Data processing and parameter identification method and device for fast access recorder, equipment and medium

Abstract

The invention discloses a data processing and parameter identification method and device for a fast access recorder, equipment and a medium, and relates to the technical field of data processing.The data processing and parameter identification method comprises the steps that fast access recorder data are obtained, the fast access recorder data are analyzed based on an analysis rule file, and original parameter data are obtained; performing data filling on the original parameter data by using a piecewise linear interpolation method to obtain complete parameter data; determining a gross error value based on the arithmetic mean value and the standard deviation of each parameter, performing replacement processing on the gross error value, and processing an abnormal value in the corresponding parameter data after initial processing to obtain target parameter data; constructing a preset evaluation data matrix, and carrying out standardization processing on data in the matrix to obtain standardized data; and constructing a specific gravity matrix through the standardized data, determining a data weight value based on the specific gravity matrix, and identifying a target parameter of the rapid access recorder data according to the size of the data weight value. And the data quality and the analysis efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and medium for data processing and parameter identification of a fast access recorder. Background Art

[0002] The Quick Access Recorder (QAR) truly records the various flight parameter data of the main systems / components of civil aircraft, reflecting the performance change trends and various working conditions of each aircraft system. It has the characteristics of high frequency, large data volume, strong time series, random disturbance, complex structure, and strong professionalism. However, the sensor recorded data will be disturbed by various factors, resulting in missing values ​​and abnormal values ​​in the parsed QAR data. Therefore, in order to provide more reliable data support for data analysis and mining, how to improve the quality, reliability and analysis efficiency of QAR data is an urgent problem to be solved. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a data processing and parameter identification method, device, equipment and medium for a fast access recorder, which can process missing values, gross error values ​​and abnormal values ​​of original parameter data, improve the quality and reliability of QAR data, and identify and extract key parameters, further improving the efficiency of QAR data analysis. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses a data processing and parameter identification method for a fast access recorder, comprising:

[0005] Acquire quick access recorder data, parse the quick access recorder data based on a parsing rule file corresponding to the quick access recorder data to obtain original parameter data, and fill in missing data in the original parameter data using a piecewise linear interpolation method to obtain complete parameter data;

[0006] Determine a gross error value in the complete parameter data based on an arithmetic mean value and a standard deviation of each parameter, replace the gross error value with the arithmetic mean value and the standard deviation to obtain initial processed parameter data, and process abnormal values ​​in the initial processed parameter data through a filter to obtain target parameter data;

[0007] Constructing a preset evaluation data matrix according to the target parameter data and the arithmetic mean values ​​of each parameter, and performing standardization processing on each data in the preset evaluation data matrix to obtain standardized data;

[0008] A weight matrix is ​​constructed through the standardized data, a data weight value of each parameter is determined based on the weight matrix, and a target parameter of the fast access recorder data is identified according to the size of the data weight value.

[0009] Optionally, determining the gross error value in the complete parameter data based on the arithmetic mean and standard deviation of each parameter includes:

[0010] Calculate the arithmetic mean and the standard deviation of each parameter;

[0011] Determine the relationship between the absolute value of the difference between each of the parameters and the corresponding arithmetic mean and the preset multiple of the standard deviation;

[0012] If the absolute value of the difference between the parameter and the corresponding arithmetic mean is less than or equal to a preset multiple of the standard deviation, the parameter is determined to be a normal value;

[0013] If the absolute value of the difference between the parameter and the corresponding arithmetic mean is greater than a preset multiple of the standard deviation, the parameter is determined to be a gross error value in the complete parameter data;

[0014] Correspondingly, the using the arithmetic mean and the standard deviation to replace the gross error value to obtain the initial processed parameter data includes:

[0015] If the difference between the gross error value and the target arithmetic mean value is greater than the preset multiple standard deviation, the gross error value is replaced by the sum of the target arithmetic mean value and the preset multiple standard deviation to obtain the initial processed parameter data; the target arithmetic mean value is the arithmetic mean value of the parameter corresponding to the gross error value;

[0016] If the difference between the gross error value and the target arithmetic mean is smaller than the negative value of the preset multiple standard deviation, the gross error value is replaced by the difference between the target arithmetic mean and the preset multiple standard deviation to obtain the initial processed parameter data.

