Nuclear power operation parameter prediction method and device

Abstract

The present disclosure belongs to the technical field of nuclear power and particularly relates to a nuclear power operation parameter prediction method and device. The nuclear power operation parameter prediction method provided by the present disclosure uses Tent chaotic mapping for population initialization, effectively improves the uniformity of the population in the search space, and improves the quality of the initial solution; a fish-eagle optimization algorithm is introduced to incorporate a local exploration strategy, enhancing the ergodicity of the algorithm in the solution space search process; in addition, an adaptive inertia weight factor is introduced to maintain a good balance between exploration and development, enhancing the adaptive ability of the algorithm. The convergence speed of the method of the present disclosure is improved, and the search process is more likely to obtain a better solution. Precise data support and scientific decision-making basis can be provided for operation personnel to develop operation and maintenance strategies in advance, guiding operators to accurately increase and decrease power, avoiding the over-limit of unit thermal power, nuclear power and the like, reducing load loss during the high-temperature period in summer, so as to realize the efficiency improvement of the nuclear power unit.

Description

Technical Field

[0001] This invention belongs to the field of nuclear power technology, specifically relating to a method and apparatus for predicting nuclear power plant operating parameters. Background Technology

[0002] In related technologies, during summer operation of coastal nuclear power units, tidal fluctuations cause temperature fluctuations at the cold-end inlet seawater, resulting in a sudden influx of high-temperature seawater into the inlet. This causes a rapid increase in the circulating water inlet temperature within a short period, leading to a surge in back pressure. If the unit maintains electrical power, nuclear power will increase. To ensure that nuclear power and thermal power do not exceed operating thresholds during daily unit parameter fluctuations, the unit's electrical power must be limited. If the unit's set power is too high, there is a risk of exceeding nuclear power limits; if the set power is too low, the unit's economic efficiency will decrease. Therefore, it is urgent to solve the problem of limited unit output due to exceeding limits in thermal power and nuclear power in nuclear power plants. Summary of the Invention

[0003] To overcome the problems existing in related technologies, a method and apparatus for predicting nuclear power plant operating parameters are provided.

[0004] According to one aspect of the present disclosure, a method for predicting nuclear power plant operating parameters is provided, the method comprising:

[0005] Step 1: Obtain historical operation data and preprocess the historical operation data to generate a sample set;

[0006] Step 2: Decompose the sample set using the VMD model to obtain the IMF sequence;

[0007] Step 3: Correct each IMF in the IMF sequence to obtain multiple corrected IMFs.

[0008] Step 4: Superimpose the predicted values ​​from multiple corrected IMF outputs to obtain the final prediction result.

[0009] In one possible implementation, step 3 includes steps 31 to 33;

[0010] Step 31: In the first stage, a global search is performed on the exploration space composed of the IMF sequence to determine the optimal region and update the position of each IMF element, as shown in Equations 5 to 7:

[0011] Formula 5

[0012] Formula Six

[0013] Formula 7

[0014] In the formula, in the formula, Represents the i-th IMF. Let be the initial value of the i-th IMF in the j-th dimension, i∈[1,N], j∈[1,m], where N is the number of IMFs in the IMF sequence and m is the number of dimensions of each IMF; The target location is randomly selected for the i-th IMF; Let i be the objective function value of the i-th IMF; The value in the j-th dimension for the target location randomly selected for the i-th IMF; This represents the new value of the i-th IMF in the j-th dimension during the first phase. yes Random integers within the range; Let i be the objective function value for the target location of the i-th IMF; This represents the objective function value of the i-th IMF after the first phase update. For the first phase of the updated IMF, It is a random natural number; It is a random number;

[0015] Step 32: In the second stage, a global search is performed on the exploration space to determine the optimal region and update the positions of elements in each IMF again, as shown in Equations 8 and 9:

[0016] Formula 8

[0017] Formula Nine

[0018] In the formula: for The j-th element in For the second phase of the updated IMF, For the new value of the i-th IMF in the j-th dimension in the second stage, This represents the objective function value of the i-th IMF in the second phase. ; This represents the current iteration number. The preset total number of iterations, for The lower bound of the search range, for The upper bound of the search range;

[0019] Step 33, in In this case, repeat steps 31 to 32 until... At that time, save and output the multiple corrected IMFs obtained from the current update.

