Nuclear power unit power control method and system based on seawater temperature and tide level prediction

Abstract

The invention relates to a nuclear power unit power control method and system based on seawater temperature and tide level prediction, and the method comprises the steps: obtaining seawater temperature data of a sea area where a nuclear power unit is located in past first set time, and predicting the seawater temperature after second set time according to the seawater temperature data, so as to obtain a predicted temperature; obtaining tide data of a sea area where the nuclear power unit is located within a third set time, and predicting a tide level after the second set time according to the tide data to obtain a predicted tide level; and obtaining historical operation data of the nuclear power unit, and determining an electric power set value of the nuclear power unit according to the historical operation data, the predicted temperature and the predicted tide level. The power generation power and stability of the nuclear power unit can be improved, and the over-power risk of the unit is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear power plant power control, and particularly to a method and system for controlling the power of a nuclear power unit based on the prediction of seawater temperature and tide level. Background Art

[0002] Currently, the power control of nuclear power units usually adopts the reactor following turbine control mode, that is, after setting the electric power value, the reactor core automatically matches the corresponding thermal power. However, when the performance of the condenser in the steam turbine generator set changes, it will cause the efficiency of the nuclear power unit to change, and the thermal power of the reactor core will also fluctuate accordingly. Moreover, the reactor following turbine control mode has hysteresis, resulting in a mismatch between the electric power and the thermal power when the set electric power value obtained based on the real-time historical operation data of the unit takes effect, which will cause the thermal power fluctuation of the nuclear power unit to become larger and the risk of reactor core over-power is relatively high. For example, when the seawater temperature rises or the tide level drops, when the performance of the condenser deteriorates, if the set electric power remains unchanged or lags, it will cause the heat in the primary loop to increase and the risk of reactor core over-power to increase. Therefore, currently, a relatively conservative method is usually adopted to control the unit power, that is, to reduce the electric power of the unit, thus resulting in a relatively low actual electric power of the unit and reducing the economic benefits of the nuclear power plant. And when the seawater temperature drops or the tide level rises, the performance of the condenser becomes better. In theory, the set value of the electric power can be increased. Due to the hysteretic characteristics of the current operation control, the thermal power cannot follow up in time, so the thermal power of the reactor core continues to decrease and the fluctuation range of the unit thermal power becomes larger, seriously affecting the economy of the unit. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for controlling the power of a nuclear power unit based on the prediction of seawater temperature and tide level.

[0004] The technical solution adopted by the present invention to solve its technical problem is to construct a method for controlling the power of a nuclear power unit based on the prediction of seawater temperature and tide level, including: Obtaining the seawater temperature data of the sea area where the nuclear power unit is located in the past first set time, and predicting the seawater temperature after the second set time according to the seawater temperature data to obtain a predicted temperature; Obtaining the tide data within the third set time of the sea area where the nuclear power unit is located, and predicting the tide level after the second set time according to the tide data to obtain a predicted tide level; Obtaining the historical operation data of the nuclear power unit, and determining the set value of the electric power of the nuclear power unit according to the historical operation data, the predicted temperature and the predicted tide level; wherein, the historical operation data includes historical thermal power data, historical electric power data, historical seawater temperature data and historical tide level data; The step of predicting the seawater temperature after a second set time based on the seawater temperature data includes: determining the extreme point in the seawater temperature data with the closest acquisition time to the current time; defining the time period from the acquisition time of the extreme point to the current time as the target time period, and extracting the data segment corresponding to the target time period from the seawater temperature data to obtain the target data segment; performing trend line fitting on the target data segment to obtain an extrapolation prediction model for predicting the future seawater temperature; and inputting the second set time into the extrapolation prediction model to obtain the predicted temperature.

[0005] Preferably, the step of obtaining the seawater temperature data of the sea area where the nuclear power unit is located in the past first set time includes: Obtaining the seawater temperature information of the sea area where the nuclear power unit is located in the past first set time at a set time resolution to obtain the seawater temperature data; wherein, the set time resolution is 1 minute.

