A method and system for monitoring and early warning of boiler faults in thermal power plants

By using an automated monitoring and early warning system and predictive models to analyze abnormal parameters of boilers in thermal power plants, the limitations of traditional manual inspections have been overcome, enabling real-time fault identification and rapid handling, thereby improving boiler safety and production efficiency.

CN120351497BActive Publication Date: 2026-11-17HUANENG TONGCHUAN ZHAOJIN COAL POWER CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510543065.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-04-27
Publication Date
2026-11-17
Estimated Expiration
2045-04-27

AI Technical Summary

Technical Problem

Traditional boiler monitoring methods in thermal power plants rely on manual inspections, which are subjective and limited, and cannot achieve comprehensive and real-time monitoring and early warning. This results in slow fault detection and untimely handling, affecting production and safety.

Method used

By acquiring boiler operation monitoring data, analyzing abnormal parameters using preset prediction models, assessing fault types and levels, and formulating corresponding early warning and response strategies, automated monitoring and early warning can be achieved.

Benefits of technology

It enables real-time monitoring of boiler status, rapid identification of potential faults, improved fault handling efficiency, ensures equipment stability and safety, and optimizes emergency response procedures.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120351497B_ABST
    Figure CN120351497B_ABST
Patent Text Reader

Abstract

This invention discloses a method and system for monitoring and early warning of boiler faults in thermal power plants. The method includes: acquiring and analyzing operational monitoring data of the thermal power plant boiler to determine abnormal operating parameters; performing data prediction on each abnormal operating parameter according to a preset prediction model to obtain corresponding abnormal prediction data, and analyzing and determining abnormal characteristics; evaluating the abnormal state of the thermal power plant boiler based on each abnormal characteristic to obtain an abnormal state evaluation value, and determining whether the thermal power plant boiler has a fault based on the evaluation value; after determining that the thermal power plant boiler has a fault, determining the fault type based on the abnormal operating parameters; determining the fault level based on the fault type, and determining an early warning response strategy based on the fault level. This invention, by analyzing operational monitoring data to predict future changes in the boiler and evaluating and determining faults based on these changes, provides early warnings, which can effectively reduce fault risks, improve boiler safety, reliability, and operating efficiency, and increase production benefits.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of early warning technology for thermal power plant boilers, and in particular to a method and system for monitoring and warning of boiler malfunctions in thermal power plants. Background Technology

[0002] In today's society, thermal power plants play a vital role, providing a large amount of electricity for people's lives and industrial production. However, as one of the core pieces of equipment in a thermal power plant, the boiler may face various malfunctions and problems during long-term operation. Once a malfunction occurs, it may lead to production interruption, safety accidents, or even economic losses.

[0003] However, traditional methods typically rely on manual inspections, which are subjective and limited, failing to achieve comprehensive and real-time monitoring and early warning. Furthermore, manual inspections are slow to react, unable to promptly detect and handle sudden faults, easily leading to production interruptions and safety accidents. Traditional methods also have limited capacity to process large amounts of data, failing to effectively analyze and mine potential information within the data, thus hindering the rapid and accurate determination of fault causes and locations, reducing the accuracy of fault prediction, and impacting fault handling efficiency. The early warning strategies of traditional methods are relatively simplistic, lacking personalization and flexibility, and cannot achieve automatic data collection, analysis, and early warning. They also cannot be adjusted and optimized in a timely manner according to actual conditions, limiting the efficiency and accuracy of the monitoring and early warning system. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method and system for monitoring and early warning of boiler faults in thermal power plants, comprising: Acquire operational monitoring data of boilers in thermal power plants, analyze the operational monitoring data, and determine abnormal operating parameters; Based on the preset prediction model, data prediction is performed on each abnormal operating parameter to obtain the corresponding abnormal prediction data. The abnormal prediction data is then analyzed to determine the abnormal characteristics. The abnormal state of the thermal power plant boiler is evaluated based on the various abnormal characteristics to obtain the abnormal state evaluation value, and the abnormal state evaluation value is used to determine whether the thermal power plant boiler has a fault. After determining that there is a fault in the boiler of the thermal power plant, the fault type of the boiler is determined based on the abnormal operating parameters. The fault level of the thermal power plant boiler is determined based on the fault type, and the early warning and response strategy for the thermal power plant boiler is determined according to the fault level.