[0020] In one possible implementation, step 1 includes:

[0021] Step 11, using a 3D model based on the normal distribution. The criteria cleaning strategy identifies and removes abnormal data from historical operational data;

[0022] Step 12: The cleaned data is dimensionless using the standardization method shown in Equation 1, thereby constructing a sample set.

[0023] Formula 1

[0024] In the formula, This represents the sample value after dimensionless processing; This represents the original sample value; Represents the mean of the original sample; It represents the standard deviation of the original sample.

[0025] In one possible implementation, in step 31, an initial IMF sequence is formed based on a Tent chaotic map, as shown in Equation 3:

[0026] Formula 3

[0027] In the formula: Indicates the first The chaos value of the second order. Indicates the first The chaos value of the second order. The domain is ; As the chaos parameter, the elements of each IMF sequence are shown in Equation 4:

[0028] Formula 4

[0029] In the formula: The chaotic element generated by the Tent mapping.

[0030] In one possible implementation, the adaptive inertia weighting factor shown in Equation 10 is used. Introducing equation six yields equation eleven:

[0031] Formula 10

[0032] Formula Eleven

[0033] Will Introducing Equation 8 yields Equation 12:

[0034] Formula Twelve

[0035] In the formula: As the initial inertia weight, The inertia weight for reaching the maximum number of iterations in the new iteration.

[0036] In one possible implementation, the method further includes step 5: splitting the sample set into a training set and a test set; using the VMD model to decompose the training set to obtain the IMF sequence; and using the coefficient of determination on the test set. The performance of multiple trained models is evaluated as shown in Equation 13:

[0037] Formula Thirteen

[0038] In the formula: This is the actual output value. To predict the output value, This represents the actual output value after averaging.

[0039] According to another aspect of the present disclosure, a nuclear power plant operating parameter prediction device is provided, the device comprising:

[0040] The preprocessing module is used to acquire historical running data and preprocess the historical running data to generate a sample set;

[0041] The decomposition module is used to decompose the sample set using the VMD model to obtain the IMF sequence;

[0042] The correction module is used to correct each IMF in the IMF sequence, resulting in multiple corrected IMFs.

[0043] The prediction module is used to superimpose multiple corrected IMF output predictions to obtain the final prediction result.

[0044] According to another aspect of the present disclosure, a nuclear power plant operating parameter prediction device is provided, the device comprising:

[0045] processor;

[0046] Memory used to store processor-executable instructions;

[0047] In this formula, the processor is configured to execute the method described above.

[0048] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, implement the above-described method.

[0049] The beneficial effects of this disclosure are as follows: The nuclear power plant operating parameter prediction method provided by this disclosure uses Tent chaotic mapping for population initialization, which effectively improves the uniformity of the population in the search space and enhances the quality of the initial solution; it introduces the Osprey optimization algorithm into the local exploration strategy, enhancing the ergodicity of the algorithm in the solution space search process; in addition, it introduces an adaptive inertia weight factor, enabling the algorithm to maintain a good balance between exploration and development, enhancing its adaptive capability. The convergence speed of the method disclosed in this disclosure is improved, and the search process is more likely to obtain better solutions. Addressing the current situation where fluctuations in cold-end inlet seawater temperature caused by tides lead to fluctuations in unit operating parameters, resulting in reduced unit output in summer to avoid exceeding operating parameter limits, this disclosure effectively constructs a seawater temperature and tide level prediction model. This model can provide accurate data support and scientific decision-making basis for operators to formulate operation and maintenance strategies in advance, guiding operators to accurately adjust power output, avoiding exceeding limits for unit thermal power and nuclear power, reducing load losses during high-temperature periods in summer, thereby improving the efficiency of nuclear power units. Attached Figure Description

[0050] Figure 1 This is a schematic diagram illustrating a method for predicting nuclear power plant operating parameters according to an embodiment of this disclosure.

