Fault diagnosis method and device for heat exchanger of nuclear power plant, electronic equipment and medium

Abstract

The invention relates to the technical field of nuclear power plants, in particular to a nuclear power plant heat exchanger fault diagnosis method and device, electronic equipment and a medium. According to the nuclear power plant heat exchanger fault diagnosis method provided by the embodiment of the invention, the nuclear power plant heat exchanger needs to be detected to obtain actual working condition data; acquiring health condition data matched with the nuclear power plant heat exchanger; performing fault rough qualitative analysis on the actual working condition data according to the healthy working condition data, and determining a heat exchange operation state of the heat exchanger of the nuclear power plant; and in response to the fact that the heat exchange operation state is determined as a fault operation state, performing fault accurate qualitative analysis based on the actual working condition data, and determining a fault diagnosis type matched with the heat exchange operation state. Therefore, the diagnosis efficiency and accuracy can be further improved in the fault diagnosis process of the heat exchanger of the nuclear power plant.

Description

Technical Field

[0001] The present application relates to the technical field of nuclear power plants, and in particular to a method for diagnosing faults of heat exchangers in nuclear power plants, and a device, electronic equipment, and medium thereof. Background Art

[0002] During normal operation or accidents of nuclear power plants, the cooling water heat exchangers of nuclear power plants are used to dissipate the heat of equipment to meet the operating conditions of user equipment and ensure the safety of nuclear power plants. The parameters of the cooling water heat exchangers of nuclear power plants change constantly during normal operation, and the operating conditions are complex. Common fault diagnosis methods do not consider the impact of changes in operating conditions and are prone to diagnose incorrect results.

[0003] In the related technologies, for heat exchangers in nuclear power plants, some fault diagnosis methods rely on the completeness and richness of the preset knowledge base; some fault diagnosis methods rely on past sample data. Once the sample data deviates from the actual situation, it may affect the accuracy of the diagnosis. Some fault diagnosis methods usually require large amounts of calculation and take a long time. Based on this, how to further improve the diagnostic efficiency and accuracy in the process of fault diagnosis of heat exchangers in nuclear power plants has become a technical problem that needs to be solved urgently in the industry. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a nuclear power plant heat exchanger fault diagnosis method and its device, electronic equipment, and medium, which can further improve the diagnostic efficiency and accuracy during the process of nuclear power plant heat exchanger fault diagnosis.

[0005] A method for diagnosing a heat exchanger fault in a nuclear power plant according to a first aspect of the present application includes:

[0006] Test the heat exchangers in nuclear power plants to obtain actual operating data;

[0007] Acquiring health condition data matching the heat exchanger of the nuclear power plant;

[0008] Performing a rough qualitative fault analysis on the actual operating condition data according to the healthy operating condition data to determine the heat exchange operation state of the heat exchanger of the nuclear power plant;

[0009] In response to the heat exchange operation state being determined as a fault operation state, a fault qualitative analysis is performed based on the actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state.

[0010] According to some embodiments of the present application, in response to the heat exchange operation state being determined as a fault operation state, performing a fault qualitative analysis based on the actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state includes:

[0011] extracting leakage diagnosis parameters from the actual operating condition data;

[0012] Substituting the leakage diagnosis parameters into a preset leakage diagnosis model for real-time calculation to obtain a leakage diagnosis calculation result;

[0013] In response to the heat exchange operation state being determined as a fault operation state, determining a fault detection time of the nuclear power plant heat exchanger;

[0014] In response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying a leakage diagnosis condition, it is determined that the fault diagnosis type includes a leakage fault type.

[0015] According to some embodiments of the present application, the leakage diagnosis parameters include the hot side mass flow, the cold side mass flow, the hot side inlet and outlet enthalpy value, and the cold side inlet and outlet enthalpy value, and the leakage diagnosis parameters are substituted into a preset leakage diagnosis model for real-time calculation to obtain the leakage diagnosis calculation results, including:

[0016] Substituting the hot side mass flow, the cold side mass flow, the hot side inlet and outlet enthalpy value, and the cold side inlet and outlet enthalpy value into the corresponding leakage diagnosis model for real-time calculation to obtain a leakage factor as the leakage diagnosis calculation result;

[0017] In response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying a leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type includes:

[0018] Calculate according to the leakage factor before the fault detection moment to obtain a corresponding fluctuation variance value;

[0019] Determining the leakage diagnosis condition based on the fluctuation variance value;

[0020] In response to the leakage factor corresponding to the fault detection moment satisfying the leakage diagnosis condition, it is determined that the fault diagnosis type includes the leakage fault type.

[0021] According to some embodiments of the present application, the leakage diagnosis parameters include cold medium volume flow rate, cold medium constant pressure specific heat, medium density, hot side inlet temperature, hot side outlet temperature, cold side inlet temperature and cold side outlet temperature, and the leakage diagnosis parameters are substituted into a preset leakage diagnosis model for real-time calculation to obtain leakage diagnosis calculation results, including:

[0022] Substituting the cold medium volume flow rate, the cold medium constant pressure specific heat, the medium density, the hot side inlet temperature, the hot side outlet temperature, the cold side inlet temperature and the cold side outlet temperature into the corresponding leakage diagnosis model for real-time calculation to obtain a leakage calculation amount as the leakage diagnosis calculation result;

[0023] In response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying a leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type includes:

[0024] Acquiring a leakage diagnosis threshold, and determining the leakage diagnosis condition according to the leakage diagnosis threshold;

[0025] In response to the leakage calculation amount satisfying the leakage diagnosis condition, it is determined that the fault diagnosis type includes the leakage fault type.

[0026] According to some embodiments of the present application, the cold medium volume flow rate, the cold medium constant pressure specific heat, the medium density, the hot side inlet temperature, the hot side outlet temperature, the cold side inlet temperature and the cold side outlet temperature are substituted into the corresponding leakage diagnosis model for real-time calculation to obtain a leakage calculation amount as the leakage diagnosis calculation result, including:

[0027] constructing a first leakage diagnosis element according to the cold side outlet temperature and the cold side inlet temperature;

[0028] determining the cold medium volume flow rate as a second leakage diagnosis element;

[0029] determining the hot side outlet temperature as a third leak diagnostic element;

[0030] According to the first leakage diagnostic element, the second leakage diagnostic element and the third leakage diagnostic element, real-time calculation is performed in the leakage diagnostic model to obtain the leakage calculation amount as the leakage diagnostic calculation result.

[0031] According to some embodiments of the present application, constructing a first leakage diagnosis element according to the cold side outlet temperature and the cold side inlet temperature includes:

[0032] The cold side outlet temperature and the cold side inlet temperature are subjected to difference processing to obtain the first leakage diagnostic element.

[0033] According to some embodiments of the present application, performing real-time calculation in the leakage diagnosis model according to the first leakage diagnosis element, the second leakage diagnosis element, and the third leakage diagnosis element to obtain the leakage calculation amount as the leakage diagnosis calculation result includes:

[0034] Determine the product of the first leakage diagnosis element and the second leakage diagnosis element as a model numerator term;

[0035] Determining a model denominator term according to the first leakage diagnostic element and the third leakage diagnostic element;

[0036] The model numerator term and the model denominator term are combined to perform real-time calculation to obtain the leakage calculation amount as the leakage diagnosis calculation result.

[0037] According to some embodiments of the present application, determining a model denominator term according to the first leakage diagnostic element and the third leakage diagnostic element includes:

[0038] Determine the third leakage diagnosis element as a subtracted element of the model denominator term;

[0039] Determining one half of the first leakage diagnostic element as a subtracted element of the denominator term of the model;

[0040] The denominator term of the model is obtained by subtracting the subtracted element and the subtracting element.

[0041] According to some embodiments of the present application, in response to the heat exchange operation state being determined as a fault operation state, performing a fault qualitative analysis based on the actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state includes:

[0042] extracting scaling diagnostic parameters from the actual operating condition data;

[0043] Substituting the scaling diagnosis parameters into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results;

[0044] In response to the heat exchange operation state being determined as a fault operation state, determining a fault detection time of the nuclear power plant heat exchanger;

[0045] In response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying a scaling diagnosis condition, it is determined that the fault diagnosis type includes a scaling fault type.

[0046] According to some embodiments of the present application, the scaling diagnosis calculation result includes an actual heat transfer efficiency, and the scaling diagnosis parameters are substituted into a preset scaling diagnosis model for real-time calculation to obtain the scaling diagnosis calculation result, including:

[0047] Obtaining a clean heat transfer efficiency and a reference heat transfer efficiency of the heat exchanger of the nuclear power plant;

[0048] Substituting the clean heat transfer efficiency, the reference heat transfer efficiency and the actual heat transfer efficiency into the corresponding fouling diagnosis model for real-time calculation to obtain a fouling factor as the fouling diagnosis calculation result;

[0049] In response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying a scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type comprises:

[0050] Acquiring a scaling diagnosis threshold, and determining the scaling diagnosis condition according to the scaling diagnosis threshold;

[0051] In response to the fouling factor satisfying the fouling diagnosis condition, it is determined that the fault diagnosis type includes the fouling fault type.

[0052] According to some embodiments of the present application, the scaling diagnosis parameters include medium flow rate and flow pressure loss, and the scaling diagnosis parameters are substituted into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results, including:

[0053] Substituting the medium flow rate and the flow pressure loss into the corresponding scaling diagnosis model for real-time calculation to obtain the scaling layer thickness as the scaling diagnosis calculation result;

[0054] In response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying a scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type comprises:

[0055] Obtaining a scale layer thickness threshold, and determining the scaling diagnosis condition according to the scale layer thickness threshold;

[0056] In response to the scaling layer thickness satisfying the scaling diagnosis condition, it is determined that the fault diagnosis type includes the scaling fault type.

