CN117217353A - High-temperature gas cooled reactor graphite dust amount prediction method and system based on support vector machine - Google Patents
High-temperature gas cooled reactor graphite dust amount prediction method and system based on support vector machine Download PDFInfo
- Publication number
- CN117217353A CN117217353A CN202310933311.2A CN202310933311A CN117217353A CN 117217353 A CN117217353 A CN 117217353A CN 202310933311 A CN202310933311 A CN 202310933311A CN 117217353 A CN117217353 A CN 117217353A
- Authority
- CN
- China
- Prior art keywords
- reactor
- graphite dust
- support vector
- vector machine
- temperature gas
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 83
- 229910002804 graphite Inorganic materials 0.000 title claims abstract description 83
- 239000010439 graphite Substances 0.000 title claims abstract description 83
- 239000000428 dust Substances 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000005457 optimization Methods 0.000 claims abstract description 25
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 239000000463 material Substances 0.000 claims abstract description 5
- 238000012795 verification Methods 0.000 claims abstract description 4
- 239000007789 gas Substances 0.000 claims description 37
- 230000006870 function Effects 0.000 claims description 35
- 238000010200 validation analysis Methods 0.000 claims description 15
- 239000001307 helium Substances 0.000 claims description 9
- 229910052734 helium Inorganic materials 0.000 claims description 9
- SWQJXJOGLNCZEY-UHFFFAOYSA-N helium atom Chemical compound [He] SWQJXJOGLNCZEY-UHFFFAOYSA-N 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000002790 cross-validation Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000009792 diffusion process Methods 0.000 abstract description 2
- 239000000446 fuel Substances 0.000 description 9
- 230000000694 effects Effects 0.000 description 4
- 238000005253 cladding Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004992 fission Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000002285 radioactive effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
- Y02E30/30—Nuclear fission reactors
Landscapes
- Monitoring And Testing Of Nuclear Reactors (AREA)
Abstract
The application discloses a high-temperature gas cooled reactor graphite dust amount prediction method based on a support vector machine, which comprises the steps of collecting in-reactor graphite dust content data after material pouring in a reactor test process or a reactor shutdown period, and preprocessing the data; selecting a support vector machine as a prediction model, and selecting a Gaussian radial basis function as a kernel function; training an SVM model by using the collected data and the selected kernel function, optimizing an objective function of the SVM by using a sequence minimum optimization algorithm to obtain a global optimal solution, and verifying the performance of the model by using a cross verification method; during normal operation of the reactor, the trained SVM model is used for predicting the content of graphite dust in the reactor, and the predicted content of graphite dust is provided for a high-temperature gas cooled reactor safety monitoring system. The generation and diffusion of graphite dust can be timely monitored and controlled, the safety risk in the operation process of the high-temperature gas cooled reactor is effectively reduced, and the safety of the reactor core is ensured.
Description
Technical Field
The application relates to the technical field of graphite dust quantity prediction methods, in particular to a high-temperature gas cooled reactor graphite dust quantity prediction method and system based on a support vector machine.
Background
Under the support of 863 high-technology plan in China, the research and development work of a 10MW high-temperature gas-cooled experimental reactor (HTR-10) is carried out since the eighties of the last century, the first critical is realized in 12 months of 2000, the full-power generation operation is realized in 29 months of 2003, and the important progress of China in the technical field of high-temperature gas-cooled reactors is marked, and China enters the international advanced line in the field.
The fuel element of the pebble-bed high-temperature gas-cooled reactor is a sphere consisting of a fuel zone with the diameter of about 50mm and a fuel-free zone with the same base material and the thickness of about 5mm, wherein the fuel zone is formed by dispersing coated fuel particles in a graphite base body. The function of the coated fuel particles is to restrict the release of fuel and fission products, conduct heat and ensure the radioactive safety of the reactor. The graphite matrix performs physical, thermal and structural functions.