[0051] Figure 2 This is a schematic diagram illustrating an application example of the present disclosure of an IMF sequence obtained by VMD decomposition.

[0052] Figures 3a to 3g This disclosure provides an application example illustrating a schematic diagram of each trained IMF.

[0053] Figure 4 This is a block diagram of a nuclear power plant operating parameter prediction device shown in an embodiment of this disclosure. Detailed Implementation

[0054] The present disclosure will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0055] Unless otherwise defined, the technical and scientific terms used in this disclosure have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains; the terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure; the term "comprising" and any variations thereof in this disclosure are intended to cover non-exclusive inclusion. Clearly, the embodiments described in this disclosure are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0056] In this disclosure, the reference to "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this disclosure. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0057] Figure 1 This is a schematic diagram illustrating a method for predicting nuclear power plant operating parameters according to an embodiment of this disclosure. This method can be executed by a terminal device, which can be a server, desktop computer, laptop computer, etc. This disclosure does not limit the type of terminal device. Figure 1 As shown, the method includes:

[0058] Step 1: Obtain historical running data and preprocess the historical running data to generate a sample set. As an example of this embodiment, Step 1 includes:

[0059] Step 11, using a 3D model based on the normal distribution. The standard cleaning strategy identifies and removes abnormal data from historical operational data to ensure data accuracy and reliability.

[0060] Step 12: The cleaned data is dimensionless using the standardized method shown in Equation 1, thereby constructing a sample set that meets the research requirements.

[0061] Formula 1

[0062] In the formula, This represents the sample value after dimensionless processing; This represents the original sample value; Represents the mean of the original sample; This represents the standard deviation of the original sample. It should be noted that the same characters in the formulas of this disclosure have the same meaning.

[0063] Step 2: Decompose the sample set using the VMD model to obtain the IMF sequence.

[0064] As an example of this embodiment, the sample set is decomposed using the VMD model to form the IMF sequence as shown in Equation 2.

[0065] Formula 2

[0066] In the formula, Represents the i-th IMF. Let be the initial value of the i-th IMF in the j-th dimension, i∈[1,N], j∈[1,m], N is the number of IMFs in the IMF sequence, and m is the number of dimensions of each IMF.

[0067] In one possible implementation, an initial IMF sequence is formed based on a Tent chaotic map, as shown in Equation 3:

[0068] Formula 3

[0069] In the formula: Indicates the first The chaos value of the second order. Indicates the first The chaos value of the second order. The domain is ; For chaotic parameters; This indicates the superiority of chaotic states, for example, Chaotic sequences generated based on the Tent chaotic map exhibit better uniformity, and the elements of each IMF sequence are shown in Equation 4:

[0070] Formula 4

[0071] In the formula: The chaotic element generated by the Tent mapping. for The lower bound of the search range, for The upper bound of the search range.

[0072] Step 3: Input each IMF in the IMF sequence into a preset model for training to obtain multiple trained IMFs (e.g., ...). Figure 1 As shown, step 3 (inputting IMF1 into Transformer1 to obtain the IMF1 prediction value) includes steps 31 to 33.

[0073] Step 31: In the first stage, a global search is performed on the exploration space composed of the IMF sequences to determine the optimal region and update the positions of the elements of each IMF, as shown in Equations 5 to 7:

[0074] Formula 5

[0075] Formula Six

[0076] Formula 7

[0077] In the formula, The target location is randomly selected for the i-th IMF; Let i be the objective function value of the i-th IMF; The value in the j-th dimension for the target location randomly selected for the i-th IMF; This represents the new value of the i-th IMF in the j-th dimension during the first phase. yes Random integers within the range; Let i be the objective function value for the target location of the i-th IMF; This represents the objective function value of the i-th IMF after the first phase update. For the first phase of the updated IMF, yes Random natural numbers within; It is a random number with a value of 1 or 2;

[0078] Step 32: In the second stage, a global search is performed on the exploration space to determine the optimal region and update the positions of elements in each IMF again, as shown in Equations 8 and 9:

[0079] Formula 8

[0080] Formula Nine

[0081] In the formula: for The j-th element in For the second phase of the updated IMF, For the new value of the i-th IMF in the j-th dimension in the second stage, This represents the objective function value of the i-th IMF in the second phase. ; This represents the current iteration number. This is the preset total number of iterations.