[0057] According to some embodiments of the present application, the scaling diagnostic parameters include a hot side mass flow rate and a cold side mass flow rate. Before substituting the scaling diagnostic parameters into a preset scaling diagnostic model for real-time calculation to obtain a scaling diagnostic calculation result, the scaling diagnostic model is also preset, specifically including:

[0058] Obtaining a hot side medium thermal conductivity sequence, a cold side medium thermal conductivity sequence, a hot side medium viscosity sequence, and a cold side medium viscosity sequence of the nuclear power plant heat exchanger;

[0059] Based on the healthy operating condition data, calculating the clean heat transfer coefficient of the heat exchanger of the nuclear power plant under clean operating conditions;

[0060] Determine the corresponding clean total thermal resistance according to the clean heat transfer coefficient;

[0061] Determine model hyperparameters according to the healthy operating condition data, the hot side medium thermal conductivity sequence, the cold side medium thermal conductivity sequence, the hot side medium viscosity sequence, the cold side medium viscosity sequence and the clean total thermal resistance;

[0062] Presetting the scaling diagnosis model according to the model hyperparameters;

[0063] Substituting the scaling diagnosis parameters into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results includes:

[0064] The hot side mass flow rate and the cold side mass flow rate are substituted into the fouling diagnosis model for real-time calculation to obtain a fouling thermal resistance value as the fouling diagnosis calculation result.

[0065] According to some embodiments of the present application, performing a rough qualitative fault analysis on the actual operating condition data according to the healthy operating condition data to determine the heat exchange operation state of the heat exchanger of the nuclear power plant includes:

[0066] Performing a multivariate state assessment on the health condition data to obtain a multidimensional health memory matrix;

[0067] Performing multivariable state assessment on the actual operating condition data to obtain a multidimensional actual operating condition matrix;

[0068] Performing a similarity comparison based on the multidimensional health memory matrix and the multidimensional actual working condition matrix to obtain a similarity comparison result;

[0069] The heat exchange operation status of the nuclear power plant heat exchanger is determined according to the similarity comparison result.

[0070] In a second aspect, an embodiment of the present application provides an electronic device, comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements a method for diagnosing a nuclear power plant heat exchanger fault as described in any one of the embodiments of the first aspect of the present application.

[0071] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement a method for diagnosing a nuclear power plant heat exchanger fault as described in any one of the embodiments of the first aspect of the present application.

[0072] The method for diagnosing a heat exchanger fault in a nuclear power plant according to the embodiment of the present application, the device, the electronic device, and the medium thereof have at least the following beneficial effects:

[0073] According to the nuclear power plant heat exchanger fault diagnosis method provided by the embodiment of the present application, it is necessary to detect the nuclear power plant heat exchanger to obtain actual operating condition data; obtain healthy operating condition data matching the nuclear power plant heat exchanger; perform a rough qualitative analysis of the actual operating condition data based on the healthy operating condition data to determine the heat exchange operation state of the nuclear power plant heat exchanger; in response to the heat exchange operation state being determined as a faulty operation state, perform a precise qualitative analysis of the fault based on the actual operating condition data to determine the fault diagnosis type matching the heat exchange operation state. In this way, the diagnostic efficiency and accuracy can be further improved in the process of fault diagnosis of nuclear power plant heat exchangers.

[0074] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0076] Figure 1 A schematic diagram of a process flow of a method for diagnosing a heat exchanger fault in a nuclear power plant provided in an embodiment of the present application;

[0077] Figure 2 Another schematic diagram of a process flow of a method for diagnosing a heat exchanger fault in a nuclear power plant provided in an embodiment of the present application;

[0078] Figure 3 Another schematic diagram of a process flow of a method for diagnosing a heat exchanger fault in a nuclear power plant provided in an embodiment of the present application;

[0079] Figure 4 Another schematic diagram of a process flow of a method for diagnosing a heat exchanger fault in a nuclear power plant provided in an embodiment of the present application;

[0080] Figure 5 Another schematic diagram of a process flow of a method for diagnosing a heat exchanger fault in a nuclear power plant provided in an embodiment of the present application;

[0081] Figure 6 Another schematic diagram of a process flow of a method for diagnosing a heat exchanger fault in a nuclear power plant provided in an embodiment of the present application;

[0082] Figure 7 Another schematic diagram of a process flow of a method for diagnosing a heat exchanger fault in a nuclear power plant provided in an embodiment of the present application;

[0083] Figure 8 Another schematic diagram of a process flow of a method for diagnosing a heat exchanger fault in a nuclear power plant provided in an embodiment of the present application;

[0084] Fig. 9An example diagram of a qualitative change trend library provided in an embodiment of the present application;

[0085] Fig.10 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0086] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0087] In the description of this application, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed", etc. are understood to exclude the number itself, and "above", "below", "within", etc. are understood to include the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0088] In the description of the present application, it should be understood that descriptions involving orientation, such as up, down, left, right, front, back, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply 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 understood as a limitation on the present application.

[0089] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0090] In the description of this application, it should be noted that, unless otherwise clearly defined, the terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in this application in combination with the specific content of the technical solution. In addition, the identification of specific steps below does not represent a limitation on the order of steps and execution logic. The execution order and execution logic between each step should be understood and inferred with reference to the contents described in the embodiment.

[0091] The equipment cooling water heat exchanger of a nuclear power plant plays an important operational and safety role. It is used to dissipate the heat of the equipment to meet the operating conditions of the user's equipment and ensure the safety of the nuclear power plant during normal operation or accidents. It should be pointed out that as a passive device, the aging, deformation, corrosion and scaling of the internal components of the heat exchanger can lead to equipment failure, resulting in unplanned shutdown of the heat exchange system, causing huge safety problems and economic losses.

[0092] There are many users on the hot side of the equipment cooling water heat exchanger in a nuclear power plant. The operation of the users changes with the operating conditions of the nuclear power plant. Therefore, the flow rate and inlet temperature on the hot side of the heat exchanger change with the operating conditions of the nuclear power plant. At the same time, the flow rate on the cold side of the equipment cooling water heat exchanger in a nuclear power plant changes with the seawater tide level, and the seawater temperature on the cold side of the heat exchanger also changes with the season. In summary, the parameters of the cold and hot sides of the equipment cooling water heat exchanger in a nuclear power plant are constantly changing during normal operation, and the operating conditions are complex. Common fault diagnosis methods do not consider the impact of changes in operating conditions and are prone to diagnose incorrect results. In addition, the operating data of the equipment cooling water heat exchanger is sent to the distributed control system in real time, and the acquisition frequency reaches the millisecond level. The amount of data collected is large, and the collected data fluctuates to a certain extent due to the influence of instruments and transmission paths.

[0093] Distributed control system (DCS) is an advanced control system used for industrial process control. It improves reliability and flexibility by distributing control functions to multiple control nodes instead of concentrating them in a central control room. In a distributed control system, each control node is able to independently perform specific control tasks while communicating and exchanging data with other nodes and the central monitoring system through the network.

[0094] Among the existing fault diagnosis technologies, there are some generally recognized methods, each of which has its own advantages, but is also accompanied by some disadvantages.

[0095] Knowledge-based methods, such as expert systems, mainly rely on the experience of experts and knowledge bases for reasoning and analysis. The advantage of this method is that it does not require the construction of complex system analysis models, and the diagnostic results are usually easy to understand and have good robustness. However, it also has obvious shortcomings, such as the difficulty in obtaining expert knowledge, and the accuracy of diagnosis is highly dependent on the completeness and richness of the knowledge base. In addition, when there are many inference rules involved, matching conflicts may occur, resulting in reduced reasoning efficiency.

[0096] The data-driven approach builds a model by analyzing historical data. The modeling process of this method is relatively simple and has good versatility and real-time performance. Machine learning algorithms are widely used in this type of method. They can use historical data to train models and perform fault diagnosis on new input data. However, this method relies on sample data after the fault and is very sensitive to data changes. Once the sample data deviates from the actual situation, it may affect the accuracy of the diagnosis. At the same time, this type of method is usually regarded as a "black box" model, and its calculation process lacks interpretability, which makes it difficult for operators to fully trust its diagnostic results.

[0097] The method based on mathematical analytical model analyzes the physical equipment by establishing a mathematical model. The advantage of this method is that it does not require fault sample data, and the physical meaning is clear and easy to explain. However, it requires the construction of a complex mathematical model, which may not be applicable to equipment with complex structures or difficult to model. At the same time, the calculation amount of this type of method is usually large, which may affect the efficiency of diagnosis.

[0098] In summary, although the existing fault diagnosis methods have performed well in some aspects, they also have some limitations, such as dependence on expert knowledge, the need for sample data, and the complexity and interpretability of the calculation process. These shortcomings may lead to reduced diagnostic efficiency and accuracy in practical applications. Therefore, researching and developing new fault diagnosis techniques to overcome these limitations remains an important research direction.

[0099] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a nuclear power plant heat exchanger fault diagnosis method and its device, electronic equipment, and medium, which can further improve the diagnostic efficiency and accuracy during the process of nuclear power plant heat exchanger fault diagnosis.

[0100] Further explanation is given below based on the accompanying drawings.