[0006] Preferably, the step of predicting the tide level after the second set time based on the tide data includes: Calculating the tidal harmonic constants corresponding to a set number of tidal components according to the harmonic analysis method and the tide data to obtain a set of harmonic constants; the set of harmonic constants includes a set number of tidal harmonic constants, and each tidal harmonic constant includes the average amplitude of the tidal component and the zone-time specific phase lag; Calculating the correlation coefficients of a set of tidal formulas according to the set of harmonic constants and the tide data; Determining the prediction time according to the current time and the second set time; Calculating the predicted tide level according to the prediction time, the set of harmonic constants and the set of tidal formulas; wherein, the set of tidal formulas is expressed as: ; represents the predicted tide level, represents the average sea surface height within the third set time, t represents the prediction time, f represents the intersection factor of the tidal component, H represents the average amplitude of the tidal component, represents the angular rate of the tidal component, represents the initial phase angle of the equilibrium tide tidal component at Greenwich zero hour, g represents the zone-time specific phase lag, represents the non-astronomical tide level.

[0007] Preferably, the step of determining the electric power setting value of the nuclear power unit according to the historical operation data, the predicted temperature and the predicted tide level includes: Constructing an initial model based on a predetermined neural network algorithm; Train the initial model according to the historical operation data. After the training is completed, an electric power determination model is obtained. The electric power determination model is used to output an electric power set value according to the input thermal power, seawater temperature, and tide level. Obtain the real-time thermal power, and input the real-time thermal power, the predicted temperature, and the predicted tide level into the electric power determination model to obtain the electric power set value.

[0008] Preferably, the predetermined neural network algorithm includes a multi-layer perceptron. The training process of the initial model includes: Preprocess the historical operation data to obtain processed data; Divide the processed data into a training set, a validation set, and a test set; Initialize the network parameters of the initial model; Use the training set, the validation set, and the test set to iteratively train the initial model, and optimize the network parameters during the training process to finally obtain an electric power determination model that meets the set prediction accuracy requirements.

[0009] Preferably, the setting range of the first set time is 300 minutes to 600 minutes, the setting range of the second set time is 10 minutes to 30 minutes, and the third set time is equal to 1 year.

[0010] Preferably, the nuclear power unit power control method based on the prediction of seawater temperature and tide level further includes: Obtain the set monitoring data, and determine whether there is an over-limit alarm for the nuclear power unit according to the set monitoring data. If so, output an alarm signal; the set monitoring data includes the real-time nuclear power and the 1-minute sliding average thermal power.

[0011] Preferably, the nuclear power unit power control method based on the prediction of seawater temperature and tide level further includes: Obtain the real-time electric power, the actual value of the 24H seawater temperature, and the actual value of the 24H tide level; Display the electric power set value, the predicted tide level, the predicted temperature, the real-time nuclear power, the real-time electric power, the actual value of the 24H seawater temperature, and the actual value of the 24H tide level.

[0012] The present invention also constructs a nuclear power unit power control system based on the prediction of seawater temperature and tide level, including: A temperature prediction unit for obtaining seawater temperature data of the sea area where the nuclear power unit is located in the past first set time with a set time resolution, and predicting the seawater temperature after the second set time according to the seawater temperature data to obtain a predicted temperature; wherein, the set time resolution is 1 minute; A tide level prediction unit, configured to obtain tide data within a third set time in the sea area where the nuclear power unit is located, and predict the tide level after the second set time according to the tide data to obtain a predicted tide level; An electric power determination unit, configured to obtain historical operation data of the nuclear power unit, and determine a set value of the electric power of the nuclear power unit according to the historical operation data, the predicted temperature, and the predicted tide level; wherein, the historical operation data includes historical thermal power data, historical electric power data, historical seawater temperature data, and historical tide level data.