The cladding layer of the cladding fuel particles forms a first barrier for preventing fission products from being released, and the good performance of the cladding layer is the basic guarantee of the design of the pebble-bed high-temperature gas cooled reactor. While under the helium atmosphere of the pebble bed reactor, the friction coefficient and the abrasion rate between the graphites are greatly increased, which results in graphite dust in the pebble bed type high temperature gas cooled reactor pressure vessel. The existence of graphite dust in the reactor can cause problems of increased radioactivity of a loop, difficult discharge of a fuel loading and unloading machine, uncertainty of retention time in the fuel reactor and the like, so that the monitoring of the content of the graphite dust in the reactor is necessary.
The application adopts a support vector machine model to predict the content of graphite dust in a pile, the support vector machine is a classical algorithm, and is proposed by Vapnik in 1995, and the support vector machine has wide application in classification, regression and density estimation. The support vector machine maps the input to a space with higher feature dimensions through nonlinear mapping, and then constructs a linear decision surface in the high-dimensional feature space as a segmentation hyperplane. For a linearly separable dataset, there are many split hyperplanes, but the most widely spaced hyperplanes are unique. The SVM itself is a linear classifier in the parameter space, but it becomes a nonlinear classifier due to the nonlinear mapping of the input space to the high-dimensional feature space. The segmentation hyperplane found by the SVM has good robustness and excellent performance on a plurality of tasks.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The present application has been made in view of the above-described problems occurring in the prior art.
Therefore, the needle is a problem that the graphite dust content in the reactor pressure vessel is difficult to measure during normal operation of the reactor in the pebble-bed high-temperature gas cooled reactor. The method is to predict the content of graphite dust by adopting a support vector machine algorithm, and can provide support assistance for a high-temperature gas cooled reactor safety monitoring system.
In order to solve the technical problems, the application provides a high-temperature gas cooled reactor graphite dust amount prediction method based on a support vector machine, which comprises the following steps: collecting in-reactor graphite dust content data after the reactor is filled in the test process or the shutdown period, and preprocessing the data; selecting a support vector machine as a prediction model, and selecting a Gaussian radial basis function as a kernel function; training an SVM model by using the collected data and the selected kernel function, optimizing an objective function of the SVM by using a sequence minimum optimization algorithm to obtain a global optimal solution, and verifying the performance of the model by using a cross verification method; during normal operation of the reactor, the trained SVM model is used for predicting the content of graphite dust in the reactor, and the predicted content of graphite dust is provided for a high-temperature gas cooled reactor safety monitoring system.
As a preferable scheme of the high-temperature gas cooled reactor graphite dust amount prediction method based on the support vector machine, the application comprises the following steps: the graphite dust content data comprise operation time, nuclear power, primary circuit pressure, helium flow and temperature of measuring points in the reactor.
As a preferable scheme of the high-temperature gas cooled reactor graphite dust amount prediction method based on the support vector machine, the application comprises the following steps: the training of the SVM model includes the goal of the support vector machine to find a hyperplane, such that the shortest distance from all samples in the whole dataset to the segmented hyperplane is maximized,
ω T x+b=0
where ω is the vector of hyperplane coefficients and b is the bias term.
As a preferable scheme of the high-temperature gas cooled reactor graphite dust amount prediction method based on the support vector machine, the application comprises the following steps: the preprocessing includes, identifying outliers using a Z-score method,
wherein X is an observed value, mu is an average value, sigma is a standard deviation, when the Z-score of one value exceeds a threshold value, the value is an abnormal value, and the data is divided into a training set and a test set by performing standardization processing.
As a preferable scheme of the high-temperature gas cooled reactor graphite dust amount prediction method based on the support vector machine, the application comprises the following steps: initializing all Lagrangian multipliers to be 0, selecting a pair of Lagrangian multipliers for optimization in each iteration, optimizing the selected pair of multipliers under the condition of fixing other multipliers, updating the selected pair of multipliers according to an optimization result, stopping iteration if all the multipliers meet a KKT condition or reach a preset maximum iteration number, and continuing to select a pair of multipliers for optimization if all the multipliers do not meet the KKT condition or do not reach the preset maximum iteration number, and calculating a deviation term and weight after all the multipliers are obtained.
As a preferable scheme of the high-temperature gas cooled reactor graphite dust amount prediction method based on the support vector machine, the application comprises the following steps: the cross-validation includes dividing a data set into k subsets, each subset having the same size, performing k times of training and validation, selecting one subset as a validation set each time, combining k-1 subsets into a new training set, training an SVM model using the new training set, testing the performance of the model on the validation set, recording the validation result of each time, calculating an average value of the k times of validation results, performing cross-validation on each set of parameters when different parameters are considered in training the SVM model, and selecting a model with optimal performance according to the results.