[0101] Reference Figure 1 According to the nuclear power plant heat exchanger fault diagnosis method provided by the embodiment of the present application, the method may include:

[0102] Step S101, testing a heat exchanger of a nuclear power plant to obtain actual operating condition data;

[0103] Step S102, obtaining health condition data matching the heat exchanger of the nuclear power plant;

[0104] Step S103, performing a rough qualitative analysis of the actual operating condition data according to the healthy operating condition data to determine the heat exchange operation state of the heat exchanger of the nuclear power plant;

[0105] Step S104 , in response to the heat exchange operation state being determined as a fault operation state, a fault qualitative analysis is performed based on actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state.

[0106] According to the nuclear power plant heat exchanger fault diagnosis method provided by the embodiment of the present application, it is necessary to detect the nuclear power plant heat exchanger to obtain actual operating condition data; obtain healthy operating condition data matching the nuclear power plant heat exchanger; perform a rough qualitative analysis of the actual operating condition data based on the healthy operating condition data to determine the heat exchange operation state of the nuclear power plant heat exchanger; in response to the heat exchange operation state being determined as a faulty operation state, perform a precise qualitative analysis of the fault based on the actual operating condition data to determine the fault diagnosis type matching the heat exchange operation state. In this way, the diagnostic efficiency and accuracy can be further improved in the process of fault diagnosis of nuclear power plant heat exchangers.

[0107] In step S101 of some embodiments, a heat exchanger of a nuclear power plant is tested to obtain actual operating condition data.

[0108] It should be noted that step S101 is the starting point of the nuclear power plant heat exchanger fault diagnosis process, which involves a comprehensive inspection of the heat exchanger to collect actual operating data. This step is crucial because it provides basic information for subsequent fault analysis and diagnosis. The detection process usually includes real-time detection of multiple key parameters of the heat exchanger, which may include but are not limited to the inlet and outlet temperature, pressure, flow rate of the heat exchange fluid, and the vibration and sound of the heat exchanger. In order to obtain these data, various sensors such as temperature sensors, pressure sensors and flow meters can be installed at key locations of the heat exchanger in the embodiment of the present application. These sensors can accurately measure and record the physical state of the heat exchanger during operation, thereby collecting real-time data.

[0109] In step S102 of some embodiments, healthy operating condition data matching a heat exchanger of a nuclear power plant is obtained.

[0110] It should be noted that healthy operating data refers to the operating parameters of the nuclear power plant heat exchanger under ideal or fault-free conditions, including the inlet and outlet temperatures, pressures, and flow rates of the heat exchange fluid.

[0111] In some more specific embodiments, the health status data may come from multiple sources, for example:

[0112] Design parameters: The design documentation for a heat exchanger will usually provide parameter ranges under expected operating conditions, which can be used as a reference for healthy operating conditions.

[0113] Historical data: Data extracted from the heat exchanger's past operating records, especially data collected during periods when the equipment was known to have performed well.

[0114] Similar Equipment Data: Use the data of other heat exchangers of the same model or under similar operating conditions as a reference.

[0115] Experimental data: Data obtained through laboratory tests or simulation experiments. These data are generated in a controlled environment and can provide performance indicators of the heat exchanger under ideal conditions.

[0116] It should be understood that the healthy operating condition data is the benchmark of the diagnostic process and is used to compare with the actual operating condition data to identify and evaluate whether there is a deviation or failure in the operating state of the heat exchanger. After obtaining these healthy operating condition data, some embodiments may perform detailed analysis and processing on them to ensure that they can accurately reflect the health status of the heat exchanger. This may include cleaning, standardization and parameterization of the data so that the healthy operating condition data can be effectively compared with the actual operating condition data.

[0117] In step S103 of some embodiments, a rough qualitative fault analysis is performed on the actual operating condition data according to the healthy operating condition data to determine the heat exchange operation state of the heat exchanger of the nuclear power plant.

[0118] In some embodiments, step S103 is a key step in the nuclear power plant heat exchanger fault diagnosis process, which involves using pre-acquired healthy operating condition data to perform a rough qualitative fault analysis on the actual operating condition data. The purpose of this step is to quickly assess whether the heat exchanger is in normal operation or whether there is a certain fault.

[0119] It should be pointed out that the rough qualitative analysis of faults is usually based on the comparative analysis method. In this process, the actual operating data of the heat exchanger detected in real time (such as inlet and outlet temperature, pressure, flow, etc.) are first compared with the healthy operating data. The healthy operating data represents the ideal operating parameters of the heat exchanger in the absence of faults. Therefore, actual operating data that deviates significantly from these healthy operating data may indicate that there are problems with the heat exchanger in the nuclear power plant. By analyzing these deviations, the operating status of the heat exchanger can be preliminarily judged. For example, if the actual temperature or pressure data continues to exceed the normal range defined by the healthy operating data, this may indicate that the heat exchanger has problems with blockage, scaling or other reduced heat transfer efficiency. On the contrary, if the actual operating data is consistent with the healthy operating data, it can be considered that the heat exchanger is currently operating normally.

[0120] In addition, the rough qualitative analysis of faults can also include trend analysis, which is to observe whether the change trend of operating parameters over time is consistent with the historical health trend. Sudden or unusual trend changes may be a precursor to a fault.

[0121] It should be understood that the heat exchange operating status obtained from the rough qualitative analysis of the fault provides a preliminary assessment of the operating status of the heat exchanger, which is crucial for deciding whether further detailed analysis or immediate maintenance measures are needed. If the rough qualitative analysis indicates that there may be a fault in the heat exchanger, the next step will be to conduct a more in-depth precise qualitative analysis to determine the specific type and cause of the fault. This hierarchical analysis method not only improves the efficiency of the diagnostic process, but also helps to quickly respond to potential operating problems, thereby ensuring the stable and safe operation of the nuclear power plant.

[0122] According to some embodiments of the present application, performing a rough qualitative fault analysis on the actual operating condition data according to the healthy operating condition data to determine the heat exchange operation state of the heat exchanger of the nuclear power plant includes:

[0123] Performing a multivariate state assessment on the health condition data to obtain a multidimensional health memory matrix;

[0124] Performing multivariable state assessment on the actual operating condition data to obtain a multidimensional actual operating condition matrix;

[0125] Performing a similarity comparison based on the multidimensional health memory matrix and the multidimensional actual working condition matrix to obtain a similarity comparison result;

[0126] The heat exchange operation status of the nuclear power plant heat exchanger is determined according to the similarity comparison result.

[0127] In some embodiments of the present application, the determination of the heat exchange operation state of the heat exchanger of the nuclear power plant is achieved through multivariate state assessment, which involves multi-dimensional evaluation and comparison of healthy operating data and actual operating data. First, a multidimensional health memory matrix is ​​constructed by performing multivariate state assessment on the healthy operating data. This multidimensional health memory matrix is ​​a key tool that stores various performance parameters of the heat exchanger in a normal or healthy state. These parameters may include temperature, pressure, flow, etc., which are considered to be characteristics of normal operation in historical data.

[0128] Then, a similar method is applied to the actual operating data, and a multi-dimensional actual operating matrix is ​​obtained through multi-variable state assessment. This multi-dimensional actual operating matrix reflects the current operating state of the heat exchanger in real time and provides a benchmark for comparison with the multi-dimensional health memory matrix.

[0129] A key step in the analysis process is to perform a similarity comparison, comparing the multidimensional healthy memory matrix and the multidimensional actual operating condition matrix. This step evaluates whether the current operating state of the heat exchanger deviates from the healthy baseline state by calculating the similarity or difference between the two matrices. The similarity comparison results can reveal the degree of deviation between the actual operating condition and the healthy operating condition, thus providing a basis for fault diagnosis.

[0130] Finally, based on the results of the similarity comparison, the heat exchange operation status of the nuclear power plant heat exchanger can be determined. If the similarity comparison results show that the actual operating conditions are highly consistent with the healthy operating conditions, then the heat exchanger can be considered to be operating normally. On the contrary, if there are significant differences, it indicates that there may be some problems with the heat exchanger, which requires further inspection and maintenance.

[0131] Through this multi-dimensional analysis and comparison, the operating status of the heat exchanger can be judged more accurately, and potential faults can be discovered and prevented in a timely manner, thereby improving the operating efficiency and safety of the nuclear power plant. This method not only improves the accuracy of fault diagnosis, but also helps to achieve predictive maintenance, reduce unexpected downtime, and optimize maintenance costs.

[0132] In step S104 of some embodiments, in response to the heat exchange operation state being determined as a faulty operation state, a fault qualitative analysis is performed based on actual operating condition data to determine a fault diagnosis type that matches the heat exchange operation state.

[0133] In some embodiments, step S104 is a key subsequent step in the nuclear power plant heat exchanger fault diagnosis process, specifically for those heat exchangers that are identified as potentially faulty in the rough qualitative analysis. Once the operating state of the heat exchanger is determined to be a faulty operating state, the purpose of step S104 is to perform a more detailed qualitative analysis of the fault to accurately determine the type of fault.

[0134] In this step, an in-depth qualitative fault analysis is first performed based on actual operating data. This step may include a more detailed inspection and evaluation of the operating parameters of the heat exchanger, such as temperature, pressure, flow, etc. Among them, the process of qualitative fault analysis may involve complex data processing and pattern recognition technology to identify specific patterns or trends associated with specific fault types. For example, if the inlet and outlet temperature difference of the heat exchanger increases abnormally, this may indicate a scaling or blockage problem; if the temperature difference decreases abnormally, it may indicate that the heat exchange area of ​​the heat exchanger is reduced or the heat transfer efficiency is reduced.

