A thermal performance analysis and optimization system for nuclear power units

Abstract

The application provides a thermal performance analysis and optimization system for a nuclear power unit, and relates to the technical field of thermal performance data processing, and comprises: a parameter calculation model, which is used for acquiring design data, measuring point data and / or simulation data to calculate a plurality of thermal parameters; wherein each thermal parameter is previously constructed with a calculation model, and each calculation model can comprise at least one calculation function; and a parameter optimization model, which is used for acquiring historical measuring point data to predict part of the thermal parameters, so as to solve the problem that the data flexibility of the existing thermal performance analysis system is poor, and the accuracy and comprehensiveness cannot meet the application requirements in some scenes.

Description

Technical Field

[0001] This invention relates to the field of thermal performance data processing technology, and in particular to a thermal performance analysis and optimization system for nuclear power units. Background Technology

[0002] Thermal performance analysis is a core tool for energy and power companies such as thermal power plants and nuclear power plants to monitor the energy efficiency, assess the condition, and optimize the operation of various units. It collects key parameters of unit operation (such as pressure, temperature, and flow rate) and calculates a series of indicators such as boiler efficiency, turbine heat rate, and thermal efficiency to evaluate the overall performance status of the unit.

[0003] In existing technologies, researchers have found that the application of thermal performance analysis systems has a certain foundation, but there are some limitations that restrict their value as tools for in-depth optimization and decision support. For example, most systems can only perform fixed and standardized thermal index calculations, lacking flexibility. They cannot perform customized modeling and adaptive analysis based on specific operating conditions, equipment modifications, or pre-inspection status. Moreover, they often operate as independent systems, lacking data fusion and functionality with other systems. Therefore, they cannot accumulate or utilize historical data for optimization. Consequently, the accuracy and comprehensiveness of the analysis results of existing systems cannot meet the application needs in some scenarios. Summary of the Invention

[0004] In order to overcome the above-mentioned technical defects, the purpose of this invention is to provide a thermal performance analysis and optimization system for nuclear power units, which is used to solve the problems that the existing thermal performance analysis system has poor data flexibility and the accuracy and comprehensiveness cannot meet the application needs in some scenarios.

[0005] This invention discloses a system for thermodynamic performance analysis and optimization of nuclear power units, comprising: A parameter calculation model is used to obtain design data, measurement point data and / or simulation data to calculate several thermodynamic parameters; wherein, a calculation model is pre-constructed for each thermodynamic parameter, and each calculation model may contain at least one calculation function; The parameter optimization model is used to predict some thermodynamic parameters by acquiring historical measurement data.

[0006] Preferably, the thermal parameters are calculated by performing data processing according to preset operating conditions step by step under the parameter calculation model.

[0007] Preferably, the system further includes: The online calculation module is used to receive instructions to acquire and / or calculate the thermodynamic parameters corresponding to the instructions in real time; The instructions are triggered by user operation or automatically by a preset program.

[0008] Preferably, predicting electrical power based on historical seawater temperature data under the parameter optimization model includes: Obtain historical seawater temperature data and predict seawater temperature changes based on the historical seawater temperature data; Obtain relevant parameters, and establish a prediction model based on the predicted seawater temperature change and relevant parameters to predict the electrical power. The relevant parameters include thermal power, high-pressure regulating valve opening, and primary loop average temperature.

[0009] Preferably, the prediction of seawater temperature changes includes: Two STL decompositions are performed to obtain two seasonal terms with periodic information. A neural network algorithm is used to obtain the prediction results. The trend terms obtained after the two decompositions are extrapolated by a polynomial to obtain the trend prediction results. The results are superimposed to predict seawater temperature changes.

[0010] Preferably, performing two STL decompositions includes: The first decomposition is performed to obtain the first seasonal term, which is then predicted using a neural network algorithm as a prediction result with periodic information. Based on the superposition of the trend term and random term obtained after the first decomposition, a second decomposition is performed to obtain the second seasonal term, which is then predicted using a neural network algorithm as another prediction result with periodic information.

[0011] Preferably, the system further includes: The autonomous optimization function is used to optimize the output of each model by constraining it with variable thermodynamic parameters.