[0017] Optionally, the processing of abnormal values ​​in the initially processed parameter data by a filter to obtain target parameter data includes:

[0018] Inputting the initially processed parameter data into the filter, determining each data point and data point sequence in the filter window, and calculating a first median of the data point sequence;

[0019] determining an absolute deviation of each of the data points from the first median, and constructing a deviation scale sequence based on the absolute deviation;

[0020] Calculating a second median of the deviation scale sequence, and determining a decision threshold based on the second median;

[0021] If the absolute deviation of the data point is greater than the determination threshold, the data point is determined to be an outlier, and the outlier is replaced by the first median to obtain the target parameter data.

[0022] Optionally, constructing a preset evaluation data matrix according to the target parameter data and the arithmetic mean of each parameter includes:

[0023] A preset evaluation data matrix is ​​constructed according to the absolute error value between the target value of each parameter in the target parameter data at the target time and the arithmetic mean value of the parameter.

[0024] Optionally, the step of normalizing each data in the preset evaluation data matrix to obtain standardized data includes:

[0025] The data in the preset evaluation data matrix are standardized using a preset standardization processing formula to obtain standardized data; wherein the preset standardization processing formula is:

[0026] ;

[0027] Among them, X ij is the value of the jth parameter at time i; is the maximum value of the jth parameter; is the minimum value of the jth parameter; is the standardized data.

[0028] Optionally, constructing a weight matrix using the standardized data includes:

[0029] The specific gravity value corresponding to the standardized data is calculated based on a preset specific gravity calculation formula, and the specific gravity matrix is ​​constructed through each specific gravity value; wherein the preset specific gravity calculation formula is:

[0030] ;

[0031] in, is the weight value of the jth parameter at time i; is the standardized data; m is the upper limit of the value at the moment; n is the upper limit of the number of parameters.

[0032] Optionally, determining the data weight value of each parameter based on the weight matrix includes:

[0033] The information entropy of the absolute error sequence of each parameter is calculated based on the preset information entropy calculation formula and the weight matrix; the preset information entropy calculation formula is:

[0034] ;

[0035] in, is the information entropy of the jth parameter absolute error sequence; k is a constant; is the weight value of the jth parameter at time i; m is the upper limit of the value at time i;

[0036] The information utility value of each parameter is calculated according to the preset information utility value calculation formula and the information entropy; the preset information utility value calculation formula is:

[0037] ;

[0038] in, is the information utility value of the jth parameter; is the information entropy of the jth parameter absolute error sequence;

[0039] The data weight value of each parameter is calculated using the preset data weight value calculation formula and the information utility value; the preset data weight value calculation formula is:

[0040] ;

[0041] in, is the data weight value of the jth parameter; is the information utility value of the jth parameter.

[0042] In a second aspect, the present application discloses a data processing and parameter identification device for a fast access recorder, comprising:

[0043] A data filling module, used for acquiring the fast access recorder data, parsing the fast access recorder data based on the parsing rule file corresponding to the fast access recorder data to obtain the original parameter data, and filling the missing data in the original parameter data by using a piecewise linear interpolation method to obtain the complete parameter data;

[0044] A gross error value processing module, used to determine the gross error value in the complete parameter data based on the arithmetic mean and standard deviation of each parameter, and replace the gross error value with the arithmetic mean and the standard deviation to obtain the initial processed parameter data;

[0045] An outlier processing module, used for processing outliers in the initially processed parameter data through a filter to obtain target parameter data;

[0046] A standardization processing module, used for constructing a preset evaluation data matrix according to the target parameter data and the arithmetic mean of each parameter, and performing standardization processing on each data in the preset evaluation data matrix to obtain standardized data;

[0047] A parameter identification module is used to construct a weight matrix through the standardized data, determine the data weight value of each parameter based on the weight matrix, and identify the target parameter of the fast access recorder data according to the size of the data weight value.

[0048] In a third aspect, the present application discloses an electronic device, comprising:

[0049] Memory, used to store computer programs;

[0050] The processor is used to execute the computer program to implement the data processing and parameter identification method of the fast access recorder as mentioned above.

[0051] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the data processing and parameter identification method of the fast access recorder as described above.

