Nuclear power plant fan fault early warning method and device, electronic equipment and storage medium

Abstract

The invention provides a nuclear power plant fan fault early warning method and device, electronic equipment and a storage medium. The nuclear power plant fan fault early warning method comprises the steps of obtaining fan operation data of a target fan; predicting the working condition data of the fan through a pre-constructed fan mechanism model to obtain flow prediction data; the pre-construction process comprises the following steps: acquiring a three-dimensional fan model of a target fan; performing fluid mechanics simulation on the three-dimensional model to generate three-dimensional flow field characteristic data; carrying out order reduction processing on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model; obtaining historical operation data of a target fan, and performing parameter calibration on the one-dimensional mechanism model based on the historical operation data to obtain a fan mechanism model; comparing the fan flow data with the flow prediction data to obtain a data comparison result; and when the data comparison result meets a preset early warning condition, performing fault early warning on the target fan. Early warning can be carried out at the early stage when the draught fan breaks down, damage to the draught fan is avoided, and therefore the maintenance cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of nuclear power safety detection, and particularly to a method and device for early warning of fan failures in nuclear power plants, an electronic device, and a storage medium. Background Art

[0002] In the operation system of a nuclear power plant, the HVAC system fan is a core device for ensuring ventilation and heat dissipation of the nuclear island and conventional island, and maintaining a negative pressure environment in the radioactive control area. If the fan fails, it may lead to serious consequences such as overheating and damage of equipment, abnormal diffusion of radioactive substances, etc.

[0003] In the related art, nuclear power plants generally adopt a monitoring method based on a single physical quantity threshold. By arranging temperature sensors at the bearing parts of the fan and pressure transmitters at the inlet and outlet of the air duct, and by real-time monitoring the bearing temperature and inlet and outlet pressure difference data, an alarm is triggered when the monitored value exceeds the preset threshold. However, this technical solution can only trigger an alarm after the mechanical components have suffered substantial damage, resulting in a relatively high maintenance cost. Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. For this purpose, the present application provides a method and device for early warning of fan failures in nuclear power plants, an electronic device, and a storage medium, which can give an early warning when the fan is in the early stage of failure, avoid damage to the fan, and thus reduce the maintenance cost.

[0005] In a first aspect, an embodiment of the present application provides a method for early warning of fan failures in a nuclear power plant, the method comprising:

[0006] Obtaining the fan operation data of the target fan; wherein, the fan operation data includes fan working condition data and fan flow data;

[0007] Predicting the fan working condition data through a pre-constructed fan mechanism model to obtain flow prediction data; wherein, the pre-construction process of the fan mechanism model includes: obtaining a three-dimensional fan model of the target fan; performing a computational fluid dynamics simulation on the three-dimensional model to generate three-dimensional flow field characteristic data under various working conditions; performing a reduction order processing on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model; obtaining the historical operation data of the target fan, and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model;

[0008] Comparing the fan flow data with the flow prediction data to obtain a data comparison result;

[0009] When the data comparison result meets a preset early warning condition, giving an early warning of a failure of the target fan.

[0010] In some embodiments, obtaining the operating data of the target wind turbine includes:

[0011] Collecting a plurality of sensor data through a plurality of parameter sensors pre - arranged inside the target wind turbine; wherein, the parameter sensors include vibration sensors, temperature sensors, pressure sensors, flow sensors, and rotational speed sensors, and the sensor data includes wind turbine vibration data, wind turbine temperature data, wind turbine pressure data, wind turbine rotational speed data, and the wind turbine flow data;

[0012] According to the preset data quality verification rules, performing quality verification on the plurality of sensor data to obtain a quality verification result;

[0013] When the quality verification result indicates that the data quality is qualified, determining the plurality of sensor data as the operating data of the wind turbine; wherein, the wind turbine operating condition data includes the wind turbine vibration data, the wind turbine temperature data, the wind turbine pressure data, and the wind turbine rotational speed data.

[0014] In some embodiments, according to the preset data quality verification rules, performing quality verification on the plurality of sensor data to obtain a quality verification result includes:

[0015] For each sensor data, counting the data points in the sensor data that exceed the preset sensor range, obtaining a first data point ratio, and when the first data point ratio exceeds a first preset ratio threshold, generating a range anomaly warning; wherein each of the sensor data includes a plurality of data points;

[0016] For each sensor data, calculating the standard deviation of all data points therein, counting the data points whose deviation from the standard deviation exceeds a preset deviation threshold, obtaining a second data point ratio, and generating a data distortion warning when the second data point ratio exceeds a second preset ratio threshold;

[0017] For each sensor data, detecting the ratio of the continuous null value segment to the duration of the sensor data among the plurality of data points, and generating a data acquisition interruption warning when the ratio of the continuous length exceeds a third preset ratio threshold;

[0018] When there is any type of warning, discarding the plurality of sensor data and triggering data re - acquisition;

[0019] When there is no warning of any type, outputting the quality verification result indicating qualified data quality.

[0020] In some embodiments, performing order reduction processing on the three - dimensional flow field characteristic data to obtain a one - dimensional mechanism model includes:

[0021] Extract a key parameter set for characterizing the performance of the fan from the three-dimensional flow field characteristic data;

[0022] Convert the key parameter set into a parameter correlation relationship;

[0023] Construct the one-dimensional mechanism model based on the parameter correlation relationship; wherein, the input information of the one-dimensional mechanism model is the fan operating condition parameters, and the output information is the theoretical prediction data of the air volume.

[0024] In some embodiments, the obtaining the historical operation data of the target fan and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model includes:

[0025] Calculate the prediction deviation value between the theoretical prediction data of the air volume of the one-dimensional mechanism model and the historical operation data;

[0026] When the prediction deviation value exceeds a preset deviation threshold, trigger a calibration process:

[0027] Select the effective operating condition data within a set time window from the historical operation data as a calibration sample set;

[0028] Adjust the parameters of the one-dimensional mechanism model according to the calibration sample set so that the theoretical prediction data of the air volume output by the one-dimensional mechanism model matches the measured value of the calibration sample set;

[0029] Update the optimized parameters to the one-dimensional mechanism model to obtain the fan mechanism model.

[0030] In some embodiments, the comparing the fan flow data with the flow prediction data to obtain a data comparison result includes:

[0031] Calculate the flow deviation degree between the fan flow data and the flow prediction data;

[0032] Statistically calculate the proportion of the deviation time when the flow deviation degree continuously exceeds a preset reference deviation threshold within a preset time window;

[0033] Based on the flow deviation degree and the proportion of the deviation time, obtain the data comparison result.