As a preferable scheme of the high-temperature gas cooled reactor graphite dust amount prediction method based on the support vector machine, the application comprises the following steps: the judging according to the actual situation comprises that when the predicted graphite dust content is in a normal range, the normal operation of the reactor is continued, the working personnel keep a normal operation state, when the predicted graphite dust content is higher than the normal range and smaller than a dangerous range, the warning level is increased, the operation state of the reactor is closely monitored, necessary measures are prepared to be taken, when the predicted graphite dust content exceeds the normal range and is higher than the dangerous range, the operation parameters of the reactor are adjusted and maintenance operation is carried out, and when the predicted graphite dust content exceeds the normal range, the operation of the reactor is immediately stopped, and detailed inspection and maintenance are carried out.
The application also aims to provide a system for predicting the graphite dust amount of the high-temperature gas cooled reactor based on the support vector machine, and the system can realize the intellectualization of the operation management of the high-temperature gas cooled reactor by combining the graphite dust amount prediction method based on the support vector machine with a corresponding system. The prediction model and the system can automatically monitor, analyze and predict the graphite dust amount, provide real-time decision support for operation management personnel, and improve the efficiency and accuracy of operation management.
As a preferable scheme of the system for predicting the graphite dust amount of the high-temperature gas cooled reactor based on the support vector machine, the system for predicting the graphite dust amount of the high-temperature gas cooled reactor based on the support vector machine is characterized in that: the system comprises a data acquisition module, a feature selection module, an SVM calculation module and an optimization module; the data acquisition module is used for: the method is used for collecting in-reactor graphite dust content data from a reactor test process or after material pouring during shutdown; the feature selection module: features for selecting input variables as samples, including run time, nuclear power, loop pressure, helium flow, and in-reactor site temperature; the SVM computing module: for computing samples in a low-dimensional space and mapping the samples from an original feature space to a higher-dimensional space using a gaussian Radial Basis Function (RBF) kernel function; the optimization module: the method is used for finding an optimal hyperplane through an optimization algorithm so as to realize accurate prediction of the graphite dust content.
A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method as described above when executing the computer program.
A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method as described above.
The application has the beneficial effects that: according to the method, the generation and diffusion of graphite dust can be timely monitored and controlled by accurately predicting the graphite dust quantity, so that the safety risk in the operation process of the high-temperature gas cooled reactor is effectively reduced, and the safety of the reactor core is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a flow chart of a method for predicting the amount of graphite dust in a high-temperature gas cooled reactor based on a support vector machine according to an embodiment of the application;
fig. 2 is a graph of fitting effects of different kernel functions of a support vector machine-based method for predicting graphite dust amount of a high-temperature gas cooled reactor on a model according to an embodiment of the application.
FIG. 3 is a graph of penalty factor versus accuracy for a support vector machine-based method for predicting the amount of graphite dust in a high temperature gas cooled reactor according to one embodiment of the present application;
FIG. 4 is a graph showing the relationship between the parameter gamma and the accuracy of the method for predicting the graphite dust amount of the high-temperature gas cooled reactor based on the support vector machine according to one embodiment of the present application;
FIG. 5 is a schematic flow chart of a high temperature gas cooled reactor graphite dust amount prediction system based on a support vector machine according to an embodiment of the present application;
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present application can be understood in detail, a more particular description of the application, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present application is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the application. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present application have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the application. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present application, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present application and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1, in a first embodiment of the present application, a method for predicting a graphite dust amount of a high temperature gas cooled reactor based on a support vector machine is provided, including:
s1: collecting in-reactor graphite dust content data after the reactor is filled in the test process or the shutdown period, and preprocessing the data;
the graphite dust content data includes operating time, nuclear power, primary circuit pressure, helium flow, and in-reactor site temperature.
Still further, the data set trained by the present application comes from the in-reactor graphite dust content collected after a pour during a reactor test procedure or during shutdown (which is difficult to achieve during reactor operation). The number of input variables to be selected is 12, and the input variables are respectively: run time, nuclear power, loop pressure, helium flow, 8 in-reactor site temperatures. The output was 1, i.e. the graphite dust content.