[0052] When the present application performs data processing and parameter identification on a quick access recorder, firstly, the quick access recorder data is acquired, and the quick access recorder data is parsed based on a parsing rule file corresponding to the quick access recorder data to obtain original parameter data, and the missing data in the original parameter data is filled by using a piecewise linear interpolation method to obtain complete parameter data; then, the gross error value in the complete parameter data is determined based on the arithmetic mean and standard deviation of each parameter, the gross error value is replaced by the arithmetic mean and the standard deviation to acquire the initial processed parameter data, and the abnormal values ​​in the initial processed parameter data are processed by a filter to obtain the target parameter data; then, a preset evaluation data matrix is ​​constructed according to the target parameter data and the arithmetic mean of each parameter, and each data in the preset evaluation data matrix is ​​standardized to obtain the standardized data; finally, a weight matrix is ​​constructed by the standardized data, the data weight value of each parameter is determined based on the weight matrix, and the target parameter of the quick access recorder data is identified according to the size of the data weight value. It can be seen that the present application parses the acquired QAR data by utilizing parsing rules to obtain QAR original parameter data, and then processes the missing values, gross error values ​​and outliers of the original parameter data to improve the quality of QAR data. Finally, the key parameters are identified and extracted based on the QAR key parameter identification method, thereby eliminating abnormal data in the QAR data and further improving the efficiency of QAR data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0054] Figure 1 A flow chart of a data processing and parameter identification method for a fast access recorder disclosed in the present application;

[0055] Figure 2 This is a schematic diagram of the structure of a data processing and parameter identification device for a fast access recorder disclosed in the present application;

[0056] Figure 3 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] At present, sensor recorded data may be interfered by various factors, resulting in the parsed QAR data containing missing values ​​and abnormal values. In order to solve the above technical problems, the present application discloses a data processing and parameter identification method for a fast access recorder, which can pre-process the parsed data, and then identify and extract key parameters to improve the quality, reliability and analysis efficiency of QAR data, and provide more reliable data support for data analysis and mining.

[0059] See also Figure 1 As shown, the embodiment of the present invention discloses a data processing and parameter identification method for a fast access recorder, comprising:

[0060] Step S11, obtaining quick access recorder data, parsing the quick access recorder data based on the parsing rule file corresponding to the quick access recorder data to obtain original parameter data, and using piecewise linear interpolation to fill in missing data in the original parameter data to obtain complete parameter data.

[0061] In this embodiment, firstly, the quick access recorder data is obtained, and then the quick access recorder data is parsed based on the parsing rule file corresponding to the quick access recorder data to obtain the original parameter data. Afterwards, in order to eliminate the missing values ​​in the QAR data, the piecewise linear interpolation method is used to fill the missing values. The QAR data is a continuous sequence based on time, which can be regarded as a function f(t) about time t on a two-dimensional plane and processed by the interpolation method. If the QAR data is missing at a certain moment, it is approximated by the piecewise linear interpolation method:

[0062] ;

[0063] Among them, f(t) is the missing QAR data, t i and t j represent the time before and after time t, respectively. t i QAR data at the moment; t j QAR data at the moment.

[0064] After calculating the missing QAR data, the missing data in the original parameter data can be filled to obtain the complete parameter data.

[0065] Step S12, determining the gross error value in the complete parameter data based on the arithmetic mean and standard deviation of each parameter, replacing the gross error value with the arithmetic mean and the standard deviation, obtaining the initial processed parameter data, and processing the abnormal values ​​in the initial processed parameter data through a filter to obtain the target parameter data.

[0066] In this embodiment, there may be some gross error values ​​in the complete parameter data obtained, so it is necessary to process the gross error values ​​to further improve the quality of QAR data. In this process, the application first calculates the arithmetic mean and standard deviation of each parameter:

[0067] ;

[0068] in, is the arithmetic mean of the parameter, is the parameter and n is the number of parameters.

[0069] ;

[0070] in, is the standard deviation of the parameter, is the parameter and n is the number of parameters.

