A risk warning detection method and device based on rule base

Abstract

The present invention discloses a risk warning detection method and device based on a rule base, the method comprising: obtaining an equipment technical status parameter time series set and rule base information; the rule base information comprises an equipment standard status time series set; the equipment technical status parameter time series set comprises an equipment performance parameter time series; the equipment performance parameter time series is a time series of each type of equipment parameter; preprocessing the equipment technical status parameter time series set to obtain an equipment status parameter sequence set; performing risk warning detection processing on the equipment status parameter sequence set and the equipment standard status time series set to obtain an equipment technical status risk value.

Description

Technical Field

[0001] The present invention relates to the field of equipment support and artificial intelligence, and in particular to a risk warning detection method and device based on a rule base. Background Art

[0002] At present, equipment technical status assessment data is a collection of diversified data collected from various equipment in various links such as research and development, production, operation, and support. Equipment technical status assessment data has the characteristics of complex data sources and diversified data types. There are many problems in data processing, such as difficulty in extracting rules, difficulty in data modeling, and complex application scenarios. How to conduct risk warning detection of the technical status of the device based on the equipment technical status assessment data, and design a risk warning detection method and device that can adapt to multiple scenarios, a wide range of processing types, and can be customized for diversified needs, so as to meet the needs of equipment technical status warning processing, is an urgent problem to be solved. Summary of the invention

[0003] The present invention mainly solves the problem of how to perform risk warning detection on the technical status of an equipment based on equipment technical status assessment data. The present invention discloses a risk warning detection method and device based on a rule base.

[0004] In a first aspect of the embodiment of the present application, a risk warning detection method based on a rule base is disclosed, comprising:

[0005] S1, obtaining a time series set of equipment technical status parameters and rule base information; the rule base information includes a time series set of equipment standard status; the time series set of equipment technical status parameters includes a time series of equipment performance parameters; the time series of equipment performance parameters is a time series of each type of equipment parameter;

[0006] S2, preprocessing the equipment technical status parameter time series set to obtain an equipment status parameter series set;

[0007] S3, performing risk warning detection processing on the equipment status parameter sequence set and the equipment standard status time series set to obtain an equipment technical status risk value.

[0008] The preprocessing of the equipment technical status parameter time series set to obtain the equipment status parameter series set includes:

[0009] S21, performing outlier elimination and normalization processing on the equipment technical status parameter time series set in sequence to obtain a normalized information set;

[0010] S22, performing category discrimination processing on the normalized information set to obtain a first information set;

[0011] S23, performing boundary check processing on the first information set to obtain an equipment status parameter sequence set.

[0012] The performing boundary check processing on the first information set to obtain an equipment status parameter sequence set includes:

[0013] S211, preset a corresponding value range for each type of equipment parameter in the first information set; the value range includes an upper limit value and a lower limit value of the value range;

[0014] S212, for each data of each type of equipment parameter in the first information set, judging whether the value of the data is within the value range according to the value range of the equipment parameter; if the data is within the value range, not processing the data; if the data is not within the value range, setting the value of the data to the upper limit value or the lower limit value of the value range that is closest to the data;

[0015] S213, after completing S212 for the data of all types of equipment parameters, a set of equipment status parameter sequences is obtained.

[0016] The performing risk warning detection processing on the equipment status parameter sequence set and the equipment standard status time series set to obtain the equipment technical status risk value includes:

[0017] S31, performing feature fitting processing on the equipment standard state time series set to obtain an equipment risk warning model;

[0018] S32, performing risk analysis on each equipment status parameter time series of the equipment status parameter sequence set to obtain a risk sequence number value set;

[0019] S33, performing cumulative calculation processing on the risk sequence value set and the equipment risk warning model to obtain an equipment technical status risk value.

[0020] The performing feature fitting processing on the equipment standard state time series set to obtain an equipment risk warning model includes:

[0021] S311, constructing a first capability matrix using the equipment standard state time series set; the row vectors of the first capability matrix are the equipment standard state time series in the equipment standard state time series set;

[0022] S312, decomposing the first capability matrix to obtain a left decomposition matrix, a characteristic matrix, and a right decomposition matrix of the first capability matrix;

[0023] S313, extracting the diagonal elements of the feature matrix to obtain a feature vector; the feature vector is represented by Ia , I a =[λ 1 ,λ 2 , …, λ N1 ], N1 is the number of elements contained in the eigenvector;

[0024] S314, performing linear fitting processing on the elements and element sequence values ​​of the characteristic vector to obtain an equipment risk warning model.