It should be noted that the preprocessing includes, identifying outliers using the Z-score method,
wherein X is an observed value, mu is an average value, sigma is a standard deviation, when the Z-score of one value exceeds a threshold value, the value is an abnormal value, and the data is divided into a training set and a test set by performing standardization processing.
S2: selecting a support vector machine as a prediction model, and selecting a Gaussian radial basis function as a kernel function;
the training of the SVM model includes the goal of the support vector machine to find a hyperplane, such that the shortest distance from all samples in the whole dataset to the segmented hyperplane is maximized,
ω T x+b=0
where ω is the vector of hyperplane coefficients and b is the bias term.
It should be noted that in the case where the original sample is linearly inseparable, the SVM first performs the computation in the low-dimensional space, then uses a kernel function to implicitly map the sample from the original feature space to the higher-dimensional space, and then finds an optimal hyperplane to segment the sample, thereby solving the linear inseparable problem in the original feature space. Among the various kernel functions, the gaussian Radial Basis Function (RBF) is the most commonly used kernel function. The training of the support vector machine is a quadratic optimization problem, and constructs a hyperplane (wherein, the vector is a hyperplane coefficient, and is a deviation term), and the objective of the support vector machine is to find a hyperplane so that the shortest distance from all samples in the whole dataset to the segmented hyperplane is maximum.
S3: training an SVM model by using the collected data and the selected kernel function, optimizing an objective function of the SVM by using a sequence minimum optimization algorithm to obtain a global optimal solution, and verifying the performance of the model by using a cross verification method;
further, the optimizing the objective function of the SVM by using the sequential minimum optimization algorithm includes initializing all the lagrangian multipliers to 0, selecting a pair of lagrangian multipliers for optimization in each iteration, optimizing the selected pair of multipliers under the condition of fixing other multipliers, updating the selected pair of multipliers according to the optimization result, stopping iteration if all the multipliers meet the KKT condition or reach the preset maximum iteration number, and continuing to select a pair of multipliers for optimization if all the multipliers do not meet the KKT condition or reach the preset maximum iteration number, and calculating the deviation term and the weight after all the multipliers are obtained.
It should be noted that the cross-validation includes dividing the data set into k subsets, each subset having the same size, performing k times of training and validation, selecting one subset as a validation set each time, combining k-1 subsets into a new training set, training the SVM model using the new training set, testing the performance of the model on the validation set, recording the validation result of each time, calculating the average value of the k times of validation results, performing cross-validation for each set of parameters when different parameters are considered in training the SVM model, and selecting the model with the optimal performance according to the result.
S4: during normal operation of the reactor, the trained SVM model is used for predicting the content of graphite dust in the reactor, and the predicted content of graphite dust is provided for a high-temperature gas cooled reactor safety monitoring system.
It should be noted that the judgment according to the actual situation includes, when the predicted graphite dust content is within the normal range, continuing to operate the reactor normally, maintaining the normal operation state by the staff, when the predicted graphite dust content is higher than the normal range and smaller than the dangerous range, raising the warning level, closely monitoring the operation state of the reactor, and preparing to take necessary measures, when the predicted graphite dust content is out of the normal range and higher than the dangerous range, adjusting the operation parameters of the reactor and performing maintenance operation, and when the predicted graphite dust content is far out of the normal range, immediately stopping the operation of the reactor, and performing detailed inspection and maintenance.
Example 2
Referring to fig. 2-4, for one embodiment of the present application, a method for predicting the amount of graphite dust in a high temperature gas cooled reactor based on a support vector machine is provided, and in order to verify the beneficial effects of the present application, scientific demonstration is performed through experiments.
Firstly, a training data set (12 parameters including the input parameters including the operation time, the nuclear power, the primary loop pressure, the helium flow and the temperature of 8 points in the reactor, and the output variables including 1 point and the graphite dust content) is generated according to the related operation data during the previous reactor test or the shutdown period, and the training set and the testing set are divided according to the proportion of 85 percent and 15 percent. And then, selecting relevant parameters of the support vector machine, and training to obtain a model with smaller prediction error.