[0071] Afterwards, the absolute value of the difference between each parameter and its corresponding arithmetic mean and the preset multiple standard deviation is determined; if the absolute value of the difference between the parameter and its corresponding arithmetic mean is less than or equal to the preset multiple standard deviation, the parameter is determined to be a normal value; if the absolute value of the difference between the parameter and its corresponding arithmetic mean is greater than the preset multiple standard deviation, the parameter is determined to be a gross error value in the complete parameter data. That is, when , then x i is the normal value; otherwise, , then x i is a gross error value.

[0072] When x i When it is a gross error value, if the difference between the gross error value and the target arithmetic mean value is greater than the preset multiple standard deviation, the gross error value is replaced by the sum of the target arithmetic mean value and the preset multiple standard deviation to obtain the initial processed parameter data; the target arithmetic mean value is the arithmetic mean value of the parameter corresponding to the gross error value; if the difference between the gross error value and the target arithmetic mean value is less than the negative value of the preset multiple standard deviation, the gross error value is replaced by the difference between the target arithmetic mean value and the preset multiple standard deviation to obtain the initial processed parameter data. In a specific embodiment, if , it will be replaced by ;if , it will be replaced by After the final replacement is completed, the initial processed parameter data is obtained.

[0073] Afterwards, the outliers in the initial processed parameter data are processed by the filter to obtain the target parameter data. In this process, the initial processed parameter data is input into the filter, each data point and the data point sequence in the filter window are determined, and the first median of the data point sequence is calculated; the absolute deviation of each data point from the first median is determined, and the deviation scale sequence is constructed based on the absolute deviation; the second median of the deviation scale sequence is calculated, and the judgment threshold is determined based on the second median; if the absolute deviation of the data point is greater than the judgment threshold, the data point is judged to be an outlier, and the outlier is replaced by the first median to obtain the target parameter data. So far, the QAR data has been processed for missing values, gross error values ​​and outliers to improve the quality of the QAR data.

[0074] Step S13: construct a preset evaluation data matrix according to the target parameter data and the arithmetic mean values ​​of the parameters, and perform standardization on the data in the preset evaluation data matrix to obtain standardized data.

[0075] In this embodiment, after the QAR data is processed for missing values, large error values ​​and outliers, the quality of the QAR data has been improved, and then the key parameters of the QAR can be identified. First, an evaluation data matrix is ​​established based on the processed QAR data:

[0076] ;

[0077] Where: X ij is the value x of the jth parameter at time i ij The average value of this parameter The absolute error value is:

[0078] ;

[0079] In other words, the present application constructs a preset evaluation data matrix based on the absolute error value between the target value of each parameter in the target parameter data at the target time and the arithmetic mean of the parameter.

[0080] Then, the data in the evaluation data matrix are standardized. In the process of standardizing the evaluation data, the acquired evaluation data needs to be unified in magnitude and dimension. In order to avoid the appearance of 0 in the standardized value, which affects the calculation of the subsequent information entropy, the normalization method after translation correction is used to standardize the data:

[0081] ;

[0082] Among them, X ij is the value of the jth parameter at time i; is the maximum value of the jth parameter; is the minimum value of the jth parameter; The data are standardized.

[0083] Step S14, constructing a weight matrix through the standardized data, determining the data weight value of each parameter based on the weight matrix, and identifying the target parameter of the fast access recorder data according to the size of the data weight value.

[0084] In this embodiment, the weight value corresponding to the normalized data is calculated based on a preset weight calculation formula, and a weight matrix is ​​constructed through each weight value; the preset weight calculation formula is:

[0085] ;

[0086] in, is the weight value of the jth parameter at time i; is the standardized data; m is the upper limit of the value at the moment; n is the upper limit of the number of parameters.

[0087] Therefore, the weight matrix Y can be constructed for the acquired evaluation data:

[0088] .

[0089] Then the parameter weights need to be calculated. First, the information entropy of the absolute error sequence of each parameter is calculated based on the preset information entropy calculation formula and the weight matrix; the preset information entropy calculation formula is:

[0090] ;

[0091] in, is the information entropy of the jth parameter absolute error sequence; k is a constant, ; is the weight value of the jth parameter at time i; m is the upper limit of the value at time i;

[0092] Then, the information utility value of each parameter is calculated according to the preset information utility value calculation formula and information entropy; the preset information utility value calculation formula is:

[0093] ;

[0094] in, is the information utility value of the jth parameter; is the information entropy of the jth parameter absolute error sequence;

[0095] Finally, the data weight value of each parameter is calculated using the preset data weight value calculation formula and the information utility value; the preset data weight value calculation formula is:

[0096] ;

[0097] in, is the data weight value of the jth parameter, and the weight of each parameter satisfies ; is the information utility value of the jth parameter.