[0013] Preferably, the nuclear power unit power control system based on seawater temperature and tide level prediction further includes: An alarm unit, configured to obtain set monitoring data, determine whether there is an over-limit alarm for the nuclear power unit according to the set monitoring data, and output an alarm signal if so; the set monitoring data includes real-time nuclear power and 1-minute sliding average thermal power; A display unit, configured to obtain real-time electric power, actual 24H seawater temperature value, and actual 24H tide level value, and display the set value of the electric power, the predicted tide level, the predicted temperature, the real-time nuclear power, the real-time electric power, the actual 24H seawater temperature value, and the actual 24H tide level value.

[0014] Implementing the present invention has the following beneficial effects: providing a nuclear power unit power control method based on seawater temperature and tide level prediction, which can prospectively determine the set value of the electric power, assist the staff in setting the electric power to a more suitable value, solve the lag problem of the reactor following turbine control mode, thereby improving the actual power generation level of the nuclear power unit and reducing the risk of over-power of the unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the drawings and embodiments, in the drawings: Figure 1 is a program flowchart of a nuclear power unit power control method based on seawater temperature and tide level prediction in some embodiments of the present invention; Figure 2 is a program flowchart of determining the predicted temperature in some embodiments of the present invention; Figure 3 is a program flowchart of determining the predicted tide level in some embodiments of the present invention; Figure 4 is a program flowchart of determining the set value of the electric power in some embodiments of the present invention; Figure 5 is a schematic structural diagram of a nuclear power unit power control system based on seawater temperature and tide level prediction in some embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to have a clearer understanding of the technical features, objectives, and effects of the present invention, the specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0017] It should be noted that the flowcharts shown in the accompanying drawings are only illustrative, and do not necessarily include all the contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined. Therefore, the actual execution order may change according to the actual situation.

[0018] The block diagrams shown in the accompanying drawings are only functional entities, and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices. Figure 1 is a program flowchart of a nuclear power unit power control method based on seawater temperature and tide level prediction in some embodiments of the present invention. This nuclear power unit power control method can predict the set value of the electric power, thereby improving the actual power generation level of the nuclear power unit, reducing the fluctuation of the core thermal power, and reducing the risk of core over-power. It should be noted that seawater temperature and tide level are one of the important factors affecting the performance of the condenser.

[0019] Please refer to Figure 1 , the nuclear power unit power control method based on seawater temperature and tide level prediction may include step S10, step S20, and step S30.

[0020] Step S10 includes: obtaining the seawater temperature data of the sea area where the nuclear power unit is located in the past first set time, and predicting the seawater temperature after the second set time based on the seawater temperature data to obtain the predicted temperature.

[0021] In some embodiments, the above-mentioned seawater temperature data can be obtained by performing the following steps: obtaining the seawater temperature information of the sea area where the nuclear power unit is located in the past first set time at a set time resolution to obtain the seawater temperature data.

[0022] It should be noted that the current nuclear power plant is equipped with seawater temperature monitoring equipment. Therefore, in this embodiment, the seawater temperature data can be obtained by establishing communication with the seawater temperature monitoring equipment. It can be understood that the seawater temperature data output by the seawater temperature monitoring equipment includes multiple seawater temperature information arranged from early to late in time, and the set time resolution refers to the time interval between two adjacent temperature information. Since the seawater temperature is generally relatively stable in a short period of time, there is no need for too small a resolution. And data simplification can significantly reduce the amount of seawater temperature data, reducing the computational workload of the processor when implementing the subsequent computer program steps. This can not only improve the computational efficiency of the present invention and reduce the hardware load, but also filter out some temperature information noise, which helps to improve the accuracy of temperature prediction. The set time resolution should not be too large. In some embodiments, the set time resolution can be 1 minute. Of course, the set time resolution can also be custom-set according to requirements.

[0023] In some embodiments, the setting range of the first set time can be from 300 minutes to 600 minutes. It should be noted that the first set time should not be too small or too large, as being too small or too large will result in a reduced reference significance. Therefore, the first set time is preferably 500 minutes.