[0025] The decomposition process is calculated as follows:

[0026] Y=UAV,

[0027] Among them, U is the left decomposition matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix.

[0028] The risk analysis is performed on each equipment status parameter time series of the equipment status parameter sequence set to obtain a risk sequence number value set, including:

[0029] S321, for each equipment state parameter time series of the equipment standard state time series set, calculating an average value of the equipment state parameter time series;

[0030] S322, for any element in the equipment status parameter time series, calculate the absolute value of the difference between the element and the average value; and confirm that the absolute value of the difference is the offset of the element;

[0031] S323, for the equipment status parameter time series, find an element with a maximum offset, and determine a sequence number value of the element in the equipment status parameter time series as a risk sequence number value of the equipment status parameter time series;

[0032] S324, constructing a risk sequence number value set by using the risk sequence number values ​​of all equipment state parameter time series of the equipment standard state time series set.

[0033] In a second aspect of the embodiment of the present application, a risk warning detection device based on a rule base is disclosed, the device comprising:

[0034] A memory storing executable program code;

[0035] a processor coupled to the memory;

[0036] The processor calls the executable program code stored in the memory to execute the risk warning detection method based on the rule base.

[0037] In a third aspect of an embodiment of the present application, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the risk warning detection method based on a rule base.

[0038] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, and the information data processing terminal is used to implement the risk warning detection method based on the rule base.

[0039] The beneficial effects of the present invention are:

[0040] The present invention performs risk warning detection on the technical status of the device based on the equipment technical status assessment data, and designs a risk warning detection method and device that are adaptable to multiple scenarios, have a wide range of processing types, and can be customized to meet diversified needs. By performing feature comparison with the rule base, fast and accurate risk warning can be achieved, thereby meeting the needs of equipment technical status warning processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0042] In order to better understand the content of the present invention, an embodiment is given here.

[0043] Figure 1 It is a flow chart for implementing the method of the present invention.

[0044] In a first aspect of the embodiment of the present application, a risk warning detection method based on a rule base is disclosed, comprising:

[0045] S1, obtaining a time series set of equipment technical status parameters and rule base information; the rule base information includes a time series set of equipment standard status; the time series set of equipment technical status parameters includes a time series of equipment performance parameters; the time series of equipment performance parameters is a time series of each type of equipment parameter;

[0046] S2, preprocessing the equipment technical status parameter time series set to obtain an equipment status parameter series set;

[0047] S3, performing risk warning detection processing on the equipment status parameter sequence set and the equipment standard status time series set to obtain an equipment technical status risk value.

[0048] The initialization process of the equipment technical status parameter time series set to obtain the equipment status parameter series set includes:

[0049] The equipment technical status parameter time series set is sequentially subjected to outlier elimination and normalization processing to obtain a normalized information set;

[0050] Performing category discrimination processing on the normalized information set to obtain a first information set;

[0051] Performing boundary check processing on the first information set to obtain an equipment status parameter sequence set;

[0052] The performing boundary check processing on the first information set to obtain an equipment status parameter sequence set includes:

[0053] S211, for each type of equipment technical status parameter in the first information set, preset a corresponding value range; the value range includes an upper limit value of the value range and a lower limit value of the value range;

[0054] S212, for each data of each type of equipment technical status parameter of the first information set, judging whether the value of the data is within the value range according to the value range of the equipment technical status parameter; if the data is within the value range, not processing the data; if the data is not within the value range, setting the value of the data to the upper limit value or the lower limit value of the value range that is closest to the data;

[0055] S213, after completing S212 for the data of all types of equipment technical status parameters, a set of equipment status parameter sequences is obtained;

[0056] The performing risk warning detection processing on the equipment status parameter sequence set and the equipment standard status time series set to obtain the equipment technical status risk value includes:

[0057] S31, performing feature fitting processing on the equipment standard state time series set to obtain an equipment risk warning model;

[0058] S32, performing risk analysis on each equipment status parameter time series of the equipment status parameter sequence set to obtain a risk sequence number value set;

[0059] S33, performing cumulative calculation processing on the risk sequence value set and the equipment risk warning model to obtain an equipment technical status risk value.