[0098] Finally, the target parameters for fast access to recorder data are identified based on the data weight values, which further improves the efficiency of QAR data analysis.

[0099] In summary, when the present application performs data processing and parameter identification on the quick access recorder, the quick access recorder data is first acquired, and the quick access recorder data is parsed based on the parsing rule file corresponding to the quick access recorder data to obtain the original parameter data, and the missing data in the original parameter data is filled by using the piecewise linear interpolation method to obtain the complete parameter data; then, the gross error value in the complete parameter data is determined based on the arithmetic mean and standard deviation of each parameter, the gross error value is replaced by the arithmetic mean and the standard deviation to obtain the initial processed parameter data, and the abnormal values ​​in the initial processed parameter data are processed by a filter to obtain the target parameter data; then, a preset evaluation data matrix is ​​constructed according to the target parameter data and the arithmetic mean of each parameter, and each data in the preset evaluation data matrix is ​​standardized to obtain the standardized data; finally, a weight matrix is ​​constructed by the standardized data, the data weight value of each parameter is determined based on the weight matrix, and the target parameter of the quick access recorder data is identified according to the size of the data weight value. It can be seen that the present application parses the acquired QAR data by utilizing parsing rules to obtain QAR original parameter data, and then processes the missing values, gross error values ​​and outliers of the original parameter data to improve the quality of QAR data. Finally, the key parameters are identified and extracted based on the QAR key parameter identification method, thereby eliminating abnormal data in the QAR data and further improving the efficiency of QAR data analysis.

[0100] Based on the previous embodiment, it can be seen that the present application will process the QAR data before identifying the QAR key parameters. The specific data processing process will be described in detail below.

[0101] After parsing the acquired QAR data based on the parsing rule file corresponding to the QAR data and obtaining the QAR original parameter data, the piecewise linear interpolation method is used to fill in the missing values ​​in the QAR data to eliminate the missing values. QAR data is a continuous sequence based on time, which can be regarded as a function f(t) about time t on a two-dimensional plane and processed using the interpolation method.

[0102] If the QAR data is missing at a certain moment, it is approximated by piecewise linear interpolation:

[0103] ;

[0104] Among them, f(t) is the missing QAR data, t i and t j represent the time before and after time t, respectively. t i QAR data at the moment; tj QAR data at the moment.

[0105] After calculating the missing QAR data, the missing data in the original parameter data can be filled to obtain the complete parameter data.

[0106] Then the gross error values ​​are processed, first calculating the arithmetic mean and standard deviation of each parameter:

[0107] ;

[0108] in, is the arithmetic mean of the parameter, is the parameter and n is the number of parameters.

[0109] ;

[0110] in, is the standard deviation of the parameter, is the parameter and n is the number of parameters.

[0111] Afterwards, the absolute value of the difference between each parameter and its corresponding arithmetic mean and the preset multiple standard deviation is determined; if the absolute value of the difference between the parameter and its corresponding arithmetic mean is less than or equal to the preset multiple standard deviation, the parameter is determined to be a normal value; if the absolute value of the difference between the parameter and its corresponding arithmetic mean is greater than the preset multiple standard deviation, the parameter is determined to be a gross error value in the complete parameter data. That is, when , then x i is the normal value; otherwise, , then x i is the gross error value. i For a gross error value, if , it will be replaced by ;if , it will be replaced by After the final replacement is completed, the initial processed parameter data is obtained.

[0112] Finally, to process the outliers, first define the size n of the filter window, for example, n=6; for each data point in the window: , calculate the median of the values ​​in the window, let The median of the data point sequence is Z k ; Then for each data point in the window, calculate its absolute deviation from the median to form an absolute deviation scale sequence as follows:

[0113] ;

[0114] Calculate the median of all absolute deviations in the scale sequence, and let the median of {d(k)} be MAD k Define a threshold constant C, for example, take C=2, to form the threshold judgment value TH:

[0115] ;

[0116] For each data point, if its absolute deviation exceeds the threshold TH, it is considered an outlier, and the median Z of the value in the window is used. k Replace it, otherwise, keep the original value. Finally, complete the processing of abnormal values.