[0024] In some embodiments, the setting range of the second set time can be from 10 minutes to 30 minutes. It should be noted that if the second set time is too small, it will not be able to ensure the lag of the compensation electric power setting, and if it is too large, it will not be conducive to the control of the prediction accuracy. Therefore, the second set time is preferably 15 minutes.

[0025] Figure 2 It is a program flowchart for determining the predicted temperature in some embodiments of the present invention. Please refer to Figure 2 In some embodiments, the seawater temperature after the second set time can be predicted by executing step S101 to step S104.

[0026] Step S101 includes: determining the extreme point in the seawater temperature data whose acquisition time is closest to the current time.

[0027] In this step, the extreme point can be a minimum value or a maximum value. In some embodiments, the extreme point can be determined by performing the following steps: Curve fitting is performed on the seawater temperature data by the least squares method to obtain a temperature change curve; it is determined whether the temperature change curve has an inflection point. When the temperature change curve has an inflection point, the inflection point with the acquisition time closest to the current time is determined as the extreme point; when the temperature change curve does not have an inflection point, the sampling point that conforms to the set regulations on the temperature change curve is set as the extreme point; wherein, the acquisition time of the sampling point is equal to the current time minus the fourth set time. Among them, the setting range of the fourth set time can be from 60 minutes to 300 minutes, preferably 100 minutes. It can be understood that when the temperature change suddenly changes from an upward trend to a downward trend or from a downward trend to an upward trend, an inflection point will be generated. The temperature change curve refers to the curve of temperature changing with the sampling time, that is, the temperature change curve includes multiple temperature values and the sampling time corresponding to each temperature value.

[0028] Step S102 includes: defining the time period from the acquisition time of the extreme point to the current time as the target time period, and extracting the data segment corresponding to the target time period from the seawater temperature data to obtain the target data segment.

[0029] Step S103 includes: performing trend line fitting on the target data segment to obtain an extrapolation prediction model for predicting the future seawater temperature. Specifically, curve fitting can be performed on the target data segment by the polynomial fitting method to obtain the extrapolation prediction model. Among them, the function of the extrapolation prediction model can be expressed as: T1 = dT / dt * △t + T0, where T1 represents the predicted temperature, dT / dt represents the slope, △t represents the second set time, and T0 represents the seawater temperature at the current time.

[0030] Step S104 includes: inputting the second set time into the extrapolation prediction model to obtain the predicted temperature.

[0031] Step S20 includes: obtaining the tidal data within the third set time in the sea area where the nuclear power unit is located, and predicting the water level after the second set time according to the tidal data to obtain the predicted water level. In this step, since the nuclear power plant records the historical tidal data of its sea area, the tidal data within the third set time can be extracted from the corresponding database. Among them, the third set time can be equal to 1 year.

[0032] Figure 3 is the program flow chart for determining the predicted water level in some embodiments of the present invention. In some embodiments, the water level after the second set time can be predicted by performing steps S201 to S204.

[0033] Step S201 includes: calculating the tidal harmonic constants corresponding to a set number of tidal constituents based on the harmonic analysis method and tidal data to obtain a set of harmonic constants. In this step, the existing harmonic analysis method can be used to analyze the tidal data to determine the tidal harmonic constants. It can be understood that the set of harmonic constants includes the tidal harmonic constants of the set number, and each tidal harmonic constant includes the average amplitude of the tidal constituent and the zone-time specific retardation angle. Among them, the set number can be equal to 60.

[0034] Step S202 includes: calculating the correlation coefficients of the set tidal formula according to the set of harmonic constants and the tidal data. Among them, the set tidal formula is used to calculate the predicted tide level according to the correlation coefficients and the prediction time.

[0035] In some embodiments, the set tidal formula can be expressed as: 。

[0036] Among them, represents the predicted tide level, represents the average sea surface height within the third set time, t represents the prediction time, f represents the intersection factor of the tidal constituent, H represents the average amplitude of the tidal constituent, represents the angular rate of the tidal constituent, represents the Greenwich mean zero equilibrium tide constituent initial phase angle (i.e., ), g represents the zone-time specific retardation angle, represents the non-astronomical tide level.