[0005] Furthermore, the acquisition of operational monitoring data from the thermal power plant boiler, and the analysis of this data to determine abnormal operating parameters, includes: Acquire the operation monitoring data of the boiler in the thermal power plant, and divide the operation monitoring data into several groups of operation parameter data according to the parameter type; Determine the preset normal data range corresponding to each set of operating parameter data, and determine the number of data in each set of operating parameter data that exceeds the corresponding preset normal data range, as the first data quantity; The parameters corresponding to the first set of running parameter data that exceeds the corresponding preset number are identified as abnormal running parameters.

[0006] Furthermore, the step of predicting data for each abnormal operating parameter according to a preset prediction model to obtain corresponding abnormal prediction data, and analyzing the abnormal prediction data to determine abnormal characteristics, includes: The preset prediction model is obtained by extracting each operating parameter, and the operating parameter data group corresponding to each abnormal operating parameter is input into the corresponding preset prediction model. The abnormal prediction data corresponding to each abnormal operating parameter is output by each preset prediction model. The amount of data in the abnormal prediction data that exceeds the corresponding preset normal data range is determined as the second data amount, and the average value of the abnormal prediction data is calculated as the second average value. A time progress curve is constructed based on the anomaly prediction data to obtain the anomaly prediction data curve, and the change amplitude of the anomaly prediction data curve is determined. The second data volume, the second average value, and the change amplitude are determined as the abnormal characteristics of the abnormal prediction data corresponding to each abnormal operating parameter.

[0007] Furthermore, the assessment of the abnormal state of the thermal power plant boiler based on various abnormal characteristics to obtain an abnormal state assessment value includes: Determine the second and first data volumes in the abnormal features, calculate the ratio of the second data volume to the first data volume, and evaluate the ratio to obtain the quantity ratio evaluation value. Determine the operating parameter data set corresponding to each abnormal operating parameter, and calculate the average value of the operating parameter data set as the first average value; Determine the second average value among the abnormal features, calculate the ratio of the second average value to the first average value, and evaluate the ratio to obtain the average ratio evaluation value; Determine the magnitude of change in the abnormal features and evaluate the magnitude of change to obtain the magnitude of change evaluation value; The abnormal evaluation value of each abnormal operating parameter is obtained by adding the quantity ratio evaluation value, average ratio evaluation value, and change range evaluation value corresponding to each abnormal operating parameter. Determine the preset weights of each abnormal operating parameter, and then calculate the weighted sum of each abnormal operating parameter and its corresponding abnormal assessment value to obtain the abnormal state assessment value of the thermal power plant boiler.

[0008] Furthermore, the step of determining whether a thermal power plant boiler has a fault based on the abnormal state assessment value includes: Determine a pre-set evaluation threshold, and judge whether there is a fault in the boiler of the thermal power plant based on the relationship between the evaluation threshold and the abnormal state evaluation value; If the abnormal state assessment value is greater than or equal to the assessment threshold, it is determined that there is a fault in the boiler of the thermal power plant. If the abnormal state assessment value is less than the assessment threshold, it is determined that there is no fault in the boiler of the thermal power plant.

[0009] Furthermore, after determining that a fault exists in the thermal power plant boiler, the method of determining the fault type of the thermal power plant boiler based on abnormal operating parameters includes: After determining that there is a fault in the boiler of the thermal power plant, identify the abnormal operating parameters and determine the type of each abnormal operating parameter; Based on the type of each abnormal operating parameter, the fault type that matches the type of all abnormal operating parameters is matched from the fault database, and the fault type is identified as the fault type of the thermal power plant boiler.

[0010] Furthermore, determining the fault level of a thermal power plant boiler based on fault type includes: A pre-defined fault level-fault type correspondence is established, where each fault type is associated with a corresponding fault level. Obtain the fault type of the thermal power plant boiler, and based on the mapping relationship between the fault type and the fault level, select the corresponding fault level to determine the fault level of the thermal power plant boiler.

[0011] Furthermore, the method for determining the early warning and response strategy for thermal power plant boilers based on the fault level includes: Determine the level of failure of thermal power plant boilers and determine the early warning and response strategies for thermal power plant boilers based on the determination results. If the fault level is greater than the first preset value, the early warning response strategy for the thermal power plant boiler is to pop up a prominent green warning in the monitoring system and record the fault in the maintenance plan. If the fault level is greater than the second preset value, the early warning response strategy for the thermal power plant boiler is to pop up a prominent orange warning in the monitoring system and trigger an automated maintenance plan. If the fault level is greater than the third preset value, the early warning response strategy for the thermal power plant boiler is to pop up a prominent red warning message in the monitoring system and automatically start the emergency shutdown procedure. Among them, the first preset value is less than the second preset value, and the second preset value is less than the third preset value.