[0034] In some embodiments, the when the data comparison result meets a preset warning condition, a fault warning is issued for the target fan, including:

[0035] When the flow deviation degree is in a first deviation interval and the proportion of the deviation time exceeds a first duration threshold, trigger a first-level fault warning;

[0036] When the flow deviation degree is within the second deviation range and the proportion of the deviation time exceeds the second duration threshold, a secondary fault warning is triggered;

[0037] When the flow deviation degree is within the third deviation range and the proportion of the deviation time exceeds the third duration threshold, a tertiary fault warning is triggered; wherein, the lower limit value of the third deviation range is greater than the upper limit value of the second deviation range, and the lower limit value of the second deviation range is greater than the upper limit value of the first deviation range.

[0038] In a second aspect, an embodiment of the present application provides a fault warning device for a nuclear power plant fan, including:

[0039] An acquisition module for acquiring the fan operation data of a target fan; wherein, the fan operation data includes fan operating condition data and fan flow data;

[0040] A prediction module for predicting the fan operating condition data through a pre-constructed fan mechanism model to obtain flow prediction data; wherein, the pre-construction process of the fan mechanism model includes: acquiring a three-dimensional fan model of the target fan; performing a computational fluid dynamics simulation on the three-dimensional model to generate three-dimensional flow field characteristic data under various operating conditions; performing a reduced-order processing on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model; acquiring the historical operation data of the target fan, and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model;

[0041] A comparison module for comparing the fan flow data with the flow prediction data to obtain a data comparison result;

[0042] An early warning module for performing a fault warning on the target fan when the data comparison result meets a preset warning condition.

[0043] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, it implements the nuclear power plant fan fault warning method according to any one of the first aspect embodiments of the present application.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the storage medium stores a program, and when the program is executed by a processor, it implements the nuclear power plant fan fault warning method according to any one of the first aspect embodiments of the present application.

[0045] According to the nuclear power plant fan fault warning method of the embodiments of the present application, it has at least the following beneficial effects:

[0046] The fan fault warning method for a nuclear power plant according to an embodiment of the present application includes: obtaining the fan operation data of a target fan; where the fan operation data includes fan working condition data and fan flow data; predicting the fan working condition data through a pre-constructed fan mechanism model to obtain flow prediction data; where the pre-construction process of the fan mechanism model includes: obtaining the three-dimensional fan model of the target fan; performing computational fluid dynamics simulation on the three-dimensional model to generate three-dimensional flow field characteristic data under various working conditions; performing order reduction processing on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model; obtaining the historical operation data of the target fan, and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model; comparing the fan flow data with the flow prediction data to obtain a data comparison result; when the data comparison result meets a preset warning condition, performing a fault warning on the target fan.

[0047] By obtaining the fan working condition data and fan flow data of the target fan, the present application can comprehensively collect key indicators reflecting the health status of the fan from the perspective of multi-dimensional operation parameters. Then, the flow of the working condition data is predicted through a pre-constructed fan mechanism model. This model generates three-dimensional flow field characteristic data under multiple working conditions based on the computational fluid dynamics simulation of the three-dimensional fan model, fully restoring the physical characteristics of the fan under the actual operating environment. Then, it is transformed into a one-dimensional mechanism model through order reduction processing, reducing the computational complexity. At the same time, the historical operation data is used for parameter calibration, effectively improving the adaptability and prediction accuracy of the mechanism model to the actual working conditions. Subsequently, the measured fan flow data is compared with the prediction data output by the mechanism model, thus avoiding the limitations of single-threshold judgment. When the comparison result meets the preset warning condition, it indicates that the flow parameters have deviated from the operating law characterized by the normal mechanism model. At this time, the fault warning mechanism is triggered. Compared with the prior art that relies on manual experience or single-sensor threshold warning, the embodiment of the present application realizes the dynamic modeling of the fan operating state and the early identification of abnormal characteristics through the multi-dimensional correlation analysis of integrating three-dimensional flow field simulation mechanism and measured data, can give an early warning when the fan is in the early stage of a fault, avoid the damage of the fan, and thus reduce the maintenance cost.

[0048] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0049] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the description of the embodiments in conjunction with the following drawings, where:

[0050] Figure 1 is a flowchart of an optional fan fault warning method for a nuclear power plant provided by an embodiment of the present application;

[0051] Figure 2Flow chart of another optional nuclear power plant fan fault warning method provided by an embodiment of the present application;

[0052] Figure 3 Schematic diagram of an optional axial flow fan measuring point configuration provided by an embodiment of the present application;

[0053] Figure 4 Schematic diagram of an optional centrifugal fan measuring point configuration provided by an embodiment of the present application;

[0054] Figure 5 Flow chart of another optional nuclear power plant fan fault warning method provided by an embodiment of the present application;

[0055] Figure 6 Flow chart of another optional nuclear power plant fan fault warning method provided by an embodiment of the present application;

[0056] Figure 7 Flow chart of another optional nuclear power plant fan fault warning method provided by an embodiment of the present application;

[0057] Figure 8 Schematic diagram of the fan three-dimensional CFD analysis result provided by an embodiment of the present application;

[0058] Figure 9 Schematic diagram of the fan one-dimensional model provided by an embodiment of the present application;

[0059] Figure 10 Schematic diagram of the flow - pressure curve provided by an embodiment of the present application;

[0060] Figure 11 Flow chart of another optional nuclear power plant fan fault warning method provided by an embodiment of the present application;

[0061] Figure 12 Flow chart of another optional nuclear power plant fan fault warning method provided by an embodiment of the present application;

[0062] Figure 13 Flow chart of another optional nuclear power plant fan fault warning method provided by an embodiment of the present application;;

[0063] Figure 14 Schematic diagram of the nuclear power plant fan fault warning device provided by an embodiment of the present application;

[0064] Figure 15 Schematic diagram of the hardware structure of the electronic device provided by an embodiment of the present application. Specific implementation mode

[0065] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where like or similar reference numerals denote like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary only for explaining the present application and should not be construed as limiting the present application.

[0066] In the description of the present application, the meaning of "several" is one or more, the meaning of "multiple" is more than two, and understandings such as "greater than", "less than", "exceeding", etc. do not include the present number, and understandings such as "above", "below", "within", etc. include the present number. If there is a description of "first" and "second", it is only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence of the indicated technical features.

[0067] In the description of the present application, it should be understood that for the orientation description, such as the orientation or positional relationship indicated by "upper", "lower", "left", "right", "front", "rear", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and it is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the present application.

[0068] In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0069] In the description of the present application, it should be noted that unless otherwise clearly defined, words such as "arrangement", "installation", "connection", etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above words in the present application in combination with the specific content of the technical solution. In addition, the identification of specific steps hereinafter does not represent a limitation on the step sequence and execution logic. The execution sequence and execution logic between each step should be understood and inferred with reference to the content described in the embodiment.

[0070] In the nuclear power plant operation system, the HVAC system fan is a core device for ensuring the ventilation and heat dissipation of the nuclear island and the conventional island and maintaining the negative pressure environment in the radioactive control area. If the fan fails, it may lead to serious consequences such as overheating and damage of equipment and abnormal diffusion of radioactive substances.

