Intelligent control system for thermal energy recovery of circulating cooling water in nuclear power station

Abstract

Disclosed is an intelligent control system for thermal energy recovery of circulating cooling water in a nuclear power station. The system comprises: a thermal energy recovery apparatus used for transferring thermal energy of circulating cooling water to other media by means of a heat exchanger; and a cooling water pump used for conveying the circulating cooling water between the thermal energy recovery apparatus and a reactor. The intelligent control system for thermal energy recovery of circulating cooling water in a nuclear power station further comprises a controller used for adjusting working parameters of the thermal energy recovery apparatus. Thus, the water consumption and discharge amount of the nuclear power station can be effectively reduced, greenhouse gas emissions are reduced, and the reliability and service life of the nuclear power station are improved.

Description

An intelligent control system for heat recovery of circulating cooling water in nuclear power plants Technical Field

[0001] The present application relates to the field of heat energy recovery, and more specifically, to an intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant. Background Art

[0002] Nuclear power plants utilize the energy released by nuclear fission reactions and convert it into electricity. During operation, nuclear power plants require cooling to maintain safe operating temperatures. However, conventional nuclear power plants typically discharge the hot cooling water or coolant directly to the outside after cooling, wasting the heat energy carried. Therefore, heat recovery from the circulating cooling water within nuclear power plants is necessary. However, the heat recovery control systems in conventional nuclear power plants lack intelligent and optimized regulation, making it difficult to effectively utilize the heat energy in the cooling water. This results in low thermal efficiency and prevents optimal economic efficiency of nuclear power plants.

[0003] Therefore, an intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant is desired. Technical issues

[0004] In view of this, the present application proposes an intelligent control system for heat energy recovery of circulating cooling water in nuclear power plants, which can effectively reduce the water consumption and emissions of nuclear power plants, reduce greenhouse gas emissions, and improve the reliability and life of nuclear power plants. Technical Solutions

[0005] According to one aspect of the present application, an intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant is provided, comprising a heat energy recovery device for transferring heat energy of circulating cooling water to other media via a heat exchanger; a cooling water pump for transporting the circulating cooling water between the heat energy recovery device and the reactor, wherein the intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant further comprises a controller for adjusting operating parameters of the heat energy recovery device;

[0006] Wherein, the controller includes:

[0007] A data acquisition module is used to obtain the heat load value of the reactor, the temperature value and the flow value of the cooling water at multiple predetermined time points within a predetermined time period;

[0008] a data parameter time series arrangement module, configured to arrange the reactor heat load values, cooling water temperature values, and flow values ​​at the plurality of predetermined time points into a heat load time series input vector, a cooling water temperature time series input vector, and a cooling water flow time series input vector, respectively, according to a time dimension;

[0009] a cooling water heat exchange timing distribution module, configured to calculate the cooling water heat exchange timing input vector obtained by multiplying the cooling water temperature timing input vector and the cooling water flow timing input vector by a point-by-point basis;

[0010] a data parameter local time series analysis module, configured to perform local time series analysis on the heat load time series input vector and the cooling water heat exchange time series input vector respectively to obtain a sequence of heat load local time series characteristic vectors and a sequence of cooling water heat exchange local time series characteristic vectors;

[0011] a heat load-heat exchange time series interaction correlation coding module, configured to perform parameter time series feature interaction correlation analysis on the sequence of the heat load local time series feature vectors and the sequence of the cooling water heat exchange local time series feature vectors to obtain a heat load-heat exchange time series interaction feature; and

[0012] The cooling water flow control module is used to determine whether the flow value of the cooling water at the current time point should be increased or decreased based on the heat load-heat exchange time sequence interaction characteristics. Beneficial effects

[0013] According to an embodiment of the present application, the system includes a heat recovery device for transferring heat energy from circulating cooling water to another medium via a heat exchanger; a cooling water pump for transporting the circulating cooling water between the heat recovery device and the reactor. The intelligent control system for heat recovery of circulating cooling water in the nuclear power plant also includes a controller for adjusting the operating parameters of the heat recovery device. This can effectively reduce the water consumption and emissions of the nuclear power plant, reduce greenhouse gas emissions, and improve the reliability and lifespan of the nuclear power plant.

[0014] Further features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the application and, together with the description, serve to explain the principles of the application.

[0016] FIG1 shows a block diagram of an intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application.

[0017] FIG2 shows a block diagram of the controller in the intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application.

[0018] FIG3 shows a block diagram of the data parameter local time series analysis module in the intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application.