Wherein, compared with the selection of different kernel functions (see fig. 2), the kernel functions adopt gaussian kernel functions (RBFs):
the advantages are that: compared with the polynomial kernel function, the polynomial kernel function has fewer parameters, and can reduce the storage space; in addition, a numerical optimization method can be used, so that numerical calculation difficulty and calculation amount are reduced.
The penalty factor C characterizes the degree of emphasis of the model on outliers, the greater C, the more emphasis, the more prone to discarding outliers. The penalty for error classification increases when the C value is large, and the penalty for error classification decreases when the C value is small. When C is larger and approaches infinity, the existence of a classification error is not allowed, and the smaller margin is, the better margin is, and the fitting is easy; when C tends to 0, the model is no longer concerned about whether classification is correct, and only the larger margin is, the better the under-fitting is easy. As shown in fig. 3, the selection concept of C is that the smaller the better on the basis of sufficiently high accuracy.
The gamma value is a coefficient of a kernel function, and as gamma increases, there are cases where the prediction effect for the test set is poor and the prediction effect for training is good, and the generalized error is liable to be over-fitted. As shown in FIG. 4, the training effects of different gamma are compared, and the corresponding gamma value is selected.
After the trained support vector machine model is obtained, the model is connected into a reactor DCS system, 12 parameters are input into the model in the parameter stabilization period in one operation period, the graphite dust content generated in the operation period is obtained, if the reactor parameters change greatly, the reactor parameters are treated in the next operation period, and the dust content generated in the previous stage is added into the current accumulated value of the graphite dust content in the reactor.
Through the scheme, the model can display the accumulated value of the graphite dust content when needed, and support is provided for operators.
Example 3
A third embodiment of the present application, which is different from the first two embodiments, is:
the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Example 4
Referring to fig. 5, in a fourth embodiment of the present application, a system for predicting a graphite dust amount of a high temperature gas cooled reactor based on a support vector machine is provided, including: the system comprises a data acquisition module, a feature selection module, an SVM calculation module and an optimization module;
the data acquisition module is used for: the method is used for collecting in-reactor graphite dust content data from a reactor test process or after material pouring during shutdown; the feature selection module: features for selecting input variables as samples, including run time, nuclear power, loop pressure, helium flow, and in-reactor site temperature; the SVM computing module: for computing samples in a low-dimensional space and mapping the samples from an original feature space to a higher-dimensional space using a gaussian Radial Basis Function (RBF) kernel function; the optimization module: the method is used for finding an optimal hyperplane through an optimization algorithm so as to realize accurate prediction of the graphite dust content.
Claims (10)
1. The method for predicting the graphite dust amount of the high-temperature gas cooled reactor based on the support vector machine is characterized by comprising the following steps of: comprising the steps of (a) a step of,
collecting in-reactor graphite dust content data after the reactor is filled in the test process or the shutdown period, and preprocessing the data;
selecting a support vector machine as a prediction model, and selecting a Gaussian radial basis function as a kernel function;
training an SVM model by using the collected data and the selected kernel function, optimizing an objective function of the SVM by using a sequence minimum optimization algorithm to obtain a global optimal solution, and verifying the performance of the model by using a cross verification method;
during normal operation of the reactor, the trained SVM model is used for predicting the content of graphite dust in the reactor, and the predicted content of graphite dust is provided for a high-temperature gas cooled reactor safety monitoring system.
2. The support vector machine-based high-temperature gas cooled reactor graphite dust amount prediction method as set forth in claim 1, wherein: the graphite dust content data comprise operation time, nuclear power, primary circuit pressure, helium flow and temperature of measuring points in the reactor.
3. The support vector machine-based high-temperature gas cooled reactor graphite dust amount prediction method as set forth in claim 2, wherein: the training of the SVM model includes the goal of the support vector machine to find a hyperplane, such that the shortest distance from all samples in the whole dataset to the segmented hyperplane is maximized,
ω T x+b=0
where ω is the vector of hyperplane coefficients and b is the bias term.