[0071] In the related art, nuclear power plants generally adopt a monitoring method based on a single physical quantity threshold. Temperature sensors are arranged at the bearing parts of the fan, and pressure transmitters are set at the inlet and outlet of the air duct. By monitoring the bearing temperature and the differential pressure data at the inlet and outlet in real time, an alarm is triggered when the monitored value exceeds the preset threshold. However, this technical solution can only trigger an alarm after the mechanical components have suffered substantial damage, resulting in high maintenance costs.

[0072] Based on this, the present application can comprehensively collect key indicators reflecting the health status of the fan from the perspective of multi-dimensional operating parameters by obtaining the fan operating condition data and the fan flow data of the target fan. Then, the flow rate is predicted for the operating condition data through a pre-constructed fan mechanism model. This model generates multi-condition three-dimensional flow field characteristic data based on the fluid mechanics simulation of the three-dimensional fan model, fully restoring the physical characteristics under the actual operating environment of the fan, and then being transformed into a one-dimensional mechanism model through order reduction processing to reduce the computational complexity. At the same time, historical operating data is used for parameter calibration, effectively improving the adaptability and prediction accuracy of the mechanism model to the actual operating conditions. Subsequently, the measured fan flow data is compared with the predicted data output by the mechanism model, thereby avoiding the limitations of single-threshold judgment. When the comparison result meets the preset warning condition, it indicates that the flow parameters have deviated from the operating law characterized by the normal mechanism model. At this time, a fault warning mechanism is triggered. Compared with the prior art that relies on manual experience or single-sensor threshold warning, the embodiment of the present application realizes the dynamic modeling of the fan operating state and the early identification of abnormal characteristics through the multi-dimensional correlation analysis of integrating three-dimensional flow field simulation mechanism and measured data, can give an early warning when the fan is in the early stage of a fault, avoid the damage of the fan, and thus reduce the maintenance cost.

[0073] Refer to Figure 1 , which is an optional flowchart of the nuclear power plant fan fault warning method provided by the embodiment of the present application. Figure 1 The method in Figure 1 may include but is not limited to steps 101 to 104. At the same time, it can be understood that the embodiment of the present application does not specifically limit the order of steps 101 to 104 in

[0074] Step 101, obtain the fan operating data of the target fan.

[0075] Step 102, predict the fan operating condition data through a pre-constructed fan mechanism model to obtain flow prediction data.

[0076] Step 103, compare the fan flow data with the flow prediction data to obtain a data comparison result.

[0077] Step 104, when the data comparison result meets the preset warning condition, give a fault warning for the target fan.

[0078] In step 101 of some embodiments, the target fan refers to a specific fan in a nuclear power plant that needs to be monitored for fault early warning. The fan operation data is the key information reflecting the current operation state of the fan, which includes fan operating condition data and fan flow data. The fan operating condition data covers various working condition parameters during the operation of the fan, such as working load, ambient temperature, humidity, etc. The fan flow data refers to the gas flow rate transported by the fan during operation, which is an important indicator for measuring the working efficiency and operation status of the fan. By obtaining this data, the real-time operation situation of the target fan can be comprehensively understood, providing basic data support for subsequent fault early warning analysis.

[0079] Please refer to Figure 2 , in some embodiments, step 101 may include, but is not limited to, steps 201 to 203.

[0080] Step 201, collect a plurality of sensor data through a plurality of parameter sensors pre-arranged inside the target fan.

[0081] Step 202, perform quality verification on the plurality of sensor data according to preset data quality verification rules to obtain a quality verification result.

[0082] Step 203, when the quality verification result indicates that the data quality is qualified, determine the plurality of sensor data as fan operation data.

[0083] In step 201 of some embodiments, the "parameter sensor" here refers to various sensors used to measure parameters related to the operation state of the fan, including vibration sensors, temperature sensors, pressure sensors, flow sensors, and speed sensors. These sensors are installed at key parts of the fan, such as bearings, motors, blades, etc., for real-time monitoring of the operation state of the fan. The "sensor data" collected includes fan vibration data, fan temperature data, fan pressure data, fan speed data, and fan flow data.

[0084] Please refer to Figure 3 , Figure 3 For the schematic diagram of the measuring points configuration of an axial flow fan, Table 1 details the installation positions and measurement parameters of different types of sensors on the axial flow fan.

[0085]

[0086]

[0087] Table 1

[0088] Please refer to Figure 4 , Figure 4Schematic diagram of the measuring point configuration for the centrifugal fan. Table 2 details the installation positions and measurement parameters of different types of sensors on the centrifugal fan.

[0089]

[0090]

[0091] Table 2

[0092] In step 202 of some embodiments, due to factors such as environmental interference and self - failure of the sensors, the collected data may have problems such as noise, missing values, and anomalies. Therefore, before data analysis, it is necessary to perform data quality verification. The "data quality verification rules" refer to the pre - set criteria for judging data quality. For example, verification rules such as data range, data change rate, and data integrity can be set. By comparing the sensor data with these rules, it can be determined whether the data quality is qualified.

[0093] Please refer to Figure 5 , in some embodiments, step 202 may include, but is not limited to, steps 501 to 505.

[0094] Step 501, for each sensor data, count the number of data points in the sensor data that exceed the preset sensor range, and obtain the proportion of the first data points. When the proportion of the first data points exceeds the first preset proportion threshold, generate a range anomaly warning.

[0095] Step 502, for each sensor data, calculate the standard deviation of all data points therein, count the data points whose deviation from the standard deviation exceeds the preset deviation threshold, and obtain the proportion of the second data points. When the proportion of the second data points exceeds the second preset proportion threshold, generate a data distortion warning.

[0096] Step 503, for each sensor data, detect the proportion of the continuous null value segment in multiple data points relative to the duration of the sensor data. When the proportion of the continuous length exceeds the third preset proportion threshold, generate an acquisition interruption warning.

[0097] Step 504, when there is any type of warning, discard multiple sensor data and trigger data re - acquisition.

[0098] Step 505, when there is no warning of any type, output a quality verification result indicating that the data quality is qualified.

[0099] In step 501 of some embodiments, for each sensor data, count the data points in the sensor data that exceed the preset sensor range, and obtain the first data point ratio. When the first data point ratio exceeds the first preset ratio threshold, a range anomaly warning is generated. For example, assume that the range of a certain temperature sensor is 0 - 100 degrees Celsius. If 15% of the collected data points exceed 100 degrees Celsius, and the "first preset ratio threshold" is set to 10%, then a "range anomaly warning" will be generated, indicating that the temperature sensor may be faulty or the measurement environment exceeds its applicable range.