[0012] The present invention also provides a boiler fault monitoring and early warning system for thermal power plants, comprising: The acquisition module is used to acquire the operation monitoring data of the boiler in the thermal power plant, and to analyze the operation monitoring data to determine abnormal operating parameters; The prediction module is used to predict the data of each abnormal operating parameter according to the preset prediction model, obtain the corresponding abnormal prediction data, and analyze the abnormal prediction data to determine the abnormal characteristics. The judgment module is used to evaluate the abnormal state of the boiler in the thermal power plant based on various abnormal characteristics, obtain the abnormal state evaluation value, and determine whether the boiler in the thermal power plant has a fault based on the abnormal state evaluation value. The determination module is used to determine the fault type of the thermal power plant boiler based on abnormal operating parameters after it is determined that there is a fault in the boiler. The early warning module is used to determine the fault level of the thermal power plant boiler based on the fault type, and to determine the early warning response strategy for the thermal power plant boiler according to the fault level.

[0013] Compared with the prior art, the beneficial effects of the boiler fault monitoring and early warning method and system of the present invention are as follows: This invention, through real-time data acquisition and predictive analysis, can monitor the operating status of boilers in thermal power plants in real time, identify potential fault risks in advance, and thus formulate preventive maintenance plans to avoid accidents. This invention determines the fault type based on abnormal operating parameters, which helps to accurately locate problems, speed up troubleshooting, and reduce the impact of faults on production. This invention develops corresponding early warning and response strategies based on the fault level, which helps optimize emergency handling procedures, improve fault handling efficiency, and ensure the stability and reliability of equipment operation. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the process structure of the boiler fault monitoring and early warning method in thermal power plants in an embodiment of the present invention; Figure 2 This is a schematic diagram of the composition of a boiler fault monitoring and early warning system for thermal power plants in an embodiment of the present invention. Detailed Implementation

[0015] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the invention.

[0016] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0017] The terms “second” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with “second” or “second” may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, “multiple” means two or more.

[0018] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0019] like Figure 1 As shown in the embodiments of this application, a method for monitoring and early warning of boiler faults in a thermal power plant is provided, including: S100: acquiring operational monitoring data of the thermal power plant boiler, analyzing the operational monitoring data, and determining abnormal operating parameters; S200: performing data prediction on each abnormal operating parameter according to a preset prediction model to obtain corresponding abnormal prediction data, and analyzing the abnormal prediction data to determine abnormal characteristics; S300: evaluating the abnormal state of the thermal power plant boiler based on each abnormal characteristic to obtain an abnormal state evaluation value, and determining whether the thermal power plant boiler has a fault based on the abnormal state evaluation value; S400: after determining that the thermal power plant boiler has a fault, determining the fault type of the thermal power plant boiler based on the abnormal operating parameters; S500: determining the fault level of the thermal power plant boiler based on the fault type, and determining the early warning response strategy of the thermal power plant boiler based on the fault level.

[0020] Furthermore, through real-time data acquisition and predictive analysis, this invention can monitor the operating status of boilers in thermal power plants in real time, identify potential fault risks in advance, and thus formulate preventive maintenance plans to avoid accidents. This invention determines the fault type based on abnormal operating parameters, which helps to accurately locate problems, speed up fault troubleshooting, and reduce the impact of faults on production. This invention formulates corresponding early warning and response strategies based on fault levels, which helps to optimize emergency handling procedures, improve fault handling efficiency, and ensure the stability and reliability of equipment operation.

[0021] In an embodiment of this application, a method for monitoring and early warning of boiler faults in a thermal power plant is provided. The method involves acquiring operational monitoring data of the thermal power plant boiler and analyzing the operational monitoring data to determine abnormal operating parameters. The method includes: acquiring operational monitoring data of the thermal power plant boiler and dividing the operational monitoring data into several groups of operational parameter data according to parameter type; determining a preset normal data range corresponding to each group of operational parameter data and determining the number of data in each group of operational parameter data that exceeds the corresponding preset normal data range as a first data quantity; and determining the parameters corresponding to the operational parameter data groups whose first data quantity exceeds the corresponding preset number as abnormal operating parameters.