[0135] It should be understood that fault qualitative analysis not only relies on real-time operating data, but can also be combined with historical data and empirical knowledge to improve the accuracy of diagnosis. By comparing actual operating data with historical data, the patterns and laws of fault occurrence can be discovered. In addition, using expert systems or machine learning algorithms, matching can be performed based on existing fault case libraries to determine the most likely fault type.

[0136] Reference Figure 2 According to some embodiments of the present application, in response to the heat exchange operation state being determined as a fault operation state, step S104 performs a fault qualitative analysis based on actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state, including:

[0137] Step S201, extracting leakage diagnosis parameters from actual operating condition data;

[0138] Step S202, substituting the leakage diagnosis parameters into a preset leakage diagnosis model for real-time calculation to obtain a leakage diagnosis calculation result;

[0139] Step S203, in response to the heat exchange operation state being determined as a fault operation state, determining a fault detection time of the heat exchanger of the nuclear power plant;

[0140] Step S204 , in response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying the leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type.

[0141] Step S201 of some embodiments involves extracting leakage diagnostic parameters from actual operating condition data. These leakage diagnostic parameters are key indicators for evaluating whether a heat exchanger has leakage, and may include inlet and outlet flow rates, pressures, temperatures, etc. of the heat exchange fluid. By detecting these leakage diagnostic parameters in real time, the required data for evaluating whether a heat exchanger has leakage conditions can be collected.

[0142] In step S202 of some embodiments, these leakage diagnosis parameters are substituted into a preset leakage diagnosis model for real-time calculation. It should be noted that the leakage diagnosis model is a mathematical model established based on physical laws and empirical data, which is used to predict and evaluate the possibility and severity of leakage. By substituting actual operating condition data into the model, leakage diagnosis calculation results can be obtained, which reflect the leakage status of the heat exchanger under the current operating state.

[0143] In step S203 of some embodiments, after the operation state of the heat exchanger is determined to be a faulty operation state, a fault detection time is determined. The fault detection time refers to a specific time point during the operation of the heat exchanger when a fault is determined to exist through detection and analysis.

[0144] Step S204 of some embodiments involves evaluating the leakage diagnosis calculation result corresponding to the fault detection time to determine whether the leakage diagnosis condition is met. If the leakage diagnosis calculation result indicates that there is a leakage and meets the preset leakage diagnosis condition, then the fault diagnosis type includes a leakage fault type.

[0145] In some embodiments, the severity of the leakage and the possible leakage location can be further analyzed so as to take appropriate maintenance and repair measures.

[0146] Therefore, step S104 extracts key parameters from actual operating data through a series of refined analysis steps, applies the leakage diagnosis model, determines the fault detection moment, and finally determines the fault type. This process not only improves the accuracy of fault diagnosis, but also helps to quickly respond to and handle leakage faults, ensuring the safe and reliable operation of nuclear power plant heat exchangers.

[0147] Reference Figure 3 According to some embodiments of the present application, the leakage diagnosis parameters may include the hot side mass flow, the cold side mass flow, the hot side inlet and outlet enthalpy value, and the cold side inlet and outlet enthalpy value. Step S202 substitutes the leakage diagnosis parameters into a preset leakage diagnosis model for real-time calculation to obtain the leakage diagnosis calculation results, which may include:

[0148] Step S301, substituting the hot side mass flow, the cold side mass flow, the hot side inlet and outlet enthalpy values, and the cold side inlet and outlet enthalpy values ​​into the corresponding leakage diagnosis model for real-time calculation to obtain a leakage factor as a leakage diagnosis calculation result;

[0149] In step S204, in response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying the leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type may include:

[0150] Step S302, calculating according to the leakage factor before the fault detection time to obtain the corresponding fluctuation variance value;

[0151] Step S303, determining leakage diagnosis conditions based on the fluctuation variance value;

[0152] Step S304 , in response to the leakage factor corresponding to the fault detection moment satisfying the leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type.

[0153] In some embodiments of the present application, the selection and application of leakage diagnosis parameters are to accurately diagnose leakage faults in heat exchangers of nuclear power plants. Leakage diagnosis parameters may include mass flow rate of hot side medium, mass flow rate of cold side medium, and inlet and outlet enthalpy values ​​of hot side and cold side. These parameters comprehensively reflect the flow characteristics and heat energy transfer of fluid in the heat exchanger, and are key indicators for evaluating whether there is leakage in the heat exchanger.

[0154] In step S301 of some embodiments, these leakage diagnosis parameters are substituted into a preset leakage diagnosis model for real-time calculation to obtain a leakage factor as a leakage diagnosis calculation result. In this embodiment, the leakage diagnosis model is a mathematical model based on physical and thermodynamic principles, which can calculate the leakage factor based on the input parameters. The leakage factor is a dimensionless parameter that characterizes the severity of the leakage. By comparing the current leakage factor with the leakage factor during normal operation, the leakage condition of the heat exchanger can be evaluated. If the value of the leakage factor deviates significantly from the normal range, this may indicate the presence of a leak.

[0155] In step S302 of some embodiments, in order to determine the diagnosis condition of leakage, the fluctuation variance value of the leakage factor before the fault detection moment is calculated. The fluctuation variance value reflects the stability of the leakage factor over time. Under normal operating conditions, the fluctuation variance value of the leakage factor is usually small, and when leakage occurs, the fluctuation variance value of the leakage factor will increase.

[0156] In step S303 of some embodiments, a leakage diagnosis condition is determined based on the fluctuation variance value, wherein the leakage diagnosis condition may be that the fluctuation variance value of the leakage factor exceeds a preset threshold value, which indicates that the fluctuation of the leakage factor exceeds the normal fluctuation range, thereby confirming a leakage fault.

[0157] In step S304 of some embodiments, if the leakage factor corresponding to the fault detection time satisfies the leakage diagnosis condition, that is, the fluctuation variance value of the leakage factor exceeds the preset threshold, then the fault diagnosis type will be determined as a leakage fault type. This diagnosis result can be used to guide subsequent maintenance and repair work to solve the leakage problem and restore the normal operation of the heat exchanger.

[0158] Based on this, by selecting leakage diagnosis parameters and preset leakage diagnosis models, the embodiment of the present application can realize accurate diagnosis of leakage faults of heat exchangers in nuclear power plants. This method not only improves the accuracy of fault diagnosis, but also helps to timely discover and deal with leakage problems, thereby ensuring the safe and reliable operation of nuclear power plants.

[0159] In some more specific embodiments, the leakage diagnosis parameters may include the hot side mass flow, the cold side mass flow, the hot side inlet and outlet enthalpy values, and the cold side inlet and outlet enthalpy values, wherein:

[0160] q l : Indicates the change in fluid mass flow rate due to leakage;

[0161] q h i: represents the mass flow rate of the hot side fluid;

[0162] q ci : represents the mass flow rate of the cold side fluid;

[0163] H1 and H2: represent the enthalpy of the hot side fluid inlet and outlet respectively;

[0164] h1 and h2: represent the enthalpy values ​​of the cold side fluid inlet and outlet respectively.

[0165] Therefore, the leakage diagnosis model for calculating the leakage factor Δ can be defined as:

[0166]

[0167] In this way, the leakage diagnosis model can be used to calculate the leakage factor in real time.

[0168] Reference Figure 4 According to some embodiments of the present application, the leakage diagnosis parameters include cold medium volume flow rate, cold medium constant pressure specific heat, medium density, hot side inlet temperature, hot side outlet temperature, cold side inlet temperature and cold side outlet temperature. Step S202 substitutes the leakage diagnosis parameters into a preset leakage diagnosis model for real-time calculation to obtain leakage diagnosis calculation results, which may include:

[0169] Step S401, substituting the cold medium volume flow rate, the cold medium constant pressure specific heat, the medium density, the hot side inlet temperature, the hot side outlet temperature, the cold side inlet temperature and the cold side outlet temperature into the corresponding leakage diagnosis model for real-time calculation to obtain a leakage calculation amount as a leakage diagnosis calculation result;

[0170] In step S204, in response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying the leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type may include:

[0171] Step S402, obtaining a leakage diagnosis threshold, and determining a leakage diagnosis condition according to the leakage diagnosis threshold;

[0172] Step S403 , in response to the leakage calculation amount satisfying the leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type.

[0173] In some embodiments of the present application, the leakage diagnosis process is implemented by comprehensively analyzing a series of leakage diagnosis parameters, which may include the volume flow rate of the cold medium, the constant pressure specific heat, the medium density, and the inlet and outlet temperatures of the hot side and the cold side.

[0174] In step S401 of some embodiments, the leakage diagnosis parameters are substituted into a preset leakage diagnosis model in real time for calculation. In this embodiment, the leakage diagnosis model is a mathematical model based on physical and thermodynamic principles, which can calculate the leakage calculation amount according to the input parameters. The leakage calculation amount is a quantitative indicator to measure the severity of the leakage, which can include changes in mass flow, estimates of energy loss, or other physical quantities related to the leakage.

[0175] In step S402 of some embodiments, in order to determine the diagnosis condition of leakage, it is necessary to obtain a leakage diagnosis threshold. The leakage diagnosis threshold is pre-set according to the design parameters, operating experience and historical data of the heat exchanger, and it defines the acceptable range of the leakage calculation amount. When the leakage calculation amount exceeds this threshold, it indicates that the heat exchanger may have a leak.

[0176] In step S403 of some embodiments, the leakage diagnosis condition is determined based on the leakage calculation amount and the leakage diagnosis threshold. If the leakage calculation amount corresponding to the fault detection time exceeds the leakage diagnosis threshold, that is, the leakage diagnosis condition is met, then the fault diagnosis type will be determined as a leakage fault type. This diagnosis result will guide subsequent maintenance and repair work to solve the leakage problem and restore the normal operation of the heat exchanger.