[0100] In step 502 of some embodiments, for each sensor data, calculate the standard deviation of all data points therein, count the data points whose deviation from the standard deviation exceeds the preset deviation threshold, and obtain the second data point ratio. When the second data point ratio exceeds the second preset ratio threshold, a data distortion warning is generated. For example, assume that the standard deviation of the data sequence collected by a certain vibration sensor is 2 m / s², and the preset "deviation threshold" is set to 3 times the standard deviation (i.e., 6 m / s²). If 8% of the collected data points have a deviation from the average value exceeding 6 m / s², and the "second preset ratio threshold" is set to 5%, then a "data distortion warning" will be generated, indicating that the vibration sensor may be strongly interfered with or malfunction itself.

[0101] In step 503 of some embodiments, for each sensor data, detect the ratio of the continuous null value segment in multiple data points to the duration length of the sensor data. When the duration length ratio exceeds the third preset ratio threshold, a data acquisition interruption warning is generated. For example, assume that a certain pressure sensor should collect 600 data points in 10 minutes (1 data point per second), but in the actually collected data, there are 3 consecutive minutes (180 data points) that are all null values. Then the "duration length ratio" is 30%. If the "third preset ratio threshold" is set to 20%, then a "data acquisition interruption warning" will be generated, indicating that the pressure sensor may have a communication failure or a power problem.

[0102] In step 504 of some embodiments, if any one of the above temperature sensor, vibration sensor, or pressure sensor issues any type of warning, all the currently collected sensor data will be immediately discarded, and the data re - acquisition process will be automatically started to ensure that the data used for subsequent analysis is of high quality.

[0103] In step 505 of some embodiments, if the data of all sensors pass the above range, distortion, and interruption checks and no warning is issued, then the system will output a quality check result of "qualified data quality", indicating that the currently collected data can be safely used for subsequent fan status assessment and fault warning.

[0104] Through steps 501 to 505, the embodiments of the present application implement a multi-dimensional and practically valuable data quality verification mechanism, which can effectively detect various common problems in sensor data and take measures in a timely manner, thereby ensuring the data quality used in subsequent analysis, improving the reliability of fault warning, and reducing the operation risk of nuclear power plants.

[0105] In step 203 of some embodiments, when the quality verification result indicates that the data quality is qualified, the multiple sensor data are determined as the fan operation data. Only when the sensor data passes the quality verification and is confirmed to be of qualified quality can it be used as "fan operation data" for subsequent analysis and warning. Here, the "fan operating condition data" refers to the data used to describe the operating state of the fan, including fan vibration data, fan temperature data, fan pressure data, and fan speed data. It should be noted that the fan flow data will be compared with the flow data predicted by the mechanism model in subsequent steps, so it is distinguished from the fan operating condition data here.

[0106] In some embodiments, the collected data will be uniformly input into the distributed message queue cluster to buffer, decrypt, parse, and convert it into the platform standard data format, and then enter the data processing layer. Through real-time data stream processing technology, the data is preprocessed in real time according to the business in memory, and the processed data is shunted, and various algorithm models are called for calculation, so as to realize different data analysis services, such as high-order index monitoring, important fan performance and failure assessment, remaining life prediction, etc. Through the data service interface, it is provided to the application layer for visual display.

[0107] Through steps 201 to 203, the embodiments of the present application constitute a complete data collection and preprocessing process. By arranging multiple parameter sensors inside the fan, the operating state data of the fan can be comprehensively collected. By performing quality verification on the collected data, the accuracy and reliability of the data can be ensured. Only when the data quality is qualified can it be used as fan operation data for subsequent analysis and warning. This method can effectively improve the data quality and provide a reliable data basis for subsequent fault warning.

[0108] In step 102 of some embodiments, the "fan mechanism model" refers to a mathematical model established based on the working principle and physical laws of the fan, which can predict the flow rate of the fan according to the operating parameters of the fan (such as speed, inlet pressure, etc.). By inputting the actual fan operating condition data into the mechanism model, the theoretically predicted flow rate data can be obtained, and this flow rate prediction data represents the expected flow rate value of the fan under normal conditions.

[0109] Please refer to Figure 6, in some embodiments, the pre - construction process of the fan mechanism model may include, but is not limited to, steps 601 to 604.

[0110] Step 601, obtain the three - dimensional fan model of the target fan.

[0111] Step 602, perform a computational fluid dynamics (CFD) simulation on the three - dimensional model to generate three - dimensional flow field characteristic data under various operating conditions.

[0112] Step 603, perform a reduction order processing on the three - dimensional flow field characteristic data to obtain a one - dimensional mechanism model.

[0113] Step 604, obtain the historical operation data of the target fan, and calibrate the parameters of the one - dimensional mechanism model based on the historical operation data to obtain the fan mechanism model.

[0114] In step 601 of some embodiments, obtaining the three - dimensional fan model of the target fan means obtaining the detailed geometric structure data of the fan. This three - dimensional model can be a CAD model, a BIM model, or a digital model obtained through three - dimensional scanning, etc. The three - dimensional model contains detailed information such as the blade shape, hub size, and housing structure of the fan, and is the basis for performing computational fluid dynamics simulation.

[0115] In step 602 of some embodiments, the computational fluid dynamics (CFD) simulation uses numerical methods to solve the fluid dynamics equations and simulate the fluid flow process inside the fan. Through the CFD simulation, three - dimensional flow field characteristic data such as Figure 8 the velocity field, pressure field, and temperature field inside the fan as shown can be obtained. Here, the "various operating conditions" refer to the states of the fan under different operating parameters. For example, different rotational speeds, different wind pressures, etc. By simulating various operating conditions, the flow field characteristic data of the fan under different operating states can be obtained.

[0116] In step 603 of some embodiments, perform a reduction order processing on the three - dimensional flow field characteristic data to obtain a one - dimensional mechanism model as shown in Figure 9 The three - dimensional flow field characteristic data contains a large amount of detailed information and the computational amount is very large. In order to improve the computational efficiency, it is necessary to perform a reduction order processing on the three - dimensional data to simplify the three - dimensional model into a one - dimensional model. The methods of reduction order processing can include modal decomposition, POD (Proper Orthogonal Decomposition), etc. The one - dimensional mechanism model can describe the operating characteristics of the fan with simple mathematical formulas or curves, such as Figure 10 shown, Figure 10 a curve graph reflecting the functional relationship between the fan flow rate and the fan pressure under different operating conditions.

[0117] Please refer to Figure 7, in some embodiments, step 603 may include, but is not limited to, steps 701 to 703.

[0118] Step 701, extract a set of key parameters for characterizing the performance of the fan from the three-dimensional flow field characteristic data.

[0119] Step 702, convert the set of key parameters into parameter correlation relationships.

[0120] Step 703, construct a one-dimensional mechanism model based on the parameter correlation relationships.

[0121] In step 701 of some embodiments, it is necessary to extract a set of key parameters for characterizing the performance of the fan from the three-dimensional flow field characteristic data generated in step 602, and screen out the parameters that have the most significant impact on the performance of the fan from the flow field data. These key parameters may include the pressure distribution on the blade surface, the intensity and position of the tip vortex, the velocity deficit in the wake region, etc.