[0022] Specifically, this involves collecting various operational monitoring data from the boilers of thermal power plants. This data may include parameters such as temperature, pressure, flow rate, and fuel consumption. The collected operational monitoring data is then categorized according to parameter type, forming several sets of operational parameter data. Each set contains parameter data of the same type. For each set of operational parameter data, a preset normal data range needs to be determined, which is the typical value range of the parameter under normal operating conditions. For each set of operational parameter data, the number of data points exceeding the preset normal data range is checked, and these out-of-range data points are taken as the first data quantity. Parameters in the operational parameter data sets whose first data quantity exceeds the corresponding preset number are identified as abnormal operating parameters, indicating that the values ​​of these parameters deviate from the normal range. This step, by grouping various operating parameter data of thermal power plant boilers, setting normal ranges, and detecting abnormal data, achieves real-time monitoring and anomaly detection of the boiler's operating status. Timely detection of abnormal operating parameters helps maintenance personnel quickly locate problems, reduce the likelihood of malfunctions, and improve equipment reliability and safety. It provides important data for preventative maintenance of thermal power plant boilers, helping to avoid potential failures and extend equipment lifespan. Data-driven anomaly detection methods improve monitoring accuracy and efficiency, reduce the subjectivity of human judgment, and provide a scientific basis for the management and maintenance of thermal power plant boiler equipment.

[0023] In an embodiment of this application, a method for monitoring and early warning of boiler faults in a thermal power plant is provided. The method involves predicting data for each abnormal operating parameter based on a preset prediction model to obtain corresponding abnormal prediction data, and analyzing the abnormal prediction data to determine abnormal characteristics. The method includes: acquiring a preset prediction model for each operating parameter extraction, inputting the operating parameter data group corresponding to each abnormal operating parameter into the corresponding preset prediction model, and outputting the abnormal prediction data corresponding to each abnormal operating parameter from each preset prediction model; determining the amount of data in the abnormal prediction data that exceeds the corresponding preset normal data range as a second data amount, and calculating the average value of the abnormal prediction data as a second average value; constructing a time progress curve based on the abnormal prediction data to obtain an abnormal prediction data curve, and determining the change amplitude of the abnormal prediction data curve; and determining the second data amount, the second average value, and the change amplitude as the abnormal characteristics of the abnormal prediction data corresponding to each abnormal operating parameter.

[0024] Specifically, for each abnormal operating parameter, a corresponding preset prediction model is extracted and set in advance. These models can be trained based on historical data and are used to predict the range of change of the parameter. The operating parameter data set corresponding to each abnormal operating parameter is input into the corresponding preset prediction model to obtain abnormal prediction data. For each abnormal prediction data, the amount of data exceeding the preset normal data range is determined as the second data quantity, and the average value of the abnormal prediction data is calculated as the second average value. Based on the abnormal prediction data, a time progress curve can be constructed to visualize the trend of the abnormal prediction data over time, resulting in an abnormal prediction data curve. The number of data points exceeding the preset normal data range in the abnormal prediction data curve is determined as the second data quantity in the abnormal features, and the average value of the abnormal prediction data curve is calculated as the second average value in the abnormal features. At the same time, the abnormal features are described by the change amplitude of the abnormal prediction data curve. This step utilizes a pre-set prediction model to predict abnormal operating parameters, enabling more accurate identification of anomalies and helping maintenance personnel to promptly identify problems and take appropriate measures. By calculating the second data volume, second average value, and change amplitude of the anomaly prediction data, the degree and characteristics of the anomaly can be quantitatively described, facilitating a rapid assessment of its severity. Constructing anomaly prediction data curves and analyzing their trends provides a clear visual representation of the anomaly's development process, offering crucial reference for further fault diagnosis and handling. The anomaly prediction method based on the pre-set prediction model combines the advantages of data analysis and model prediction, enhancing the monitoring and prediction capabilities for anomalies in thermal power plant boilers and contributing to improved equipment reliability and safety.

[0025] In embodiments of this application, a method for monitoring and early warning of boiler faults in thermal power plants is provided. The method involves evaluating the abnormal state of the thermal power plant boiler based on various abnormal features to obtain an abnormal state evaluation value. This includes: determining a second data quantity and a first data quantity in the abnormal features; calculating the ratio of the second data quantity to the first data quantity and evaluating the ratio to obtain a quantity ratio evaluation value; determining the operating parameter data group corresponding to each abnormal operating parameter and calculating the average value of the operating parameter data group as a first average value; determining a second average value in the abnormal features; calculating the ratio of the second average value to the first average value and evaluating the ratio to obtain an average ratio evaluation value; determining the change amplitude in the abnormal features and evaluating the change amplitude to obtain a change magnitude evaluation value; adding the quantity ratio evaluation value, average ratio evaluation value, and change magnitude evaluation value corresponding to each abnormal operating parameter to obtain an abnormal evaluation value for each abnormal operating parameter; determining a preset weight for each abnormal operating parameter and weighting and adding the preset weight of each abnormal operating parameter to the corresponding abnormal evaluation value to obtain an abnormal state evaluation value for the thermal power plant boiler.