[0177] In some more specific embodiments, the leakage diagnosis parameters may include cold medium volume flow rate, cold medium constant pressure specific heat, medium density, hot side inlet temperature, hot side outlet temperature, cold side inlet temperature and cold side outlet temperature, wherein:

[0178] V c is the volume flow rate of cold medium;

[0179] c is the specific heat of the cold medium at constant pressure;

[0180] ρ is the fluid density;

[0181] t hi is the hot side inlet temperature;

[0182] t ho is the hot side outlet temperature;

[0183] t ci is the cold side inlet temperature;

[0184] t co is the cold side outlet temperature;

[0185] According to some embodiments of the present application, a first leakage diagnostic element is constructed according to the cold side outlet temperature and the cold side inlet temperature. According to some embodiments of the present application, a first leakage diagnostic element is constructed according to the cold side outlet temperature and the cold side inlet temperature, including:

[0186] The cold side outlet temperature and the cold side inlet temperature are subtracted to obtain the first leakage diagnosis element, that is, (Δt co -Δt ci );

[0187] The cold medium volume flow is determined as the second leakage diagnosis element, namely V c ;

[0188] The hot side outlet temperature is determined as the third leak diagnosis element, that is, t ho ;

[0189] According to the first leakage diagnosis element (Δt co -Δt ci ), the second leak diagnostic element V c and the third leak diagnostic element t ho , perform real-time calculation in the leakage diagnosis model to obtain the leakage calculation amount as the leakage diagnosis calculation result. Specifically, it may include:

[0190] The first leakage diagnosis element (Δt co -Δt ci ) and the second leak diagnostic element V c The product of is determined as the model molecule term, that is, V c (Δt co -Δt ci );

[0191] Determining a model denominator item according to the first leakage diagnostic element and the third leakage diagnostic element; wherein, according to some embodiments of the present application, determining the model denominator item according to the first leakage diagnostic element and the third leakage diagnostic element may include:

[0192] The third leakage diagnosis element is determined as the subtracted element t of the denominator of the model ho ;

[0193] Determine half of the first leak diagnostic element as the minus element of the model denominator term

[0194] By subtracting the subtracted element and the subtracting element, we get the denominator of the model, that is,

[0195] The numerator and denominator of the model are calculated in real time to obtain the leakage calculation amount as the leakage diagnosis calculation result. Therefore, the leakage diagnosis model for calculating the leakage calculation amount x can be defined as:

[0196]

[0197] In this way, the leakage diagnosis model can be used to determine that the fault diagnosis type includes the leakage fault type.

[0198] In some other more specific embodiments, the leakage diagnosis calculation results may also be determined by other methods. For example, using the heat transfer efficiency ε and the leakage factor △, a combined model is established to diagnose the leakage fault of the heat exchanger:

[0199] Defining variables and Among them, ε1 represents the heat transfer efficiency of the hot side fluid at the current detection moment, ε0 represents the benchmark heat transfer efficiency of the hot side fluid, Δ1 represents the leakage factor of the hot side fluid at the current detection moment, Δ0 represents the benchmark leakage factor of the hot side fluid, and σ represents the standard deviation corresponding to the calculated heat transfer efficiency.

[0200] According to the weights β1 and β2 of the above two parameters in judging the performance of the heat exchanger, a failure coefficient λ defined as the failure coefficient of the heat exchanger is calculated:

[0201] λ=α1β1+α2β2

[0202] The stable value range of the fault coefficient λ before leakage is extracted from the actual working condition data, and the fault coefficient λ value is calculated from the data after leakage as the leakage diagnosis parameter. According to the change of the fault coefficient λ, the leakage of the heat exchanger and the corresponding leakage degree can be confirmed.

[0203] Based on the embodiment of the present application shown in step S401 to step S403, the embodiment of the present application can realize accurate diagnosis of leakage faults of heat exchangers in nuclear power plants by calculating leakage diagnosis parameters in real time and comparing them with leakage diagnosis thresholds. This method not only improves the accuracy of fault diagnosis, but also helps to timely discover and deal with leakage problems, thereby ensuring the safe and reliable operation of nuclear power plants. Through this refined diagnosis process, false positives and false negatives can be effectively reduced, and the maintenance efficiency of heat exchangers can be improved.

[0204] Reference Figure 5 According to some embodiments of the present application, in response to the heat exchange operation state being determined as a fault operation state, step S104 performs a fault qualitative analysis based on actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state, which may include:

[0205] Step S501, extracting scaling diagnosis parameters from actual operating condition data;

[0206] Step S502, substituting the scaling diagnosis parameters into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results;

[0207] Step S503, in response to the heat exchange operation state being determined as a fault operation state, determining a fault detection time of the heat exchanger of the nuclear power plant;

[0208] Step S504: in response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying the scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type.

[0209] In step S501 of some embodiments, scaling diagnostic parameters are extracted from the actual operating condition data detected in real time. These scaling diagnostic parameters may include the inlet and outlet temperature, pressure, flow rate, pH value, conductivity or other chemical and physical properties related to scaling formation of the fluid. These data provide necessary input information for subsequent scaling analysis.

[0210] In step S502 of some embodiments, the extracted fouling diagnosis parameters are substituted into a preset fouling diagnosis model for real-time calculation. This fouling diagnosis model can be developed based on physical and chemical principles, historical data, empirical formulas or machine learning algorithms to predict and evaluate the possibility and degree of fouling conditions. Through this fouling diagnosis model, fouling diagnosis calculation results can be calculated, and these fouling diagnosis calculation results reflect the fouling status of the heat exchanger under the current operating conditions.

[0211] Step S503 of some embodiments involves determining the fault detection moment of the heat exchanger of the nuclear power plant, that is, during the operation of the heat exchanger, the specific time point at which the fault is determined through detection and analysis, that is, the fault detection moment. This fault detection moment is crucial for timely response and handling of the fault, because it marks the specific moment when the fault occurs and is recognized by the system.

[0212] In step S504 of some embodiments, based on the scaling diagnosis calculation results corresponding to the fault detection time, it is evaluated whether these data meet the preset scaling diagnosis conditions. These scaling diagnosis conditions may include that the scaling diagnosis calculation results exceed the threshold value of the normal range, or show characteristics similar to historical scaling events. If the scaling diagnosis calculation results meet these scaling diagnosis conditions, it means that the fault diagnosis type includes the scaling fault type.

[0213] The embodiment of the present application shown by steps S501 to S504 can accurately diagnose the scaling fault of the heat exchanger, thereby helping to take timely measures to clean or prevent scaling and ensure the efficient and stable operation of the heat exchanger. This refined fault diagnosis method not only improves the efficiency of fault handling, but also helps to reduce performance degradation and potential safety risks caused by scaling.

[0214] Reference Figure 6 According to some embodiments of the present application, the scaling diagnosis calculation result includes the actual heat transfer efficiency. Step S502 substitutes the scaling diagnosis parameter into the preset scaling diagnosis model for real-time calculation to obtain the scaling diagnosis calculation result, which may include:

[0215] Step S601, obtaining the clean heat transfer efficiency and reference heat transfer efficiency of the heat exchanger of the nuclear power plant;

[0216] Step S602, substituting the clean heat transfer efficiency, the reference heat transfer efficiency and the actual heat transfer efficiency into the corresponding fouling diagnosis model for real-time calculation to obtain a fouling factor as a fouling diagnosis calculation result;

[0217] In step S504, in response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying the scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type may include:

[0218] Step S603, obtaining a scaling diagnosis threshold, and determining a scaling diagnosis condition according to the scaling diagnosis threshold;

[0219] Step S604: in response to the fouling factor satisfying the fouling diagnosis condition, determining that the fault diagnosis type includes a fouling fault type.

[0220] In some embodiments of the present application, fouling diagnosis is a key process that identifies whether fouling occurs by analyzing the heat transfer efficiency of the heat exchanger. The diagnostic calculation results include the actual heat transfer efficiency, which is an important indicator for measuring the performance of the heat exchanger.

[0221] In step S601 of some embodiments, it is necessary to obtain the clean heat transfer efficiency and reference heat transfer efficiency of the heat exchanger in the nuclear power plant. The clean heat transfer efficiency refers to the heat transfer efficiency of the heat exchanger without the influence of fouling, which is usually obtained based on design parameters or test results under known fouling-free conditions. The reference heat transfer efficiency is set based on historical data or operating data of similar equipment, and represents the heat transfer efficiency that the heat exchanger should achieve under specific conditions.

[0222] In step S602 of some embodiments, the obtained clean heat transfer efficiency, reference heat transfer efficiency and actual heat transfer efficiency monitored in real time are substituted into the fouling diagnosis model for real-time calculation to obtain a fouling factor as a fouling diagnosis calculation result. This fouling diagnosis model can use a physical or empirical formula to evaluate the impact of fouling on heat transfer efficiency. Through this calculation, a fouling factor as a fouling diagnosis calculation result can be obtained, which is a quantitative indicator of the degree of fouling of the heat exchanger.

[0223] In step S603 of some embodiments, in order to diagnose the fouling fault, it is necessary to obtain a fouling diagnosis threshold. This fouling diagnosis threshold can be set based on experience, historical fault data or expert knowledge, and is used to determine whether the fouling factor exceeds a normal range. It should be understood that the fouling diagnosis condition may include the fouling factor exceeding a specific threshold, which indicates that the heat transfer efficiency of the heat exchanger has been significantly affected.