[0019] FIG4 shows a flow chart of an intelligent control method for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application.

[0020] FIG5 shows a schematic diagram of the architecture of sub-step S130 in the intelligent control method for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application.

[0021] FIG6 shows an application scenario diagram of an intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application. Modes for Carrying Out the Invention

[0022] The following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts also fall within the scope of protection of this application.

[0023] As used in this application and the claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0024] Various exemplary embodiments, features, and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0025] In addition, numerous specific details are provided in the detailed description below to better illustrate the present application. Those skilled in the art will appreciate that the present application can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present application.

[0026] In response to the above-mentioned technical problems, the technical solution of this application proposes an intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant, which is a technology that utilizes the heat energy of circulating cooling water to improve the thermal efficiency and economy of the nuclear power plant. The system consists of a heat energy recovery device, an intelligent controller and a cooling water pump. The heat energy recovery device transfers the heat energy of the circulating cooling water to other media, such as air, water or steam, through a heat exchanger, thereby realizing the utilization of heat energy. The intelligent controller automatically adjusts the operating parameters of the heat energy recovery device, such as heat exchange capacity, flow rate and temperature, according to the operating status of the nuclear power plant to ensure the safe and stable operation of the nuclear power plant. The cooling water pump is responsible for transporting the circulating cooling water between the heat energy recovery device and the reactor, and maintaining the pressure and flow rate of the circulating cooling water. This system can effectively reduce the water consumption and emissions of nuclear power plants, reduce greenhouse gas emissions, and improve the reliability and life of nuclear power plants.

[0027] Figure 1 shows a block diagram of an intelligent control system for heat recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application. As shown in Figure 1, the intelligent control system 100 for heat recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application includes: a heat recovery device 110 for transferring heat energy from the circulating cooling water to another medium via a heat exchanger; a cooling water pump 120 for transporting the circulating cooling water between the heat recovery device 110 and the reactor; and a controller 130 for adjusting the operating parameters of the heat recovery device 110.

[0028] Accordingly, in the intelligent control system for heat recovery from circulating cooling water in nuclear power plants, the intelligent controller can monitor and analyze the plant's operating status in real time, including the reactor's heat load, cooling water temperature, and flow rate. Based on this data, the intelligent controller can determine the current operating status and make appropriate adjustments based on pre-set control strategies.

[0029] Specifically, when the nuclear power plant's load is low, the intelligent controller can reduce the heat exchange rate and flow rate of the heat recovery device to avoid overheating and energy waste. Under higher load conditions, the intelligent controller can increase the heat exchange rate and flow rate to meet the plant's thermal needs. By precisely controlling and adjusting the operating parameters of the heat recovery device, the intelligent controller maximizes system efficiency and ensures that the system operates within a safe and stable range. Furthermore, the intelligent controller can automatically adjust the temperature control of the heat recovery device according to different operating modes to adapt to different operating conditions. For example, when the cooling water temperature is low, the intelligent controller can increase the temperature of the heat recovery device to improve heat exchange efficiency. When the cooling water temperature is high, the intelligent controller can reduce the temperature of the heat recovery device to prevent overheating and equipment damage.

[0030] FIG2 shows a block diagram of the controller 130 in the intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application. As shown in FIG2 , according to the intelligent control system 100 for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application, the controller 130 includes: a data acquisition module 131 for acquiring the heat load value, cooling water temperature value and flow value of the reactor at multiple predetermined time points within a predetermined time period; a data parameter timing arrangement module 132 for arranging the heat load value, cooling water temperature value and flow value of the reactor at the multiple predetermined time points into a heat load timing input vector, a cooling water temperature timing input vector and a cooling water flow timing input vector according to the time dimension; a cooling water heat exchange timing distribution module 133 for calculating the cooling water temperature timing input vector and the cooling water flow timing input vector by multiplying the position points by the cooling water temperature timing input vector and the cooling water flow timing input vector. a water heat exchange timing input vector; a data parameter local timing analysis module 134 for performing local timing analysis on the heat load timing input vector and the cooling water heat exchange timing input vector respectively to obtain a sequence of heat load local timing feature vectors and a sequence of cooling water heat exchange local timing feature vectors; a heat load-heat exchange timing interaction correlation encoding module 135 for performing parameter timing feature interaction correlation analysis on the sequence of heat load local timing feature vectors and the sequence of cooling water heat exchange local timing feature vectors to obtain a heat load-heat exchange timing interaction feature; and a cooling water flow control module 136 for determining whether the flow value of cooling water at the current time point should be increased or decreased based on the heat load-heat exchange timing interaction feature.