[0026] Specifically, the process involves: determining the second and first data volumes in the abnormal features; calculating the ratio of the second to the first data volume, which reflects the proportion of abnormal data in the total data volume and is used to assess the magnitude of the abnormal data; determining the second and first average values ​​in the abnormal features and calculating the ratio of the second to the first average value, which is used to assess the degree of change of the average value of the abnormal data relative to the normal situation; evaluating the magnitude of change in the abnormal features to obtain a magnitude of change assessment value, which describes the degree of change in the abnormal data; adding the quantity ratio assessment value, the average ratio assessment value, and the magnitude of change assessment value to obtain the abnormal assessment value for each abnormal operating parameter, which comprehensively considers the abnormal data volume, the change in the average value, and the magnitude of change, and is used to quantify the severity of the abnormal situation; determining the preset weights for each abnormal operating parameter, multiplying the abnormal assessment value of each abnormal operating parameter by its corresponding weight, and adding them together to obtain the abnormal state assessment value for the thermal power plant boiler, which is a comprehensive assessment of the abnormal situation of each abnormal parameter and helps to determine the severity of the overall abnormal situation. This step, by quantitatively assessing abnormal characteristics and comprehensively considering factors such as quantity, average value, and magnitude of change, can more comprehensively evaluate the severity of abnormal situations, helping maintenance personnel to quickly locate problems and take corresponding measures. Introducing preset weights allows for weighted assessment of abnormal situations based on the importance of different abnormal parameters, improving the accuracy and practicality of the assessment results. By calculating the abnormal state assessment value of thermal power plant boilers, it can provide managers with intuitive abnormal state information, guiding decision-making and optimizing maintenance strategies, further improving equipment reliability and safety.

[0027] In an embodiment of this application, a method for monitoring and early warning of boiler faults in a thermal power plant is provided. The step of determining whether a thermal power plant boiler has a fault based on an abnormal state assessment value includes: determining a pre-set assessment threshold; determining whether a thermal power plant boiler has a fault based on the relationship between the assessment threshold and the abnormal state assessment value; if the abnormal state assessment value is greater than or equal to the assessment threshold, then determining that the thermal power plant boiler has a fault; if the abnormal state assessment value is less than the assessment threshold, then determining that the thermal power plant boiler does not have a fault.

[0028] Specifically, an evaluation threshold is pre-set in the system. This threshold can be determined based on experience, historical data, or expert knowledge. This threshold serves as the standard for judging whether a thermal power plant boiler has a fault. Based on the relationship between the abnormal state evaluation value and the pre-set evaluation threshold, a judgment is made. If the abnormal state evaluation value is greater than or equal to the evaluation threshold, the thermal power plant boiler is judged to have a fault; if the abnormal state evaluation value is less than the evaluation threshold, the thermal power plant boiler is judged not to have a fault. This step, by setting the relationship between the evaluation threshold and the abnormal state evaluation value, establishes a simple and effective fault diagnosis mechanism, helping maintenance personnel to quickly and accurately determine the status of thermal power plant boilers. Different evaluation thresholds can be set according to specific circumstances to adapt to different operating environments and equipment states, improving the accuracy and flexibility of the judgment. By automatically comparing the abnormal state evaluation value with the evaluation threshold, the influence of human subjective factors on fault diagnosis is reduced, improving the objectivity and consistency of the judgment.

[0029] In an embodiment of this application, a method for monitoring and early warning of boiler faults in a thermal power plant is provided. The step of determining the fault type of the thermal power plant boiler based on abnormal operating parameters after determining that a fault exists in the thermal power plant boiler includes: determining each abnormal operating parameter and determining the type of each abnormal operating parameter after determining that a fault exists in the thermal power plant boiler; matching the fault type consistent with the type of all abnormal operating parameters from the fault database according to the type of each abnormal operating parameter, and determining the fault type as the fault type of the thermal power plant boiler.