[0012] Preferably, the system further includes: The real-time monitoring function is used to perform data correlation fitting based on various thermodynamic parameters in order to monitor each unit / operating condition at each stage in real time. The correlation data includes: seawater temperature - corrected power and seawater temperature - condensate temperature.

[0013] Preferably, the system further includes: The verification function is used to verify the calculated thermodynamic parameters. And / or, an early warning function, used for equipment fault detection and early warning based on design data, measurement point data, simulation data and / or thermodynamic parameters.

[0014] Preferably, the system further includes: The display function presents design data, measurement data, simulation data, and / or thermal parameters in a preset format on the page.

[0015] Compared with existing technologies, the above technical solution has the following advantages: 1. A real-time calculation model for thermodynamic parameters is developed based on design data (thermal balance diagram), simulation prototype data, and measurement point data. This model integrates multiple calculation functions and operating condition control processes to calculate thermodynamic parameters such as thermal power, internal efficiency, and heat transfer coefficient. It is used for thermodynamic performance analysis and optimization, including data visualization, data optimization, data prediction, and fault diagnosis. Through interaction with other systems, it collects data from multiple sources, including operational design data, unit operation data, and test system data, which are then fed into the data analysis and model. The data is processed to generate valuable data that corresponds to actual operating conditions, thus overcoming the problems of low accuracy and incomplete index calculations in existing thermodynamic data models.

[0016] 2. The system provides data display functions, including but not limited to periodic display of thermal parameter monitoring, thermal performance index comparison, performance display, thermal performance report, and horizontal comparison of units. It can also perform data filtering and online thermal parameter calculation according to user operation.

[0017] 3. The thermal performance analysis system can provide verification based on thermal parameters to achieve data monitoring and optimization; it also provides prediction based on historical data, such as predicting thermal parameters such as actual power output under different seawater temperatures and tide levels; the prediction of time-series data is decomposed multiple times to improve the accuracy of the prediction results; furthermore, variable thermal parameters can be input for constraints to optimize the model. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of a module of an embodiment of a thermodynamic performance analysis and optimization system for nuclear power units according to the present invention; Figure 2 This is a flowchart illustrating the seawater temperature prediction process performed by a parameter optimization model in an embodiment of a thermodynamic performance analysis and optimization system for nuclear power units according to the present invention. Figure 3 This is a functional schematic diagram of a thermal performance analysis and optimization system for nuclear power units according to the present invention.

[0019] Figure label: 1-Thermodynamic performance analysis and optimization system; 11-Parameter calculation model; 12-Parameter optimization model. Detailed Implementation

[0020] The advantages of the present invention will be further illustrated below with reference to the accompanying drawings and specific embodiments. Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description relating to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0021] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0022] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0023] In the description of this invention, unless otherwise specified and limited, it should be noted that the terms "installation," "connection," and "linkage" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal communication between two components. They can be direct connections or indirect connections via an intermediate medium. Those skilled in the art can understand the specific meaning of these terms according to the specific circumstances. In the following description, the use of suffixes such as "module," "component," or "unit" to denote components is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module" and "component" can be used interchangeably.

[0024] Example: This embodiment provides a thermal performance analysis and optimization system for nuclear power units. It constructs real-time thermal parameter calculation models based on design data (such as heat balance diagrams), real-time thermal parameter calculation models based on simulation prototype data, daily thermal parameter calculation models based on output analysis reports, and optimization models based on historical data. Based on simulation data, design data, and unit measurement point data, it calculates thermal performance parameters for key equipment such as steam generators and turbines, and displays the data in the form of lists and curves. It can achieve functions such as thermal data acquisition, online thermal performance calculation, real-time thermal performance monitoring, and automated output of thermal performance reports. Furthermore, it provides optimization functions, establishes predictive models, predicts thermal parameters based on collected historical thermal parameters, and develops mapping relationship models between different thermal performance parameters based on neural network algorithms. This enables optimized prediction of key unit performance indicators, such as power prediction based on seawater temperature prediction, to further improve the timeliness and accuracy of thermal parameter monitoring and achieve functions such as data early warning, providing reference for operators.