[0122] In step 702 of some embodiments, it is necessary to convert the set of key parameters extracted in step 701 into parameter correlation relationships. The parameter correlation relationship refers to the mutual influence relationship between these key parameters, which can be represented by mathematical formulas, empirical formulas, or data-driven models (such as neural networks). For example, the functional relationship between the pressure distribution on the blade surface and the wind speed, and this relationship can be described by a mathematical model. Converting the set of key parameters into parameter correlation relationships is essentially to abstract complex physical phenomena into mathematical expressions, laying a foundation for constructing a one-dimensional mechanism model.

[0123] In step 703 of some embodiments, construct a one-dimensional mechanism model based on the parameter correlation relationships obtained in step 702. This one-dimensional mechanism model takes the fan operating condition parameters as input information and the theoretical prediction data of the air volume as output information. The air volume refers to the volume of air passing through the swept area of the fan per unit time. The process of constructing the one-dimensional mechanism model is actually to integrate the parameter correlation relationships into a whole to form a mathematical model that can predict the performance of the fan (specifically referring to the air volume here) according to the input operating condition parameters. This model can be used for performance evaluation of the fan, optimization of control strategies, etc.

[0124] Through steps 701 to 703, the embodiments of the present application start from the three-dimensional flow field characteristic data, first extract the key parameter set characterizing the performance of the fan, and these parameters are the refinement and abstraction of the original flow field data. Then, the mutual relationship between these key parameters is transformed into a parameter correlation relationship, and this correlation relationship is a mathematical description of the complex physical process inside the fan. Finally, a one-dimensional mechanism model is constructed based on these parameter correlation relationships, and this model can predict the air volume according to the input fan operating conditions parameters. Therefore, the embodiments of the present application construct a one-dimensional mechanism model with high computational efficiency and capable of reflecting the key performance of the fan through the step-by-step dimensionality reduction of the three-dimensional flow field data, providing an effective tool for the online monitoring and control of the fan.

[0125] In step 604 of some embodiments, the historical operation data of the target fan is obtained, and the parameters of the one-dimensional mechanism model are calibrated based on these historical operation data to obtain the final fan mechanism model. The historical operation data includes the actual operation parameters of the fan at different time periods, such as flow rate, pressure, temperature, etc. These data provide an empirical basis for the accuracy of the model. By comparing with the one-dimensional mechanism model, the parameters in the model can be adjusted to make it better conform to the actual operation situation. The fan mechanism model calibrated with parameters can more accurately reflect the dynamic characteristics of the fan and provide a reliable prediction basis for subsequent fault warnings.

[0126] Please refer to Figure 11 , in some embodiments, step 604 may include, but is not limited to, steps 1101 to 1105.

[0127] Step 1101, calculate the prediction deviation value between the theoretically predicted air volume data of the one-dimensional mechanism model and the historical operation data.

[0128] Step 1102, when the prediction deviation value exceeds the preset deviation threshold, trigger the calibration process.

[0129] Step 1103, select the effective operating condition data within the set time window from the historical operation data as the calibration sample set.

[0130] Step 1104, adjust the parameters of the one-dimensional mechanism model according to the calibration sample set so that the theoretically predicted air volume data output by the one-dimensional mechanism model matches the measured values of the calibration sample set.

[0131] Step 1105, update the optimized parameters to the one-dimensional mechanism model to obtain the fan mechanism model.

[0132] In step 1101 of some embodiments, it is necessary to calculate the prediction deviation value between the theoretical predicted air volume data of the one-dimensional mechanism model and the historical operation data. This step is an evaluation of the prediction accuracy of the one-dimensional mechanism model. The theoretical predicted air volume data calculated by the one-dimensional mechanism model according to the operating condition parameters (such as wind speed, wind direction, etc.) in the historical operation data is compared with the actually recorded air volume value in the historical operation data, and the difference between the two is calculated, that is, the prediction deviation value. The prediction deviation value reflects the gap between the model prediction value and the actual value.

[0133] In step 1102 of some embodiments, it is judged whether the prediction deviation value calculated in step 1101 exceeds a preset deviation threshold. The preset deviation threshold is a preset allowable deviation range, which is used to judge whether the prediction accuracy of the model meets the requirements. If the prediction deviation value exceeds this threshold, it is considered that the prediction accuracy of the model is insufficient and calibration is required, so the calibration process is triggered.

[0134] In step 1103 of some embodiments, if the calibration process is triggered in step 1102, it is necessary to select the effective operating condition data within the set time window from the historical operation data as the calibration sample set. The set time window refers to the time range for selecting historical data, such as data in the most recent month or the most recent week. The effective operating condition data refers to the data during the normal operation of the fan, excluding the data under abnormal conditions such as faults and shutdowns.

[0135] In step 1104 of some embodiments, through optimization algorithms (such as gradient descent method, genetic algorithm, etc.), the adjustable parameters in the one-dimensional mechanism model can be adjusted so that the theoretical predicted air volume data calculated by the model according to the operating condition parameters in the calibration sample set matches the corresponding actually measured air volume value in the calibration sample set as much as possible, that is, the prediction error is minimized.

[0136] In step 1105 of some embodiments, the optimized parameters in step 1104 are updated to the one-dimensional mechanism model to obtain the final fan mechanism model. After parameter calibration, the parameters of the one-dimensional mechanism model are optimized, and it can more accurately reflect the actual operating characteristics of the target fan, and the final fan mechanism model that can be used in actual applications is obtained.

[0137] Through steps 1101 to 1105, the embodiments of the present application first evaluate the prediction accuracy of the one-dimensional mechanism model, and determine whether calibration is required by calculating the prediction deviation value and comparing it with a preset threshold. When the prediction accuracy is insufficient, a suitable calibration sample set is selected from the historical operation data, and the optimization algorithm is used to adjust the model parameters to make the model prediction value match the actual measurement value as much as possible. Finally, the optimized parameters are updated into the model to obtain the final fan mechanism model. Therefore, by introducing a calibration process, the embodiments of the present application ensure that the fan mechanism model can be dynamically adjusted according to the actual operation conditions, maintain the accuracy and reliability of the model, so as to better adapt to the changes in the fan operation state and improve the practical value of the model.

[0138] Through steps 601 to 604, in the pre-construction process of the fan mechanism model in the present application, an accurate three-dimensional fan model is obtained, comprehensive fluid mechanics simulations are carried out, complex data is reduced in order, and parameter calibration is carried out based on historical data, thus constructing an accurate, efficient and practical fan mechanism model. This model fully considers various operating conditions and actual historical situations of the fan operation, avoiding the problem of being out of touch with the actual operation situation that may exist in traditional models. Through this model, the operating parameters such as the flow rate of the fan can be predicted more accurately, providing a basis for subsequent fault warnings, and effectively improving the accuracy and timeliness of the fan fault warning in nuclear power plants, reducing the risks and losses caused by fan failures, and ensuring the safe and stable operation of nuclear power plants.