[0031] Specifically, in the technical solution of the present application, first, the heat load value of the reactor, the temperature value of the cooling water, and the flow value of the cooling water at multiple predetermined time points within a predetermined time period are obtained. Then, considering that the heat load value of the reactor, the temperature value of the cooling water, and the flow value of the cooling water all have a time-series dynamic change law in the time dimension, in order to be able to integrate the time-series change patterns and trends of these data parameters to perform parameter control of the heat recovery device, in the technical solution of the present application, it is necessary to arrange the heat load value of the reactor, the temperature value of the cooling water, and the flow value of the cooling water at the multiple predetermined time points into a heat load time-series input vector, a cooling water temperature time-series input vector, and a cooling water flow time-series input vector according to the time dimension, so as to respectively integrate the distribution information of the heat load value of the reactor, the temperature value of the cooling water, and the flow value in the time series.

[0032] It should be understood that the heat exchange of cooling water refers to the process of heat exchange between cooling water and other media in a heat recovery device. The temperature and flow rate of cooling water are important factors affecting the heat exchange effect. Therefore, it is necessary to associate and encode the two in order to more fully analyze the heat exchange characteristics and timing change patterns of cooling water. Specifically, in the technical solution of the present application, the cooling water temperature timing input vector and the cooling water flow timing input vector are further calculated by multiplying the position points to obtain the cooling water heat exchange timing input vector. In particular, here, the cooling water heat exchange timing input vector reflects the combined influence of cooling water temperature and flow rate.

[0033] Then, considering that the heat load time series input vector is a vector that describes the change in the heat load of the reactor, and the cooling water heat exchange time series input vector is a vector that describes the heat exchange situation of the cooling water in the heat energy recovery device. In addition, since the change in the heat load of the reactor and the heat exchange situation of the cooling water in the heat energy recovery device will show different change patterns and trends under different time period spans in the time dimension. Therefore, in order to be able to more fully analyze the heat exchange situation and process of the heat load and cooling water, in the technical solution of the present application, the heat load time series input vector and the cooling water heat exchange time series input vector are further vector-segmented to obtain a sequence of heat load local time series input vectors and a sequence of cooling water heat exchange local time series input vectors.

[0034] Then, the sequence of the local time series input vectors of the heat load and the sequence of the local time series input vectors of the cooling water heat exchange are respectively subjected to feature mining in a time series feature extractor based on a one-dimensional convolutional layer to extract the local time series feature information of the heat load and the cooling water heat exchange in the time dimension, thereby obtaining a sequence of local time series feature vectors of the heat load and a sequence of local time series feature vectors of the cooling water heat exchange.

[0035] Correspondingly, as shown in Figure 3, the data parameter local time series analysis module 134 includes: a vector segmentation unit 1341, which is used to perform vector segmentation on the heat load time series input vector and the cooling water heat exchange time series input vector respectively to obtain a sequence of heat load local time series input vectors and a sequence of cooling water heat exchange local time series input vectors; and a parameter local time series feature extraction unit 1342, which is used to pass the sequence of heat load local time series input vectors and the sequence of cooling water heat exchange local time series input vectors through a time series feature extractor based on a one-dimensional convolutional layer to obtain a sequence of heat load local time series feature vectors and a sequence of cooling water heat exchange local time series feature vectors.

[0036] It should be understood that the data parameter local time series analysis module 134 comprises two main units: a vector segmentation unit 1341 and a parameter local time series feature extraction unit 1342. The vector segmentation unit 1341 segments the input heat load time series input vector and the cooling water heat exchange time series input vector into a sequence of multiple local time series input vectors. This decomposes the original input vector into multiple smaller local time series vectors for subsequent processing. The parameter local time series feature extraction unit 1342 processes the sequence of heat load local time series input vectors and the sequence of cooling water heat exchange local time series input vectors using a time series feature extractor based on a one-dimensional convolutional layer. This extracts a corresponding sequence of time series feature vectors from each local time series vector for subsequent data analysis and processing. In short, the vector segmentation unit is used to segment the input vector into a sequence of local time series vectors, while the parameter local time series feature extraction unit is used to extract a sequence of feature vectors from these local time series vectors. The combination of these two units enables the data parameter local time series analysis module to analyze and process the input time series data.