[0025] Specifically, this application provides a system for thermal performance analysis and optimization of nuclear power units. This system interacts with a simulation model system and a unit control system (including equipment such as steam generators, steam turbines, steam-water separators, reheaters, and regenerative heaters) to obtain simulation data and measurement point data. The data can be various types of data obtained using different data interfaces and acquisition methods, thereby performing thermal performance calculations. The design data is pre-provided data, and a database can be preset to store various types of data for data processing by the various models described below.

[0026] For details, please refer to Figure 1-3 The system includes: The parameter calculation model acquires design data, measurement point data, and / or simulation data to calculate several thermodynamic parameters. Each thermodynamic parameter is pre-constructed with a calculation model, and each calculation model may contain at least one calculation function (including but not limited to a combination of multiple functions). The thermodynamic parameters include, but are not limited to, thermal power, heat transfer coefficient, inlet and outlet flow rate, relative internal efficiency, heat exchange, etc. The parameter optimization model uses historical measurement data to predict some thermal parameters, including seawater temperature and electrical power parameters.

[0027] Specifically, the parameter calculation model provides data analysis configuration based on the collected data. Specifically, each calculation model calculates the corresponding thermodynamic parameters of each device (or index), such as calculating the thermal power and heat transfer coefficient for a steam generator; calculating the inlet and outlet flow rates, relative internal efficiency, pressure ratio, and characteristic flow area for a steam turbine; and calculating the upper and lower end temperature difference, feedwater temperature rise, logarithmic mean temperature difference, heat exchange, and heat transfer coefficient for a regenerating heater. The above are just examples, and the actual calculations can be based on the unit's operating conditions and are not limited to these.

[0028] The above calculation models can be combined with one or more calculation formulas. For example, for a steam generator, the heat balance equation is established as follows: ; where Q SG The thermal power of the steam generator is expressed in kW; G m,f The water supply flow rate is expressed in kg / s and h. g Specific enthalpy of saturated vapor, kJ / kg; h fw Specific enthalpy of water supply, kJ / kg; G m,d The discharge flow rate is expressed in kg / s, and its value is the total discharge flow rate divided by 3; h sa The specific enthalpy of saturated water is given in kJ / kg. The specific enthalpy of the saturated steam at the steam generator outlet is calculated by consulting a preset steam table using the outlet saturated steam pressure and the set saturated steam dryness fraction. The corresponding thermodynamic parameters of the steam generator are obtained from the above heat balance equation.

[0029] The above are merely examples; it is understood that other examples can also establish heat balance equations (i.e., the calculation functions in the above calculation model) similarly to those for steam generators. As a special example, some thermodynamic parameters can also be a set of multiple calculation functions, such as the inlet steam flow rate G of the high-pressure cylinder. m,hi The following two calculation functions are used for calculation: ; Among them, G m,g G represents the steam flow rate at the steam generator outlet, in kg / s. m,re The steam flow rate for the secondary reheat in the steam-water separator reheater is expressed in kg / s. The calculation of the high-pressure cylinder exhaust flow rate, and the inlet and outlet steam flow rates of the intermediate and low-pressure cylinders, utilizes multiple calculation functions: ; ; ; Among them, G m,ho G represents the exhaust flow rate of the high-pressure cylinder, in kg / s. m,mi G m,mo , respectively, are the steam flow rates at the inlet and outlet of the intermediate pressure cylinder, kg / s; G m,li G m,lo These are the steam flow rates at the inlet and outlet of the low-pressure cylinder, respectively, in kg / s; f h f m fli f lo These represent the proportions of steam flow from the high-pressure cylinder exhaust, the intermediate-pressure cylinder inlet, and the low-pressure cylinder inlet and exhaust to the steam generator outlet steam flow. These values ​​are determined by the corresponding unit's heat balance data or design data, or can be obtained directly from the simulation model of the corresponding pipe and node parameters.

[0030] Understandably, the calculation functions used for processing each thermodynamic parameter are pre-arranged in the calculation model. These calculation functions can be existing general formulas used to calculate the corresponding thermodynamic parameters, or they can be formulas independently established based on the operating conditions, and can be adjusted according to actual applications.