[0060] The performing feature fitting processing on the equipment standard state time series set to obtain an equipment risk warning model includes:

[0061] S311, constructing a first capability matrix using the equipment standard state time series set; the row vectors of the first capability matrix are the equipment standard state time series in the equipment standard state time series set;

[0062] S312, decomposing the first capability matrix to obtain a left decomposition matrix, a characteristic matrix, and a right decomposition matrix of the first capability matrix;

[0063] S313, extracting the diagonal elements of the feature matrix to obtain a feature vector; the feature vector is represented by I a , I a =[λ 1 ,λ 2 , …, λ N1 ], N1 is the number of elements contained in the eigenvector;

[0064] S314, performing linear fitting processing on the elements and element sequence values ​​of the characteristic vector to obtain an equipment risk warning model;

[0065] The decomposition process is calculated as follows:

[0066] Y=UAV,

[0067] Among them, U is the left decomposition matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix;

[0068] The risk analysis is performed on each equipment status parameter time series of the equipment status parameter sequence set to obtain a risk sequence number value set, including:

[0069] S321, for each equipment state parameter time series of the equipment standard state time series set, calculating an average value of the equipment state parameter time series;

[0070] S322, for each element in the equipment status parameter time series, calculate the absolute value of the difference between the element and the average value, and determine the absolute value of the difference as the offset of the element;

[0071] S323, for the equipment status parameter time series, find an element with a maximum offset, and determine a sequence number value of the element in the equipment status parameter time series as a risk sequence number value of the equipment status parameter time series;

[0072] S324, constructing a risk sequence number value set by using the risk sequence number values ​​of all equipment state parameter time series of the equipment standard state time series set.

[0073] For example, in the equipment state parameter time series p i In the ij For the element with the largest offset, the sequence number value is determined to be j.

[0074] The linear fitting process uses the characteristic vector element serial number value Ix as a known independent variable and the characteristic vector element value as a known dependent variable. The known independent variable and the known dependent variable are used to construct the curve to be approximated, and the function approximation method is used to perform curve fitting on the curve to be approximated to obtain the equipment risk warning model f(Ix).

[0075] The curve to be approximated is fitted by the function approximation method, and the best consistent linear approximation method can be used. The equipment risk warning model f(Ix) is expressed as:

[0076] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α 2 (Ix) 2 +α 1 (Ix))+α 0 ,

[0077] Wherein, P1 is the order of the equipment risk warning model f(Ix), α0, α1, α2, ..., α P1 is the coefficient of the equipment risk warning model f(Ix);

[0078] The decomposition process can be implemented by using a matrix singular value decomposition algorithm.

[0079] The cumulative calculation of the risk sequence number value set and the equipment risk warning model to obtain the equipment technical status risk value is to bring each risk sequence number value in the risk sequence number value set into the equipment risk warning model for calculation and processing to obtain the corresponding result value, and accumulate all the result values ​​to obtain the equipment technical status risk value; the equipment technical status risk value represents the probability of a risk occurring in the equipment technical status, and the larger the risk value, the more likely the equipment technical status is to have a risk.

[0080] The performing risk warning detection processing on the equipment status parameter sequence set and the equipment standard status time series set to obtain the equipment technical status risk value also includes:

[0081] S21, constructing a difference matrix by subtracting the matrix corresponding to the equipment state parameter sequence set from the matrix corresponding to the equipment standard state time series set; the row vector of the difference matrix is ​​the difference sequence between the equipment state parameter time series in the equipment standard state time series set and the standard state time series;

[0082] S22, performing cross-correlation calculation on the difference matrix to obtain a cross-correlation matrix;

[0083] S23, performing feature extraction processing on the mutual correlation matrix to obtain a weighted vector and an eigenvalue sequence;

[0084] S24, using the weighted vector, performing weighted summation on the risk sequence value set to obtain the equipment technical status risk value.

[0085] The step of using the weighted vector to perform weighted summation on the risk sequence value set to obtain the equipment technical status risk value includes:

[0086] The i-th element in the weighted vector is used as the weighted value of the i-th deviation sequence value in the risk sequence value set, and the risk sequence value set is weighted and summed to obtain the equipment technical status risk value.

[0087] The cross-correlation value calculation process is performed on the difference matrix to obtain the cross-correlation matrix, including:

[0088] Performing cross-correlation calculation processing on the row vectors of the difference matrix to obtain cross-correlation values, and constructing a cross-correlation matrix using the cross-correlation values; the elements of the i-th row and j-th column of the cross-correlation matrix are obtained by performing cross-correlation calculation on the i-th row vector and the j-th row vector of the difference matrix;

[0089] The performing feature extraction processing on the mutual correlation matrix to obtain a weighted vector includes:

[0090] The eigenvalue sequence and the corresponding eigenvector of the cross-correlation matrix are calculated; the cross-correlation matrix is ​​expressed as:

[0091]

[0092] Among them, r ij represents the mutual correlation coefficient between the i-th row vector and the j-th row vector of the difference matrix, i, j = 1, 2 ..., z, z = 5; the eigenvalue sequence is expressed as λ 1 ,λ 2 , …, λ z , where λ i represents the eigenvalue of the i-th row vector, and the eigenvector corresponding to the i-th row vector is f i ;

[0093] The eigenvalues ​​are used to perform normalized accumulation processing on the eigenvectors to obtain normalized accumulated eigenvectors; the normalized accumulation processing includes:

[0094] Perform normalized accumulation calculation on each element of the feature vector to obtain the corresponding normalized accumulated value; use all the normalized accumulated values ​​to construct a normalized accumulated feature vector;

[0095] The process of normalized cumulative calculation is:

[0096]

[0097] Among them, f ij Denotes the eigenvector f i The jth element of u represents the eigenvalue of the u-th row vector of the first capability matrix, l ij represents the i-th normalized cumulative feature vector l i The j-th element of .

[0098] Using the eigenvalue sequence, the corresponding normalized accumulated eigenvectors are weighted and summed to obtain a weighted vector; the weighted vector is expressed as [y 1 ,y 2 , …, y 10 ], where the jth element y of the weighted vector j The calculation expression is:

[0099]

[0100] Among them, y j It represents the j-th element of the weighted vector and also the weighted value corresponding to the j-th row vector.

[0101] The performing boundary check processing on the first information set to obtain an equipment status parameter sequence set includes:

[0102] S221, for each type of equipment technical status parameter data of the first information set, take the data collection information of the data as the known independent variable, take the data value of the data as the known dependent variable, use the known independent variable and the known dependent variable to construct a curve to be approximated, use the function approximation method to perform curve fitting on the curve to be approximated, and obtain the best consistent approximation polynomial f(Ix) of the class data attribute; use the best consistent approximation polynomial f(Ix) to calculate and process the known independent variables to obtain an approximate dependent variable; determine whether the absolute value of the difference between the approximate dependent variable and the corresponding known dependent variable is greater than a set second regression discrimination threshold; if it is greater than the second regression discrimination threshold, delete the data from the first information set; if it is less than the second regression discrimination threshold, do not process the data;

[0103] S222, executing S221 for all equipment technical status parameter data of the first information set to obtain an equipment status parameter sequence set;

[0104] The curve fitting of the curve to be approximated by the function approximation method may be performed by using the best consistent linear approximation method. The best consistent approximation polynomial f(Ix) is expressed as:

[0105] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α 2 (Ix) 2 +α 1 (Ix)+α 0 ,

[0106] Where P1 is the order of the best consistent approximation polynomial f(Ix), α0, α1, α2, …, α P1 are the coefficients of the optimal consistent approximation polynomial f(Ix);

[0107] The data collection information includes equipment serial number information, collection time information, collection space information, etc.

[0108] The outlier elimination includes filling missing values, smoothing noise data, smoothing or deleting outlier points; the smoothed noise data is first determined to obtain noise data, and then the noise data is smoothed according to the data before and after the noise data; the noise data is a value whose value is less than the detection sensitivity of the sensor of the observed data, or greater than the measurement upper limit of the sensor of the observed data. The outlier point can be determined by the Kalman filtering method. The filling value of the missing value can be determined by averaging the measured values ​​within a certain sampling interval before and after the missing value.

[0109] The normalization process is to map data in different value ranges to a specified value range, and its mathematical expression is:

[0110]

[0111] Among them, t is a data value in the data set, t max is the maximum value of all data in the data set, t min is the minimum value of all data in the data set, t 归一化 is the value of data t after normalization;

[0112] The category discrimination process is to discriminate the attributes of each data in each category of information in the normalized information set to see whether it is within the preset attribute range of the information, and to remove data that is not within the attribute range from the information.

[0113] In a second aspect of the embodiment of the present application, a risk warning detection device based on a rule base is disclosed, the device comprising:

[0114] A memory storing executable program code;

[0115] a processor coupled to the memory;

[0116] The processor calls the executable program code stored in the memory to execute the risk warning detection method based on the rule base.