[0037] In this step, the tidal data includes the seawater periodic ebb and flow time, sea surface height, and tidal constituent information (including amplitude, angular rate, phase angle, retardation angle, etc.) within the third set time, and the correlation coefficients include the average sea surface height, intersection factor set, angular rate set of tidal constituents, Greenwich mean zero equilibrium tide constituent initial phase angle set, and non-astronomical tide level. Among them, the intersection factor set includes the intersection factors of multiple tidal constituents corresponding one by one to each tidal harmonic constant, the angular rate set of tidal constituents includes the angular rates of multiple tidal constituents corresponding one by one to each tidal harmonic constant, and the Greenwich mean zero equilibrium tide constituent initial phase angle set includes the Greenwich mean zero equilibrium tide constituent initial phase angles of multiple tidal constituents corresponding one by one to each tidal harmonic constant. It can be understood that the tidal data is substituted into the set tidal formula to calculate the said correlation coefficients. Among them, the non-astronomical tide level is random and can be regarded as noise.

[0038] Step S203 includes: determining the prediction time according to the current time and the second set time. In this step, adding the second set time to the current time can obtain the prediction time.

[0039] Step S204 includes: calculating the predicted tide level according to the predicted time, the set of harmonic constants, and the set tidal formula. In this step, by substituting the predicted time and the set of harmonic constants into the set tidal formula, the predicted tide level can be obtained.

[0040] Of course, the existing tide level prediction methods can also be used to predict the tide level, so as to obtain the predicted tide level.

[0041] Step S30 includes: obtaining the historical operation data of the nuclear power unit, and determining the electric power setting value of the nuclear power unit according to the historical operation data, the predicted temperature, and the predicted tide level; wherein, the historical operation data includes historical thermal power data, historical electric power data, historical seawater temperature data, and historical tide level data.

[0042] Figure 4 It is the program flow chart for determining the electric power setting value in some embodiments of the present invention. In some embodiments, the electric power setting value of the nuclear power unit can be determined by executing Step S301 to Step S203.

[0043] Step S301 includes: constructing an initial model based on a predetermined neural network algorithm. In this step, the predetermined neural network algorithm can include neural network algorithms such as multi-layer perceptron (MLP) and recurrent neural network (RNN). Preferably, the initial model is constructed by using a multi-layer perceptron. The multi-layer perceptron has the advantages of being easy to implement and having strong flexibility, which helps to reduce the R & D cost and cycle of the present invention project.

[0044] Step S302 includes: training the initial model according to the historical operation data. After the training is completed, an electric power determination model is obtained. The electric power determination model is used to output the electric power setting value according to the input thermal power, seawater temperature, and tide level. Taking the multi-layer perceptron as an example, the training steps of the multi-layer perceptron include: preprocessing the historical operation data (including normalization processing and standardization processing) to obtain the processed data; dividing the processed data into a training set, a validation set, and a test set; initializing the network parameters of the initial model (including weights, biases, loss functions, optimizers, activation functions, etc.); using the training set, the validation set, and the test set to perform iterative training on the initial model, and optimizing the network parameters during the training process, and finally obtaining an electric power determination model that meets the set prediction accuracy requirements.

[0045] Step S303 includes: obtaining the real-time thermal power, and inputting the real-time thermal power, the predicted temperature, and the predicted tide level into the electric power determination model to obtain the electric power setting value.

[0046] Please refer to Figure 1 , in some embodiments, the nuclear power unit power control method may further include Step S40 and Step S50.

[0047] Step S40 includes: obtaining the set monitoring data, determining whether there is an over-limit alarm for the nuclear power unit according to the set monitoring data, and outputting an alarm signal if so; the set monitoring data includes the real-time nuclear power and the 1-minute sliding average thermal power. It should be noted that the 1-minute sliding average thermal power includes the thermal power within the most recent 1 minute, and the 1-minute sliding average thermal power can be obtained through communication with the DCS system of the nuclear power plant.