[0030] Specifically, determining a fault in a thermal power plant boiler requires identifying the abnormal operating parameters causing the fault. For each abnormal parameter, its specific abnormality type is determined, such as excessively high, excessively low, or excessively fluctuating values. This helps to more accurately pinpoint the specific cause of the fault. The type of each abnormal operating parameter is then matched with records in the fault database to find fault types that match all abnormal parameter types. These fault types are previously recorded fault cases corresponding to the abnormality types. The matched fault types are then identified as the fault type of the thermal power plant boiler. This helps to quickly and accurately identify the problem and take appropriate maintenance measures. This step, by matching the types of abnormal operating parameters with records in the fault database, can quickly and accurately determine the fault type of the thermal power plant boiler, saving time and effort in fault diagnosis. The matching method based on historical data and experience can improve the accuracy and reliability of fault diagnosis, ensuring targeted problem-solving and reducing the risk of misdiagnosis. It helps to establish a knowledge base and experience accumulation for fault diagnosis, providing reference and guidance for similar faults in the future, improving the efficiency and quality of fault handling. By automating the matching of fault types, the influence of human subjective factors on fault diagnosis is reduced, improving the objectivity and consistency of judgment.

[0031] In an embodiment of this application, a method for monitoring and early warning of boiler faults in a thermal power plant is provided. The method for determining the fault level of the thermal power plant boiler based on the fault type includes: pre-setting a fault level-fault type correspondence, wherein the fault level-fault type correspondence is associated with a corresponding fault level for each fault type; obtaining the fault type of the thermal power plant boiler, and selecting the corresponding fault level as the fault level of the thermal power plant boiler based on the mapping relationship of the fault type in the fault level-fault type correspondence.

[0032] Specifically, a fault level-fault type mapping table is established beforehand, where each fault type corresponds to one or more fault levels. Once the fault type of the thermal power plant boiler is determined, the corresponding mapping relationship is found in the fault level-fault type mapping table, and the corresponding fault level is selected and designated as the fault level of the thermal power plant boiler. This step, by mapping fault types to corresponding fault levels, helps maintenance personnel to more clearly understand and assess the fault situation of the thermal power plant boiler, facilitating the development of appropriate handling plans and priorities. The pre-set fault level-fault type mapping relationship can be adjusted and optimized according to actual conditions, making the determination of fault levels more accurate and reasonable. It facilitates rapid and systematic fault classification and grading, improving the efficiency and quality of fault handling. By automatically mapping fault types to fault levels, the influence of human subjective factors on fault level judgment is reduced, improving the objectivity and consistency of the judgment.

[0033] In an embodiment of this application, a method for monitoring and early warning of boiler faults in a thermal power plant is provided. The method for determining an early warning response strategy for the thermal power plant boiler based on the fault level includes: determining the level of the fault in the thermal power plant boiler and determining an early warning response strategy based on the determination result; if the fault level is greater than a first preset value, the early warning response strategy is determined to be to display a prominent green warning message in the monitoring system and record the fault in the maintenance plan; if the fault level is greater than a second preset value, the early warning response strategy is determined to be to display a prominent orange warning message in the monitoring system and trigger an automated maintenance plan; if the fault level is greater than a third preset value, the early warning response strategy is determined to be to display a prominent red warning message in the monitoring system and automatically initiate an emergency shutdown procedure; wherein the first preset value is less than the second preset value, and the second preset value is less than the third preset value.

[0034] Specifically, based on the fault levels determined in the previous steps, the fault levels of the thermal power plant boilers are classified. According to the fault level, corresponding early warning response strategies are determined. If the fault level is greater than the first preset value, the early warning response strategy is to display a prominent green warning message in the monitoring system and record the fault in the maintenance plan. If the fault level is greater than the second preset value, the early warning response strategy is to display a prominent orange warning message in the monitoring system and trigger the automated maintenance plan. If the fault level is greater than the third preset value, the early warning response strategy is to display a prominent red warning message in the monitoring system and automatically initiate the emergency shutdown procedure. It should be noted that the first preset value is less than the second preset value, and the second preset value is less than the third preset value, to ensure the increasing order of the early warning levels. This step determines the early warning response strategy based on the fault level, allowing for targeted measures to be taken according to the severity of the fault, thus improving the efficiency and timeliness of fault handling. Setting different levels of early warning response strategies allows for flexible responses to various fault situations based on actual conditions, improving the system's robustness and responsiveness. Automating the triggering of early warning response strategies reduces the possibility of human delays, improving the speed and accuracy of fault response. Recording faults and triggering maintenance plans, automated maintenance plans, and emergency shutdown procedures helps maintenance personnel to understand and handle faults in a timely manner, ensuring the safe operation and production efficiency of thermal power plant boilers.