[0117] In a third aspect of an embodiment of the present application, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the risk warning detection method based on a rule base.

[0118] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, and the information data processing terminal is used to implement the risk warning detection method based on the rule base.

[0119] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A risk warning detection method based on a rule base, characterized in that: include: S1, obtaining a time series set of equipment technical status parameters and rule base information; the rule base information includes a time series set of equipment standard status; the time series set of equipment technical status parameters includes a time series of equipment performance parameters; the time series of equipment performance parameters is a time series of each type of equipment parameter; S2, preprocessing the equipment technical status parameter time series set to obtain an equipment status parameter series set; S3, performing risk warning detection processing on the equipment status parameter sequence set and the equipment standard status time series set to obtain an equipment technical status risk value; The preprocessing of the equipment technical status parameter time series set to obtain the equipment status parameter series set includes: S21, performing outlier elimination and normalization processing on the equipment technical status parameter time series set in sequence to obtain a normalized information set; S22, performing category discrimination processing on the normalized information set to obtain a first information set; S23, performing boundary check processing on the first information set to obtain an equipment status parameter sequence set; The performing boundary check processing on the first information set to obtain an equipment status parameter sequence set includes: S211, preset a corresponding value range for each type of equipment parameter in the first information set; the value range includes an upper limit value and a lower limit value of the value range; S212, for each data of each type of equipment parameter in the first information set, judging whether the value of the data is within the value range according to the value range of the equipment parameter; if the data is within the value range, not processing the data; if the data is not within the value range, setting the value of the data to the upper limit value or the lower limit value of the value range that is closest to the data; S213, after completing S212 for the data of all types of equipment parameters, a set of equipment status parameter sequences is obtained; The performing risk warning detection processing on the equipment status parameter sequence set and the equipment standard status time series set to obtain the equipment technical status risk value includes: S31, performing feature fitting processing on the equipment standard state time series set to obtain an equipment risk warning model; S32, performing risk analysis on each equipment status parameter time series of the equipment status parameter sequence set to obtain a risk sequence number value set; S33, performing cumulative calculation processing on the risk sequence value set and the equipment risk warning model to obtain an equipment technical status risk value; The performing feature fitting processing on the equipment standard state time series set to obtain an equipment risk warning model includes: S311, constructing a first capability matrix using the equipment standard state time series set; the row vectors of the first capability matrix are the equipment standard state time series in the equipment standard state time series set; S312, decomposing the first capability matrix to obtain a left decomposition matrix, a characteristic matrix, and a right decomposition matrix of the first capability matrix; S313, extracting the diagonal elements of the feature matrix to obtain a feature vector; the feature vector is represented by I a , I a =[λ1,λ2,…,λ N1 ], N1 is the number of elements contained in the eigenvector; S314, performing linear fitting processing on the elements and element sequence values ​​of the characteristic vector to obtain an equipment risk warning model; The risk analysis is performed on each equipment status parameter time series of the equipment status parameter sequence set to obtain a risk sequence number value set, including: S321, for each equipment state parameter time series of the equipment standard state time series set, calculating an average value of the equipment state parameter time series; S322, for any element in the equipment status parameter time series, calculate the absolute value of the difference between the element and the average value; and confirm that the absolute value of the difference is the offset of the element; S323, for the equipment status parameter time series, find an element with a maximum offset, and determine a sequence number value of the element in the equipment status parameter time series as a risk sequence number value of the equipment status parameter time series; S324, constructing a risk sequence number value set by using the risk sequence number values ​​of all equipment state parameter time series of the equipment standard state time series set; The risk number value set and the equipment risk warning model are cumulatively calculated to obtain the equipment technical status risk value, which is to bring each risk number value in the risk number value set into the equipment risk warning model for calculation and processing to obtain the corresponding result value, and all the result values ​​are cumulatively processed to obtain the equipment technical status risk value.

2. The risk early warning detection method based on rule base according to claim 1 is characterized in that: The decomposition process is calculated as follows: Y=UAV, Among them, U is the left decomposition matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix.

3. A risk warning detection device based on a rule base, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the risk warning detection method based on the rule base as described in any one of claims 1 to 2.

4. A computer storable medium, characterized in that: The computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the risk warning detection method based on the rule base as described in any one of claims 1 to 2.

5. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the risk early warning detection method based on the rule base as described in any one of claims 1 to 2.

Images