[0037] Furthermore, considering that the sequence of the heat load local time series characteristic vectors and the sequence of the cooling water heat exchange local time series characteristic vectors represent the local time series characteristics of the heat load and the local time series characteristics of the cooling water heat exchange, respectively, in order to be able to integrate the heat load local time series and the cooling water heat exchange local time series to comprehensively control the parameters of the heat energy recovery device, in the technical solution of the present application, a parameter feature sequence time series interactor is further used to process the sequence of the heat load local time series characteristic vectors and the sequence of the cooling water heat exchange local time series characteristic vectors to obtain a heat load-heat exchange time series interaction feature vector. It should be understood that by using the parameter feature sequence time series interactor, the sequence of the heat load local time series characteristic vectors and the sequence of the cooling water heat exchange local time series characteristic vectors can be interacted and integrated, so as to better capture and represent the correlation and mutual influence between the heat load and the heat exchange.

[0038] Correspondingly, the heat load-heat exchange timing interaction association encoding module 135 is used to: use a parameter feature sequence timing interactor to process the sequence of the heat load local timing feature vectors and the sequence of the cooling water heat exchange local timing feature vectors to obtain a heat load-heat exchange timing interaction feature vector as the heat load-heat exchange timing interaction feature.

[0039] Specifically, the heat load-heat exchange time series interaction correlation coding module 135 is further configured to calculate the correlation between each heat load local time series feature vector in the sequence of the heat load local time series feature vector and each cooling water heat exchange local time series feature vector in the sequence of the cooling water heat exchange local time series feature vector using the following correlation formula, wherein the correlation formula is: ;in, The first in the sequence of the local time series characteristic vector of the heat load is represented by The first time series characteristic vector of the heat load and the local time series characteristic vector of the cooling water heat exchange are The correlation between the local time series feature vectors of cooling water heat exchange, The first in the sequence of the local time series characteristic vector of the heat load is represented by local time series characteristic vectors of heat load, and The first sequence of the local time series feature vectors of cooling water heat exchange is represented by The local time series characteristic vector of cooling water heat exchange, Represents a transposition operation; based on the correlation between each heat load local time series feature vector in the sequence of the heat load local time series feature vector and all cooling water heat exchange local time series feature vectors in the sequence of the cooling water heat exchange local time series feature vector and all cooling water heat exchange local time series feature vectors in the sequence of the cooling water heat exchange local time series feature vector, interactively update each heat load local time series feature vector in the sequence of the heat load local time series feature vector to obtain a sequence of updated heat load local time series feature vectors; based on the correlation between each cooling water heat exchange local time series feature vector in the sequence of the cooling water heat exchange local time series feature vector and all heat load local time series feature vectors in the sequence of the heat load local time series feature vector and all Thermal load local time series feature vector, interactively updating each cooling water heat exchange local time series feature vector in the sequence of cooling water heat exchange local time series feature vectors to obtain a sequence of updated cooling water heat exchange local time series feature vectors; fusing the sequence of thermal load local time series feature vectors and the sequence of updated thermal load local time series feature vectors to obtain a sequence of interactively fused thermal load local time series feature vectors; fusing the sequence of cooling water heat exchange local time series feature vectors and the sequence of updated cooling water heat exchange local time series feature vectors to obtain a sequence of interactively fused cooling water heat exchange local time series feature vectors; and, splicing the sequence of interactively fused thermal load local time series feature vectors and the sequence of interactively fused cooling water heat exchange local time series feature vectors to obtain the ground state multi-scale feature vector.

[0040] The heat load-heat exchange time-series interaction feature vector is then passed through a classifier to obtain a classification result. This classification result indicates whether the cooling water flow rate at the current point in time should be increased or decreased. In other words, the classification process utilizes the interactive correlation feature information between the local time-series characteristics of the heat load and the local time-series characteristics of the cooling water heat exchange, thereby enabling real-time adaptive control of the parameters of the heat recovery device.

[0041] Accordingly, the cooling water flow control module 136 is used to pass the heat load-heat exchange time series interaction feature vector through a classifier to obtain a classification result, wherein the classification result is used to indicate whether the cooling water flow value at the current time point should be increased or decreased.

[0042] More specifically, the cooling water flow control module 136 is further used to: use the fully connected layer of the classifier to fully connect the heat load-heat exchange time series interaction feature vector to obtain a coded classification feature vector; and input the coded classification feature vector into the Softmax classification function of the classifier to obtain the classification result.