[0048] In some embodiments, it is possible to determine whether there is an over-limit alarm for the nuclear power unit by performing the following steps: Judge whether the real-time nuclear power is greater than the set nuclear power threshold, and output a nuclear power over-limit alarm signal if so; Judge whether the 1-minute sliding average thermal power is greater than the set thermal power threshold, and output a thermal power over-limit alarm signal if so; Calculate the temperature change rates corresponding to multiple set gradients of the seawater temperature within the fifth set time based on the seawater temperature data, obtain multiple temperature change rates corresponding one by one to the multiple set gradients, judge whether each temperature change rate is greater than the corresponding preset change rate threshold, and when there is at least one temperature change rate greater than its corresponding preset change rate threshold, output a seawater temperature gradient alarm signal.

[0049] It should be noted that the multiple set gradients can be set according to requirements, and the preset change rate thresholds corresponding to each set gradient can be different or the same. The fifth set time can be equal to 30 minutes.

[0050] Since the present invention determines the electric power set value based on the predicted temperature and the predicted tide level, and the predicted temperature and the predicted tide level may not be highly consistent with the future actual situation (theoretically, the predicted value and the actual situation do not differ much, and a certain deviation is normal). When there is a large difference between the predicted value and the future actual value, there may be a certain safety risk. The function of step S40 is to monitor the short-term nuclear power, nuclear power, and the changes in seawater temperature of the nuclear power unit to eliminate the above-mentioned safety risk and ensure the safe operation of the nuclear power unit.

[0051] Step S50 includes: obtaining the real-time electric power, the actual value of the seawater temperature in 24 hours, and the actual value of the tide level in 24 hours, and displaying the electric power set value, the predicted tide level, the predicted temperature, the real-time nuclear power, the real-time electric power, the actual value of the seawater temperature in 24 hours, and the actual value of the tide level in 24 hours.

[0052] It should be noted that the actual 24H seawater temperature includes the seawater temperature information sensed by the seawater temperature monitoring device within the most recent 24 hours; the actual 24H tide level includes the tide level information within the most recent 24 hours, which can be obtained through existing tide level monitoring devices. The real-time nuclear power can be extracted from the 1-minute nuclear power data. In step S50, the electric power set value, predicted tide level, predicted temperature, real-time nuclear power, real-time electric power, actual 24H seawater temperature value, and actual 24H tide level value can be input into the display terminal, and then the above parameters can be displayed, enabling the staff to observe the above parameters in real time on-site so as to take corresponding measures in a timely manner when abnormalities are found. In addition, the real-time electric power can be obtained by communicating with the DCS system.

[0053] It can be understood that the present invention pre-stores according to the historical change trends of seawater temperature and tide level to obtain the predicted temperature and predicted tide level after the second set time in the future, and then prospectively determines the electric power set value based on the historical operation data, predicted temperature, and predicted tide level of the nuclear power unit, assisting the staff to set the electric power to a more suitable value, solving the lag problem of the reactor following turbine control mode, thereby improving the actual power generation of the nuclear power unit and reducing the risk of over-power of the unit.

[0054] Figure 5 It is a schematic structural diagram of a nuclear power unit power control system based on the prediction of seawater temperature and tide level in some embodiments of the present invention. Please refer to Figure 5 , the nuclear power unit power control system based on the prediction of seawater temperature and tide level may include a temperature prediction unit 1, a tide level prediction unit 2, and an electric power determination unit 3.

[0055] The temperature prediction unit 1 is used to obtain the seawater temperature data of the sea area where the nuclear power unit is located in the past first set time with a set time resolution, and predict the seawater temperature after the second set time based on the seawater temperature data to obtain the predicted temperature. It should be noted that the determination process of the predicted temperature can refer to the specific steps of step 10 above and will not be elaborated here.

[0056] The tide level prediction unit 2 is used to obtain the tidal data within the third set time of the sea area where the nuclear power unit is located, and predict the tide level after the second set time based on the tidal data to obtain the predicted tide level. It should be noted that the determination process of the predicted tide level can refer to the specific steps of step 20 above and will not be elaborated here.