4. The method for predicting the graphite dust amount of the high-temperature gas cooled reactor based on the support vector machine as set forth in claim 3, wherein the method comprises the following steps of: the preprocessing includes, identifying outliers using a Z-score method,
wherein X is an observed value, mu is an average value, sigma is a standard deviation, when the Z-score of one value exceeds a threshold value, the value is an abnormal value, and the data is divided into a training set and a test set by performing standardization processing.
5. The support vector machine-based high-temperature gas cooled reactor graphite dust amount prediction method as set forth in claim 4, wherein: initializing all Lagrangian multipliers to be 0, selecting a pair of Lagrangian multipliers for optimization in each iteration, optimizing the selected pair of multipliers under the condition of fixing other multipliers, updating the selected pair of multipliers according to an optimization result, stopping iteration if all the multipliers meet a KKT condition or reach a preset maximum iteration number, and continuing to select a pair of multipliers for optimization if all the multipliers do not meet the KKT condition or do not reach the preset maximum iteration number, and calculating a deviation term and weight after all the multipliers are obtained.
6. The support vector machine-based high-temperature gas cooled reactor graphite dust amount prediction method as set forth in claim 5, wherein: the cross-validation includes dividing a data set into k subsets, each subset having the same size, performing k times of training and validation, selecting one subset as a validation set each time, combining k-1 subsets into a new training set, training an SVM model using the new training set, testing the performance of the model on the validation set, recording the validation result of each time, calculating an average value of the k times of validation results, performing cross-validation on each set of parameters when different parameters are considered in training the SVM model, and selecting a model with optimal performance according to the results.
7. The support vector machine-based high-temperature gas cooled reactor graphite dust amount prediction method as set forth in claim 6, wherein: the judging according to the actual situation comprises that when the predicted graphite dust content is in a normal range, the normal operation of the reactor is continued, the working personnel keep a normal operation state, when the predicted graphite dust content is higher than the normal range and smaller than a dangerous range, the warning level is increased, the operation state of the reactor is closely monitored, necessary measures are prepared to be taken, when the predicted graphite dust content exceeds the normal range and is higher than the dangerous range, the operation parameters of the reactor are adjusted and maintenance operation is carried out, and when the predicted graphite dust content exceeds the normal range, the operation of the reactor is immediately stopped, and detailed inspection and maintenance are carried out.
8. A system based on the support vector machine-based method for predicting graphite dust amount of high-temperature gas cooled reactor according to any one of claims 1 to 7, which is characterized in that: the system comprises a data acquisition module, a feature selection module, an SVM calculation module and an optimization module;
the data acquisition module is used for: the method is used for collecting in-reactor graphite dust content data from a reactor test process or after material pouring during shutdown;
the feature selection module: features for selecting input variables as samples, including run time, nuclear power, loop pressure, helium flow, and in-reactor site temperature;
the SVM computing module: for computing samples in a low-dimensional space and mapping the samples from an original feature space to a higher-dimensional space using a gaussian Radial Basis Function (RBF) kernel function;
the optimization module: the method is used for finding an optimal hyperplane through an optimization algorithm so as to realize accurate prediction of the graphite dust content.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310933311.2A CN117217353A (en) | 2023-07-27 | 2023-07-27 | High-temperature gas cooled reactor graphite dust amount prediction method and system based on support vector machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310933311.2A CN117217353A (en) | 2023-07-27 | 2023-07-27 | High-temperature gas cooled reactor graphite dust amount prediction method and system based on support vector machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117217353A true CN117217353A (en) | 2023-12-12 |
Family
ID=89037725