[0082] Step 33, in In this case, repeat steps 31 to 32 until... At that time, save and output the multiple trained IMFs obtained from the current update.

[0083] Step 4: Superimpose the predicted values ​​from multiple trained IMF outputs to obtain the final prediction result.

[0084] In one possible implementation, an adaptive inertia weighting factor as shown in Equation 10 is used in both the first and second stages. The methods disclosed herein can maintain a certain balance between exploration and development, and enhance adaptability.

[0085] Formula 10

[0086] In the formula: As the initial inertia weight, The inertia weight for reaching the maximum number of iterations in the new iteration.

[0087] Weighting factors Introducing equation six yields equation eleven:

[0088] Formula Eleven

[0089] Weighting factors Introducing Equation 8 yields Equation 12:

[0090] Formula Twelve

[0091] This disclosure introduces adaptive inertia weighting factors in the first and second stages to maintain a good balance between exploration and development, enhancing the algorithm's adaptability. This improves the overall model's convergence speed and makes it easier to obtain better solutions during the search process.

[0092] In one possible implementation, the method further includes: step 5, splitting the sample set into a training set and a test set, for example, dividing 80% of the sample set into a training set and 20% into a test set. Based on the training set, an IMF sequence is obtained using a VMD model decomposition; based on the test set, the coefficient of determination is used... The performance of multiple trained models is evaluated as shown in Equation 13:

[0093] Formula Thirteen

[0094] In the formula: This is the actual output value. To predict the output value, This represents the actual output value after averaging.

[0095] The nuclear power plant operating parameter prediction method disclosed herein employs Tent chaotic mapping for population initialization, effectively improving the uniformity of the population in the search space and enhancing the quality of the initial solution. It incorporates the Osprey optimization algorithm with a local exploration strategy, enhancing the ergodicity of the algorithm during the solution space search process. Furthermore, it introduces an adaptive inertia weight factor to maintain a good balance between exploration and development, enhancing its adaptability. The convergence speed of this method is improved, and the search process more easily obtains better solutions. Addressing the issue that fluctuations in cold-end inlet seawater temperature caused by tides lead to fluctuations in unit operating parameters, resulting in reduced unit output in summer to avoid exceeding operating parameter limits, this method effectively constructs a seawater temperature and tide level prediction model. This model provides accurate data support and scientific decision-making basis for operators to formulate maintenance strategies in advance, guiding operators to precisely adjust power output, avoiding exceeding limits for unit thermal power and nuclear power, reducing load losses during high-temperature periods in summer, thereby improving the efficiency of nuclear power units.

[0096] In one application example, historical running data is acquired and preprocessed to generate a sample set.

[0097] The IMF sequences shown in Table 1 are obtained by decomposing the sample set using VMD. In this embodiment, the center frequency of the sample set is used as the criterion for determining whether the decomposition has reached a stable state. When the last component obtained by the decomposition tends to stabilize, the corresponding K value is the optimal K value. The penalty coefficient for VMD decomposition is also shown. Set to 2000, convergence tolerance Set as Lagrange multiplier replacement rate The value is set to 0.01. Table 1 presents the center frequency distribution of the example data under different K values. When the K value is 7 and 8 respectively, the center frequency of the last layer component shows a trend towards stability. It can be inferred from this that variational mode decomposition (VMD) can achieve the optimal decomposition effect when K is 7.

[0098] Table 1

[0099]

[0100] The IMF components were obtained through VMD decomposition, and residual components were removed, resulting in seven IMF components. The original data was then compared with these components. Figure 2 As shown.