[0043] It's easy to understand that a classifier uses given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression and SVM are commonly used to solve binary classification problems. For multi-class classification, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-class classification. However, this approach is error-prone and inefficient. A commonly used multi-classification method is the Softmax classification function.

[0044] Furthermore, in the technical solution of the present application, the intelligent control system for heat energy recovery of circulating cooling water in the nuclear power plant also includes a training module for training the one-dimensional convolutional layer-based temporal feature extractor, the parameter feature sequence temporal interactor and the classifier.

[0045] In one example, the training module includes: a training data acquisition unit for acquiring training data, wherein the training data includes the training heat load value of the reactor, the training temperature value of the cooling water and the training flow value at multiple predetermined time points within a predetermined time period, and a real value for indicating whether the flow value of the cooling water at the current time point should be increased or decreased; a training data parameter timing arrangement unit for arranging the training heat load value of the reactor, the training temperature value of the cooling water and the training flow value at the multiple predetermined time points into a training heat load timing input vector, a training cooling water temperature timing input vector and a training cooling water flow timing input vector according to the time dimension; a training cooling water heat exchange timing distribution unit for calculating the position point multiplication between the training cooling water temperature timing input vector and the training cooling water flow timing input vector to obtain a training cooling water heat exchange timing input vector; a training data parameter local timing analysis unit for respectively analyzing the training heat load timing input vector and the training cooling water temperature timing input vector. The training cooling water heat exchange time series input vector is subjected to local time series analysis to obtain a sequence of training heat load local time series feature vectors and a sequence of training cooling water heat exchange local time series feature vectors; a training heat load-heat exchange time series interaction correlation encoding unit is used to use a parameter feature sequence time series interactor to process the sequence of training heat load local time series feature vectors and the sequence of training cooling water heat exchange local time series feature vectors to obtain a training heat load-heat exchange time series interaction feature vector; a training correction unit is used to correct the training heat load-heat exchange time series interaction feature vector to obtain an optimized training heat load-heat exchange time series interaction feature vector; a training classification unit is used to pass the optimized training heat load-heat exchange time series interaction feature vector through a classifier to obtain a classification loss function value; and a loss training unit is used to train the one-dimensional convolutional layer-based time series feature extractor, the parameter feature sequence time series interactor and the classifier based on the classification loss function value.

[0046] In particular, in the technical solution of the present application, the sequence of the training heat load local time series feature vectors and the sequence of the training cooling water heat exchange local time series feature vectors respectively express the local time domain time series correlation characteristics of the heat load value and the heat exchange value of the cooling water in the local time domain determined from the global time domain through vector segmentation. In this way, after using the parameter feature sequence time series interactor to process the sequence of the training heat load local time series feature vectors and the sequence of the training cooling water heat exchange local time series feature vectors, the training heat load-heat exchange time series interaction feature vector, in addition to the local time domain time series correlation characteristics of the heat load value and the heat exchange value of the cooling water, also includes a time series interaction feature based on the local time domain sequence distribution, that is, the training heat load-heat exchange time series interaction feature vector has a multi-dimensional time series feature representation with multiple time domain scales.

[0047] However, considering that the distribution differences of time series feature representations at multiple time domain scales and multi-dimensional features will lead to the sparse distribution of local features relative to the overall feature representation of the training heat load-heat exchange time series interaction feature vector, that is, the sparse sub-manifold outside the distribution relative to the overall high-dimensional feature manifold, this will result in poor convergence of the training heat load-heat exchange time series interaction feature vector to the predetermined class probability category representation in the probability space when the training heat load-heat exchange time series interaction feature vector is subjected to class probability regression mapping through a classifier, thereby affecting the accuracy of the classification results. Therefore, it is preferred that the training heat load-heat exchange time series interaction feature vector be corrected.

[0048] Accordingly, in one example, the training correction unit is configured to correct the training heat load-heat exchange timing interaction feature vector using the following correction formula to obtain the optimized training heat load-heat exchange timing interaction feature vector; wherein the correction formula is: ;in, is the training heat load-heat exchange time series interaction feature vector, is the training heat load-heat exchange time series interaction feature vector No. The eigenvalues ​​at the positions, represents an exponential operation of a value, wherein the exponential operation of the value represents calculating the value of a natural exponential function with the value as a power, is the first character vector of the optimized training heat load-heat exchange time series interaction The eigenvalues ​​at each position.