[0117] It can be seen that this application can improve the quality of QAR data by processing missing values, gross error values ​​and outliers in QAR data, and then can accurately extract key parameters and improve the efficiency of QAR data analysis.

[0118] See also Figure 2 As shown, the embodiment of the present invention discloses a data processing and parameter identification device for a fast access recorder, comprising:

[0119] A data filling module 11 is used to obtain the fast access recorder data, parse the fast access recorder data based on the parsing rule file corresponding to the fast access recorder data to obtain the original parameter data, and fill the missing data in the original parameter data by using a piecewise linear interpolation method to obtain the complete parameter data;

[0120] A gross error value processing module 12 is used to determine the gross error value in the complete parameter data based on the arithmetic mean and standard deviation of each parameter, and replace the gross error value with the arithmetic mean and the standard deviation to obtain the initial processed parameter data;

[0121] An outlier processing module 13 is used to process outliers in the initially processed parameter data through a filter to obtain target parameter data;

[0122] A standardization processing module 14 is used to construct a preset evaluation data matrix according to the target parameter data and the arithmetic mean of each parameter, and perform standardization processing on each data in the preset evaluation data matrix to obtain standardized data;

[0123] The parameter identification module 15 is used to construct a weight matrix through the standardized data, determine the data weight value of each parameter based on the weight matrix, and identify the target parameter of the fast access recorder data according to the size of the data weight value.

[0124] It can be seen that the present application parses the acquired QAR data by utilizing parsing rules to obtain QAR original parameter data, and then processes the missing values, gross error values ​​and outliers of the original parameter data to improve the quality of QAR data. Finally, the key parameters are identified and extracted based on the QAR key parameter identification method, thereby eliminating abnormal data in the QAR data and further improving the efficiency of QAR data analysis.

[0125] In some specific embodiments, the gross error value processing module 12 can be specifically used to calculate the arithmetic mean and the standard deviation of each parameter; determine the size relationship between the absolute value of the difference between each parameter and the corresponding arithmetic mean and the preset multiple of the standard deviation; if the absolute value of the difference between the parameter and the corresponding arithmetic mean is less than or equal to the preset multiple of the standard deviation, then the parameter is determined to be a normal value; if the absolute value of the difference between the parameter and the corresponding arithmetic mean is greater than the preset multiple of the standard deviation, then the parameter is determined to be a gross error value in the complete parameter data; If the difference between the gross error value and the target arithmetic mean is greater than the standard deviation of the preset multiple, the gross error value is replaced by the sum of the target arithmetic mean and the standard deviation of the preset multiple to obtain the initial processed parameter data; the target arithmetic mean is the arithmetic mean of the parameter corresponding to the gross error value; if the difference between the gross error value and the target arithmetic mean is less than the negative value of the standard deviation of the preset multiple, the gross error value is replaced by the difference between the target arithmetic mean and the standard deviation of the preset multiple to obtain the initial processed parameter data.

[0126] In some specific embodiments, the outlier processing module 13 can be specifically used to input the initial processed parameter data into the filter, determine each data point and data point sequence in the filter window, and calculate the first median of the data point sequence; determine the absolute deviation of each data point from the first median, and construct a deviation scale sequence based on the absolute deviation; calculate the second median of the deviation scale sequence, and determine a judgment threshold based on the second median; if the absolute deviation of the data point is greater than the judgment threshold, the data point is judged to be an outlier, and the first median is used to replace the outlier to obtain the target parameter data.

[0127] In some specific embodiments, the standardization processing module 14 can be specifically used to construct a preset evaluation data matrix according to the absolute error value between the target value of each parameter in the target parameter data at the target time and the arithmetic mean value of the parameter.

[0128] In some specific embodiments, the standardization processing module 14 can be specifically used to perform standardization processing on each data in the preset evaluation data matrix using a preset standardization processing formula to obtain standardized data; wherein the preset standardization processing formula is:

[0129] ;

[0130] Among them, X ij is the value of the jth parameter at time i; is the maximum value of the jth parameter; is the minimum value of the jth parameter; is the standardized data.

