following steps are involved: Step S1: Acquire power plant equipment site information data; Configure the site equipment data transmission channel for the power plant equipment site information data and generate the site equipment data transmission channel; Use the site equipment data transmission channel to integrate the power plant equipment site information data and generate a power plant equipment operation data integration platform; Step S2: monitoring the power plant equipment operation on the power plant equipment operation data integration platform, thereby obtaining the power plant equipment operation monitoring data; Calculate the equipment multi-condition trend fluctuations on the power plant equipment operation monitoring data to obtain the equipment condition trend fluctuation data; According to the equipment operating condition trend fluctuation data, the power plant equipment operation monitoring data is divided into equipment operation modes to generate equipment steady-state operation mode and equipment non-steady-state operation mode; Analyze the abnormal state transition of equipment based on the non-steady-state operation mode of the equipment, and generate the probability data of the non-steady-state abnormal state transition of power plant equipment; Step S3: Acquire rated life data of power plant equipment; Conduct equipment loss analysis on rated life data of power plant equipment based on steady-state operation mode of equipment to generate steady-state operation mode loss data of power plant equipment; construct health assessment model through non-steady-state abnormal state transition probability data of power plant equipment and steady-state operation mode loss data of power plant equipment to generate power plant equipment health assessment model; Step S4: Importing the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment into the power plant equipment health assessment model to perform a comprehensive health assessment and generate a power plant equipment health assessment report; Equipment repair decisions are made based on the power plant equipment health assessment report to perform power plant equipment health operations.

2. The method for constructing a power plant equipment health assessment model according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire power plant equipment site information data; Step S12: performing data preprocessing on the power plant equipment site information data to generate standard power plant equipment site information data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization; Step S13: configuring a site equipment data transmission channel for the standard power plant equipment site information data to generate a site equipment data transmission channel; Step S14: Use the site equipment data transmission channel to deploy the edge perception computing gateway for the standard power plant equipment site information data to generate edge perception computing gateway deployment data; integrate the standard power plant equipment site information data based on the edge perception computing gateway deployment data to generate a power plant equipment operation data integration platform.

3. The method for constructing a power plant equipment health assessment model according to claim 2, characterized in that: The construction method of the power plant equipment health assessment model includes: Based on the edge perception computing gateway deployment data, the standard power plant equipment site information data is uploaded to the edge perception computing gateway for data spatiotemporal alignment to generate power plant equipment site spatiotemporal alignment data; Perform data characteristic analysis on the spatiotemporal alignment data of power plant equipment sites to generate data characteristics of power plant equipment sites; perform weighted fusion of associated data on the spatiotemporal alignment data of power plant equipment sites according to the data characteristics of power plant equipment sites to generate associated fusion data of power plant equipment sites; The associated integrated data of power plant equipment sites are connected to the cloud platform to generate a power plant equipment operation data integration platform.

4. The method for constructing a power plant equipment health assessment model according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: monitoring the operation of power plant equipment on the power plant equipment operation data integration platform, thereby obtaining the power plant equipment operation monitoring data; performing multi-dimensional graph conversion on the power plant equipment operation monitoring data, and generating a multi-dimensional graph of the power plant equipment operation; Step S22: performing comparative analysis of equipment multi-operating condition related trends on the power plant equipment operation monitoring data according to the multi-dimensional graph of power plant equipment operation, and generating equipment multi-operating condition trend comparative analysis data; Step S23: performing trend fluctuation calculation on the equipment multi-operating condition trend comparison analysis data to obtain equipment operating condition trend fluctuation data; dividing the power plant equipment operation monitoring data into equipment operation modes according to the equipment operating condition trend fluctuation data to generate equipment steady-state operation mode and equipment non-steady-state operation mode; Step S24: Based on the non-steady-state operation mode of the equipment, the multi-dimensional graph of the power plant equipment operation is monitored and early-warning data is screened to obtain non-steady-state early-warning data of the power plant equipment; abnormal state transfer analysis is performed on the non-steady-state early-warning data of the power plant equipment to generate non-steady-state abnormal state transfer probability data of the power plant equipment.

5. The method for constructing a power plant equipment health assessment model according to claim 4, characterized in that: The multi-dimensional graph conversion of power plant equipment operation monitoring data includes: Perform power plant equipment operation signal conversion on power plant equipment operation monitoring data to generate power plant equipment operation signals; perform waveform conversion on power plant equipment operation signals to generate power plant equipment operation signal waveforms; perform time domain analysis on power plant equipment operation signal waveforms to generate power plant equipment time domain signal waveforms; Perform order ratio analysis on the time domain signal waveform of power plant equipment to generate an order ratio diagram of power plant equipment; Perform signal waveform extraction on the time domain signal waveform of power plant equipment to obtain the time domain signal waveform curve of power plant equipment; perform FFT transformation on the time domain signal waveform curve of power plant equipment to generate the frequency domain waveform curve of power plant equipment; perform power spectrum analysis on the frequency domain waveform curve of power plant equipment to generate the power spectrum diagram of power plant equipment; Extract equipment influencing parameters from the power spectrum of power plant equipment to obtain power influencing parameters of power plant equipment; perform waterfall chart analysis on the power spectrum of power plant equipment based on the power influencing parameters of power plant equipment to generate a waterfall chart of power plant equipment; The time domain signal waveform diagram of power plant equipment, the order ratio diagram of power plant equipment, the power spectrum diagram of power plant equipment and the waterfall diagram of power plant equipment are integrated to generate a multi-dimensional diagram of the power plant equipment operation.