[0049] That is, the sparse distribution in the high-dimensional feature space is processed by regularization based on heavy probability to activate the training heat load-heat exchange time series interaction feature vector The natural distribution transfer from the geometric manifold in the high-dimensional feature space to the probability space is achieved by training the heat load-heat exchange time series interaction feature vector The distribution sparse submanifold of the high-dimensional feature manifold is smoothed and regularized based on re-probability to improve the category convergence of the complex high-dimensional feature manifold with high spatial sparsity under the predetermined class probability, thereby improving the training heat load-heat exchange time series interaction feature vector The accuracy of the classification results obtained by the classifier. In this way, the parameters of the heat recovery device can be adaptively controlled based on the time-series changes in the reactor's thermal load and the temperature and flow of the cooling water, thereby improving the efficiency of the heat recovery device and ensuring that the heat recovery device can operate within a safe and stable operating range, thereby improving the thermal efficiency and economy of the nuclear power plant and reducing greenhouse gas emissions.

[0050] Furthermore, the loss training unit is used to: use the classifier to process the optimized training heat load-heat exchange time series interaction feature vector using the following training classification formula to obtain a training classification result; wherein the training classification formula is: ;in, arrive is the weight matrix, arrive is the bias vector, The optimization training heat load-heat exchange time series interaction feature vector is performed; and the cross entropy value between the training classification result and the true value is calculated as the classification loss function value.

[0051] In summary, the intelligent control system 100 for heat energy recovery of circulating cooling water in a nuclear power plant based on the embodiment of the present application is explained, which can effectively reduce the water consumption and emissions of the nuclear power plant, reduce greenhouse gas emissions, and improve the reliability and life of the nuclear power plant.

[0052] As described above, the intelligent control system 100 for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application can be implemented in various terminal devices, such as a server having an intelligent control algorithm for heat energy recovery of circulating cooling water in a nuclear power plant. In one example, the intelligent control system 100 for heat energy recovery of circulating cooling water in a nuclear power plant can be integrated into a terminal device as a software module and / or a hardware module. For example, the intelligent control system 100 for heat energy recovery of circulating cooling water in a nuclear power plant can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the intelligent control system 100 for heat energy recovery of circulating cooling water in a nuclear power plant can also be one of the many hardware modules of the terminal device.

[0053] Alternatively, in another example, the intelligent control system 100 for heat energy recovery of circulating cooling water in the nuclear power plant and the terminal device may also be separate devices, and the intelligent control system 100 for heat energy recovery of circulating cooling water in the nuclear power plant may be connected to the terminal device through a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0054] Figure 4 shows a flow chart of an intelligent control method for heat recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application. As shown in Figure 4, the intelligent control method for heat recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application includes: S110, transferring heat energy of the circulating cooling water to other media via a heat exchanger of a heat recovery device; S120, transporting the circulating cooling water between the heat recovery device and the reactor via a cooling water pump; and S130, adjusting operating parameters of the heat recovery device.

[0055] FIG5 is a schematic diagram showing the system architecture of sub-step S130 of the intelligent control method for heat energy recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application. As shown in FIG5 , in one possible implementation, adjusting the operating parameters of the heat energy recovery device includes: obtaining the heat load value of the reactor, the temperature value of the cooling water, and the flow value at a plurality of predetermined time points within a predetermined time period; arranging the heat load value, the temperature value of the cooling water, and the flow value at the plurality of predetermined time points into a heat load time series input vector, a cooling water temperature time series input vector, and a cooling water flow time series input vector according to the time dimension; calculating the cooling water heat load value obtained by multiplying the cooling water temperature time series input vector and the cooling water flow time series input vector by the position point. exchanging timing input vectors; performing local timing analysis on the heat load timing input vector and the cooling water heat exchange timing input vector respectively to obtain a sequence of heat load local timing characteristic vectors and a sequence of cooling water heat exchange local timing characteristic vectors; performing parameter timing characteristic interaction correlation analysis on the sequence of heat load local timing characteristic vectors and the sequence of cooling water heat exchange local timing characteristic vectors to obtain a heat load-heat exchange timing interaction characteristic; and, based on the heat load-heat exchange timing interaction characteristic, determining whether the flow value of cooling water at the current time point should be increased or decreased.

[0056] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned intelligent control method for heat energy recovery of circulating cooling water in a nuclear power plant have been introduced in detail in the description of the intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant with reference to Figures 1 to 3 above, and therefore, its repeated description will be omitted.