[0131] In some specific embodiments, the parameter identification module 15 can be specifically used to calculate the specific gravity value corresponding to the standardized data based on a preset specific gravity calculation formula, and construct the specific gravity matrix through each specific gravity value; wherein the preset specific gravity calculation formula is:

[0132] ;

[0133] in, is the weight value of the jth parameter at time i; is the standardized data; m is the upper limit of the value at the moment; n is the upper limit of the number of parameters.

[0134] In some specific embodiments, the parameter identification module 15 can be specifically used to calculate the information entropy of the absolute error sequence of each parameter based on a preset information entropy calculation formula and the weight matrix; the preset information entropy calculation formula is:

[0135] ;

[0136] in, is the information entropy of the jth parameter absolute error sequence; k is a constant; is the weight value of the jth parameter at time i; m is the upper limit of the value at time i;

[0137] The information utility value of each parameter is calculated according to the preset information utility value calculation formula and the information entropy; the preset information utility value calculation formula is:

[0138] ;

[0139] in, is the information utility value of the jth parameter; is the information entropy of the jth parameter absolute error sequence;

[0140] The data weight value of each parameter is calculated using the preset data weight value calculation formula and the information utility value; the preset data weight value calculation formula is:

[0141] ;

[0142] in, is the data weight value of the jth parameter; is the information utility value of the jth parameter.

[0143] Furthermore, the present application also discloses an electronic device. Figure 3 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0144] Figure 3 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the data processing and parameter identification method of the fast access recorder disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0145] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0146] In addition, the memory 22 as a carrier for storing resources may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0147] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, and can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the data processing and parameter identification method of the fast access recorder executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks.

[0148] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the data processing and parameter identification method of the fast access recorder disclosed above is implemented. For the specific steps of the method, reference may be made to the corresponding contents disclosed in the above embodiments, and no further description will be given here.

[0149] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0150] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0151] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0152] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0153] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present 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 a limitation on the present application.

Claims

1. A method for data processing and parameter identification of a fast access recorder, characterized in that: include: Acquire quick access recorder data, parse the quick access recorder data based on a parsing rule file corresponding to the quick access recorder data to obtain original parameter data, and fill in missing data in the original parameter data using a piecewise linear interpolation method to obtain complete parameter data; Determine a gross error value in the complete parameter data based on an arithmetic mean value and a standard deviation of each parameter, replace the gross error value with the arithmetic mean value and the standard deviation to obtain initial processed parameter data, and process abnormal values ​​in the initial processed parameter data through a filter to obtain target parameter data; Constructing a preset evaluation data matrix according to the target parameter data and the arithmetic mean values ​​of each parameter, and performing standardization processing on each data in the preset evaluation data matrix to obtain standardized data; A weight matrix is ​​constructed through the standardized data, a data weight value of each parameter is determined based on the weight matrix, and a target parameter of the fast access recorder data is identified according to the size of the data weight value.

2. The method for data processing and parameter identification of a fast access recorder according to claim 1, characterized in that: The determining of the gross error value in the complete parameter data based on the arithmetic mean and standard deviation of each parameter comprises: Calculate the arithmetic mean and the standard deviation of each parameter; Determine the relationship between the absolute value of the difference between each of the parameters and the corresponding arithmetic mean and the preset multiple of the standard deviation; If the absolute value of the difference between the parameter and the corresponding arithmetic mean is less than or equal to a preset multiple of the standard deviation, the parameter is determined to be a normal value; If the absolute value of the difference between the parameter and the corresponding arithmetic mean is greater than a preset multiple of the standard deviation, the parameter is determined to be a gross error value in the complete parameter data; Correspondingly, the using the arithmetic mean and the standard deviation to replace the gross error value to obtain the initial processed parameter data includes: If the difference between the gross error value and the target arithmetic mean value is greater than the preset multiple standard deviation, the gross error value is replaced by the sum of the target arithmetic mean value and the preset multiple standard deviation to obtain the initial processed parameter data; the target arithmetic mean value is the arithmetic mean value of the parameter corresponding to the gross error value; If the difference between the gross error value and the target arithmetic mean is smaller than the negative value of the preset multiple standard deviation, the gross error value is replaced by the difference between the target arithmetic mean and the preset multiple standard deviation to obtain the initial processed parameter data.