[0101] Each IMF sequence is input into a preset model to obtain, as follows: Figures 3a to 3g The diagram shows multiple trained models. Finally, the predicted values ​​of each IMF sequence are superimposed to obtain the final prediction result.

[0102] The embodiments disclosed herein accurately predict the changing patterns and trends of seawater temperature and liquid level in front of the grid, providing precise data support and decision-making basis for operators to formulate power setting strategies in advance, guiding operators to accurately adjust power, reducing load loss during high-temperature periods in summer and avoiding exceeding limits for unit thermal power and nuclear power, effectively contributing to the improvement of unit output efficiency.

[0103] According to another aspect of the present disclosure, a nuclear power plant operating parameter prediction device is provided, the device comprising:

[0104] The preprocessing module is used to acquire historical running data and preprocess the historical running data to generate a sample set;

[0105] The decomposition module is used to decompose the sample set using the VMD model to obtain the IMF sequence;

[0106] The correction module is used to correct each IMF in the IMF sequence, resulting in multiple corrected IMFs.

[0107] The prediction module is used to superimpose multiple corrected IMF output predictions to obtain the final prediction result.

[0108] The description of the above-mentioned apparatus has been elaborated in detail in the description of the above-mentioned method, and will not be repeated here.

[0109] Figure 4 This is a block diagram illustrating a nuclear power plant operating parameter prediction device according to an embodiment of this disclosure. For example, device 1900 can be provided as a server. (See also...) Figure 4 The apparatus 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0110] Device 1900 may also include a power supply component 1926 configured to perform power management of device 1900, a wired or wireless network interface 1950 configured to connect device 1900 to a network, and an input / output (I / O) interface 1958. Device 1900 can operate on an operating system stored in memory 1932, such as Windows Server™, MacOS X™, Unix™, Linux™, FreeBSD™, or similar.

[0111] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of the device 1900 to perform the above-described method.

[0112] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0113] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0114] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0115] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0116] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0117] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0118] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0120] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they 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 chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for predicting nuclear power plant operating parameters, characterized in that, The method includes: Step 1: Obtain historical operation data and preprocess the historical operation data to generate a sample set; Step 2: Decompose the sample set using the VMD model to obtain the IMF sequence; Step 3: Correct each IMF in the IMF sequence to obtain multiple corrected IMFs. Step 4: Superimpose the predicted values ​​from multiple corrected IMF outputs to obtain the final prediction result; Step 3 includes steps 31 to 33; Step 31: In the first stage, a global search is performed on the exploration space composed of the IMF sequence to determine the optimal region and update the position of each IMF element, as shown in Equations 5, 10, 11 and 7: In the formula, X i Let x represent the i-th IMF. i,j Let P be the initial value of the i-th IMF in the j-th dimension, i∈[1,N], j∈[1,m], where N is the number of IMFs in the IMF sequence and m is the number of dimensions of each IMF; i The target location is randomly selected for the i-th IMF; F i Let P be the objective function value of the i-th IMF; i,j The value in the j-th dimension for the target location randomly selected for the i-th IMF; Let be the new value of the i-th IMF in the j-th dimension during the first stage; k is a random integer in the range [1, N]. Let i be the objective function value for the target location of the i-th IMF; This represents the objective function value of the i-th IMF after the first phase update. For the IMF updated in the first phase, a is a random natural number; I is a random number; λ(t) is the adaptive inertia weighting factor; λ s λ is the initial inertia weight. e The inertia weight for reaching the maximum iteration number in the new iteration; Step 32: In the second stage, a global search is performed on the exploration space to determine the optimal region and update the positions of elements in each IMF again, as shown in Equations XII and IX: In the formula: for The j-th element in For the second phase of the updated IMF, For the new value of the i-th IMF in the j-th dimension in the second stage, Let αb represent the objective function value of the i-th IMF in the second stage, t = 1, 2, ..., T; t is the current iteration number, T is the preset total number of iterations, and αb j For x i,j The lower bound of the search range, βb j For x i,j The upper bound of the search range; Step 33: If t < T, repeat steps 31 to 32 until t = T, then save and output the multiple corrected IMFs obtained from the current update.