[0031] Furthermore, the aforementioned parameter model can also perform calculations sequentially / level by level according to operating conditions. The parameter calculation model also performs: data processing based on preset operating conditions configured level by level to calculate the corresponding thermodynamic parameters. For example, in a steam-water separation reheater module, the calculation of the outlet steam flow rate and condensate flow rate of multi-stage heaters, the outlet steam dryness set according to the heat balance diagram, and the heat balance calculation of heaters with or without condensate coolers are all examples. As an example only, the inlet steam on the shell side of the first-stage reheater comes from high-pressure cylinder extraction steam and the outlet steam on the shell side of the second-stage reheater. The following steps are performed sequentially: assuming the pressures of the first-stage and second-stage reheaters - obtaining the collector characteristic parameters - assuming the shell-side pressure of the first-stage reheater - sequentially calculating the shell-side outlet mass specific enthalpy, shell-side heat release, and other parameters of the first-stage reheater - calculating the first-stage heat transfer - calculating the shell-side pressure of the first-stage reheater - calculating the error until the pre-set conditions are met. The first-stage reheater is determined according to the above iterative cycle. Other thermodynamic parameters can also be pre-configured with calculation steps, referring to the above example.

[0032] Based on the above example, a calculation model can be constructed to calculate thermal parameters. It is worth noting that the thermal parameters in the above scheme can be thermal parameters related to the equipment, or they can be some economic indicators (performance indicator models), such as thermal efficiency, heat consumption rate, etc. Corresponding calculation functions can also be established for data processing, or the thermal parameters calculated in the above example can be obtained for further calculation.

[0033] Based on the above parameter calculation model, several thermodynamic parameters can be calculated, improving the comprehensiveness and flexibility of the data. Furthermore, the system in this embodiment differs from existing thermodynamic analysis systems in that it can achieve further optimization, improving the accuracy of the analysis results. Specifically, optimization may include, but is not limited to: autonomously optimizing the above calculation models and providing data prediction functions.

[0034] Understandably, some of the collected data is periodically changing, so magnetic properties can be used for prediction. The prediction function refers to the ability to make predictions based on historical data, and to perform data analysis, early warning, and verification based on the predicted data, thereby further improving the system's analytical flexibility.

[0035] Considering the optimization characteristics of actual operation, taking temperature prediction as an example, specifically, the above parameter optimization model is constructed to perform seawater temperature prediction, and further predict electrical power. The actual steps for performing the prediction can be: obtaining historical seawater temperature data, predicting seawater temperature changes based on the historical seawater temperature data; then obtaining relevant parameters, establishing a prediction model based on the predicted seawater temperature changes and relevant parameters to predict electrical power, where relevant parameters include but are not limited to thermal power, high-pressure regulating valve opening, and primary loop average temperature, etc.

[0036] Specifically, it can be understood that seawater temperature is generally affected by the natural environment and has a certain periodic regularity. Therefore, such data can be predicted. Furthermore, the electric power can be obtained by fitting the predicted seawater temperature changes and related data (thermal power, high-pressure valve opening, primary circuit average temperature, etc.) using a random forest regression model.

[0037] As mentioned above, seawater temperature has a certain periodicity. The above prediction of seawater temperature changes includes: performing two STL decompositions to obtain two prediction results with periodic information and using a neural network to predict them; directly extrapolating the trend terms obtained after performing the two decompositions to obtain trend prediction results; and superimposing the results to predict seawater temperature changes.

[0038] Specifically, by performing two STL decompositions, the periodic fluctuations at different time scales in the sea surface temperature data are captured, and combined with the extrapolation of the trend term, a comprehensive and high-precision prediction of future sea surface temperature is achieved. STL can decompose the data into three core components: trend term: describing the long-term, slow upward or downward direction of the data; seasonal term: describing the near-repeating fluctuations in the data with a fixed period; residual term (i.e., random term): representing the unexplained random noise remaining after removing the trend and seasonal terms.

[0039] Specifically, the above-mentioned two STL decompositions include: performing a first decomposition to obtain the first seasonal term result as a prediction result with periodic information and using a neural network for prediction; and performing a second decomposition based on the trend term and random term results obtained after the first decomposition to obtain the second seasonal term and using a neural network for prediction result as another prediction result with periodic information.