[0057] The electric power determination unit 3 is used to obtain the historical operation data of the nuclear power unit, and determine the electric power set value of the nuclear power unit based on the historical operation data, predicted temperature, and predicted tide level; wherein, the historical operation data includes historical thermal power data, historical electric power data, historical seawater temperature data, and historical tide level data. It should be noted that the determination process of the electric power set value can refer to the specific steps of step 30 above and will not be elaborated here.

[0058] Please refer to Figure 5 , in some embodiments, the nuclear power unit power control system may further include an alarm unit 4 and a display unit 5.

[0059] The alarm unit 4 is configured to obtain set monitoring data, determine whether there is an over-limit alarm for the nuclear power unit according to the set monitoring data, and output an alarm signal if so; the set monitoring data includes real-time nuclear power and 1-minute sliding average thermal power.

[0060] The display unit 5 is configured to obtain the actual 24H seawater temperature value and the actual 24H tide level value, and display the electric power set value, predicted tide level, predicted temperature, real-time nuclear power, real-time electric power, actual 24H seawater temperature value and actual 24H tide level value.

[0061] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, please refer to the description of the method part.

[0062] Those skilled in the art can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0063] The steps of the methods or algorithms described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0064] It can be understood that the above embodiments only represent the preferred embodiments of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the present invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, the above technical features can be freely combined, and several deformations and improvements can also be made, which all fall within the protection scope of the present invention. Therefore, all equivalent transformations and modifications made to the scope of the claims of the present invention shall fall within the scope covered by the claims of the present invention.

Claims

1. A method for controlling nuclear power unit power based on seawater temperature and tide level prediction, characterized in that: include: Acquire seawater temperature data of the sea area where the nuclear power unit is located at a first set time in the past, and predict the seawater temperature after a second set time based on the seawater temperature data to obtain a predicted temperature; Acquiring tidal data of the sea area where the nuclear power unit is located within a third set time, and predicting the tidal level after the second set time according to the tidal data to obtain a predicted tidal level; Acquire historical operation data of the nuclear power unit, and determine the electric power setting value of the nuclear power unit according to the historical operation data, the predicted temperature and the predicted tide level; wherein the historical operation data includes thermal power historical data, electric power historical data, seawater temperature historical data and tide level historical data; The step of predicting the seawater temperature after a second set time based on the seawater temperature data includes: determining the extreme point in the seawater temperature data that is closest to the current time at the time of collection; defining the time period from the time of collection of the extreme point to the current time as the target time period, extracting the data segment corresponding to the target time period from the seawater temperature data to obtain the target data segment; performing trend line fitting on the target data segment to obtain an extrapolated prediction model for predicting future seawater temperature; and inputting the second set time into the extrapolated prediction model to obtain the predicted temperature.

2. The method for controlling nuclear power unit power based on seawater temperature and tide level prediction according to claim 1, characterized in that: The step of obtaining the seawater temperature data of the first set time in the past in the sea area where the nuclear power unit is located includes: The seawater temperature information of the sea area where the nuclear power unit is located at the first set time in the past is obtained with a set time resolution to obtain seawater temperature data; wherein the set time resolution is 1 minute.

3. The method for controlling nuclear power unit power based on seawater temperature and tide level prediction according to claim 1, characterized in that: The step of predicting the tide level after the second set time according to the tide data comprises: Calculate the tidal harmonic constants corresponding to a set number of partial tides according to the harmonic analysis method and the tidal data to obtain a set of harmonic constants; the set of harmonic constants includes a set number of tidal harmonic constants, each of which includes an average amplitude of the partial tide and a time-specific delay angle; Calculate the correlation coefficient of the set tidal formula according to the set of harmonic constants and the tidal data; Determine the predicted time according to the current time and the second set time; The predicted tide level is calculated according to the predicted time, the set of harmonic constants and the set tide formula; wherein the set tide formula is expressed as: ; represents the predicted tide level, represents the average sea level within the third setting time, t represents the predicted time, f represents the intersection factor of the partial tide, H represents the average amplitude of the partial tide, represents the tidal angle rate, It represents the initial phase angle of the equilibrium tidal component at Greenwich zero hour, g represents the time delay angle for the zone time, Represents non-astronomical tide levels.