[0139] In step 103 of some embodiments, the "fan flow rate data" refers to the fan flow rate value obtained by actual measurement, and the "flow rate prediction data" is the theoretical flow rate value predicted by the mechanism model in step 102. By comparing the two, the deviation between the actual flow rate and the predicted flow rate can be calculated. This deviation can be expressed in various forms, such as absolute deviation, relative deviation, root mean square error, etc. The data comparison result reflects the difference between the actual operation state and the theoretical state of the fan, and is an important basis for judging whether the fan is abnormal.

[0140] Please refer to Figure 12 , in some embodiments, step 103 may include, but is not limited to, steps 1201 to 1203.

[0141] Step 1201, calculate the flow rate deviation degree between the fan flow rate data and the flow rate prediction data.

[0142] Step 1202, count the proportion of the deviation time during which the flow rate deviation degree continuously exceeds the preset reference deviation threshold within a preset time window.

[0143] Step 1203, based on the flow rate deviation degree and the proportion of the deviation time, obtain the data comparison result.

[0144] In step 1201 of some embodiments, the fan flow data refers to the actual fan flow value obtained through sensors or other measurement means, while the flow prediction data refers to the fan flow prediction value calculated through a fan mechanism model or other prediction models. The flow deviation degree is an index to measure the difference between these two values, and it can usually be obtained by calculating the relative error or absolute error between the two. This index reflects the prediction accuracy of the prediction model for the actual fan flow. For example, the fan flow data measured in real time through a flow meter installed on the fan is 1000 m² / s (cubic meters per second). At the same time, using the previously constructed fan mechanism model, based on the current operating condition parameters such as wind speed, wind direction, and pitch angle, the calculated flow prediction data is 950 m² / s. To calculate the flow deviation degree, the relative error method can be used:

[0145] Flow deviation degree = |(actual flow - predicted flow) / actual flow|

[0146] = |(1000 - 950) / 1000| * 100% = 5%

[0147] In step 1202 of some embodiments, it is necessary to count the proportion of deviation time during which the flow deviation degree continuously exceeds a preset baseline deviation threshold within a preset time window. The preset time window refers to a preset time period, such as the most recent hour, day, or week. The baseline deviation threshold is a preset allowable deviation range used to determine whether the flow deviation degree is too large. The proportion of deviation time refers to the proportion of the duration during which the flow deviation degree exceeds the baseline deviation threshold in the total time within this time window. Assume that the preset time window is set as the most recent 1 hour and the baseline deviation threshold is 10%. If the deviation between the flow predicted by the model and the actual flow exceeds 10%, it is considered that the deviation is too large. For example, within the past 1 hour (i.e., 60 minutes), the flow deviation degree is calculated once per minute. Assume that within these 60 minutes, there are 12 minutes during which the flow deviation degree exceeds 10%. Then, the proportion of deviation time is 20%, indicating that within the past 1 hour, the flow deviation predicted by the model exceeds the allowable range for 20% of the time.

[0148] In step 1203 of some embodiments, based on the flow deviation degree calculated in step 1201 and the proportion of deviation time counted in step 1202, a data comparison result is obtained. The data comparison result is a comprehensive evaluation of the consistency between the fan flow data and the flow prediction data. This result can be a qualitative conclusion (such as accurate prediction, large prediction deviation, etc.), or it can be a quantitative index. The data comparison result can be used to evaluate the performance of the prediction model, or trigger further operations, such as model calibration or fault diagnosis.

[0149] Through steps 1201 to 1203, the embodiments of the present application first calculate the flow deviation degree between the actual flow rate of the fan and the predicted flow rate by the model. This indicator reflects the accuracy of the prediction. Then, the proportion of the duration during which the deviation degree exceeds the allowable range within a certain period of time is statistically calculated. This indicator reflects the reliability of the prediction. Finally, by comprehensively considering the deviation degree and the proportion of the deviation time, the data comparison result is obtained, which is a comprehensive evaluation of the model prediction performance. Therefore, through the comprehensive evaluation of the accuracy and reliability of the prediction, the embodiments of the present application can more accurately judge the credibility of the model prediction result, provide a more reliable basis for subsequent decisions based on the model prediction result, and avoid misjudgments that may be caused by a single indicator.

[0150] In step 104 of some embodiments, when the data comparison result meets the preset warning conditions, a fault warning is issued for the target fan. The "warning conditions" refer to the thresholds or rules set based on experience or historical data for judging whether a fan needs to be warned. For example, it can be set that when the relative deviation between the actual flow rate and the predicted flow rate exceeds a certain threshold, a warning is triggered. The warning conditions can be adjusted according to factors such as the type of the fan, the operating environment, and the importance. When the data comparison result meets the warning conditions, the system will issue a warning signal to prompt the maintenance personnel to check the fan in time to avoid the occurrence of faults.

[0151] Please refer to Figure 13 , in some embodiments, step 104 may include, but is not limited to, steps 1301 to 1303.

[0152] Step 1301, when the flow deviation degree is in the first deviation interval and the proportion of the deviation time exceeds the first duration threshold, a first-level fault warning is triggered.

[0153] Step 1302, when the flow deviation degree is in the second deviation interval and the proportion of the deviation time exceeds the second duration threshold, a second-level fault warning is triggered.

[0154] Step 1303, when the flow deviation degree is in the third deviation interval and the proportion of the deviation time exceeds the third duration threshold, a third-level fault warning is triggered.

[0155] In step 1301 of some embodiments, the first deviation range refers to a preset relatively small flow deviation range, such as 2% to 5%. The first duration threshold refers to a preset time ratio threshold, such as 10%. This means that if the deviation between the flow predicted by the model and the actual flow is between 2% and 5%, and the duration of this deviation exceeds 10% of the total time, a first-level fault warning is triggered. The first-level fault warning usually indicates that there may be minor abnormalities or potential problems with the fan, which need attention, but it is not necessarily necessary to stop the machine immediately. For example, if the actual flow is 1000 m2 / s, the predicted flow is 970 m2 / s, and the flow deviation is 3%, which is within the first deviation range (2% - 5%). At the same time, within the past 1 hour, the flow deviation has been within this range for 15 minutes, and the deviation time ratio is 25% (15 / 60), exceeding the first duration threshold of 10%, then a first-level fault warning is triggered.

[0156] In step 1302 of some embodiments, when the flow deviation is within the second deviation range and the deviation time ratio exceeds the second duration threshold, a second-level fault warning is triggered. The second deviation range refers to a preset flow deviation range that is larger than the first deviation range, such as 5% to 10%. The second duration threshold can be the same as or different from the first duration threshold, such as 15%. This means that if the deviation between the flow predicted by the model and the actual flow is between 5% and 10%, and the duration of this deviation exceeds 15% of the total time, a second-level fault warning is triggered. The second-level fault warning usually indicates that there may be obvious abnormalities with the fan, which requires more detailed inspection and analysis, and some corrective measures may need to be taken. For example, if the actual flow is 1000 m2 / s, the predicted flow is 920 m2 / s, and the flow deviation is 8%, which is within the second deviation range (5% - 10%). At the same time, within the past 1 hour, the flow deviation has been within this range for 20 minutes, and the deviation time ratio is 33.3% (20 / 60), exceeding the second duration threshold of 15%, then a second-level fault warning is triggered.