2. The method according to claim 1, characterized in that, Step 1 includes: Step 11: Use the 3σ criterion cleaning strategy based on normal distribution to identify and remove abnormal data from historical operation data; Step 12: The cleaned data is dimensionless using the standardization method shown in Equation 1, thereby constructing a sample set. In the formula, Y ′ Y represents the dimensionless sample value; Y represents the original sample value. M represents the mean of the original sample; M represents the standard deviation of the original sample.

3. The method according to claim 1, characterized in that, In step 31, an initial IMF sequence is formed using a Tent chaotic mapping, as shown in Equation 3: In the formula: y l Let y represent the chaotic value at the l-th time. l+1 Let y represent the chaotic value at the (l+1)th iteration. l The domain is [0,1]; μ is the chaos parameter, and the elements of each IMF sequence are shown in Equation 4: x i,j =ab j +(βb j -αb j )y i,j Formula 4 In the formula: y i,j The chaotic element generated by the Tent mapping.

4. The method according to claim 1, characterized in that, The method further includes step 5, which splits the sample set to obtain a training set and a test set, uses the VMD model to decompose the training set to obtain the IMF sequence, and uses the coefficient of determination R to evaluate the performance of multiple trained models based on the test set, as shown in Equation 13: In the formula: z t The actual output value, z′ t To predict the output value, This represents the actual output value after averaging.

5. A nuclear power plant operating parameter prediction device, characterized in that, The device includes: The preprocessing module is used to acquire historical running data and preprocess the historical running data to generate a sample set; The decomposition module is used to decompose the sample set using the VMD model to obtain the IMF sequence; The correction module is used to correct each IMF in the IMF sequence, resulting in multiple corrected IMFs. The prediction module is used to superimpose multiple corrected IMF output predictions to obtain the final prediction result. The correction module includes: The first correction submodule is used in the first stage to perform a global search of the exploration space composed of IMF sequences, determine the optimal region, and update the position of each IMF element, as shown in Equations 5, 10, 11, and 7: In the formula, X i Let x represent the i-th IMF. i,j Let P be the initial value of the i-th IMF in the j-th dimension, i∈[1,N], j∈[1,m], where N is the number of IMFs in the IMF sequence and m is the number of dimensions of each IMF; i The target location is randomly selected for the i-th IMF; F i Let P be the objective function value of the i-th IMF; i,j The value in the j-th dimension for the target location randomly selected for the i-th IMF; Let be the new value of the i-th IMF in the j-th dimension during the first stage; k is a random integer in the range [1, N]. Let i be the objective function value for the target location of the i-th IMF; This represents the objective function value of the i-th IMF after the first phase update. For the IMF updated in the first phase, a is a random natural number; I is a random number; λ(t) is the adaptive inertia weighting factor; λ s λ is the initial inertia weight. e The inertia weight for reaching the maximum iteration number in the new iteration; The second correction submodule is used in the second stage to perform a global search of the exploration space, determine the optimal area, and update the positions of elements in each IMF again, as shown in Equations XII and IX: In the formula: for The j-th element in For the second phase of the updated IMF, For the new value of the i-th IMF in the j-th dimension in the second stage, Let αb represent the objective function value of the i-th IMF in the second stage, t = 1, 2, ..., T; t is the current iteration number, T is the preset total number of iterations, and αb j For x i,j The lower bound of the search range, βb j For x i,j The upper bound of the search range; The third correction submodule is used to repeat steps 31 to 32 when t < T, until t = T, and then save and output the multiple corrected IMFs obtained from the current update.

6. A nuclear power plant operating parameter prediction device, characterized in that, The device includes: processor; Memory used to store processor-executable instructions; In this formula, the processor is configured to perform the method described in any one of claims 1 to 4.

7. A non-volatile computer-readable storage medium storing computer program instructions thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 4.

Images