[0224] In step S604 of some embodiments, in response to the fouling factor satisfying the fouling diagnosis condition, determining that the fault diagnosis type includes a fouling fault type. If the fouling factor exceeds a preset fouling diagnosis threshold, then it can be determined that the fault diagnosis type includes a fouling fault type. This means that the heat transfer efficiency of the heat exchanger is reduced due to fouling, and corresponding cleaning or maintenance measures need to be taken.

[0225] In some more specific embodiments, the fouling diagnosis calculation results include actual heat transfer efficiency, and in the process of substituting the fouling diagnosis parameters into the preset fouling diagnosis model for real-time calculation, it is necessary to obtain the clean heat transfer efficiency and reference heat transfer efficiency of the nuclear power plant heat exchanger, wherein:

[0226] ε clean It is the heat transfer efficiency when the heat transfer surface is completely clean, that is, the clean heat transfer efficiency;

[0227] ε dirt It is the heat transfer efficiency that the heat exchanger should achieve under specific conditions, that is, the reference heat transfer efficiency;

[0228] ε is the actual heat transfer efficiency.

[0229] Therefore, the fouling diagnostic model for calculating the fouling factor f can be defined as:

[0230]

[0231] In this way, the fouling factor can be calculated in real time using this fouling diagnostic model.

[0232] Through the embodiment of the present application shown in step S601 to step S604, by real-time calculation and analysis of heat transfer efficiency and comparison with a preset fouling diagnosis threshold, the embodiment of the present application can accurately diagnose the fouling fault of the heat exchanger. This method not only improves the accuracy of fault diagnosis, but also helps to take timely measures to reduce performance degradation and potential safety risks caused by fouling, and ensure the stable and efficient operation of the heat exchanger in the nuclear power plant.

[0233] Reference Figure 7 According to some embodiments of the present application, the scaling diagnosis parameters include medium flow rate and flow pressure loss. Step S502 substitutes the scaling diagnosis parameters into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results, which may include:

[0234] Step S701, substituting the medium flow rate and flow pressure loss into the corresponding scaling diagnosis model for real-time calculation to obtain the scaling layer thickness as the scaling diagnosis calculation result;

[0235] In step S504, in response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying the scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type may include:

[0236] Step S702, obtaining a scale layer thickness threshold, and determining a scaling diagnosis condition according to the scale layer thickness threshold;

[0237] Step S703: in response to the scaling layer thickness satisfying the scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type.

[0238] In some embodiments of the present application, scaling diagnosis is a key step for evaluating and determining whether a heat exchanger has scaling problems. This process involves specific scaling diagnostic parameters, including medium flow rate and flow pressure loss, which are important indicators for analyzing scaling conditions inside a heat exchanger.

[0239] In step S701 of some embodiments, the medium flow rate and flow pressure loss are substituted into a predetermined fouling diagnosis model for real-time calculation. This fouling diagnosis model can estimate the thickness of the fouling layer by analyzing the changes in flow rate and pressure drop based on the principles of fluid mechanics and heat transfer. Among them, the thickness of the fouling layer is a direct indicator of the degree of fouling, which reflects the amount of fouling accumulated on the heat transfer surface of the heat exchanger. Through this calculation, the thickness of the fouling layer can be obtained as the fouling diagnosis calculation result, which provides an important basis for subsequent fault diagnosis.

[0240] In step S702 of some embodiments, in order to diagnose the scaling fault, it is necessary to obtain a scale thickness threshold. This scale thickness threshold can be set based on experience, historical data or expert knowledge, and is used to determine whether the scale thickness exceeds a normal range. The scaling diagnosis condition may include that the scale thickness exceeds a specific scale thickness threshold, which indicates that the heat transfer efficiency of the heat exchanger has been significantly affected and needs to be cleaned or maintained.

[0241] In step S703 of some embodiments, in response to the scaling thickness satisfying the scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type. If the scaling thickness exceeds a preset scaling thickness threshold, then it can be determined that the fault diagnosis type includes a scaling fault type. This means that the performance degradation of the heat exchanger is mainly caused by scaling, and corresponding measures need to be taken to remove the scaling and restore the normal operation of the heat exchanger.

[0242] In some specific practical examples, scaling diagnostic parameters include medium flow rate and flow pressure loss. In order to quantitatively analyze the impact of scaling, a functional relationship between the scale layer thickness and the flow pressure loss and medium flow rate can be established.

[0243] It should be pointed out that the formation of scale will add additional thermal resistance to the heat transfer surface of the heat exchanger, which not only reduces the heat transfer efficiency, but also may lead to an increase in the pressure drop of the fluid flow. Flow pressure loss refers to the pressure drop caused by friction and local resistance when the fluid passes through the heat exchanger. This pressure drop is related to the flow rate of the fluid, the geometry of the pipe, and the thickness of the scale layer on the heat transfer surface. Further, using the established functional relationship, the monitored flow pressure loss and medium flow rate are substituted into the established functional relationship to calculate the thickness of the scale layer.

[0244] In this way, the fouling of heat exchangers can be effectively monitored and controlled, reducing energy consumption, extending the service life of the equipment, and ensuring the efficiency and reliability of the heat exchange process.

[0245] Through the embodiment of the present application shown in step S701 to step S703, by calculating the medium flow rate and flow pressure loss in real time and substituting them into the scaling diagnosis model, the embodiment of the present application can accurately diagnose the scaling fault of the heat exchanger. This method not only improves the accuracy of fault diagnosis, but also helps to take timely measures to reduce the performance degradation and potential safety risks caused by scaling, and ensure the stable and efficient operation of the heat exchanger. Through this refined diagnostic process, the performance of the heat exchanger can be effectively managed and optimized, and the service life of the equipment can be extended.

[0246] Reference Figure 8 According to some embodiments of the present application, the scaling diagnosis parameters include the hot side mass flow rate and the cold side mass flow rate. In step S502, the scaling diagnosis parameters are substituted into a preset scaling diagnosis model for real-time calculation. Before obtaining the scaling diagnosis calculation result, the scaling diagnosis model is preset, specifically including:

[0247] Step S801, obtaining a hot side medium thermal conductivity sequence, a cold side medium thermal conductivity sequence, a hot side medium viscosity sequence, and a cold side medium viscosity sequence of a nuclear power plant heat exchanger;

[0248] Step S802, calculating the clean heat transfer coefficient of the heat exchanger of the nuclear power plant under clean conditions based on the healthy condition data;

[0249] Step S803, determining the corresponding clean total thermal resistance according to the clean heat transfer coefficient;

[0250] Step S804, determining model hyperparameters according to the healthy working condition data, the hot side medium thermal conductivity sequence, the cold side medium thermal conductivity sequence, the hot side medium viscosity sequence, the cold side medium viscosity sequence and the clean total thermal resistance;

[0251] Step S805, presetting the scaling diagnosis model according to the model hyperparameters;

[0252] In step S502, the scaling diagnosis parameters are substituted into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results, which may include:

[0253] Step S806: Substitute the hot side mass flow rate and the cold side mass flow rate into the fouling diagnosis model for real-time calculation to obtain a fouling thermal resistance value as a fouling diagnosis calculation result.

[0254] In some embodiments of the present application, fouling diagnosis is a comprehensive process that includes not only real-time calculation of fouling diagnostic parameters, but also careful presetting of fouling diagnostic models. The purpose of this process is to ensure that the diagnostic model can accurately reflect the fouling status of the heat exchanger under actual operating conditions.

[0255] In step S801 of some embodiments, it is necessary to obtain the thermal conductivity sequence and viscosity sequence of the hot side medium and the cold side medium of the nuclear power plant heat exchanger. These parameters are key indicators of the heat transfer and fluid flow characteristics of the heat exchanger. They change with the temperature, pressure and medium composition, and are crucial to scaling diagnosis.

[0256] Thermal conductivity series of hot side medium: refers to a series of values ​​of the thermal conductivity of the medium on the hot side of the heat exchanger (usually a high-temperature fluid, such as heating steam or high-temperature water) that varies with clean working conditions. Thermal conductivity is a physical quantity that measures the ability of the medium to transfer heat, which directly affects the heat exchange efficiency. Thermal conductivity may vary under different temperatures, pressures or fluid compositions.

[0257] Cold side medium thermal conductivity series: Similar to the hot side, this refers to a series of values ​​of the thermal conductivity of the medium on the cold side of the heat exchanger (usually a low-temperature fluid such as cooling water or air) that varies with clean conditions. The thermal conductivity of the cold side medium also affects the heat transfer efficiency of the heat exchanger.

[0258] Hot side medium viscosity series: Viscosity is a physical quantity that measures the resistance to fluid flow, which affects the fluid's fluidity and pumping energy consumption. The viscosity of the hot side medium changes with changes in temperature, pressure, and fluid composition. These change data are very important for analyzing fluid flow characteristics and predicting possible flow problems (such as blockage).

[0259] Cold Side Media Viscosity Series: Likewise, the viscosity of the cold side media will vary with operating conditions and is equally important to ensure efficient operation of the heat exchanger and predict potential flow problems.

[0260] In step S802 of some embodiments, based on the healthy operating condition data, the clean heat transfer coefficient of the heat exchanger of the nuclear power plant under clean operating conditions is calculated. The clean heat transfer coefficient refers to the heat transfer efficiency of the heat exchanger without the influence of fouling. This parameter provides a benchmark for subsequent fouling analysis.

[0261] In some embodiments, step S803 is to determine the corresponding clean total thermal resistance according to the calculated clean heat transfer coefficient. The clean total thermal resistance is the thermal resistance value of the heat exchanger in a non-fouling state, which is an important reference for evaluating the impact of fouling.