[0157] In step 1303 of some embodiments, when the flow deviation degree is in the third deviation range and the proportion of the deviation time exceeds the third duration threshold, a third-level fault warning is triggered. The third deviation range refers to a preset range of flow deviation degrees that is larger than the second deviation range, for example, more than 10%. The third duration threshold can be the same as or different from the first and second duration thresholds, for example, 20%. This means that if the deviation between the flow predicted by the model and the actual flow exceeds 10%, and this deviation lasts for more than 20% of the total time, a third-level fault warning is triggered. The lower limit value of the third deviation range is greater than the upper limit value of the second deviation range, and the lower limit value of the second deviation range is greater than the upper limit value of the first deviation range, ensuring that the three deviation ranges do not overlap. The third-level fault warning usually indicates that there may be a serious fault or abnormality in the fan, and it is necessary to stop the machine immediately for inspection to avoid more serious damage. For example, if the actual flow is 1000 m2 / s, the predicted flow is 850 m2 / s, and the flow deviation degree is 15%, which is in the third deviation range (>10%). At the same time, in the past 1 hour, the flow deviation degree has been in this range for 30 minutes, and the proportion of the deviation time is 50% (30 / 60), exceeding the third duration threshold of 20%, then a third-level fault warning is triggered.

[0158] Through steps 1301 to 1303, the embodiments of the present application establish a set of hierarchical fault warning mechanisms. This mechanism divides the possible faults or abnormalities of the fan into different levels according to two key indicators: the flow deviation degree and the proportion of the deviation time. Different levels of faults correspond to different deviation ranges and duration thresholds. The greater the deviation and the longer the duration, the higher the fault level. This hierarchical warning mechanism can more precisely reflect the operating state of the fan and timely detect potential problems. By setting different levels of warnings, it can not only prevent small problems from being ignored but also avoid overreacting to minor deviations, improving the efficiency and accuracy of fault diagnosis, and helping the operation and maintenance personnel of the wind farm to take more reasonable countermeasures to ensure the safe and stable operation of the fan.

[0159] Please refer to Figure 14 , the embodiments of the present application also provide a nuclear power plant fan fault warning device 1400, which can implement the above nuclear power plant fan fault warning method, including:

[0160] An acquisition module 1401, configured to acquire the fan operation data of the target fan; wherein, the fan operation data includes fan condition data and fan flow data;

[0161] A prediction module 1402, configured to predict the fan operating condition data through a pre-built fan mechanism model to obtain flow prediction data. The pre-building process of the fan mechanism model includes: obtaining a three-dimensional fan model of the target fan; performing a computational fluid dynamics (CFD) simulation on the three-dimensional model to generate three-dimensional flow field characteristic data under various operating conditions; performing a reduction order process on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model; obtaining the historical operation data of the target fan, and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model.

[0162] A comparison module 1403, configured to compare the fan flow data with the flow prediction data to obtain a data comparison result.

[0163] An early warning module 1404, configured to perform a fault early warning on the target fan when the data comparison result meets a preset early warning condition.

[0164] According to the nuclear power plant fan fault early warning method of the embodiment of the present application, it includes: obtaining the fan operation data of the target fan. The fan operation data includes fan operating condition data and fan flow data; predicting the fan operating condition data through a pre-built fan mechanism model to obtain flow prediction data. The pre-building process of the fan mechanism model includes: obtaining a three-dimensional fan model of the target fan; performing a computational fluid dynamics (CFD) simulation on the three-dimensional model to generate three-dimensional flow field characteristic data under various operating conditions; performing a reduction order process on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model; obtaining the historical operation data of the target fan, and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model; comparing the fan flow data with the flow prediction data to obtain a data comparison result; performing a fault early warning on the target fan when the data comparison result meets a preset early warning condition.

[0165] By obtaining the fan operating condition data and fan flow data of the target fan, this application can comprehensively collect key indicators reflecting the fan health status from the perspective of multi-dimensional operating parameters. Then, the flow rate of the operating condition data is predicted through a pre-constructed fan mechanism model. This model generates multi-condition three-dimensional flow field characteristic data based on the fluid mechanics simulation of the three-dimensional fan model, fully restoring the physical characteristics under the actual operating environment of the fan. After that, it is transformed into a one-dimensional mechanism model through order reduction processing to reduce the computational complexity. At the same time, historical operating data is used for parameter calibration, effectively improving the adaptability and prediction accuracy of the mechanism model to the actual operating conditions. Subsequently, the measured fan flow data is compared with the predicted data output by the mechanism model to avoid the limitations of single-threshold judgment. When the comparison result meets the preset warning conditions, it indicates that the flow rate parameter has deviated from the operating law characterized by the normal mechanism model. At this time, the fault warning mechanism is triggered. Compared with the prior art that relies on manual experience or single-sensor threshold warning, the embodiments of this application realize dynamic modeling of the fan operating state and early identification of abnormal characteristics through the multi-dimensional correlation analysis of the three-dimensional flow field simulation mechanism and measured data, can give early warnings when the fan is in the early stage of a fault, avoid damage to the fan, and thus reduce the maintenance cost.

[0166] Refer to Figure 15 , Figure 15 schematically shows the hardware structure of an electronic device according to another embodiment. The electronic device includes:

[0167] A processor 1501, which can be implemented in ways such as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided by the embodiments of this application;

[0168] A memory 1502, which can be implemented in forms such as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1502 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1502 and are called by the processor 1501 to execute the nuclear power plant fan fault warning method of the embodiments of this application;

[0169] An input / output interface 1503, which is used to implement information input and output;

[0170] A communication interface 1504 for implementing communication interaction between this device and other devices, which can achieve communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, Wi-Fi, Bluetooth, etc.);

[0171] A bus 1505 for transmitting information between various components of the device (such as a processor 1501, a memory 1502, an input / output interface 1503, and a communication interface 1504);

[0172] Among them, the processor 1501, the memory 1502, the input / output interface 1503, and the communication interface 1504 achieve communication connections with each other inside the device through the bus 1505.

[0173] The embodiment of this application also provides a computer program product, which includes a computer program. The processor of the computer device reads and executes this computer program, so that the computer device executes the nuclear power plant fan fault warning method described above.