[0057] FIG6 illustrates an application scenario of an intelligent control system for heat recovery of circulating cooling water in a nuclear power plant according to an embodiment of the present application. As shown in FIG6 , in this application scenario, first, the reactor's heat load value (e.g., D1 as shown in FIG6 ), cooling water temperature value, and flow rate value (e.g., D2 as shown in FIG6 ) at multiple predetermined time points within a predetermined time period are obtained. Then, the reactor's heat load value, cooling water temperature value, and flow rate value at these multiple predetermined time points are input into a server (e.g., S as shown in FIG6 ) that is deployed with an intelligent control algorithm for heat recovery of circulating cooling water in a nuclear power plant. The server can use the intelligent control algorithm for heat recovery of circulating cooling water in a nuclear power plant to process the reactor's heat load value, cooling water temperature value, and flow rate value at these multiple predetermined time points to obtain a classification result indicating whether the cooling water flow rate value at the current time point should be increased or decreased.

[0058] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a special hardware-based system that performs the function or action of the specification, or can be implemented by a combination of special hardware and computer instructions.

[0059] The embodiments of the present application have been described above. The above description is illustrative and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to the technology in the market, or to enable other persons skilled in the art to understand the embodiments disclosed herein.

Claims

1. An intelligent control system for heat recovery of circulating cooling water in a nuclear power plant, comprising: Heat recovery device, used to transfer the heat energy of circulating cooling water to other media through a heat exchanger; A cooling water pump, used to transport the circulating cooling water between the heat energy recovery device and the reactor, characterized in that the heat energy recovery intelligent control system for circulating cooling water in the nuclear power plant also includes a controller, and the controller is used to adjust the working parameters of the heat energy recovery device; Wherein, the controller comprises: A data acquisition module, used to obtain the heat load value of the reactor, the temperature value and the flow value of the cooling water at a plurality of predetermined time points within a predetermined time period; A data parameter time series arrangement module, used for arranging the heat load values, cooling water temperature values ​​and flow values ​​of the reactor at the plurality of predetermined time points into a heat load time series input vector, a cooling water temperature time series input vector and a cooling water flow time series input vector according to the time dimension; A cooling water heat exchange timing distribution module, used for calculating the cooling water heat exchange timing input vector obtained by multiplying the cooling water temperature timing input vector and the cooling water flow timing input vector by a position point; A data parameter local time series analysis module, used for performing local time series analysis on the heat load time series input vector and the cooling water heat exchange time series input vector respectively to obtain a sequence of heat load local time series characteristic vectors and a sequence of cooling water heat exchange local time series characteristic vectors; A heat load-heat exchange time series interaction coding module, used for performing parameter time series feature interaction analysis on the sequence of the heat load local time series feature vectors and the sequence of the cooling water heat exchange local time series feature vectors to obtain a heat load-heat exchange time series interaction feature; and The cooling water flow control module is used to determine whether the flow value of the cooling water at the current time point should be increased or decreased based on the heat load-heat exchange timing interaction characteristics.

2. The intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to claim 1, characterized in that: The data parameter local timing analysis module comprises: a vector segmentation unit, configured to segment the heat load time series input vector and the cooling water heat exchange time series input vector respectively to obtain a sequence of heat load local time series input vectors and a sequence of cooling water heat exchange local time series input vectors; and A parameter local time series feature extraction unit is used to pass the sequence of the local time series input vector of the heat load and the sequence of the local time series input vector of the cooling water heat exchange through a time series feature extractor based on a one-dimensional convolutional layer to obtain a sequence of the local time series feature vectors of the heat load and a sequence of the local time series feature vectors of the cooling water heat exchange.

3. The intelligent control system for heat recovery of circulating cooling water in a nuclear power plant according to claim 2, characterized in that: The heat load-heat exchange timing interaction correlation coding module is used to: A parameter feature sequence timing interactor is used to process the sequence of the heat load local timing feature vectors and the sequence of the cooling water heat exchange local timing feature vectors to obtain a heat load-heat exchange timing interaction feature vector as the heat load-heat exchange timing interaction feature.