[0262] In step S804 of some embodiments, the hyperparameters of the fouling diagnosis model are determined using the healthy operating condition data, the thermal conductivity series of the hot-side medium and the cold-side medium, the viscosity series, and the clean total thermal resistance.

[0263] In step S805 of some embodiments, the scaling diagnosis model is preset according to the determined model hyperparameters. This step ensures that the scaling diagnosis model can accurately predict the scaling condition according to the given operating conditions and medium characteristics.

[0264] In some more specific embodiments, the clean heat transfer coefficient K of the heat exchanger of the nuclear power plant under various clean conditions can be calculated based on the healthy condition data. The clean heat transfer coefficient K can be expressed as:

[0265]

[0266] Among them, Q h , Q c are the power of the hot side and the cold side respectively, A is the heat exchange area, ΔT m is the logarithmic mean temperature difference.

[0267] In addition, when there is no dirt attached to the heat exchanger, the current clean heat transfer coefficient K can be calculated. clean . Further, the total clean thermal resistance R clean :

[0268]

[0269] Furthermore, the hot side flow sequence and cold side flow sequence of past data are determined from the healthy working condition data, the historical hot side mass flow is determined based on the hot side flow sequence, and the historical cold side mass flow is determined based on the cold side flow sequence. The hot side medium thermal conductivity, cold side medium thermal conductivity, hot side medium viscosity, and cold side medium viscosity under different clean working conditions are determined from the hot side medium thermal conductivity sequence, cold side medium thermal conductivity sequence, hot side medium viscosity, and cold side medium viscosity.

[0270] It should be understood that the clean-dirty thermal resistance equation is an important mathematical tool in heat exchanger performance analysis and fault diagnosis. It describes the thermal resistance characteristics of the heat exchanger under different working conditions in a quantitative way, and provides a theoretical basis for the design, optimization and maintenance of the heat exchanger. Among them, the clean-dirty thermal resistance equation is expressed as follows:

[0271] R clean =A·(μx-y ·λ y-1 ·q -x ) SEC +B·(μ x-y ·λ y-1 ·q -x ) RRI +C

[0272] (μ x-y ·λ y-1 Ωq -x ) SEC It represents the calculation element formed by the medium viscosity, medium thermal conductivity and historical mass flow rate on the cold side;

[0273] (μ x-y ·λ y-1 ·q -x ) RRI It represents the calculation element formed by the medium viscosity, medium thermal conductivity and historical mass flow rate on the hot side;

[0274] Among them, A, B, C, x, and y are all hyperparameters.

[0275] It should be noted that the clean fouling thermal resistance equation quantitatively describes the thermal resistance of the heat exchanger without the influence of fouling by combining the physical properties of the medium (viscosity, thermal conductivity) and the operating conditions (historical mass flow rate). This expression allows the model to capture the changes in the performance of the heat exchanger under different operating conditions.

[0276] By adjusting the values ​​of x and y, the relative importance of the effects of different physical properties on thermal resistance can be simulated, which is very useful for optimizing heat exchanger design and operating conditions.

[0277] Furthermore, in the embodiment of the present application, the least square method can be used to obtain the values ​​of hyperparameters A, B, C and x, y, and only the model parameters that best fit the actual monitoring data are found. This involves constructing an objective function (usually the sum of squares of errors), and then minimizing this objective function through an optimization algorithm (such as gradient descent, genetic algorithm, etc.) to obtain the model parameters that best fit the actual data. In this way, the scaling diagnosis model can be preset according to these model parameters.

[0278] It should be pointed out that after the scaling diagnosis model is preset according to the hyperparameters A, B, C, x, and y, the hot side mass flow rate and the cold side mass flow rate in the scaling diagnosis parameters can be substituted into the scaling diagnosis model for real-time calculation to obtain the scaling thermal resistance value as the scaling diagnosis calculation result. Among them, the preset scaling diagnosis model is expressed as:

[0279]

[0280] Among them, Rtotal is the total fouling thermal resistance, It is the thermal resistance value after removing dirt under the current working conditions.

[0281] In this way, the fouling thermal resistance value can be calculated in real time through the preset fouling diagnosis model

[0282] After the scaling diagnosis model is preset, step S502 substitutes the scaling diagnosis parameters, i.e., the hot side mass flow rate and the cold side mass flow rate, into the preset scaling diagnosis model for real-time calculation. This calculation process utilizes the model's hyperparameters and real-time monitoring data to evaluate the scaling condition of the heat exchanger.

[0283] In step S806 of some embodiments, the fouling diagnosis model can calculate the fouling thermal resistance value as the fouling diagnosis calculation result through the hot side and cold side flow data obtained by real-time calculation. The fouling thermal resistance value is a key indicator for evaluating the impact of fouling, which reflects the actual impact of fouling on the heat transfer efficiency of the heat exchanger. The generated fouling diagnosis calculation result provides important information for the operation and maintenance of the heat exchanger, which helps to take cleaning or optimization measures in time to ensure the efficient operation of the heat exchanger.

[0284] In some embodiments of the present application, a blockage fault is a common and serious fault type in a heat exchanger. When the flow channel of a heat exchanger is partially or completely blocked by impurities, sediments or other substances, it will significantly affect the flow characteristics of the fluid and the overall performance of the heat exchanger. The direct consequence of this fault is an increase in pressure drop and a decrease in heat exchange efficiency, which are important bases for the diagnosis of blockage faults.

[0285] First, blockage reduces the cross-sectional area of ​​the fluid flow, thereby increasing the resistance to fluid flow. This increase in resistance is directly reflected in an increase in pressure drop, that is, the pressure difference required for the fluid to pass through the heat exchanger increases. In the operation of the heat exchanger, monitoring the pressure drop is one of the routine maintenance tasks. Therefore, by monitoring the change in pressure drop, the occurrence of blockage can be discovered in time. Compared with leakage failures, the pressure drop change caused by blockage failures is usually more drastic and obvious. This is because leakage mainly affects the sealing of the fluid, while blockage directly affects the flow path of the fluid.

[0286] Secondly, blockage failure will also affect the heat exchange efficiency of the heat exchanger. Due to the presence of blocking materials, the effective heat transfer area of ​​the heat exchanger is reduced. At the same time, blockage may also cause uneven fluid flow, further reducing the heat exchange efficiency. This decrease in efficiency may be manifested as a change in outlet temperature, for example, the temperature drop of the hot fluid is less than expected, or the temperature increase of the cold fluid is less than expected.

[0287] In actual operation, by monitoring and analyzing the changes in pressure drop and heat transfer efficiency, combined with the design parameters and historical operating data of the heat exchanger, blockage faults can be effectively identified. Once blockage is determined, appropriate cleaning or maintenance measures can be taken to restore the normal operation of the heat exchanger. In addition, regular maintenance and cleaning plans are also important measures to prevent blockage faults. By monitoring and analyzing key parameters such as pressure drop and heat transfer efficiency, blockage problems can be discovered and dealt with in a timely manner, thereby avoiding performance degradation and potential safety risks, and ensuring efficient and reliable operation of the heat exchanger.

[0288] Reference Fig. 9 , showing a feasible qualitative change trend library. In the embodiment of the present application, a preliminary qualitative analysis of the actual operating condition data can also be performed by constructing a qualitative change trend library of three typical faults: blockage, scaling and leakage. Fig. 9 The upward arrow in the figure indicates that the corresponding subdivision data in the actual operating condition data gradually increases, and the downward arrow in the figure indicates that the corresponding subdivision data in the actual operating condition data gradually decreases.

[0289] In summary, step S104 provides accurate fault types for fault diagnosis of heat exchangers in nuclear power plants through in-depth analysis based on actual operating data. This step ensures that heat exchangers can be properly maintained and repaired in a timely manner, which helps reduce unexpected downtime and improve the operating efficiency and safety of nuclear power plants. Through this sophisticated fault analysis, the performance of heat exchangers can be more effectively managed and optimized to ensure the stable operation of nuclear power plants.

[0290] After step S104, an explanation and report of the corresponding diagnosis result may be generated based on the fault diagnosis type of the heat exchange operation state. In the explanation and report, the diagnosis result needs to be presented in a clear and accurate manner to ensure that the nature of the fault can be fully displayed therein. The detailed diagnosis report may include the fault type, possible cause, recommended maintenance measures, and expected effects.

[0291] Reference Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0292] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0293] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the nuclear power plant heat exchanger fault diagnosis method of the embodiment of the present application;

[0294] Input / output interface 1003, used to implement information input and output;

[0295] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0296] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0297] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0298] The embodiment of the present application further provides a computer program product, which includes a computer program. A processor of a computer device reads and executes the computer program, so that the computer device executes the above-mentioned nuclear power plant heat exchanger fault diagnosis method.

[0299] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "comprises" and "comprising" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0300] It should be understood that in the present disclosure, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, which may include any combination of single items or plural items. For example, at least 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.

[0301] It should be understood that in the description of the embodiments of the present application, the meaning of multiple (or multiple items) is more than two, greater than, less than, exceed, etc. are understood to not include the number, and above, below, within, etc. are understood to include the number.

[0302] In the several embodiments provided in 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 only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. 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 mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0303] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0304] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0305] 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 this understanding, the technical solution of the present disclosure, 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, and the computer software product is stored in a storage medium, which may include several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0306] It should also be understood that the various implementations provided in the embodiments of the present application can be combined arbitrarily to achieve different technical effects.

[0307] The above is a specific description of the implementation methods of the present disclosure, but the present disclosure is not limited to the above implementation methods. Technical personnel familiar with the art can also make various equivalent modifications or substitutions without violating the spirit of the present disclosure. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present disclosure.