[0174] Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification of this disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances, so that the embodiments of this disclosure described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "contain" and any of their variations are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0175] It should be understood that in this disclosure, "at least one (item)" means one or more, and "multiple" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (one) of the following" or its similar expression refers to any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0176] It should be understood that in the description of the embodiments of the present application, the meaning of "a plurality of (or multiple)" is more than two. Understanding "greater than", "less than", "exceeding", etc. does not include the present number, and understanding "above", "below", "within", etc. includes the present number.

[0177] In several embodiments provided by the present disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0178] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0179] In addition, the functional units in each embodiment of the present disclosure can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0180] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present disclosure. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM for short), random access memories (RAM for short), magnetic disks, or optical discs that can store program codes.

[0181] It should also be understood that the various implementation manners provided in the embodiments of the present application can be combined arbitrarily to achieve different technical effects.

[0182] The above is a specific description of the embodiments of the present disclosure. However, the present disclosure is not limited to the above embodiments. Those skilled in the art can still make various equivalent deformations or substitutions without departing from the spirit of the present disclosure, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present disclosure.

Claims

1. A method for early warning of fan faults in a nuclear power plant, characterized in that, The method includes: Obtaining the fan operation data of the target fan; wherein, the fan operation data includes fan operating condition data and fan flow rate data; Predicting the fan operating condition data through a pre-constructed fan mechanism model to obtain flow rate prediction data; wherein, the pre-construction process of the fan mechanism model includes: obtaining the three-dimensional fan model of the target fan; performing fluid dynamics simulation on the three-dimensional model to generate three-dimensional flow field characteristic data under various operating conditions; performing order reduction processing on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model; obtaining the historical operation data of the target fan, and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model; Comparing the fan flow rate data with the flow rate prediction data to obtain a data comparison result; When the data comparison result meets the preset warning condition, a fault warning is given to the target fan.

2. The method for warning of nuclear power plant fan faults according to claim 1, wherein, The obtaining the fan operation data of the target fan includes: Collecting a plurality of sensor data through a plurality of parameter sensors pre-arranged inside the target fan; wherein, the parameter sensors include vibration sensors, temperature sensors, pressure sensors, flow rate sensors and speed sensors, and the sensor data includes fan vibration data, fan temperature data, fan pressure data, fan speed data and the fan flow rate data; Performing quality verification on the plurality of sensor data according to a preset data quality verification rule to obtain a quality verification result; When the quality verification result indicates that the data quality is qualified, determining the plurality of sensor data as the fan operation data; wherein, the fan operating condition data includes the fan vibration data, the fan temperature data, the fan pressure data and the fan speed data.

3. The nuclear power plant fan fault warning method according to claim 2, wherein, The performing quality verification on the plurality of sensor data according to a preset data quality verification rule to obtain a quality verification result includes: For each sensor data, counting the data points in the sensor data that exceed the preset sensor range to obtain a first data point ratio. When the first data point ratio exceeds a first preset ratio threshold, a range anomaly warning is generated; wherein, each sensor data includes a plurality of data points; For each sensor data, calculating the standard deviation of all data points therein, counting the data points with a deviation exceeding a preset deviation threshold from the standard deviation to obtain a second data point ratio. When the second data point ratio exceeds a second preset ratio threshold, a data distortion warning is generated; For each sensor data, detecting the ratio of the continuous null value segment in the plurality of data points to the duration of the sensor data. When the duration ratio exceeds a third preset ratio threshold, a data acquisition interruption warning is generated; When there is any type of warning, discarding the plurality of sensor data and triggering data re-acquisition; When there is no warning of any type, outputting the quality verification result indicating qualified data quality.

4. The nuclear power plant fan fault warning method according to claim 1, characterized in that The performing order reduction processing on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model includes: Extracting a key parameter set for characterizing the fan performance from the three-dimensional flow field characteristic data; Convert the set of key parameters into parameter correlation relationships; Construct the one-dimensional mechanism model based on the parameter correlation relationships; wherein, the input information of the one-dimensional mechanism model is the fan operating condition parameters, and the output information is the theoretical predicted air volume data.

5. The method for early warning of nuclear power plant fan faults according to claim 4, characterized in that, The obtaining the historical operation data of the target fan and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model includes: Calculate the prediction deviation value between the theoretical predicted air volume data of the one-dimensional mechanism model and the historical operation data; When the prediction deviation value exceeds the preset deviation threshold, trigger the calibration process: Select the effective operating condition data within a set time window from the historical operation data as the calibration sample set; Adjust the parameters of the one-dimensional mechanism model according to the calibration sample set so that the theoretical predicted air volume data output by the one-dimensional mechanism model matches the measured values of the calibration sample set; Update the optimized parameters to the one-dimensional mechanism model to obtain the fan mechanism model.

6. The method for early warning of fan faults in a nuclear power plant according to claim 1, wherein The comparing the fan flow data with the flow prediction data to obtain a data comparison result includes: Calculate the flow deviation degree between the fan flow data and the flow prediction data; Statistically calculate the proportion of the deviation time when the flow deviation degree continuously exceeds the preset reference deviation threshold within a preset time window; Based on the flow deviation degree and the proportion of the deviation time, obtain the data comparison result.

7. The method for early warning of nuclear power plant fan failure according to claim 6, characterized in that, When the data comparison result meets the preset warning conditions, perform a fault warning on the target fan, including: When the flow deviation degree is in the first deviation interval and the proportion of the deviation time exceeds the first duration threshold, trigger a first-level fault warning; When the flow deviation degree is in the second deviation interval and the proportion of the deviation time exceeds the second duration threshold, trigger a second-level fault warning; When the flow deviation degree is in the third deviation interval and the proportion of the deviation time exceeds the third duration threshold, trigger a third-level fault warning; wherein, the lower limit value of the third deviation interval is greater than the upper limit value of the second deviation interval, and the lower limit value of the second deviation interval is greater than the upper limit value of the first deviation interval.

8. A nuclear power plant fan fault warning device, characterized in that, Includes: An acquisition module for acquiring the fan operation data of the target fan; wherein, the fan operation data includes fan operating condition data and fan flow data; A prediction module for predicting the fan operating condition data through a pre-constructed fan mechanism model to obtain flow prediction data; wherein, the pre-construction process of the fan mechanism model includes: obtaining the three-dimensional fan model of the target fan; performing a fluid mechanics simulation on the three-dimensional model to generate three-dimensional flow field characteristic data under various operating conditions; performing a reduced-order processing on the three-dimensional flow field characteristic data to obtain a one-dimensional mechanism model; obtaining the historical operation data of the target fan and calibrating the parameters of the one-dimensional mechanism model based on the historical operation data to obtain the fan mechanism model; A comparison module for comparing the fan flow data with the flow prediction data to obtain a data comparison result; An early warning module for performing a fault warning on the target fan when the data comparison result meets the preset warning conditions.

9. An electronic device, characterized in that, Comprising: A memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, it implements the nuclear power plant fan fault warning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, and when the program is executed by the processor, it implements the nuclear power plant fan fault warning method according to any one of claims 1 to 7.

Images