4. The intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to claim 3, characterized in that: The heat load-heat exchange timing interaction correlation coding module is used to: The correlation between each heat load local time series feature vector in the sequence of the heat load local time series feature vector and each cooling water heat exchange local time series feature vector in the sequence of the cooling water heat exchange local time series feature vector is calculated using the following correlation formula, wherein the correlation formula is: ;in, The first in the sequence of the local time series characteristic vector of the heat load is represented by The first in the sequence of the local time series characteristic vector of the heat load and the local time series characteristic vector of the cooling water heat exchange The correlation between the local time series feature vectors of cooling water heat exchange, The first in the sequence of the local time series characteristic vector of the heat load is represented by local time series characteristic vector of heat load, and The sequence of local time series feature vectors of cooling water heat exchange is The local time series characteristic vector of cooling water heat exchange, Represents a transpose operation; Based on the correlation between each heat load local time series feature vector in the sequence of the heat load local time series feature vector and all cooling water heat exchange local time series feature vectors in the sequence of the cooling water heat exchange local time series feature vector and all cooling water heat exchange local time series feature vectors in the sequence of the cooling water heat exchange local time series feature vector, interactively updating each heat load local time series feature vector in the sequence of the heat load local time series feature vector to obtain a sequence of updated heat load local time series feature vectors; Based on the correlation between each cooling water heat exchange local time series feature vector in the sequence of cooling water heat exchange local time series feature vectors and all heat load local time series feature vectors in the sequence of heat load local time series feature vectors and all heat load local time series feature vectors in the sequence of heat load local time series feature vectors, interactively updating each cooling water heat exchange local time series feature vector in the sequence of cooling water heat exchange local time series feature vectors to obtain a sequence of updated cooling water heat exchange local time series feature vectors; Fusion of the sequence of heat load local time series feature vectors and the sequence of updated heat load local time series feature vectors to obtain an interactive fusion sequence of heat load local time series feature vectors; Fusing the sequence of cooling water heat exchange local time series feature vectors and the sequence of updated cooling water heat exchange local time series feature vectors to obtain an interactively fused sequence of cooling water heat exchange local time series feature vectors; and The sequence of the interactively fused heat load local time series feature vectors and the sequence of the interactively fused cooling water heat exchange local time series feature vectors are spliced ​​to obtain the ground state multi-scale feature vector.

5. The intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to claim 4, characterized in that: The cooling water flow control module is used for: The heat load-heat exchange time series interaction feature vector is passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the flow value of the cooling water at the current time point should be increased or decreased.

6. The intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to claim 5, characterized in that: It also includes a training module for training the one-dimensional convolutional layer-based temporal feature extractor, the parameter feature sequence temporal interactor and the classifier.

7. The intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to claim 6, characterized in that: The training module comprises: A training data acquisition unit, used to obtain training data, wherein the training data includes training heat load values ​​of the reactor, training temperature values ​​and training flow values ​​of cooling water at multiple predetermined time points within a predetermined time period, and a real value indicating that the flow value of cooling water at a current time point should be increased or decreased; A training data parameter time series arrangement unit, used to arrange the training heat load values ​​of the reactor, the training temperature values ​​of the cooling water and the training flow values ​​at the plurality of predetermined time points into a training heat load time series input vector, a training cooling water temperature time series input vector and a training cooling water flow time series input vector according to the time dimension respectively; A training cooling water heat exchange timing distribution unit, used for calculating the training cooling water temperature timing input vector and the training cooling water flow timing input vector by multiplying them by position points to obtain a training cooling water heat exchange timing input vector; A training data parameter local time series analysis unit, used to perform local time series analysis on the training heat load time series input vector and the training cooling water heat exchange time series input vector respectively to obtain a sequence of training heat load local time series feature vectors and a sequence of training cooling water heat exchange local time series feature vectors; A training heat load-heat exchange time series interaction correlation encoding unit, used to process the sequence of the training heat load local time series feature vectors and the sequence of the training cooling water heat exchange local time series feature vectors using a parameter feature sequence time series interactor to obtain a training heat load-heat exchange time series interaction feature vector; A training correction unit, used for correcting the training heat load-heat exchange timing interaction feature vector to obtain an optimized training heat load-heat exchange timing interaction feature vector; A training classification unit, used for passing the optimized training heat load-heat exchange time series interaction feature vector through a classifier to obtain a classification loss function value; and A loss training unit is used to train the one-dimensional convolutional layer-based temporal feature extractor, the parameter feature sequence temporal interactor and the classifier based on the classification loss function value.

8. The intelligent control system for heat energy recovery of circulating cooling water in a nuclear power plant according to claim 7, characterized in that: The loss training unit is used to: The classifier is used to process the optimized training heat load-heat exchange time series interaction feature vector using the following training classification formula to obtain a training classification result; wherein the training classification formula is: ;in, arrive is the weight matrix, arrive is the bias vector, training a heat load-heat exchange time series interaction feature vector for said optimization; and A cross entropy value between the training classification result and the true value is calculated as the classification loss function value.

Images