Claims

1. A method for diagnosing a heat exchanger fault in a nuclear power plant, characterized in that: include: Test the heat exchangers in nuclear power plants to obtain actual operating data; Acquiring health condition data matching the heat exchanger of the nuclear power plant; Performing a rough qualitative fault analysis on the actual operating condition data according to the healthy operating condition data to determine the heat exchange operation state of the heat exchanger of the nuclear power plant; In response to the heat exchange operation state being determined as a fault operation state, a fault qualitative analysis is performed based on the actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state.

2. The method according to claim 1, characterized in that In response to the heat exchange operation state being determined as a fault operation state, performing a fault qualitative analysis based on the actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state includes: extracting leakage diagnosis parameters from the actual operating condition data; Substituting the leakage diagnosis parameters into a preset leakage diagnosis model for real-time calculation to obtain a leakage diagnosis calculation result; In response to the heat exchange operation state being determined as a fault operation state, determining a fault detection time of the nuclear power plant heat exchanger; In response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying a leakage diagnosis condition, it is determined that the fault diagnosis type includes a leakage fault type.

3. The method according to claim 2, characterized in that The leakage diagnosis parameters include the hot side mass flow, the cold side mass flow, the hot side inlet and outlet enthalpy value, and the cold side inlet and outlet enthalpy value. Substituting the leakage diagnosis parameters into a preset leakage diagnosis model for real-time calculation to obtain leakage diagnosis calculation results includes: Substituting the hot side mass flow, the cold side mass flow, the hot side inlet and outlet enthalpy value, and the cold side inlet and outlet enthalpy value into the corresponding leakage diagnosis model for real-time calculation to obtain a leakage factor as the leakage diagnosis calculation result; In response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying a leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type includes: Calculate according to the leakage factor before the fault detection moment to obtain a corresponding fluctuation variance value; Determining the leakage diagnosis condition based on the fluctuation variance value; In response to the leakage factor corresponding to the fault detection moment satisfying the leakage diagnosis condition, it is determined that the fault diagnosis type includes the leakage fault type.

4. The method according to claim 2, characterized in that: The leakage diagnosis parameters include cold medium volume flow rate, cold medium constant pressure specific heat, medium density, hot side inlet temperature, hot side outlet temperature, cold side inlet temperature and cold side outlet temperature. Substituting the leakage diagnosis parameters into a preset leakage diagnosis model for real-time calculation to obtain leakage diagnosis calculation results includes: Substituting the cold medium volume flow rate, the cold medium constant pressure specific heat, the medium density, the hot side inlet temperature, the hot side outlet temperature, the cold side inlet temperature and the cold side outlet temperature into the corresponding leakage diagnosis model for real-time calculation to obtain a leakage calculation amount as the leakage diagnosis calculation result; In response to the leakage diagnosis calculation result corresponding to the fault detection time satisfying a leakage diagnosis condition, determining that the fault diagnosis type includes a leakage fault type includes: Acquiring a leakage diagnosis threshold, and determining the leakage diagnosis condition according to the leakage diagnosis threshold; In response to the leakage calculation amount satisfying the leakage diagnosis condition, it is determined that the fault diagnosis type includes the leakage fault type.

5. The method according to claim 4, characterized in that Substituting the cold medium volume flow rate, the cold medium constant pressure specific heat, the medium density, the hot side inlet temperature, the hot side outlet temperature, the cold side inlet temperature and the cold side outlet temperature into the corresponding leakage diagnosis model for real-time calculation to obtain a leakage calculation amount as the leakage diagnosis calculation result, including: constructing a first leakage diagnosis element according to the cold side outlet temperature and the cold side inlet temperature; determining the cold medium volume flow rate as a second leakage diagnosis element; determining the hot side outlet temperature as a third leak diagnostic element; According to the first leakage diagnostic element, the second leakage diagnostic element and the third leakage diagnostic element, real-time calculation is performed in the leakage diagnostic model to obtain the leakage calculation amount as the leakage diagnostic calculation result.

6. The method according to claim 5, characterized in that The step of constructing a first leakage diagnosis element according to the cold side outlet temperature and the cold side inlet temperature comprises: The cold side outlet temperature and the cold side inlet temperature are subjected to difference processing to obtain the first leakage diagnostic element.

7. The method according to claim 6, characterized in that The step of performing real-time calculation in the leakage diagnosis model according to the first leakage diagnosis element, the second leakage diagnosis element, and the third leakage diagnosis element to obtain the leakage calculation amount as the leakage diagnosis calculation result includes: Determine the product of the first leakage diagnosis element and the second leakage diagnosis element as a model numerator term; Determining a model denominator term according to the first leakage diagnostic element and the third leakage diagnostic element; The model numerator term and the model denominator term are combined to perform real-time calculation to obtain the leakage calculation amount as the leakage diagnosis calculation result.

8. The method according to claim 7, characterized in that The determining of the model denominator term according to the first leakage diagnosis element and the third leakage diagnosis element comprises: Determine the third leakage diagnosis element as a subtracted element of the model denominator term; Determining one half of the first leakage diagnostic element as a subtracted element of the denominator term of the model; The denominator term of the model is obtained by subtracting the subtracted element and the subtracting element.

9. The method according to claim 1, characterized in that: In response to the heat exchange operation state being determined as a fault operation state, performing a fault qualitative analysis based on the actual operating condition data to determine a fault diagnosis type matching the heat exchange operation state includes: extracting scaling diagnostic parameters from the actual operating condition data; Substituting the scaling diagnosis parameters into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results; In response to the heat exchange operation state being determined as a fault operation state, determining a fault detection time of the nuclear power plant heat exchanger; In response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying a scaling diagnosis condition, it is determined that the fault diagnosis type includes a scaling fault type.

10. The method according to claim 9, characterized in that The scaling diagnosis calculation result includes the actual heat transfer efficiency. The scaling diagnosis parameters are substituted into a preset scaling diagnosis model for real-time calculation to obtain the scaling diagnosis calculation result, including: Obtaining a clean heat transfer efficiency and a reference heat transfer efficiency of the heat exchanger of the nuclear power plant; Substituting the clean heat transfer efficiency, the reference heat transfer efficiency and the actual heat transfer efficiency into the corresponding fouling diagnosis model for real-time calculation to obtain a fouling factor as the fouling diagnosis calculation result; In response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying a scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type comprises: Acquiring a scaling diagnosis threshold, and determining the scaling diagnosis condition according to the scaling diagnosis threshold; In response to the fouling factor satisfying the fouling diagnosis condition, it is determined that the fault diagnosis type includes the fouling fault type.

11. The method according to claim 10, characterized in that The scaling diagnosis parameters include medium flow rate and flow pressure loss. Substituting the scaling diagnosis parameters into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results includes: Substituting the medium flow rate and the flow pressure loss into the corresponding scaling diagnosis model for real-time calculation to obtain the scaling layer thickness as the scaling diagnosis calculation result; In response to the scaling diagnosis calculation result corresponding to the fault detection time satisfying a scaling diagnosis condition, determining that the fault diagnosis type includes a scaling fault type comprises: Obtaining a scale layer thickness threshold, and determining the scaling diagnosis condition according to the scale layer thickness threshold; In response to the scaling layer thickness satisfying the scaling diagnosis condition, it is determined that the fault diagnosis type includes the scaling fault type.

12. The method according to claim 10, characterized in that The scaling diagnosis parameters include the hot side mass flow and the cold side mass flow. Before substituting the scaling diagnosis parameters into a preset scaling diagnosis model for real-time calculation to obtain the scaling diagnosis calculation result, the scaling diagnosis model is preset, specifically including: Obtaining a hot side medium thermal conductivity sequence, a cold side medium thermal conductivity sequence, a hot side medium viscosity sequence, and a cold side medium viscosity sequence of the nuclear power plant heat exchanger; Based on the healthy operating condition data, calculating the clean heat transfer coefficient of the heat exchanger of the nuclear power plant under clean operating conditions; Determine the corresponding clean total thermal resistance according to the clean heat transfer coefficient; Determine model hyperparameters according to the healthy operating condition data, the hot side medium thermal conductivity sequence, the cold side medium thermal conductivity sequence, the hot side medium viscosity sequence, the cold side medium viscosity sequence and the clean total thermal resistance; Presetting the scaling diagnosis model according to the model hyperparameters; Substituting the scaling diagnosis parameters into a preset scaling diagnosis model for real-time calculation to obtain scaling diagnosis calculation results includes: The hot side mass flow rate and the cold side mass flow rate are substituted into the fouling diagnosis model for real-time calculation to obtain a fouling thermal resistance value as the fouling diagnosis calculation result.

13. The method according to claim 1, characterized in that The performing a rough qualitative fault analysis on the actual operating condition data according to the healthy operating condition data to determine the heat exchange operation state of the heat exchanger of the nuclear power plant includes: Performing a multivariate state assessment on the health condition data to obtain a multidimensional health memory matrix; Performing multivariable state assessment on the actual operating condition data to obtain a multidimensional actual operating condition matrix; Performing a similarity comparison based on the multidimensional health memory matrix and the multidimensional actual working condition matrix to obtain a similarity comparison result; The heat exchange operation status of the nuclear power plant heat exchanger is determined according to the similarity comparison result.

14. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for diagnosing faults of a heat exchanger in a nuclear power plant as claimed in any one of claims 1 to 13 is implemented.

15. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the nuclear power plant heat exchanger fault diagnosis method according to any one of claims 1 to 13.

Images