[0040] In this implementation, two decompositions are performed in a single operation, and the second decomposition is based on the results obtained from the first decomposition. This differs from existing data prediction methods that rely on only one decomposition or multiple random decompositions. Specifically, the first decomposition captures interannual and long-term trends. The random terms obtained from the first decomposition are then further decomposed to capture fluctuations with periods shorter than one year (such as quarterly or monthly changes). This dual decomposition strategy can progressively separate periodic signals at different time scales, making the model more refined and the results more accurate. Furthermore, separating the long-term trend from the short-term trend nested within the random terms and directly extrapolating it can effectively reduce prediction bias caused by the mixing of multiple trends, further improving the accuracy of the prediction results.

[0041] As mentioned above, the above example of seawater temperature prediction can be used as an example. In fact, time-series data with periodic changes, including but not limited to temperature data and flow rate, can be decomposed and predicted. The actual number of decompositions or the decomposition algorithm can also be adjusted according to the actual data type.

[0042] Based on the above, the system processing provided in this embodiment can realize optimization based on actual operation, such as the data prediction mentioned above. It can also serve as a better implementation of the autonomous optimization function of the model. In other words, the system also performs input of variable thermodynamic parameters for constraint in order to optimize the model output.

[0043] Specifically, it allows input of variable thermodynamic parameters (such as ambient temperature, main steam pressure, back pressure, etc.) as boundary conditions to dynamically constrain the built-in calculation model or calculation function. The model output (such as efficiency, power, etc.) will be optimized under these constraints to generate reference values ​​that best match the current operating conditions, thereby optimizing the system.

[0044] Furthermore, as a preferred implementation, the system can also provide online display / calculation functions. Specifically, an online calculation module is set up to receive instructions and acquire and / or calculate the corresponding thermodynamic parameters in real time according to the instructions, so as to realize data display and interaction; the instructions are triggered by user operation or automatically triggered by a preset program.

[0045] Specifically, the above parameter calculation model acquires multiple types of parameters to achieve data processing. The thermal parameters are calculated by constructing a calculation model containing calculation functions. Due to the complexity and large amount of data, offline calculation is preferred. Therefore, an additional online calculation module is deployed. This module can be used to realize the online acquisition and / or calculation of various thermal parameters according to instructions (such as user selection or pre-programmed triggering instructions).

[0046] Specifically, the online calculation module performs the following steps: determining the thermal parameters to be calculated according to the instructions, acquiring the corresponding design data and / or measurement point data, and calling the corresponding interface or calculation function to calculate the thermal parameters. These instructions can be pre-set by the user and triggered, or set by the user after acquiring the thermal parameters, or triggered automatically by a pre-defined program in the system. As an example, the user can select a certain time range based on the thermal parameters obtained from the first parameter calculation model to perform thermal power calculation and output analysis of the experimental instrument system. In other words, instructions can be defined according to the actual scenario and user needs, and even pre-configured / associated calculation functions / programs, thereby improving the flexibility of thermal parameter analysis.

[0047] Understandably, both the aforementioned parameter calculation model and the online calculation module are used to obtain thermal parameters. The online calculation module can directly obtain the thermal parameters calculated by the parameter calculation model, or it can configure calculation functions independently. The calculation model / functions used in the parameter calculation model to calculate thermal parameters can also be partially or fully applied to the online calculation module. It is worth noting that the online calculation model must be triggered by instructions to calculate the specified thermal parameters. The difference between the online and offline online calculation models is that the parameter calculation model can autonomously calculate thermal parameters based on pre-defined calculation functions, both online and offline, and its calculated thermal parameters are more extensive and comprehensive.

[0048] Therefore, as an example, it can be applied to a scenario where the thermal parameters calculated by the above parameter calculation model under normal conditions can be displayed on the user interface. At the same time, the online calculation module is triggered to run calculations based on the user's operations on the interface, such as the above example, to filter and calculate the thermal power within a certain time range.

[0049] Furthermore, the system also has a verification function, which can be configured with a verification module or a specific verification program to verify the calculated thermodynamic parameters. Specifically, this includes, but is not limited to: acquiring a real-time heat balance diagram provided by the unit as a standard operating condition, dynamically adjusting the calculation of thermodynamic parameters under different operating conditions for verification; or, under the same operating conditions, comparing the thermodynamic parameters calculated by the model (such as the extraction steam flow rate, enthalpy, efficiency, etc. at each stage) with measured or design values ​​for verification. It is understood that the above verification can also be further used for model calibration, thus serving as an aid to the aforementioned model optimization.

