Validity verification method and device for ship equipment simulation data

Abstract

The invention discloses a ship equipment simulation data validity verification method and device, and relates to the technical field of data verification, and the method comprises the steps: obtaining reference data and simulation data of ship equipment; the reference data comprises a plurality of first sample sequences, and the simulation data comprises a plurality of second sample sequences; judging whether grey correlation analysis is performed or not according to the characteristics of the reference data to obtain a judgment result; if the judgment result is yes, extracting a first feature vector of each preprocessed first sample sequence and a second feature vector of each preprocessed second sample sequence; each of the first feature vector and the second feature vector comprises a plurality of indexes; calculating the weight of each index by adopting an entropy method according to the first sample sequence set; based on the weight of each index, determining the weighted grey correlation degree of each second feature vector and the reference feature vector; and verifying the validity of each second sample sequence according to each weighted grey relational degree. According to the method, the objectivity of validity verification of the simulation data is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data verification, and in particular to a method and device for verifying the validity of ship equipment simulation data. Background Art

[0002] Ship equipment evaluation is a key link in improving the efficiency of ship equipment construction and use. With the continuous development of science and technology, especially computer technology, the maturity of simulation technology has greatly reduced the cost of ship equipment evaluation. Data simulation of ship equipment is crucial to improving the maintainability, combat effectiveness and equipment integrity of ships. It reduces costs and risks through virtual technology, optimizes equipment support systems, and provides data support for decision-making and planning, thereby achieving in-depth analysis and evaluation of ship equipment performance and maintenance strategies.

[0003] However, in the process of testing, simulating, collecting and processing data of ship equipment, due to the failure of simulation equipment or random errors in manual parameter entry and other unavoidable reasons, there are erroneous data. If false numbers are counted as true numbers, not only will the processed results be meaningless, but also false information will cause wrong control and decision-making, which will affect the scientific nature of decision-making and control. Therefore, it is necessary to test the validity of ship equipment test simulation data to ensure objectivity and authenticity.

[0004] Non-periodic time series data accounts for the main part in the collaborative characteristic test simulation and is the focus of data validity verification. Commonly used methods for analyzing the validity of non-periodic time series data include TIC method, feature matching method, regression analysis method, correlation analysis method, dynamic consistency test, etc. However, these methods often have limitations such as human subjectivity, difficulty in converging results, and complex parameter estimation process. In addition, the subjectivity and ambiguity of their safety evaluation indicators are too strong, which easily leads to the evaluation results being not objective enough and the results obtained being too one-sided. Summary of the invention

[0005] The purpose of this application is to provide a method and device for verifying the validity of ship equipment simulation data, thereby improving the objectivity of the verification of the validity of simulation data.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for verifying the validity of ship equipment simulation data, the method comprising:

[0008] Acquire reference data and simulation data of ship equipment; the reference data is a first sample sequence set consisting of a plurality of first sample sequences, and the simulation data is a second sample sequence set consisting of a plurality of second sample sequences;

[0009] Determine whether to perform grey relational analysis according to the characteristics of the reference data, and obtain a determination result;

[0010] If the judgment result is yes, preprocessing each of the first sample sequences and each of the second sample sequences;

[0011] Extracting a first feature vector of each of the first sample sequences after preprocessing and a second feature vector of each of the second sample sequences after preprocessing; the first feature vector and the second feature vector both include a plurality of indicators;

[0012] Calculating the weight of each indicator using an entropy method according to the first sample sequence set;

[0013] Based on the weight of each indicator, determine the weighted grey correlation degree between each of the second feature vectors and the first feature vector set; the first feature vector set is a set consisting of each of the first feature vectors;

[0014] Verifying the validity of each of the second sample sequences according to each of the weighted grey relational degrees;

[0015] If the judgment result is no, the verification is stopped.

[0016] Optionally, judging whether to perform grey relational analysis according to the characteristics of the reference data to obtain a judgment result specifically includes:

[0017] If the data amount of the first sample sequence set is less than the set data amount, it is determined that the grey relational analysis is not to be performed;

[0018] If the data amount of the first sample sequence set is greater than or equal to the set data amount, determining whether the reference data is time series data;

[0019] If the first sample sequence is not time series data, it is determined not to perform grey relational analysis;

[0020] If the first sample sequence is time series data, determining whether the first sample sequence has periodicity;

[0021] If the first sample sequence does not have periodicity, it is determined to perform grey relational analysis;

[0022] If the first sample sequence is periodic and the period is greater than a set time period, it is determined to perform grey relational analysis;

[0023] If the first sample sequence is periodic and the period is less than or equal to the set time period, it is determined not to perform grey relational analysis.

[0024] Optionally, preprocessing each of the first sample sequences and each of the second sample sequences specifically includes:

[0025] Eliminate outliers in each of the first sample sequences and each of the second sample sequences;

[0026] And the interpolation method is used to perform time series consistency processing on the first sample sequence and the second sample sequence after the abnormal values ​​are removed.

[0027] Optionally, the indicators in the first eigenvector and the second eigenvector include mean, peak, kurtosis, root mean square value, peak factor, pulse factor, waveform factor, margin factor and energy.

[0028] Optionally, calculating the weight of each indicator by using an entropy method according to the first sample sequence set specifically includes:

[0029] Normalizing the index of each of the first feature vectors;

[0030] Calculating the proportion of each normalized index in each of the first eigenvectors;

[0031] Calculate the information entropy of each indicator according to its weight;

[0032] The weight of each indicator is calculated according to its information entropy.

[0033] Optionally, based on the weight of each indicator, determining the weighted grey correlation degree between each of the second feature vectors and the set of first feature vectors specifically includes:

[0034] For any second eigenvector, calculate the grey correlation coefficient between the second eigenvector and each index in each first eigenvector;

[0035] Determine an initial weighted grey correlation degree according to the grey correlation coefficients of the second eigenvector and each index in each first eigenvector, and obtain N initial weighted grey correlation degrees, where N is the number of the first eigenvectors;

[0036] The average value of the N initial weighted grey relational degrees is taken as the weighted grey relational degree of the second feature vector and the first feature vector set.

[0037] Optionally, for any second eigenvector, calculating the grey correlation coefficient between the second eigenvector and each indicator in each first eigenvector specifically includes:

[0038] According to the formula Calculating the grey relational coefficient of each index of each second eigenvector;

[0039] Among them, i(j) is the grey relational coefficient of the jth index in the i-th second eigenvector, x0(j) represents the reference value of the jth index of the reference eigenvector, x i (j) is the value of the jth index in the i-th second eigenvector, ρ represents the resolution coefficient, min i Indicates the minimum value of the index in the second eigenvector, min j Represents the minimum value of all j-th indices in the second eigenvector.

[0040] Optionally, determining an initial weighted grey relational degree according to the grey relational coefficients of the second eigenvector and each indicator in each first eigenvector specifically includes:

[0041] According to the formula Calculate each initial weighted grey relational degree;

[0042] Among them, γ oi represents the initial weighted grey relational degree between the i-th second eigenvector and the reference eigenvector, m is the number of indicators, w j is the weight of the jth indicator, ζ i (j) is the grey relational coefficient of the jth index in the i-th second eigenvector.

[0043] Optionally, verifying the validity of each of the second sample sequences according to each of the weighted grey relational degrees specifically includes:

[0044] Determine whether the weighted grey correlation degree is greater than the set threshold;

[0045] If the weighted grey relational degree is greater than the set threshold, the second sample sequence corresponding to the weighted grey relational degree is determined to be valid data;

[0046] If the weighted grey relational degree is less than or equal to the set threshold, the second sample sequence corresponding to the weighted grey relational degree is determined to be invalid data.

[0047] In a second aspect, the present application provides a device for verifying the validity of ship equipment simulation data, the device comprising:

[0048] A data acquisition module, used to acquire reference data and simulation data of ship equipment; the reference data is a first sample sequence set consisting of a plurality of first sample sequences, and the simulation data is a second sample sequence set consisting of a plurality of second sample sequences;

[0049] A module for judging whether to perform correlation analysis is used to judge whether to perform grey correlation analysis according to the characteristics of the reference data and obtain a judgment result;

[0050] a preprocessing module, configured to preprocess each of the first sample sequences and each of the second sample sequences if the judgment result is yes;

[0051] A feature vector extraction module, used to extract a first feature vector of each of the first sample sequences after preprocessing and a second feature vector of each of the second sample sequences after preprocessing; the first feature vector and the second feature vector both include multiple indicators;

[0052] An indicator weight calculation module, used to calculate the weight of each indicator using an entropy method according to the first sample sequence set;

[0053] A weighted grey correlation determination module, used to determine the weighted grey correlation between each of the second feature vectors and a first feature vector set based on the weight of each indicator; the first feature vector set is a set consisting of each of the first feature vectors;

[0054] A validity verification module, used for verifying the validity of each of the second sample sequences according to each of the weighted grey relational degrees;

[0055] The verification stopping module is used to stop verification if the judgment result is no.

[0056] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0057] The present application provides a method and device for verifying the validity of simulation data of ship equipment. Based on the entropy method and grey correlation, the weighted grey correlation between each simulation data and the reference data is calculated, which can quantitatively realize the validity verification of the simulation data. The algorithm has strong interpretability, reduces human subjective influence, and improves the objectivity of the verification of the validity of the simulation data. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 A schematic diagram of a flow chart of a method for verifying the validity of ship equipment simulation data provided in an embodiment of the present application;

[0060] Figure 2 A detailed flowchart of a method for verifying the validity of ship equipment simulation data provided in one embodiment of the present application. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0062] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0063] This application provides a method for verifying the validity of ship equipment simulation data. Figure 1 and Figure 2 As shown, the method for verifying the validity of ship equipment simulation data includes steps 101 to 108.

[0064] Step 101: Acquire reference data and simulation data of ship equipment; the reference data is a first sample sequence set consisting of a plurality of first sample sequences, and the simulation data is a second sample sequence set consisting of a plurality of second sample sequences.

[0065] Step 102: Determine whether to perform grey relational analysis based on the characteristics of the reference data to obtain a determination result.

[0066] If the judgment result is yes, step 103 is executed.

[0067] Step 103: pre-process each of the first sample sequences and each of the second sample sequences.

[0068] Step 104: extracting a first feature vector of each of the first sample sequences after preprocessing and a second feature vector of each of the second sample sequences after preprocessing; the first feature vector and the second feature vector both include a plurality of indicators.

[0069] Step 105: Calculate the weight of each indicator using the entropy method according to the first sample sequence set.

[0070] Step 106: Based on the weight of each indicator, determine the weighted grey correlation degree between each of the second feature vectors and the first feature vector set; the first feature vector set is a set consisting of each of the first feature vectors.

[0071] Step 107: verifying the validity of each of the second sample sequences according to each of the weighted grey relational degrees;

[0072] If the judgment result is no, execute step 108.

[0073] Step 108: Stop verification.

[0074] This application is based on the entropy method and grey correlation to calculate the weighted grey correlation between each simulation data and the reference data, which can quantitatively verify the validity of the simulation data. The algorithm has strong interpretability, reduces human subjective influence, and improves the objectivity of the verification of the validity of the simulation data.

[0075] The first sample sequence of reference data and the second sample sequence of simulation data are generally respectively a time sequence generated by an actual system within a specific time and a simulation time sequence generated by a simulation system within a specific time.

[0076] In an exemplary embodiment, step 102 specifically includes:

[0077] If the data volume of the first sample sequence set is less than the set data volume, it is determined that the grey correlation analysis is not performed. The set data volume is the minimum value to ensure the accuracy of validity verification. If the reference data is insufficient, the grey correlation analysis cannot be performed and the verification is stopped.

[0078] If the data volume of the first sample sequence set is greater than or equal to the set data volume, it is determined whether the reference data is time series data, that is, whether the data type of the reference data is static data or dynamic data. Static data is random data, which refers to simulation data whose output of the simulation model has nothing to do with time, such as hit rate, damage probability, etc. Dynamic data is a time series, including non-periodic and periodic sequences, and the data changes with time.

[0079] If the first sample sequence is not time series data, that is, if the first sample sequence is static data, it is determined not to perform grey relational analysis and the verification is stopped.

[0080] If the first sample sequence is time series data, it is determined whether the first sample sequence has periodicity.

[0081] If the first sample sequence does not have periodicity, it is determined to perform grey relational analysis.

[0082] If the first sample sequence has periodicity and the period is greater than a set time period, it is determined to perform grey relational analysis.

[0083] If the first sample sequence is periodic and the period is less than or equal to the set time period, it is determined that the grey correlation analysis is not performed and the verification is stopped. The time series is periodic and has a large frequency, so it is not suitable to use the grey correlation analysis method.

[0084] Preprocessing includes two aspects: data review and data cleaning. The main contents of data review include checking whether the amount of data meets the minimum requirements of the grey correlation analysis method in simulation model verification; whether the simulation time series and reference time series data are comprehensive and sufficient; checking the data type of each time series, the magnitude, maximum value, minimum value, etc. of the data; checking whether the data has obvious error values, abnormal values, suspicious values, and missing values.

[0085] The main contents of data cleaning include processing outliers and missing values ​​found during the data review process; checking whether there are outliers in the reference time series and simulation time series, and removing them if they do; checking whether there are missing values ​​in the reference time series and simulation time series, and if they do, using interpolation methods to process the time series consistency.

[0086] In an exemplary embodiment, step 103 specifically includes:

[0087] Outliers in each of the first sample sequences and each of the second sample sequences are eliminated.

[0088] And the interpolation method is used to perform time series consistency processing on the first sample sequence and the second sample sequence after the abnormal values ​​are removed.

[0089] In an exemplary embodiment, the indicators in the first eigenvector and the second eigenvector include mean, peak, kurtosis, root mean square value, peak factor, pulse factor, waveform factor, margin factor and energy.

[0090] Calculate the mean of a time series The formula is: The time series is the first sample sequence or the second sample sequence.

[0091] Where Q is the total number of data points in the time series; x q' is the value of the q'th data point.

[0092] Calculate the peak value X of the time series p' The formula is: X p' =X max -X min Among them, X max is the maximum value in the time series data; X min is the minimum value in the time series data.

[0093] Calculate the kurtosis X of the time series kur The formula is: Among them, X σ is the standard deviation of the time series.

[0094] Calculate the RMS value of the time series Xrms The formula is:

[0095] Calculate the peak factor I of the time series p' The formula is:

[0096] Calculate the impulse factor I of a time series e' The formula is:

[0097] Calculate the waveform factor I of the time series ω' The formula is:

[0098] Calculate the margin factor I of the time series m The formula is:

[0099] Calculate the energy E of the time series q' The formula is:

[0100] Among them; c q' (t) is the value of q' time series at time t; dt represents the integration of t.

[0101] In an exemplary embodiment, step 105 specifically includes:

[0102] The indicators of each of the first feature vectors are normalized to ensure that the indicators of the reference data feature vectors have the same dimension; it should be noted that the data transformation is only calculated and used in this step, and the purpose is to calculate the weight of the information amount of each indicator of the reference data feature vector.

[0103] Normalization processing specifically adopts the min-max normalization processing method. Each indicator is divided into positive indicators and negative indicators.

[0104] The normalization formula of the positive indicator is:

[0105] The normalization formula for negative indicators is:

[0106]

[0107] Among them, x' i′ (j′) is the index value of the i′th index of the j′th first eigenvector after normalization processing, x i′ (j′) is the value of the i′th index of the j′th first eigenvector, X i′ is the vector of index values ​​of the i′th index, max(X i )-min(X i )≠0, if max(Xi )=min(X i ), then x' i′ (j′) = x i′ (j′).

[0108] The proportion of each normalized index in the index of each first feature vector is calculated.

[0109] The formula for calculating specific gravity is: P i′ (j′) is the weight of the i′th index of the j′th first eigenvector, and N is the number of first eigenvectors, that is, the number of first sample sequences.

[0110] If a column (a certain indicator) of data is less than or equal to 0, then add a "shift value" to the column of data (the value is the absolute value of the minimum value of the column of data + 0.01). At this time, all data are positive and calculated according to the following formula:

[0111] When there is x' i When (j)≤0,

[0112] Calculate the information entropy e of each indicator according to the weight of each indicator i′ , X' i′ It is the vector consisting of the index values ​​of the i′th index after normalization.

[0113] e i′ is the information entropy of the i′th indicator.

[0114] Calculate the weight w of each indicator according to the information entropy of each indicator i′ .

[0115]

[0116] Among them, d i′ is the information utility value of the i′th indicator, w i′ is the entropy weight of the i′th indicator, that is, the weight.

[0117] In an exemplary embodiment, step 106 specifically includes:

[0118] For any second eigenvector, the grey correlation coefficient between the second eigenvector and each index in each first eigenvector is calculated.

[0119] An initial weighted grey correlation degree is determined according to the grey correlation coefficients of the second eigenvector and each index in each first eigenvector, and N initial weighted grey correlation degrees are obtained; N is the number of the first eigenvectors.

[0120] The average value of the N initial weighted grey relational degrees is taken as the weighted grey relational degree of the second feature vector and the first feature vector set.

[0121] In an exemplary embodiment, for any second eigenvector, calculating the grey correlation coefficient between the second eigenvector and each indicator in each first eigenvector specifically includes:

[0122] According to the formula Calculate the grey relational coefficient of each index of each second eigenvector.

[0123] Among them, i (j) is the grey relational coefficient of the jth index in the i-th second eigenvector, x0(j) represents the reference value of the jth index of the reference eigenvector, x i (j) is the value of the jth index in the i-th second eigenvector, ρ represents the resolution coefficient, min i Indicates the minimum value of the index in the second eigenvector, min j Represents the minimum value of all j-th indices in the second eigenvector.

[0124] In an exemplary embodiment, determining an initial weighted grey relational degree according to the grey relational coefficients of the second eigenvector and each indicator in each first eigenvector specifically includes:

[0125] According to the formula Calculate each initial weighted grey relational degree.

[0126] Among them, γ oi represents the initial weighted grey correlation degree between the i-th second eigenvector and the reference eigenvector, m is the number of indicators, i.e. the dimension of the second eigenvector, w j is the weight of the jth indicator, ζ i (j) is the grey relational coefficient of the jth index in the i-th second eigenvector.

[0127] The average value of N initial weighted grey relational degrees is the weighted grey relational degree of the second feature vector and the set of first feature vectors, that is, the weighted grey relational degree between the corresponding simulation data and the reference data.

[0128] In an exemplary embodiment, step 107 specifically includes:

[0129] Determine whether the weighted grey relational degree is greater than the set threshold.

[0130] If the weighted grey relational degree is greater than the set threshold, the second sample sequence corresponding to the weighted grey relational degree is determined to be valid data.

[0131] If the weighted grey relational degree is less than or equal to the set threshold, the second sample sequence corresponding to the weighted grey relational degree is determined to be invalid data.

[0132] The present application discloses a method for verifying the validity of ship equipment simulation data based on entropy method and grey correlation. According to the pre-processed ship equipment reference data and ship equipment simulation data, the feature vectors of the reference data and the simulation data are obtained; the weight of the information amount of each indicator of the reference data feature vector is calculated by the entropy method; the weighted grey correlation between each simulation data feature vector and the reference data feature vector is determined; and the validity of the ship equipment simulation data is verified based on the calculated value and the threshold. The weighted grey correlation value of the simulation data is obtained by the entropy method and the grey correlation algorithm, and compared with the preset threshold value, so as to quantitatively reflect the validity of the ship equipment simulation data, and provide a reliable technical basis for the verification of simulation data for the actual ship equipment test. Compared with the related technology, the present application has a lower requirement for the number of reference data, a strong algorithm interpretation, and uses objective data calculation to reduce subjective influence.

[0133] Based on the same inventive concept, the embodiment of the present application also provides a ship equipment simulation data validity verification device for implementing the ship equipment simulation data validity verification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more ship equipment simulation data validity verification device embodiments provided below can refer to the limitations of the ship equipment simulation data validity verification method above, and will not be repeated here.

[0134] In an exemplary embodiment, the present application provides a device for verifying the validity of ship equipment simulation data, including:

[0135] The data acquisition module is used to acquire reference data and simulation data of ship equipment; the reference data is a first sample sequence set consisting of multiple first sample sequences, and the simulation data is a second sample sequence set consisting of multiple second sample sequences.

[0136] The module for determining whether to perform a correlation analysis is used to determine whether to perform a grey correlation analysis according to the characteristics of the reference data to obtain a determination result.

[0137] A preprocessing module is used for preprocessing each of the first sample sequences and each of the second sample sequences if the judgment result is yes.

[0138] The feature vector extraction module is used to extract the first feature vector of each of the first sample sequences after preprocessing and the second feature vector of each of the second sample sequences after preprocessing; the first feature vector and the second feature vector both include multiple indicators.

[0139] The indicator weight calculation module is used to calculate the weight of each indicator using the entropy method according to the first sample sequence set.

[0140] The weighted grey correlation determination module is used to determine the weighted grey correlation between each of the second feature vectors and the first feature vector set based on the weight of each indicator; the first feature vector set is a set composed of each of the first feature vectors.

[0141] The validity verification module is used to verify the validity of each of the second sample sequences according to each of the weighted grey relational degrees.

[0142] The verification stopping module is used to stop verification if the judgment result is no.

[0143] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for verifying the validity of ship equipment simulation data, characterized in that: The method for verifying the validity of ship equipment simulation data includes: Acquire reference data and simulation data of ship equipment; the reference data is a first sample sequence set consisting of a plurality of first sample sequences, and the simulation data is a second sample sequence set consisting of a plurality of second sample sequences; Determine whether to perform grey relational analysis according to the characteristics of the reference data, and obtain a determination result; If the judgment result is yes, preprocessing each of the first sample sequences and each of the second sample sequences; Extracting a first feature vector of each of the first sample sequences after preprocessing and a second feature vector of each of the second sample sequences after preprocessing; the first feature vector and the second feature vector both include a plurality of indicators; Calculating the weight of each indicator using an entropy method according to the first sample sequence set; Based on the weight of each indicator, determine the weighted grey correlation degree between each of the second feature vectors and the first feature vector set; the first feature vector set is a set consisting of each of the first feature vectors; Verifying the validity of each of the second sample sequences according to each of the weighted grey relational degrees; If the judgment result is no, the verification is stopped.

2. The method for verifying the validity of ship equipment simulation data according to claim 1, characterized in that: Judging whether to perform grey correlation analysis according to the characteristics of the reference data and obtaining a judgment result specifically includes: If the data amount of the first sample sequence set is less than the set data amount, it is determined that the grey relational analysis is not to be performed; If the data amount of the first sample sequence set is greater than or equal to the set data amount, determining whether the reference data is time series data; If the first sample sequence is not time series data, it is determined not to perform grey relational analysis; If the first sample sequence is time series data, determining whether the first sample sequence has periodicity; If the first sample sequence does not have periodicity, it is determined to perform grey relational analysis; If the first sample sequence is periodic and the period is greater than a set time period, it is determined to perform grey relational analysis; If the first sample sequence is periodic and the period is less than or equal to the set time period, it is determined not to perform grey relational analysis.

3. The method for verifying the validity of ship equipment simulation data according to claim 1, characterized in that: Preprocessing each of the first sample sequences and each of the second sample sequences specifically includes: Eliminate outliers in each of the first sample sequences and each of the second sample sequences; And the interpolation method is used to perform time series consistency processing on the first sample sequence and the second sample sequence after the abnormal values ​​are removed.

4. The method for verifying the validity of ship equipment simulation data according to claim 1, characterized in that: The indicators in the first eigenvector and the second eigenvector include mean, peak, kurtosis, root mean square value, peak factor, pulse factor, waveform factor, margin factor and energy.

5. The method for verifying the validity of ship equipment simulation data according to claim 1, characterized in that: The weight of each indicator is calculated using the entropy method according to the first sample sequence set, specifically including: Normalizing the index of each of the first feature vectors; Calculating the proportion of each normalized index in each of the first eigenvectors; Calculate the information entropy of each indicator according to its weight; The weight of each indicator is calculated according to its information entropy.

6. The method for verifying the validity of ship equipment simulation data according to claim 1, characterized in that: Based on the weights of the indicators, the weighted grey correlation degree between each of the second feature vectors and the first feature vector set is determined, specifically including: For any second eigenvector, calculate the grey correlation coefficient between the second eigenvector and each index in each first eigenvector; Determine an initial weighted grey correlation degree according to the grey correlation coefficients of the second eigenvector and each index in each first eigenvector, and obtain N initial weighted grey correlation degrees, where N is the number of the first eigenvectors; The average value of the N initial weighted grey relational degrees is taken as the weighted grey relational degree of the second feature vector and the first feature vector set.

7. The method for verifying the validity of ship equipment simulation data according to claim 6, characterized in that: For any second eigenvector, calculating the grey correlation coefficient between the second eigenvector and each indicator in each first eigenvector specifically includes: According to the formula Calculating the grey relational coefficient of each index of each second eigenvector; Among them, i (j) is the grey relational coefficient of the jth index in the i-th second eigenvector, x0(j) represents the reference value of the jth index of the reference eigenvector, x i (j) is the value of the jth index in the i-th second eigenvector, ρ represents the resolution coefficient, min i Indicates the minimum value of the index in the second eigenvector, min j Represents the minimum value of all j-th indices in the second eigenvector.

8. The method for verifying the validity of ship equipment simulation data according to claim 6, characterized in that: Determining an initial weighted grey correlation degree according to the grey correlation coefficients of the second eigenvector and each index in each first eigenvector specifically includes: According to the formula Calculate each initial weighted grey relational degree; Among them, γ oi represents the initial weighted grey relational degree between the i-th second eigenvector and the reference eigenvector, m is the number of indicators, w j is the weight of the jth indicator, ζ i (j) is the grey relational coefficient of the jth index in the i-th second eigenvector.

9. The method for verifying the validity of ship equipment simulation data according to claim 6, characterized in that: Verifying the validity of each of the second sample sequences according to each of the weighted grey relational degrees specifically includes: Determine whether the weighted grey correlation degree is greater than the set threshold; If the weighted grey relational degree is greater than the set threshold, the second sample sequence corresponding to the weighted grey relational degree is determined to be valid data; If the weighted grey relational degree is less than or equal to the set threshold, the second sample sequence corresponding to the weighted grey relational degree is determined to be invalid data.

10. A device for verifying the validity of ship equipment simulation data, characterized in that: The device for verifying the validity of ship equipment simulation data comprises: A data acquisition module, used to acquire reference data and simulation data of ship equipment; the reference data is a first sample sequence set consisting of a plurality of first sample sequences, and the simulation data is a second sample sequence set consisting of a plurality of second sample sequences; A module for judging whether to perform correlation analysis is used to judge whether to perform grey correlation analysis according to the characteristics of the reference data and obtain a judgment result; a preprocessing module, configured to preprocess each of the first sample sequences and each of the second sample sequences if the judgment result is yes; A feature vector extraction module, used to extract a first feature vector of each of the first sample sequences after preprocessing and a second feature vector of each of the second sample sequences after preprocessing; the first feature vector and the second feature vector both include multiple indicators; An indicator weight calculation module, used to calculate the weight of each indicator using an entropy method according to the first sample sequence set; A weighted grey correlation determination module, used to determine the weighted grey correlation between each of the second feature vectors and a first feature vector set based on the weight of each indicator; the first feature vector set is a set consisting of each of the first feature vectors; A validity verification module, used for verifying the validity of each of the second sample sequences according to each of the weighted grey relational degrees; The verification stopping module is used to stop verification if the judgment result is no.

Images