[0035] like Figure 2As shown in the embodiments of this application, a fault monitoring and early warning system for thermal power plant boilers is provided, comprising: an acquisition module for acquiring operational monitoring data of the thermal power plant boiler, analyzing the operational monitoring data, and determining abnormal operating parameters; a prediction module for predicting data for each abnormal operating parameter according to a preset prediction model, obtaining corresponding abnormal prediction data, and analyzing the abnormal prediction data to determine abnormal characteristics; a judgment module for evaluating the abnormal state of the thermal power plant boiler based on each abnormal characteristic, obtaining an abnormal state evaluation value, and determining whether the thermal power plant boiler has a fault based on the abnormal state evaluation value; a determination module for determining the fault type of the thermal power plant boiler based on the abnormal operating parameters after determining that the thermal power plant boiler has a fault; and an early warning module for determining the fault level of the thermal power plant boiler based on the fault type, and determining an early warning response strategy for the thermal power plant boiler based on the fault level.

[0036] In summary, this invention provides a method and system for monitoring and early warning of boiler faults in thermal power plants. The method includes: acquiring and analyzing operational monitoring data of the thermal power plant boiler to determine abnormal operating parameters; performing data prediction on each abnormal operating parameter according to a preset prediction model to obtain corresponding abnormal prediction data, and analyzing and determining abnormal characteristics; evaluating the abnormal state of the thermal power plant boiler based on each abnormal characteristic to obtain an abnormal state evaluation value, and determining whether the thermal power plant boiler has a fault based on the evaluation value; after determining that the thermal power plant boiler has a fault, determining the fault type based on the abnormal operating parameters; determining the fault level based on the fault type, and determining an early warning response strategy based on the fault level. This invention, by analyzing operational monitoring data to predict future changes in the boiler and evaluating and determining faults based on these changes, can effectively reduce fault risks, improve boiler safety, reliability, and operating efficiency, and increase production benefits.

[0037] Finally, it should be noted that those skilled in the art can obviously make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0038] The above description is merely one embodiment of the present invention, and should not be construed as limiting the scope of the invention. Any structural changes made based on the present invention, as long as they do not depart from the essence of the invention, should be considered as falling within the protection scope of the present invention and subject to its restrictions. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the platform described above can be referred to the corresponding processes in the foregoing platform embodiments, and will not be repeated here.

[0039] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, platform, article, or device / platform that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to those processes, platforms, articles, or devices / platforms.

[0040] The technical solutions of the present invention have been described in conjunction with the accompanying drawings and further embodiments. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to closely related technical features, and the technical solutions resulting from such changes or substitutions will all fall within the scope of protection of the present invention.

[0041] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. A method for monitoring and early warning of boiler faults in thermal power plants, characterized in that, include: Acquire operational monitoring data of boilers in thermal power plants, analyze the operational monitoring data, and determine abnormal operating parameters; Based on the preset prediction model, data prediction is performed on each abnormal operating parameter to obtain the corresponding abnormal prediction data. The abnormal prediction data is then analyzed to determine the abnormal characteristics. The abnormal state of the thermal power plant boiler is evaluated based on the various abnormal characteristics to obtain the abnormal state evaluation value, and the abnormal state evaluation value is used to determine whether the thermal power plant boiler has a fault. After determining that there is a fault in the boiler of the thermal power plant, the fault type of the boiler is determined based on the abnormal operating parameters. The fault level of the thermal power plant boiler is determined based on the fault type, and the early warning and response strategy of the thermal power plant boiler is determined according to the fault level. The acquisition of operational monitoring data from thermal power plant boilers, and the analysis of this data to determine abnormal operating parameters, include: Acquire the operation monitoring data of the boiler in the thermal power plant, and divide the operation monitoring data into several groups of operation parameter data according to the parameter type; Determine the preset normal data range corresponding to each set of operating parameter data, and determine the number of data in each set of operating parameter data that exceeds the corresponding preset normal data range, as the first data quantity; The parameters corresponding to the first set of running parameter data that exceed the corresponding preset number are identified as abnormal running parameters. The step involves predicting data for each abnormal operating parameter based on a preset prediction model to obtain corresponding abnormal prediction data, and then analyzing the abnormal prediction data to determine the abnormal characteristics, including: The preset prediction model is obtained by extracting each operating parameter, and the operating parameter data group corresponding to each abnormal operating parameter is input into the corresponding preset prediction model. The abnormal prediction data corresponding to each abnormal operating parameter is output by each preset prediction model. The amount of data in the abnormal prediction data that exceeds the corresponding preset normal data range is determined as the second data amount, and the average value of the abnormal prediction data is calculated as the second average value. A time progress curve is constructed based on the anomaly prediction data to obtain the anomaly prediction data curve, and the change amplitude of the anomaly prediction data curve is determined. The second data volume, the second average value, and the change amplitude are determined as the abnormal characteristics of the abnormal prediction data corresponding to each abnormal operating parameter; The assessment of abnormal states of thermal power plant boilers based on various abnormal characteristics to obtain abnormal state assessment values ​​includes: Determine the second and first data volumes in the abnormal features, calculate the ratio of the second data volume to the first data volume, and evaluate the ratio to obtain the quantity ratio evaluation value. Determine the operating parameter data set corresponding to each abnormal operating parameter, and calculate the average value of the operating parameter data set as the first average value; Determine the second average value among the abnormal features, calculate the ratio of the second average value to the first average value, and evaluate the ratio to obtain the average ratio evaluation value; Determine the magnitude of change in the abnormal features and evaluate the magnitude of change to obtain the magnitude of change evaluation value; The abnormal evaluation value of each abnormal operating parameter is obtained by adding the quantity ratio evaluation value, average ratio evaluation value, and change range evaluation value corresponding to each abnormal operating parameter. Determine the preset weights of each abnormal operating parameter, and then calculate the weighted sum of each abnormal operating parameter with the corresponding abnormal assessment value to obtain the abnormal state assessment value of the thermal power plant boiler. The method of determining whether a thermal power plant boiler has a fault based on anomaly assessment values ​​includes: Determine a pre-set evaluation threshold, and judge whether there is a fault in the boiler of the thermal power plant based on the relationship between the evaluation threshold and the abnormal state evaluation value; If the abnormal state assessment value is greater than or equal to the assessment threshold, it is determined that there is a fault in the boiler of the thermal power plant. If the abnormal state assessment value is less than the assessment threshold, it is determined that there is no fault in the boiler of the thermal power plant. After determining that a fault exists in the thermal power plant boiler, the method of determining the fault type of the thermal power plant boiler based on abnormal operating parameters includes: After determining that there is a fault in the boiler of the thermal power plant, identify the abnormal operating parameters and determine the type of each abnormal operating parameter; Based on the type of each abnormal operating parameter, the fault type that matches the type of all abnormal operating parameters is matched from the fault database, and the fault type is identified as the fault type of the thermal power plant boiler.