[0050] As an example, the following table shows a comparison of some (not all, only for example) calculated and designed parameter values ​​obtained from the 90% standard operating condition verification: As can be seen, all parameter deviations are within ±2%, which is basically consistent with the design parameters. Therefore, the thermodynamic parameters calculated by this system meet the data accuracy verification requirements. In addition, it also meets the requirements when compared with other working conditions, which will not be shown here.

[0051] As a preferred implementation, the system can also perform data correlation fitting based on thermodynamic parameters to monitor each unit / operating condition at various stages in real time. The correlated data includes: seawater temperature-corrected electrical power (used to analyze the impact of condenser cooling water source temperature on the unit's maximum output and efficiency), seawater temperature-condensate temperature (used to monitor condenser terminal temperature changes and evaluate condenser heat exchanger tube performance in real time), etc. Based on the above, isolated measurement point data can be transformed into performance curves and correlation graphs with monitoring significance within the system, thereby further optimizing the system, increasing the correlation between data, and achieving comprehensive management of the unit's thermodynamic performance.

[0052] Based on the above data processing, as a further preferred implementation, the system also has a display function, which displays design data, measurement point data, simulation data and / or thermal parameters in a preset format on a page, and can be combined with the above online calculation module to realize the display and calculation of real-time data.

[0053] Specifically, it provides a display of thermal parameters (including list and main graph displays), which can display important thermal parameters in real time on the corresponding positions on the main thermal performance graph. Based on the thermal parameters, predicted data, and monitoring data output by the above-mentioned models, it provides functions such as parameter trend comparison and thermal parameter anomaly alarms. Alternatively, it can capture user operations or receive commands to filter and display thermal parameters or perform online calculations. For example, users can filter thermal parameters by unit, time, operating conditions, etc., through drop-down menus, checkboxes, etc., to customize personalized views.

[0054] Based on the above, another preferred implementation is that the system also provides an early warning function, which can also be implemented based on the aforementioned online calculation module. A calculation threshold is set, and the online calculation module is used for comparison. When the threshold is exceeded, an early warning message is triggered. The early warning message can be displayed on the visualization page as described above, or it can directly output an early warning signal (sound, prompt box, data color reminder, etc.). Specifically, equipment fault detection and early warning are performed based on design data, measurement point data, simulation data, and / or thermodynamic parameters using preset diagnostic rules. For example: "The condenser terminal temperature difference continuously exceeds the design value by X%, and simultaneously accompanied by a decrease in the circulating water inlet and outlet temperature difference by Y%" -> Early warning "Condenser tube bundle may be scaled or blocked," etc.

[0055] Based on the above, this system can utilize the aforementioned parameter calculation model and / or online calculation module to select historical data and optimal operating condition data based on operating conditions to present and analyze the correlation trends of multiple parameters, set alarm thresholds for thermal parameter deviations, and display anomalies (fault location). It can also compare multiple sets of data to dynamically and accurately display thermal parameters.

[0056] In addition, the above-mentioned fault diagnosis includes fault monitoring based on direct comparison of various data. If a certain type of data exceeds the threshold, it may also include equipment fault location based on existing algorithms, such as equipment fault location based on the SVM algorithm. This can be achieved by building a model into the above system or introducing a corresponding data interface. The specifics will not be elaborated further.

[0057] This application acquires unit operation data, including design data, unit operation data, and test instrument system data, and inputs them into data analysis and models. After calculation of thermodynamic parameters and performance indicators, thermodynamic performance analysis and optimization are performed, including data display, data optimization, data prediction, and fault diagnosis, thereby achieving comprehensive management of the unit's thermodynamic performance.

[0058] In summary, this system optimizes thermal system management by integrating real-time monitoring, model simulation, interactive verification, and intelligent early warning, establishing multiple models to generate valuable thermal parameters that closely match actual operating conditions. This overcomes the problem of low accuracy and single data in existing thermal data models. Further model optimization allows for multiple decompositions of time-series data for prediction, enabling prediction of individual thermal parameters and improving the accuracy of model thermal analysis results. It also provides dynamic monitoring for comprehensive monitoring of thermal performance.