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310933311.2A Pending CN117217353A (en) | 2023-07-27 | 2023-07-27 | High-temperature gas cooled reactor graphite dust amount prediction method and system based on support vector machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117217353A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103065066A (en) * | 2013-01-22 | 2013-04-24 | 四川大学 | Drug combination network based drug combined action predicting method |
CN103278434A (en) * | 2013-05-20 | 2013-09-04 | 清华大学 | Device and method for measuring concentration of graphite dust in primary loop pipeline of high temperature gas cooled reactor |
CN110705794A (en) * | 2019-10-09 | 2020-01-17 | 苏州卡泰里环保能源有限公司 | Method for predicting window state based on support vector machine algorithm |
CN113191599A (en) * | 2021-04-12 | 2021-07-30 | 国家石油天然气管网集团有限公司华南分公司 | Pipeline risk level evaluation method and device based on support vector machine |
CN113239314A (en) * | 2021-04-09 | 2021-08-10 | 国网河北省电力有限公司沧州供电分公司 | Method, device, terminal and computer-readable storage medium for carbon emission prediction |
CN116383727A (en) * | 2023-04-11 | 2023-07-04 | 西安交通大学 | Method, system, equipment and medium for identifying coarse errors in power plant system measurement |
-
2023
- 2023-07-27 CN CN202310933311.2A patent/CN117217353A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103065066A (en) * | 2013-01-22 | 2013-04-24 | 四川大学 | Drug combination network based drug combined action predicting method |
CN103278434A (en) * | 2013-05-20 | 2013-09-04 | 清华大学 | Device and method for measuring concentration of graphite dust in primary loop pipeline of high temperature gas cooled reactor |
CN110705794A (en) * | 2019-10-09 | 2020-01-17 | 苏州卡泰里环保能源有限公司 | Method for predicting window state based on support vector machine algorithm |
CN113239314A (en) * | 2021-04-09 | 2021-08-10 | 国网河北省电力有限公司沧州供电分公司 | Method, device, terminal and computer-readable storage medium for carbon emission prediction |
CN113191599A (en) * | 2021-04-12 | 2021-07-30 | 国家石油天然气管网集团有限公司华南分公司 | Pipeline risk level evaluation method and device based on support vector machine |
CN116383727A (en) * | 2023-04-11 | 2023-07-04 | 西安交通大学 | Method, system, equipment and medium for identifying coarse errors in power plant system measurement |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI464748B (en) | Reduced order stress model for online maneuvering, diagnostics of fuel failure and design of core loading patterns of light water reactors | |
US7685079B2 (en) | Methods for evaluating robustness of solutions to constraint problems | |
KR101119548B1 (en) | Axial direction output distribution control method, axial direction output distribution control system and axial direction output distribution control program | |
CN110427588B (en) | Intrinsic orthogonal decomposition sample selection method for reactor core power online reconstruction | |
EP1927994B1 (en) | Systems and methods of predicting a critical effective k for a nuclear reactor | |
Williamson et al. | Multi-dimensional simulation of LWR fuel behavior in the BISON fuel performance code | |
Bratton et al. | Rod internal pressure quantification and distribution analysis using FRAPCON | |
Lee et al. | Prediction of DNBR using fuzzy support vector regression and uncertainty analysis | |
JPH06347586A (en) | Monitoring method for drying of core in boiling water reactor | |
CN117217353A (en) | High-temperature gas cooled reactor graphite dust amount prediction method and system based on support vector machine | |
Wallace et al. | Control rod monitoring of advanced gas-cooled reactors | |
CN116631524A (en) | Calculation method for corrosion behavior of zirconium alloy | |
EP2400503B1 (en) | Axial output distribution prediction device | |
CN111898066B (en) | Reactor core xenon concentration distribution prediction method based on intrinsic orthogonal decomposition | |
JP4526781B2 (en) | Method and apparatus for evaluating fuel assembly thermal characteristics | |
Kastanya | ADORE-GA: Genetic algorithm variant of the ADORE algorithm for ROP detector layout optimization in CANDU reactors | |
West et al. | Knowledge-directed characterization of nuclear power plant reactor core parameters | |
CN117391230A (en) | Neural network-based high-temperature gas cooled reactor graphite dust quantity prediction method and system | |
JPH0875891A (en) | Reactor core performance computing method and apparatus therefor | |
Kastanya | Evaluating the effect of mutation rate on the ADORE-GA performance | |
JPH06186380A (en) | Performance calculator for reactor core | |
Lee et al. | Validation of MERCURY code under LOCA condition with Out-of-pile and In-pile tests | |
Anupreethi et al. | Sensitivity analysis of AHWR flux mapping system for unavailability of SPNDs | |
Lee et al. | Predicting diametral creep of the pressure tubes in CANDU reactors using fuzzy neural networks | |
Salmassian et al. | Diagnosing core local flow blockages in a VVER-1000/446 reactor using ex-core detectors and neural networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |