WO2012050262A1 - Procédé et système de contrôle des performances d'instruments d'usine en utilisant une fsvr et un glrt - Google Patents

Procédé et système de contrôle des performances d'instruments d'usine en utilisant une fsvr et un glrt Download PDF

Info

Publication number
WO2012050262A1
WO2012050262A1 PCT/KR2010/008308 KR2010008308W WO2012050262A1 WO 2012050262 A1 WO2012050262 A1 WO 2012050262A1 KR 2010008308 W KR2010008308 W KR 2010008308W WO 2012050262 A1 WO2012050262 A1 WO 2012050262A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
fsvr
glrt
power plant
cluster
Prior art date
Application number
PCT/KR2010/008308
Other languages
English (en)
Korean (ko)
Inventor
서인용
하복남
이성우
신창훈
박민호
Original Assignee
한국전력공사
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 한국전력공사 filed Critical 한국전력공사
Publication of WO2012050262A1 publication Critical patent/WO2012050262A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • G—PHYSICS
    • G21—NUCLEAR PHYSICS; NUCLEAR ENGINEERING
    • G21D—NUCLEAR POWER PLANT
    • G21D3/00—Control of nuclear power plant
    • G—PHYSICS
    • G21—NUCLEAR PHYSICS; NUCLEAR ENGINEERING
    • G21D—NUCLEAR POWER PLANT
    • G21D3/00—Control of nuclear power plant
    • G21D3/001—Computer implemented control
    • 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

Definitions

  • the present invention relates to a technology required to monitor the performance of the safety monitoring instrument of a nuclear power plant at all times while the power plant is operating.
  • the clustering of data FCM clustering, principal component extraction and FSVR (Fuzzy Support Vector Regression)
  • FCM clustering principal component extraction
  • FSVR Fuzzy Support Vector Regression
  • the method is used to model the system for various cases, and then the three parameters of the regression equation are optimized using response surface methodology, modeled the power plant system, and then used to monitor the instrument signals.
  • FFSy Fuzzy Support Vector Regression
  • GLRT Generalized Likelihood Ratio Test
  • GLRT Generalized Likelihood Ratio Test
  • the comparison module 2 compares the measured value with the predicted value and inputs the difference into the judgment logic 3 and continuously monitors the drift and the failure of the measuring instrument.
  • MSET Multivariate State Estimation Technique
  • Knelnel Regression to calculate the instrument's predictions. This method selects other instrument signals that have a high linear correlation with the instrument signal to be predicted as shown in Equation 1, and calculates the regression coefficient so that the sum of the error squares of the predicted and measured values is minimized.
  • Linear regression analysis can predict independent variables for unknown dependent variables when the regression coefficients are determined by known and independent variables.
  • the conventional linear regression method when the dependent variables are linearly related to each other, a problem of multiple collinearity occurs, and a large error occurs in the independent variable for the small noise included in the dependent variable.
  • Kernel regression does not use parameters such as regression coefficients or weights to optimize the correlation between inputs and outputs, like conventional linear regression or neural networks. It is a non-parametric regression method that calculates the weight of the kernel from the Euclidean distance of the training data set in the memory vector and applies it to the memory vector. Nonparametric regression methods, such as kernel regression, have robust advantages over models and signal noise where input / output relationships are nonlinear. The following is the calculation procedure of the existing kernel regression method.
  • Step 1 Display training data in the form of a matrix.
  • X is the training data matrix stored in the memory vector
  • n is the number of training data
  • m is the number of the measuring instrument.
  • Step 2 Sum the Euclidean distance of the training data for the first instrument signal set.
  • x is training data
  • q is test data (or Query data)
  • trn is the number of training data
  • j is the number of the measuring instrument.
  • Step 3 Using the kernel function, find the weights for each training dataset and a given test dataset.
  • the Gaussian kernel is used as the weighting function and is defined as follows.
  • Step 4 The test data estimate is obtained by multiplying each training data by the weight and dividing the sum of the weights.
  • Step 5 Repeat the process from Step 2 to Step 4 to get predictions for the entire test data.
  • AAKR auto-associative kernel regression
  • the present invention has been invented in view of the above, and the optimization of parameters (kernel bandwidth ⁇ , loss function ⁇ , penalty C) of FSVR model regression using normalization, fuzzy clustering, extraction of principal components, response surface analysis, and
  • the FSVR model implementation and output value prediction, the denormalization method of the prediction value, and the failure determination by GLRT are used to model the power plant system and then monitor the signal signal prediction and abnormality of the instrument.
  • the purpose of this study is to provide the performance monitoring method of power plant instrumentation using Fuzzy Support Vector Regression (FSVR) and Generalized Likelihood Ratio Test (GLRT), which can improve the accuracy of prediction calculation and detect early failure.
  • FSVR Fuzzy Support Vector Regression
  • GLRT Generalized Likelihood Ratio Test
  • the malfunction of the measuring instrument can be monitored in real time to improve the reliability of the measuring instrument, and the instrument calibration cycle of the nuclear power plant is Increase the fuel replacement cycle from 18 months to a maximum of 8 years to reduce calibration costs and radiation exposure of calibration workers in the radiation zone, and to prevent unnecessary downtime by reducing the number of unnecessary calibrations, and to prevent plant outages.
  • the power consumption it is possible to increase the utilization rate of the power plant.
  • fuzzy clustering principal component analysis, response surface analysis, and FSVR regression modeling can be used to improve the accuracy of prediction calculations compared to conventional kernel regression, and GLRT can be used to detect an early failure of the instrument. Will be.
  • the prediction method for power plant instrument performance monitoring using Principal Component Analysis (FSVR), Fuzzy Support Vector Regression (FSVR), and GLRT method includes normalization of plant data, extraction of principal components, data clustering, and response surface analysis.
  • the conventional kernel regression method used by optimizing the parameters of the FSVR model regression equation (kernel bandwidth ⁇ , loss function ⁇ , penalty C), implementing the power plant system model using the FSVR, and de-normalizing the output predictions Compared with this, the accuracy of the prediction calculation can be improved.
  • even in the case of a very small shift drift that cannot be detected by an ordinary alarm system it is possible to accurately identify a failure early by using the GLRT technique proposed by the present invention to determine the failure of the instrument. .
  • FIG. 1 is a block diagram of a performance monitoring system of a general power plant instrument
  • FIG. 2 is a schematic configuration diagram of a performance monitoring system of a power plant instrument according to an embodiment of the present invention.
  • FIG. 3 is a flowchart of a power plant instrument performance monitoring method using principal component analysis, fuzzy support vector regression (FSVR) and GLRT method according to the present invention.
  • FSVR fuzzy support vector regression
  • 4 is a general conceptual diagram of an optimal regression line by an SVR.
  • 5 is a diagram illustrating a measurement example of the fuzzy membership size for each cluster.
  • FIG. 6 is a diagram for explaining an example of a reaction surface for clusters 1 and 2;
  • FIG. 7 is a diagram showing an experimental point in the central composition plan when there are three model parameters.
  • FIG. 8 is a diagram illustrating a method of extracting an optimal point from a response surface for cluster 2.
  • FIG. 10 is a diagram illustrating an example of calculating a value of MSE (GT i ) according to a window size.
  • Fig. 11 is a diagram showing an example of failure determination for the case of a normal state and an abnormal state of a measuring instrument.
  • 13 is a graph showing the nuclear power plant pressurizer water level data for accuracy test.
  • FIG. 14 is a graph illustrating steam flow rate data of a steam generator for a nuclear power plant for accuracy test.
  • 15 is a graph showing the nuclear power plant steam generator narrow level data for accuracy test.
  • 16 is a graph showing nuclear power plant steam generator pressure data for accuracy test.
  • FIG. 17 is a graph showing wide-range water level data for a nuclear power plant steam generator for accuracy test.
  • 19 is a graph showing nuclear power plant turbine output data for accuracy test.
  • 20 is a graph illustrating primary flow rate flow rate data for a nuclear power plant for accuracy test.
  • 21 is a graph showing the residual heat removal flow rate data of nuclear power plants for accuracy test.
  • 22 is a graph showing the temperature of the reactor coolant temperature of the nuclear power plant for the accuracy test.
  • an input unit 11 receiving time-series field signals for the m field sensors and sending them to the clustering unit 12;
  • a clustering unit 12 dividing an input signal for the time series field signal received from the input unit 11 into N desired data clusters using a fuzzy clustering method
  • a PCA unit 13 for extracting a main component for each data cluster divided into N data clusters received from the clustering unit 12;
  • An FSVR unit 14 for calculating fuzzy membership grade for each data cluster, training a model, obtaining optimal parameters of the model using response surface analysis, and performing signal prediction on test data;
  • a comparison operation unit 15 for comparing a signal predicted by the FSVR unit 14 with an input signal to obtain a difference
  • the GLRT unit 16 for calculating the statistic of the GLRT using the output of the comparison operation unit to determine the drift of the sensor is characterized in that it is configured.
  • Each FSVR model of reacting with a surface analysis method the optimization of each data cluster of data (Zopt) for (Z opt1, Z opt2) minimizes the prediction error of the optimization data (Zopt) for optimal constant And Obtaining a sixth step;
  • the normalized test data obtained in step 10 is normalized to the original range by denormalizing the predicted value of each sensor of the original scale. Eleventh step of obtaining according to equation 45 and;
  • the matrix in the first step is
  • the normalized entire data set (Z) is
  • the normalized training (Ztr), optimization (Zopt), experimental (Zts) data set is a formula
  • the present invention in the fourth step, the variance of the main components in order of magnitude, starting from the main component having the largest percentage variance value until the cumulative sum is 99.5% or more (Ztr), for optimization ( Zopt), the main component (Ptr, Pop, Pts) of each data set of the test (Zts) is selected to extract the main component.
  • Step 4-1 represented by;
  • the present invention is characterized in that the desired percentage dispersion in the above 4-6 step is 99.98%.
  • the training data (Ztr) is divided into two groups Ztr1 and Ztr2 by using a Fuzzy C-Means (FCM) clustering method.
  • FCM Fuzzy C-Means
  • step 5-1 for the optimization data (Zopt) and the test data (Zts), and dividing them into normalized data clusters (Zopt1, Zopt2, Zts1, Zts2) and principal component clusters (Popt1, Popt2, Pts1, Pts2), respectively. It is characterized by consisting of the 5-2 step.
  • the present invention the FCM (Fuzzy C-Means) clustering method
  • the termination condition in the step 4 is It is characterized by represented by.
  • the potential (P 1 ) of each data pointer is calculated using the Euclidean distance between each data pointer of the first cluster of training data (Ztr1) and all other input data, and the fuzzy membership grade is used. ) 6-1 step of calculating the;
  • Step 6-2 selecting the first test point ( v 1 , v 2 , v 3 ) of the test point for the cluster 1;
  • Step 6-4 by using a Popt svi 1 and to obtain a radial basis function (radial basis function) (Kopt1) ;
  • Step 6-6 After repeating steps 6-3 to 6-5 with respect to the other instrument signals of Ztr1, the prediction matrix output is performed. Step 6-6 to obtain;
  • Step 6-11 to obtain; characterized in that made up.
  • steps 6-4 of obtaining a radial basis function Kopt1 are given by
  • Beta vector with index of svi among beta vector (here, : Beta vector with index of svi among beta vector)
  • the present invention in the sixth to eighth step of the central synthesis plan (CCD) to the test three times (test points 15, 16, 17), but the 15th test using the entire Zopt, 16th
  • the test is characterized in that 1/2 of Zopt and 17th test are performed on the other half of Zopt.
  • the present invention also provides an optimal constant for the FSVR model for cluster 2.
  • the present invention the method for obtaining the optimum constant of the FSVR model using the response surface analysis method in the sixth step,
  • the data set Pop is input into m AAFSVRs to normalize the predictions of the optimization data. 6-10-8 calculating the MSE, which is the accuracy of the output model, from Equation 38;
  • Optimal condition It is characterized by consisting of; 6-10-11 step to convert to the original unit.
  • the search range for the cluster 1 in the step 6-10-2 0.2 to 2.0, : 0.0005 to 0.05, : 0.1 to 10.0, and the search range for cluster 2 is 0.3 to 1.9; : 0.0001 to 0.0009, It is characterized by setting to 0.1-10.
  • the present invention the MSE that is the accuracy of the output model in the step 6-10-8,
  • reaction surface is a formula
  • the estimated response surface is a
  • the optimal parameters for cluster # 1 , , The estimated log (MSE) under this condition is -5.3249,
  • step 8-1 of generating a model of FSVR 1 by obtaining w 1 (n ⁇ 1) and a bias constant b 1 ;
  • Step 8-1 for the second to m th measurement signals and Step 8-2 to generate a model of the FSVR 2 ⁇ FSVR m by obtaining the;
  • the kernel function ( K ts1 (n ⁇ n)) of the Gaussian Radial Basis Function is obtained using the principal component (Ptr1) of the training data and the principal component (Pts1) of the test data.
  • K ts1 (n ⁇ n) The kernel function ( K ts1 (n ⁇ n)) of the Gaussian Radial Basis Function is obtained using the principal component (Ptr1) of the training data and the principal component (Pts1) of the test data.
  • 8-8-3 obtaining an output of the FSVR 1 using the support vector weight w 1 and the bias constant b 1 of the FSVR model obtained in the 8-8 step;
  • the prediction value for the test data Zts1 is expressed by
  • the prediction value for the test data Zts2 is
  • the predicted value (Zts_hat) for the entire data in the ninth step is:
  • the prediction value for each sensor of the original scale in the eleventh step Expression
  • the present invention also provides a twelfth step of determining the drift of the sensor
  • GT is obtained by generating the same number random numbers of normal distributions having the same mean and standard deviation as the mean and standard deviation of the residuals in the normal case calculated in step 12-1, and repeating 1000 times to obtain the maximum GT .
  • Step 12-4 taking the upper control limit (UCL) taken;
  • model residual (R) which is the difference between the input value and the predicted value in the step 12-1 is expressed by the equation:
  • the present invention is characterized in that the average value of the residual for the normal case in step 12-2 is -0.00096347, and the standard deviation ( ⁇ ) is 0.0069.
  • the GLRT test statistic GT is defined as the largest within the window size in the GLR obtained at the time point t ,
  • the optimum window size is set in that the decrease of MSE (GT i ) is slowed down.
  • Reactor output (%), pressurizer level (%), steam generator steam flow rate (Mkg / hr), steam generator narrow water level data (%), steam generator pressure data (Kg / cm 2 ), steam generator wide water level data (% ), Steam generator main feed water flow data (Mkg / hr), turbine output data (MWe), reactor coolant fill flow data (m 3 / hr), residual heat removal flow rate data (m 3 / hr), reactor top coolant temperature data ( It is characterized by the above).
  • N is the number of test data, : estimate of the model for the i test data, : measured value of the i-th test data
  • FIG. 2 is a schematic configuration diagram of a performance monitoring system of a power plant instrument according to an embodiment of the present invention.
  • the performance monitoring system of the power plant meter includes an input unit 11, a clustering unit 12, a PCA unit 13, an FSVR unit 14, and a comparison operation unit 15. And a GLRT unit 16.
  • the input unit 11 receives time-series field signals from m field sensors and sends them to the clustering unit 12.
  • the clustering unit 12 divides the input signal for the time series field signal received from the input unit 11 into N desired data clusters using a fuzzy clustering method.
  • the PCA unit 13 extracts a principal component for each data cluster divided into N data clusters received from the clustering unit 12.
  • the FSVR unit 14 calculates a fuzzy membership grade for each data cluster, trains the model, obtains optimal parameters of the model using response surface analysis, and performs signal prediction on the test data. do.
  • the comparison operation unit 15 compares the signal predicted by the FSVR unit 14 with the input signal to obtain a difference.
  • the GLRT unit 16 sets the window size optimization and management limit line, and then calculates a GLRT test statistic using the output of the comparison operation unit to determine whether there is a drift of the sensor.
  • FIG. 3 is a flowchart of a power plant instrument performance monitoring method using principal component analysis, fuzzy support vector regression (FSVR) and generalized likelihood ratio test (GLRT) method according to the present invention.
  • FSVR fuzzy support vector regression
  • GLRT generalized likelihood ratio test
  • the power plant instrument performance monitoring method comprises a first step (ST1) for displaying the entire data set (X) in the form of a matrix; A second step ST2 of normalizing the entire data set; A third step ST3 of dividing the data set into a training (Ztr), an optimization (Zopt), and a test (Zts); A fourth step ST4 of extracting main components Ptr, Popt, and Pts of each normalized data set; A fifth step ST5 of dividing the data set and the main component into as many data clusters as desired using fuzzy clustering; A sixth step (ST6) of obtaining an optimum constant (epsilon, C, sigma) of the FSVR model which minimizes the prediction error of the optimization data using the response surface method; A seventh step (ST7) of calculating a fuzzy membership grade for each cluster of training data; An eighth step (ST8) of training the FSVR model using the data and the optimal parameters for each cluster, and then calculating the output prediction value of each cluster; A first step (ST1) for displaying the entire data
  • the conventional kernel regression method calculates weights using only the Euclidean distance of training data and test data, and weights them on the training data to calculate the predicted value of the test data.
  • the present invention improves the accuracy of predictive calculation and proposes a new discrimination method for measuring instrument anomalies by using principal component analysis, data clustering, optimization using response surface analysis, and FSVR regression modeling. .
  • the entire data set (X) is expressed in the form of a matrix as shown in Equation 6, and divided into training, optimization, and test, respectively, and is called Xtr, Xopt, and Xts, respectively.
  • Equation 8 The normalized entire data Z is expressed as in Equation 8 below.
  • the normalized data set (Z) is divided into training, optimization, and test, and divided into Ztr, Zopt, and Zts, respectively.
  • the data is divided into n data sets as shown in Equation 9 below.
  • each normalized data set Ztr, Zop, Zts is extracted. List the variances of the principal components (ie, the eigenvalues of the covariance matrix) in order of magnitude, with the principal components for Ztr, Zop, and Zts starting with the principal component with the largest percentage variance and reaching a cumulative sum of at least 99.5%. Select (Ptr, Pop, Pts).
  • Principal Component Analysis is a useful method for compressing many input variables into a few variables through linear transformation.
  • the compressed variable is called the principal component and the extraction method is as follows.
  • the seven principal components account for 99.98% of the variance, with only 0.02% of the loss of information resulting from the abandonment of the remaining principal components.
  • Table 1 below shows the dispersion of the main components.
  • Equation 20 m- dimensional input variable For When the predicted value of the first output is obtained using the FSVR, it can be expressed as an optimal regression line (ORL) as shown in Equation 20 below.
  • Equation 20 the weight of the support vector (SV) And bias
  • Equation 21 the normalized risk function using the fuzzy concept is defined as in Equation 21 below, and w k and b k are minimized.
  • Is The magnitude of the fuzzy membership for the I data of the first signal.
  • Output variable The insensitive loss function is defined as in Equation 22 below.
  • Equation 23 In order to find the ORL of the equation, the optimization problem is converted into a constrained risk function as shown in Equation 23.
  • Equation 23 After converting Equation 23 into Lagrangian function, it is solved by quadratic programming.
  • Wow After obtaining the value of AAFSVR, Determine the nonlinear regression equation for the first output variable.
  • Equation 25 a Gaussian Radial Basis Function (RBF) is used, as shown in Equation 25 below.
  • the bias term is any SV (Support Vector) as shown in Equation 26 below.
  • the data set and principal components are divided into as many data clusters as desired.
  • data is divided into two groups, and the procedure for the present invention will be described based on this.
  • the training data (Ztr) is divided into two groups Ztr1 and Ztr2 using the FCM (Fuzzy C-Means) clustering method.
  • the main component Ptr is also divided into the same number of clusters Ptr1 and Ptr2 by using the same index of each generated data group.
  • i is the number of clusters
  • k is the number of patterns
  • r is the number of repetitions
  • N is the number of sampled data for each sensor
  • u ik is the membership size of data group X k belonging to group i.
  • the center vector vi (r) and membership u ik for each cluster are calculated as in Equation 28 below.
  • fuzzy membership grade for the first cluster of training data (Ztr1) Calculate Using the Euclidean distance between each data pointer of Ztr1 and all other input data, the potential (P 1 ) of each data pointer is calculated according to Equation 31, and using this, fuzzy membership grade Calculate
  • 5 is a diagram illustrating a measurement example of the fuzzy membership size for each cluster.
  • test points 15, 16, 17 are performed for the origin of the central synthesis plan (CCD). The whole test is used for the 15th test, half of Zopt for the 16th test, and the other half of Zopt for the 17th test.
  • 6a shows an example of the response surface for cluster 1
  • 6b shows the response surface for cluster 2.
  • the search range for Cluster 1 is : 0.2 to 2.0, : 0.0005 to 0.05, : 0.1 to 10.0, and the search range for cluster 2 is 0.3 to 1.9; : 0.0001 to 0.0009, : 0.1-10 were set.
  • FIG. 7 is a diagram illustrating an experimental point in the central synthesis plan when three model parameters are shown.
  • FIG. 7 is a diagram illustrating an experimental point in the central synthesis plan when three model parameters are shown.
  • Tables 3-1 and 3-2 show the Experimental point of), Table 3-1 shows the experimental point of Cluster 1, Table 3-2 shows the experimental point of Cluster 2.
  • the data set Pop is input to m AAFSVRs to normalize the predictions of the optimization data. Obtain From this, the accuracy of the output model, ie MSE, is calculated according to equation 38.
  • Table 4 shows the experimental MSE calculation results.
  • Table 4-1 shows the MSE of cluster # 1
  • Table 4-2 shows the MSE of cluster # 2.
  • the estimated response surface in this example is as follows.
  • the optimal condition (0,0.04525,0).
  • the optimal parameters for cluster # 1 are , ,
  • the estimated log (MSE) under this condition is -5.3249.
  • the optimal parameters for cluster # 2 are , ,
  • the estimated log (MSE) under this condition is -5.4170.
  • FIG. 8 is a diagram illustrating a method of extracting an optimal point from a response surface for cluster 2.
  • the output prediction values Zts1_hat and Zts2_hat are obtained by inputting each cluster principal component vector Pts1 and Pts2 of Zts) as follows.
  • the kernel function ( K ts1 (n ⁇ n)) of the Gaussian Radial Basis Function is obtained and the FSVR model obtained above.
  • the output of FSVR 1 is obtained using w 1 , the bias constant b 1 , which is the weight of SV (Support vector) of.
  • the prediction value for the test data Zts2 is obtained as shown in Equation 43 below.
  • the prediction values (Zts_hat) for the entire data are obtained by connecting the prediction values (Zts1_hat and Zts2_hat) for each cluster according to Equation 44.
  • the normalized test data obtained in step 10 is denormalized to the original range to estimate the estimated value for each sensor of the original scale. Is obtained according to equation 45.
  • the prediction program is executed to calculate the difference (residual) between the predicted value and the measured value for each sensor.
  • the mean value and standard deviation ( ⁇ ) for the residuals are calculated.
  • the model residual (R) is a difference between an input value and a predicted value, as shown in Equation 46 below.
  • the mean value of the residuals for the normal case is -0.00096347 and the standard deviation is 0.0069.
  • the GT statistic for each window size is calculated using the residual when the meter is normal, increasing the window size w by 5 from minimum (eg, 5) to maximum (eg, 150).
  • Recent window size Means the average of the data, and 48 is expressed as follows.
  • the test statistic GT of GLRT is defined as the largest within the window size among the GLRs obtained at time t , and is obtained as in Equation 49 below.
  • MSE calculated by the difference between the GT statistic in each window size GT statistic and the maximum window in the formula 50.
  • FIG. 10 is a diagram illustrating an example of calculating a value of MSE (GT i ) according to a window size.
  • the horizontal axis represents window size
  • the vertical axis represents MSE (GT i )
  • the 12.1) to generate the same number of random numbers has mean and standard deviation values and the same mean and standard deviation of the residuals for, if the normal calculated normal distribution obtain and GT in, by repeating 1000 times this takes the maximum value of GT management limit Set to (UCL: Upper Control Limit).
  • UCL is set to 28.25.
  • FIG. 11 is a diagram illustrating an example of failure determination for a case where the meter is in a normal state and an abnormal state.
  • FIG. 11A is a case where a shift drift occurs in the meter when the meter is in a normal state. will be.
  • FIG. 11B the occurrence of the drift of the sensor is detected at the 58th step.
  • the output of the actual nuclear power plant was increased from 0% to 100%.
  • the data used in the analysis was measured on a total of 11 sensors.
  • Table 5 is a table comparing the accuracy of the instrument prediction according to the conventional kernel regression method and the present invention.
  • Accuracy is the most basic measure for applying predictive models to driving surveillance. In most cases, accuracy is expressed as the mean square error between model predictions and actual measurements. The following 51 is a formula for the accuracy of one instrument.
  • N the number of test data
  • the present invention extracts the principal component of the measuring instrument signal, obtains the optimal constant of the FSVR model using the response data, using the response analysis surface method, and trained the model using the training data and tested the test data using the existing data. Improve the accuracy of prediction calculations compared to kernel regression. In addition, even when a very fine shift drift occurs that cannot be detected by an ordinary alarm system, failure can be identified early by using the GLRT method according to the present invention.
  • a graph of the data as a function of time is as follows.
  • FIG. 13 is a graph showing the nuclear power plant pressurizer water level data for accuracy test, the "Measured” line corresponds to the test input data X ts_2 of Equation 6, and the "Predicted” line is predicted using the algorithm of the present invention.
  • Estimated Data for Test Input X ts_2 in Equation 45 Indicates.
  • FIG. 15 is a graph showing the narrow-range water level data of a nuclear power plant steam generator for accuracy test, wherein a "Measured” line corresponds to the test input data X ts_4 of Equation 6, and a "Predicted” line is predicted using the algorithm of the present invention.
  • Estimate data for test input X ts_4 in Equation 45 Indicates.
  • 16 is a graph showing the steam generator pressure data for the accuracy test, the "Measured” line corresponds to the test input data X ts_5 of Equation 6, and the "Predicted” line is predicted using the algorithm of the present invention.
  • Estimate data for test input X ts_5 in equation 45 Indicates.
  • 17 is a graph showing the water level data of the nuclear power plant steam generator for accuracy test, the line "Measured” corresponds to the test input data X ts_6 of Equation 6, and the line “Predicted” is predicted using the algorithm of the present invention.
  • Estimate data for test input X ts_6 in Equation 45 Indicates.
  • FIG. 19 is a graph showing nuclear power plant turbine output data for accuracy test, in which the "Measured” line corresponds to the test input data X ts_8 of Equation 6 and the "Predicted” line is predicted using the algorithm of the present invention. Estimate data for test input X ts_8 at 45 Indicates.
  • Equation 20 is a graph showing the primary side charge flow rate data for the nuclear power plant for accuracy test, the "Measured” line corresponds to the test input data X ts_9 of Equation 6, and the "Predicted” line is predicted using the algorithm of the present invention.
  • Estimate data for test input X ts_9 in Equation 45 Indicates.
  • 21 is a graph showing the residual heat removal flow rate data of a nuclear power plant for accuracy test, where the "Measured” line corresponds to the test input data X ts_10 of Equation 6, and the "Predicted” line is predicted using the algorithm of the present invention.
  • Estimate data for test input X ts_10 in equation 45 Indicates.
  • FIG. 22 is a graph showing temperature data of the upper reactor coolant temperature of a nuclear power plant for accuracy test, in which the "Measured” line corresponds to the test input data X ts_11 of Equation 6, and the "Predicted” line is predicted using the algorithm of the present invention.
  • Estimate data for test input X ts_11 in Equation 45 Indicates.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Plasma & Fusion (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

La présente invention concerne un procédé de contrôle des performances d'instruments d'usine en utilisant une FSVR et un GLRT, le procédé comportant : une première étape consistant à représenter l'ensemble de données (X) tout entier comme une matrice et à classifier l'ensemble de données en trois sous-ensembles de données pour l'apprentissage (Xtr), l'optimisation (Xopt) et le test (Xts) ; une deuxième étape consistant à normaliser toutes les données représentées comme une matrice lors de la première étape ; une troisième étape consistant à classifier l'ensemble (Z) de données normalisées en trois sous-ensembles de données d'apprentissage (Ztr), d'optimisation (Zopt) et de test (Zts) ; une quatrième étape consistant à extraire des composantes principales des sous-ensembles (Z) de données d'apprentissage (Ztr), d'optimisation (Zopt) et de test (Zts) ; une cinquième étape consistant à diviser les ensembles de données et les composantes principales en groupes de données d'après un nombre souhaité ; une sixième étape consistant à calculer des coefficients optimaux (ε1,C1,σ1) et (ε2,C2,σ2) de chaque modèle FSVR ; une septième étape consistant à calculer un degré d'appartenance floue (μ1,μ2) ; une huitième étape consistant à calculer des valeurs de prédiction de sortie (Zts1_hat et Zts2_hat) ; une neuvième étape consistant à calculer une valeur de prédiction pour toutes les données (Zts_hat) ; une dixième étape consistant à classifier les valeurs de prédiction des données de test ; une onzième étape consistant à calculer des valeurs de prédiction pour les capteurs sur une échelle d'origine ; et une douzième étape consistant à déterminer la dérive des capteurs.
PCT/KR2010/008308 2010-10-15 2010-11-24 Procédé et système de contrôle des performances d'instruments d'usine en utilisant une fsvr et un glrt WO2012050262A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020100100697A KR101178235B1 (ko) 2010-10-15 2010-10-15 에프에스브이알과 지엘알티를 이용한 발전소 계측기 성능감시 방법 및 시스템
KR10-2010-0100697 2010-10-15

Publications (1)

Publication Number Publication Date
WO2012050262A1 true WO2012050262A1 (fr) 2012-04-19

Family

ID=45938460

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2010/008308 WO2012050262A1 (fr) 2010-10-15 2010-11-24 Procédé et système de contrôle des performances d'instruments d'usine en utilisant une fsvr et un glrt

Country Status (2)

Country Link
KR (1) KR101178235B1 (fr)
WO (1) WO2012050262A1 (fr)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107291991A (zh) * 2017-05-25 2017-10-24 华侨大学 一种基于动态网络标志的风电机组早期缺陷预警方法
CN108490923A (zh) * 2018-04-28 2018-09-04 南京航空航天大学 用于电气牵引系统的微小故障检测与定位的系统设计方法
CN109270907A (zh) * 2018-10-24 2019-01-25 中国计量大学 一种基于分层概率密度分解的过程监测和故障诊断方法
CN110472689A (zh) * 2019-08-19 2019-11-19 东北大学 基于集成高斯过程回归的有杆泵抽油井动液面软测量方法
CN110823474A (zh) * 2019-09-27 2020-02-21 一汽解放汽车有限公司 一种燃油系统泄漏程度评估方法及存储介质
CN112069457A (zh) * 2020-08-13 2020-12-11 山东科技大学 一种基于动态平稳子空间分析的非平稳动态过程异常监测方法
CN113433913A (zh) * 2021-07-06 2021-09-24 上海新氦类脑智能科技有限公司 系统监测模型生成及监测方法、处理器芯片以及工业系统
CN116215293A (zh) * 2023-05-08 2023-06-06 广东电网有限责任公司佛山供电局 一种电动汽车充电桩运行状态预测方法及装置

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101998553B1 (ko) * 2012-08-01 2019-07-10 한국전력공사 단기 풍속 예측을 통한 풍력 발전량 예측 방법과, 그 기능을 이용한 배전선로 전압 예측 방법
CN107678930A (zh) * 2017-09-11 2018-02-09 华东理工大学 一种基于光滑支持向量机的银行自动终端异常报警方法
CN107606745B (zh) * 2017-09-27 2019-09-27 南京中灿科技有限公司 地铁空调季逐时环控能耗预测方法
KR102130272B1 (ko) * 2018-07-17 2020-07-08 한국전력공사 경험모델 기반 예측 알고리즘의 최적화 방법
KR102470112B1 (ko) * 2020-02-27 2022-11-23 한국수력원자력 주식회사 원전의 지능형 상태감시 방법 및 시스템
CN113640607B (zh) * 2021-08-18 2023-02-28 江苏科技大学 一种针对高速列车逆变电路及电机的早期故障诊断方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100340967B1 (ko) * 1999-10-08 2002-06-20 손재익 일반 회귀 신경망을 이용한 고장 검출 방법
US20050261837A1 (en) * 2004-05-03 2005-11-24 Smartsignal Corporation Kernel-based system and method for estimation-based equipment condition monitoring
KR100867938B1 (ko) * 2007-09-27 2008-11-10 한국전력공사 종속변수 유사도와 커널 회귀법을 이용한 발전소 계측기성능감시용 예측방법

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100340967B1 (ko) * 1999-10-08 2002-06-20 손재익 일반 회귀 신경망을 이용한 고장 검출 방법
US20050261837A1 (en) * 2004-05-03 2005-11-24 Smartsignal Corporation Kernel-based system and method for estimation-based equipment condition monitoring
KR100867938B1 (ko) * 2007-09-27 2008-11-10 한국전력공사 종속변수 유사도와 커널 회귀법을 이용한 발전소 계측기성능감시용 예측방법

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
IN-YONG SEO ET AL., JOURNAL OF THE KOREA SOCIETY FOR SIMULATION, vol. 18, no. 3, September 2009 (2009-09-01), pages 103 - 112 *
NA, M.G. ET AL.: "A SOFT-SENSING MODEL FOR FEEDWATER FLOW RATE USING FUZZY SUPPORT VECTOR REGRESSION", NUCLEAR ENGINEERING AND TECHNOLOGY, vol. 40, no. 1, February 2008 (2008-02-01), pages 69 - 76 *
YANG, H.Y. ET AL.: "FUZZY SUPPORT VECTOR REGRESSION MODEL FOR THE CALCULATION OF THE COLLAPSE MOMENT FOR WALL-THINNED PIPES", NUCLEAR ENGINEERING AND TECHNOLOGY, vol. 40, no. 7, December 2008 (2008-12-01), pages 607 - 614 *

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107291991A (zh) * 2017-05-25 2017-10-24 华侨大学 一种基于动态网络标志的风电机组早期缺陷预警方法
CN107291991B (zh) * 2017-05-25 2020-08-07 华侨大学 一种基于动态网络标志的风电机组早期缺陷预警方法
CN108490923A (zh) * 2018-04-28 2018-09-04 南京航空航天大学 用于电气牵引系统的微小故障检测与定位的系统设计方法
CN109270907B (zh) * 2018-10-24 2020-07-28 中国计量大学 一种基于分层概率密度分解的过程监测和故障诊断方法
CN109270907A (zh) * 2018-10-24 2019-01-25 中国计量大学 一种基于分层概率密度分解的过程监测和故障诊断方法
CN110472689A (zh) * 2019-08-19 2019-11-19 东北大学 基于集成高斯过程回归的有杆泵抽油井动液面软测量方法
CN110472689B (zh) * 2019-08-19 2022-11-15 东北大学 基于集成高斯过程回归的有杆泵抽油井动液面软测量方法
CN110823474A (zh) * 2019-09-27 2020-02-21 一汽解放汽车有限公司 一种燃油系统泄漏程度评估方法及存储介质
CN112069457A (zh) * 2020-08-13 2020-12-11 山东科技大学 一种基于动态平稳子空间分析的非平稳动态过程异常监测方法
CN112069457B (zh) * 2020-08-13 2023-11-17 山东科技大学 一种基于动态平稳子空间分析的非平稳动态过程异常监测方法
CN113433913A (zh) * 2021-07-06 2021-09-24 上海新氦类脑智能科技有限公司 系统监测模型生成及监测方法、处理器芯片以及工业系统
CN116215293A (zh) * 2023-05-08 2023-06-06 广东电网有限责任公司佛山供电局 一种电动汽车充电桩运行状态预测方法及装置
CN116215293B (zh) * 2023-05-08 2023-07-04 广东电网有限责任公司佛山供电局 一种电动汽车充电桩运行状态预测方法及装置

Also Published As

Publication number Publication date
KR101178235B1 (ko) 2012-08-30
KR20120039160A (ko) 2012-04-25

Similar Documents

Publication Publication Date Title
WO2012050262A1 (fr) Procédé et système de contrôle des performances d'instruments d'usine en utilisant une fsvr et un glrt
WO2009131376A2 (fr) Système de communication à antennes multiples comprenant la mise à jour et le changement adaptatifs de livres de codes
WO2011136627A2 (fr) Système de communication entrée multiple sortie multiple utilisant un livre de codes correspondant à chaque mode de rapport
WO2020242260A1 (fr) Procédé et dispositif de compression d'image basée sur l'apprentissage machine utilisant un contexte global
WO2015030343A1 (fr) Ellipsomètre à matrice de mueller de type à rotation d'élément optique et procédé de mesure de matrice de mueller d'échantillon l'utilisant
WO2018182170A1 (fr) Système d'analyse vitesse-puissance de voilier dans des conditions de navigation standard
WO2014069710A1 (fr) Dispositif de précorrection numérique à faible coût pour un procédé de retour d'informations de détection d'enveloppe, et procédé correspondant
WO2023080379A1 (fr) Appareil de génération d'informations d'apparition de maladie basé sur une corrélation temporelle à l'aide d'un score de risque polygénique et son procédé
WO2022031059A1 (fr) Système et procédé d'optimisation d'excitation de courant pour l'identification d'un paramètre électrochimique de batterie à partir d'une formule de sensibilité analytique
WO2021034106A1 (fr) Dispositif pour optimiser un indicateur d'apprentissage d'un modèle de prédiction d'environnement, et son procédé de fonctionnement
WO2013180427A1 (fr) Programme de débitmètre de gaz de dispositif d'étranglement et dispositif et procédé de mesure de débit l'utilisant
WO2018182171A1 (fr) Procédé pour effectuer une analyse de puissance de vitesse de navigation standard d'un vaisseau à voile
Talib et al. Fuzzy decision-making framework for sensitively prioritizing autism patients with moderate emergency level
WO2022108420A1 (fr) Appareil et procédé permettant de commander une conversion de puissance de formation de réseau
WO2014030930A2 (fr) Procédé de gestion d'énergie par modélisation d'objet de gestion d'énergie
WO2011068315A4 (fr) Appareil permettant de sélectionner une base de données optimale en utilisant une technique de reconnaissance de force conceptuelle maximale et procédé associé
WO2023158121A1 (fr) Procédé de création de données en vue de l'établissement d'un système de fabrication intelligent global et d'une normalisation internationale
WO2023191206A1 (fr) Système et procédé d'automatisation d'analyse de données d'exploration sur la base d'attributs variables
WO2019045320A1 (fr) Procédé et dispositif électronique permettant de prédire une structure électronique de matériau
WO2020060161A1 (fr) Système d'analyse statistique et méthode d'analyse statistique utilisant une interface conversationnelle
WO2017018593A1 (fr) Dispositif et procédé de détermination de la puissance de transmission dans un système de communication de dispositif à dispositif
WO2022145590A1 (fr) Appareil et procédé de prédiction de temps de rétention dans une analyse chromatographique d'un analyte
WO2023106844A1 (fr) Système de revêtement métallique rouleau à rouleau à grande vitesse et procédé de séchage à grande vitesse optimal pour revêtement métallique l'utilisant
WO2023229094A1 (fr) Procédé et appareil pour la prédiction d'actions
WO2023080766A1 (fr) Appareil pour générer des informations de mutation de gène à risque spécifique à une maladie à l'aide d'un modèle prs reposant sur une covariable variant dans le temps, et procédé associé

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 10858449

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 10858449

Country of ref document: EP

Kind code of ref document: A1