4. The method for controlling nuclear power unit power based on seawater temperature and tide level prediction according to any one of claims 1 to 3, characterized in that: The step of determining the electric power setting value of the nuclear power unit according to the historical operation data, the predicted temperature and the predicted tide level comprises: Constructing an initial model based on a predetermined neural network algorithm; The initial model is trained according to the historical operation data, and after the training is completed, an electric power determination model is obtained, wherein the electric power determination model is used to output an electric power setting value according to input thermal power, seawater temperature and tide level; The real-time thermal power is acquired, and the real-time thermal power, the predicted temperature and the predicted tide level are input into the electric power determination model to obtain the electric power setting value.

5. The method for controlling nuclear power unit power based on seawater temperature and tide level prediction according to claim 4, characterized in that: The predetermined neural network algorithm includes a multi-layer perceptron, and the initial model training process includes: Preprocessing the historical operation data to obtain processed data; Dividing the processed data into a training set, a validation set and a test set; Initializing network parameters of the initial model; The initial model is iteratively trained using the training set, the validation set and the test set, and network parameters are optimized during the training process, so as to finally obtain an electric power determination model that meets the set prediction accuracy requirements.

6. The method for controlling nuclear power unit power based on seawater temperature and tide level prediction according to claim 4, characterized in that: The setting range of the first setting time is 300 minutes to 600 minutes, the setting range of the second setting time is 10 minutes to 30 minutes, and the third setting time is equal to 1 year.

7. The method for controlling nuclear power unit power based on seawater temperature and tide level prediction according to claim 5, characterized in that: Also includes: Acquire set monitoring data, determine whether the nuclear power unit has an over-limit alarm according to the set monitoring data, and if so, output an alarm signal; The set monitoring data includes real-time nuclear power and 1-minute sliding average thermal power.

8. The method for controlling nuclear power unit power based on seawater temperature and tide level prediction according to claim 7, characterized in that: Also includes: Obtain real-time electric power, 24-hour actual seawater temperature and 24-hour actual tide level; The electric power setting value, the predicted tide level, the predicted temperature, the real-time nuclear power, the real-time electric power, the 24-hour actual seawater temperature value and the 24-hour actual tide level value are displayed.

9. A nuclear power unit power control system based on seawater temperature and tide level prediction, characterized in that: include: A temperature prediction unit is used to obtain seawater temperature data of the sea area where the nuclear power unit is located at a first set time in the past with a set time resolution, and predict the seawater temperature after a second set time based on the seawater temperature data to obtain a predicted temperature; wherein the set time resolution is 1 minute; A tide level prediction unit, used for obtaining tide data of the sea area where the nuclear power unit is located within a third set time, and predicting the tide level after the second set time according to the tide data to obtain a predicted tide level; The electric power determination unit is used to obtain the historical operation data of the nuclear power unit, and determine the electric power setting value of the nuclear power unit according to the historical operation data, the predicted temperature and the predicted tide level; wherein the historical operation data includes thermal power historical data, electric power historical data, seawater temperature historical data and tide level historical data.

10. The nuclear power unit power control system based on seawater temperature and tide level prediction according to claim 9, characterized in that: Also includes: An alarm unit is used to obtain set monitoring data, determine whether the nuclear power unit has an over-limit alarm according to the set monitoring data, and output an alarm signal if so; The monitoring data are set to include real-time nuclear power and 1-minute sliding average thermal power; The display unit is used to obtain the real-time electric power, the actual value of the 24-hour seawater temperature and the actual value of the 24-hour tide level, and to display the electric power setting value, the predicted tide level, the predicted temperature, the real-time nuclear power, the real-time electric power, the actual value of the 24-hour seawater temperature and the actual value of the 24-hour tide level.

Images