3. The data processing and parameter identification method of the fast access recorder according to claim 1, characterized in that: The step of processing the abnormal values ​​in the initially processed parameter data by a filter to obtain target parameter data includes: Inputting the initially processed parameter data into the filter, determining each data point and data point sequence in the filter window, and calculating a first median of the data point sequence; determining an absolute deviation of each of the data points from the first median, and constructing a deviation scale sequence based on the absolute deviation; Calculating a second median of the deviation scale sequence, and determining a decision threshold based on the second median; If the absolute deviation of the data point is greater than the determination threshold, the data point is determined to be an outlier, and the outlier is replaced by the first median to obtain the target parameter data.

4. The method for data processing and parameter identification of a fast access recorder according to claim 1, characterized in that: The step of constructing a preset evaluation data matrix according to the target parameter data and the arithmetic mean values ​​of the parameters includes: A preset evaluation data matrix is ​​constructed according to the absolute error value between the target value of each parameter in the target parameter data at the target time and the arithmetic mean value of the parameter.

5. The data processing and parameter identification method of the fast access recorder according to claim 1, characterized in that: The step of performing standardization on each data in the preset evaluation data matrix to obtain standardized data includes: The data in the preset evaluation data matrix are standardized using a preset standardization processing formula to obtain standardized data; wherein the preset standardization processing formula is: ； Among them, X ij is the value of the jth parameter at time i; is the maximum value of the jth parameter; is the minimum value of the jth parameter; is the standardized data.

6. The method for data processing and parameter identification of a fast access recorder according to any one of claims 1 to 5, characterized in that: The step of constructing a weight matrix using the standardized data includes: The specific gravity value corresponding to the standardized data is calculated based on a preset specific gravity calculation formula, and the specific gravity matrix is ​​constructed through each specific gravity value; wherein the preset specific gravity calculation formula is: ； in, is the weight value of the jth parameter at time i; is the standardized data; m is the upper limit of the value at the moment; n is the upper limit of the number of parameters.

7. The method for data processing and parameter identification of a fast access recorder according to claim 6, characterized in that: The determining the data weight value of each parameter based on the weight matrix includes: The information entropy of the absolute error sequence of each parameter is calculated based on the preset information entropy calculation formula and the weight matrix; the preset information entropy calculation formula is: ； in, is the information entropy of the jth parameter absolute error sequence; k is a constant; is the weight value of the jth parameter at time i; m is the upper limit of the value at time i; The information utility value of each parameter is calculated according to the preset information utility value calculation formula and the information entropy; the preset information utility value calculation formula is: ； in, is the information utility value of the jth parameter; is the information entropy of the jth parameter absolute error sequence; The data weight value of each parameter is calculated using the preset data weight value calculation formula and the information utility value; the preset data weight value calculation formula is: ； in, is the data weight value of the jth parameter; is the information utility value of the jth parameter.

8. A data processing and parameter identification device for a fast access recorder, characterized in that: include: A data filling module, used for acquiring the fast access recorder data, parsing the fast access recorder data based on the parsing rule file corresponding to the fast access recorder data to obtain the original parameter data, and filling the missing data in the original parameter data by using a piecewise linear interpolation method to obtain the complete parameter data; A gross error value processing module, used to determine the gross error value in the complete parameter data based on the arithmetic mean and standard deviation of each parameter, and replace the gross error value with the arithmetic mean and the standard deviation to obtain the initial processed parameter data; An outlier processing module, used for processing outliers in the initially processed parameter data through a filter to obtain target parameter data; A standardization processing module, used for constructing a preset evaluation data matrix according to the target parameter data and the arithmetic mean of each parameter, and performing standardization processing on each data in the preset evaluation data matrix to obtain standardized data; A parameter identification module is used to construct a weight matrix through the standardized data, determine the data weight value of each parameter based on the weight matrix, and identify the target parameter of the fast access recorder data according to the size of the data weight value.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the data processing and parameter identification method of the fast access recorder as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the data processing and parameter identification method of the fast access recorder according to any one of claims 1 to 7 is implemented.

Images