6. The method for constructing a power plant equipment health assessment model according to claim 4, characterized in that: The equipment operation mode classification of power plant equipment operation monitoring data based on equipment condition trend fluctuation data includes: Based on a preset time range, the equipment operating condition trend fluctuation data is segmented into adjacent fluctuation curve segments to obtain a first equipment operating condition trend fluctuation curve segment and a second equipment operating condition trend fluctuation curve segment; trend fluctuation peak values ​​are calculated for the first equipment operating condition trend fluctuation curve segment and the second equipment operating condition trend fluctuation curve segment to obtain a first fluctuation curve peak value and a second fluctuation curve peak value; Calculate the frequency domain signal ratio of the first fluctuation curve peak value and the second fluctuation curve peak value to obtain the first fluctuation curve frequency domain signal ratio data and the second fluctuation curve frequency domain signal ratio data, wherein the frequency domain signal includes a low-frequency signal and a high-frequency signal; perform frequency characteristic analysis based on the first fluctuation curve frequency domain signal ratio data and the first fluctuation curve peak value to generate first frequency fluctuation characteristic data; perform frequency characteristic analysis based on the second fluctuation curve frequency domain signal ratio data and the second fluctuation curve peak value to generate second frequency fluctuation characteristic data; The first frequency fluctuation characteristic data and the second frequency fluctuation characteristic data are calculated for similarity to obtain frequency fluctuation characteristic similarity data; the frequency fluctuation characteristic similarity data is compared with a preset standard similarity threshold; when the frequency fluctuation characteristic similarity data is greater than or equal to the preset standard similarity threshold, the power plant equipment corresponding to the equipment operating condition trend fluctuation data is marked as a steady-state operation mode; when the frequency fluctuation characteristic similarity data is less than the preset standard similarity threshold, the power plant equipment corresponding to the equipment operating condition trend fluctuation data is marked as a non-steady-state operation mode.

7. The method for constructing a power plant equipment health assessment model according to claim 4, characterized in that: The abnormal state transfer analysis of non-steady-state warning data of power plant equipment includes: Extract warning parameters from the non-steady-state warning data of power plant equipment to obtain non-steady-state warning parameters of power plant equipment; confirm warning timestamps for non-steady-state warning parameters of power plant equipment to obtain non-steady-state warning timestamps of power plant equipment; Dynamically screen the warning parameters of the non-steady-state warning parameters of the power plant equipment with adjacent timestamps through the non-steady-state warning timestamps of the power plant equipment to obtain warning correlation parameters; use the warning correlation parameters to perform abnormal state correlation analysis on the non-steady-state warning parameters of the power plant equipment to generate non-steady-state abnormal state correlation data of the power plant equipment; The Markov chain is constructed for the non-steady-state abnormal state correlation data of the power plant equipment to generate the power plant equipment state transition diagram; the edge distance of the power plant equipment state transition diagram is calculated to generate the non-steady-state abnormal state transition probability data of the power plant equipment.

8. The method for constructing a power plant equipment health assessment model according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Acquire rated life data of power plant equipment; Step S32: performing a power plant equipment operation load analysis on the multi-dimensional graph of power plant equipment operation based on the steady-state operation mode of the equipment to generate steady-state operation power plant equipment operation load data; performing an equipment loss analysis on the rated life data of the power plant equipment based on the steady-state operation power plant equipment operation load data to generate steady-state operation mode loss data of the power plant equipment; Step S33: dividing the data set of the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment to generate a model training set and a model test set; Step S34: Perform model training on the model training set through a feedforward neural network algorithm to generate a power plant equipment health assessment pre-model; perform model optimization iteration on the power plant equipment health assessment pre-model using the model test set to generate a power plant equipment health assessment model.

9. The method for constructing a power plant equipment health assessment model according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Importing the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment into the power plant equipment health assessment model to perform a comprehensive health assessment and generate power plant equipment health assessment data; Step S42: Visualize the power plant equipment health assessment data to generate a power plant equipment health assessment report; construct equipment repair decisions based on the power plant equipment health assessment report to perform power plant equipment health operations.

10. A system for constructing a power plant equipment health assessment model, characterized in that: The method for constructing a power plant equipment health assessment model according to claim 1 is used to execute the method, wherein the system for constructing a power plant equipment health assessment model comprises: The data integration module is used to obtain the site information data of the power plant equipment; configure the site equipment data transmission channel for the site information data of the power plant equipment to generate the site equipment data transmission channel; integrate the site information data of the power plant equipment using the site equipment data transmission channel to generate the power plant equipment operation data integration platform; The operating condition analysis module is used to monitor the operation of power plant equipment on the power plant equipment operation data integration platform, so as to obtain the power plant equipment operation monitoring data; perform equipment multi-operating condition trend fluctuation calculation on the power plant equipment operation monitoring data to obtain equipment operating condition trend fluctuation data; divide the power plant equipment operation monitoring data into equipment operation modes according to the equipment operating condition trend fluctuation data, and generate equipment steady-state operation mode and equipment non-steady-state operation mode; perform equipment abnormal state transfer analysis based on the equipment non-steady-state operation mode, and generate power plant equipment non-steady-state abnormal state transfer probability data; The health prediction module is used to obtain the rated life data of power plant equipment; perform equipment loss analysis on the rated life data of power plant equipment based on the steady-state operation mode of the equipment to generate the steady-state operation mode loss data of the power plant equipment; construct a health assessment model based on the non-steady-state abnormal state transition probability data of the power plant equipment and the steady-state operation mode loss data of the power plant equipment to generate the power plant equipment health assessment model; The evaluation and decision-making module is used to import the non-steady-state abnormal state transition probability data of power plant equipment and the steady-state operation mode loss data of power plant equipment into the power plant equipment health assessment model to conduct a comprehensive health assessment and generate a power plant equipment health assessment report; based on the power plant equipment health assessment report, equipment repair decision-making is constructed to execute power plant equipment health operations.

Images