[0059] The system provided in this application builds a model based on design data (thermal balance diagram), simulation prototype data, and measurement point data for data processing. This overcomes the problems of existing systems having limited data and incomplete index calculations, improving flexibility, further increasing predictive data, and optimizing the accuracy of system results. It provides predictions based on historical data and performs multiple decompositions on time-series data, such as predicting electrical power at different seawater temperatures. This effectively solves the problems of existing thermal performance analysis systems having poor data flexibility and insufficient accuracy and comprehensiveness to meet the application needs of certain scenarios.

[0060] The above embodiments are merely illustrative of the principles and effects of the patented device and are not intended to limit the scope of the patented device. Any person skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the patented device. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the patented device shall still be covered by the claims of the patented device.

[0061] It is understood that the device of this embodiment can also be integrated with other general control modules / equipment for the operation of nuclear power unit systems in different scenarios.

[0062] It should be noted that the embodiments of the present invention have better implementability and are not intended to limit the present invention in any way. Any person skilled in the art may use the above-disclosed technical content to change or modify it into equivalent effective embodiments. However, any modifications or equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of the technical solution of the present invention.

Claims

1. A thermal performance analysis and optimization system for nuclear power plant units, characterized in that, include: A parameter calculation model is used to obtain design data, measurement point data and / or simulation data to calculate several thermodynamic parameters; wherein, a calculation model is pre-constructed for each thermodynamic parameter, and each calculation model may contain at least one calculation function; The parameter optimization model is used to predict some thermodynamic parameters by acquiring historical measurement data.

2. The thermodynamic performance analysis and optimization system of claim 1, wherein, The thermal parameters are calculated by performing data processing according to preset operating conditions in a step-by-step configuration under the parameter calculation model.

3. The thermodynamic performance analysis and optimization system of claim 1, wherein, The system also includes: The online calculation module is used to receive instructions to acquire and / or calculate the thermodynamic parameters corresponding to the instructions in real time; The instructions are triggered by user operation or automatically by a preset program.

4. The thermodynamic performance analysis and optimization system according to claim 1, characterized in that, Predicting electrical power based on historical seawater temperature data under the parameter optimization model includes: Obtain historical seawater temperature data and predict seawater temperature changes based on the historical seawater temperature data; Obtain relevant parameters, and establish a prediction model based on the predicted seawater temperature change and relevant parameters to predict the electrical power. The relevant parameters include thermal power, high-pressure regulating valve opening, and primary loop average temperature.

5. The thermodynamic performance analysis and optimization system according to claim 4, characterized in that, The method for predicting seawater temperature changes includes: performing two STL decompositions to obtain two seasonal terms with periodic information and using a neural network algorithm to obtain prediction results; performing polynomial extrapolation on the trend terms obtained after the two decompositions to obtain trend prediction results; and superimposing the results to predict seawater temperature changes.

6. The thermodynamic performance analysis and optimization system according to claim 5, characterized in that, The process of performing two STL decompositions includes: The first decomposition is performed to obtain the first seasonal term, which is then predicted using a neural network algorithm as a prediction result with periodic information. Based on the superposition of the trend term and random term obtained after the first decomposition, a second decomposition is performed to obtain the second seasonal term, which is then predicted using a neural network algorithm as another prediction result with periodic information.

7. The thermodynamic performance analysis and optimization system according to claim 1, characterized in that, The system also includes: The autonomous optimization function is used to optimize the output of each model by constraining it with variable thermodynamic parameters.

8. The thermodynamic performance analysis and optimization system according to claim 1, characterized in that, The system also includes: The real-time monitoring function is used to perform data correlation fitting on various thermal parameters based on neural networks, so as to monitor each unit / operating condition at each stage in real time. The correlation data includes: seawater temperature - corrected power and seawater temperature - condensate temperature.

9. The thermodynamic performance analysis and optimization system according to claim 1, characterized in that, The system also includes: The verification function is used to verify the calculated thermodynamic parameters. And / or, an early warning function, used for equipment fault detection and early warning based on design data, measurement point data, simulation data and / or thermodynamic parameters.

10. The thermodynamic performance analysis and optimization system according to claim 1, characterized in that, The system also includes: The display function presents design data, measurement data, simulation data, and / or thermal parameters in a preset format on the page.

Images