2. A method for monitoring and early warning of boiler faults in a thermal power plant according to claim 1, characterized in that, The method of determining the fault level of a thermal power plant boiler based on fault type includes: A pre-defined fault level-fault type correspondence is established, where each fault type is associated with a corresponding fault level. Obtain the fault type of the thermal power plant boiler, and based on the mapping relationship between the fault type and the fault level, select the corresponding fault level to determine the fault level of the thermal power plant boiler.

3. A method for monitoring and early warning of boiler faults in a thermal power plant according to claim 2, characterized in that, The aforementioned early warning and response strategy for determining the boilers in thermal power plants based on the fault level includes: Determine the level of failure of thermal power plant boilers and determine the early warning and response strategies for thermal power plant boilers based on the determination results. If the fault level is greater than the first preset value, the early warning response strategy for the thermal power plant boiler is to pop up a prominent green warning in the monitoring system and record the fault in the maintenance plan. If the fault level is greater than the second preset value, the early warning response strategy for the thermal power plant boiler is to pop up a prominent orange warning in the monitoring system and trigger an automated maintenance plan. If the fault level is greater than the third preset value, the early warning response strategy for the thermal power plant boiler is to pop up a prominent red warning message in the monitoring system and automatically start the emergency shutdown procedure. Among them, the first preset value is less than the second preset value, and the second preset value is less than the third preset value.

4. A boiler fault monitoring and early warning system for thermal power plants using the method described in claim 1, characterized in that, include: The acquisition module is used to acquire the operation monitoring data of the boiler in the thermal power plant, and to analyze the operation monitoring data to determine abnormal operating parameters; The prediction module is used to predict the data of each abnormal operating parameter according to the preset prediction model, obtain the corresponding abnormal prediction data, and analyze the abnormal prediction data to determine the abnormal characteristics. The judgment module is used to evaluate the abnormal state of the boiler in the thermal power plant based on various abnormal characteristics, obtain the abnormal state evaluation value, and determine whether the boiler in the thermal power plant has a fault based on the abnormal state evaluation value. The determination module is used to determine the fault type of the thermal power plant boiler based on abnormal operating parameters after it is determined that there is a fault in the boiler. The early warning module is used to determine the fault level of the thermal power plant boiler based on the fault type, and to determine the early warning response strategy for the thermal power plant boiler according to the fault level.

Citation Information

Patent Citations

  • Boiler anti-abrasion and anti-explosion online early warning system based on sensor and big data

    CN119468188A

  • Intelligent monitoring method and device for boiler state and electronic equipment

    CN119475151A