A metal alloy current sensing resistor detection data processing method and system

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for processing data for metal alloy current-sensing resistor detection. The method includes the following steps: collecting a number of current data and voltage drop data, and obtaining each subwindow of each current data; obtaining the stability of each subwindow of each current data, and obtaining the authenticity of each subwindow of each current data according to the stability of each subwindow of each current data and the connection between the numerical changes of the current data and the voltage data; obtaining a reference window of each current data according to the authenticity; obtaining a fuzzy entropy value of each current data according to the reference window of each current data, and obtaining each abnormal data according to the fuzzy entropy value of each current data, thereby completing the judgment of the abnormal situation of the metal alloy current-sensing resistor. The present invention avoids the influence of noise and improves the accuracy of abnormality detection.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for processing detection data of a metal alloy current-sensing resistor. Background Art

[0002] With the development of electronic equipment, communication systems, aerospace, energy storage and other fields, the application of metal alloy materials can be seen everywhere; the resistance characteristics of metal alloys directly affect their performance in these fields, especially in situations that require high-precision current control, voltage stability and reliability; to ensure the quality and stability of metal alloy materials, real-time detection of their current changes is crucial; the existing method for anomaly detection of current data flowing through alloys is the fuzzy entropy method. The fuzzy entropy method can not only improve the reliability and accuracy of the system through its effective capture of the dynamic complexity of data and its efficient anomaly detection capabilities, but also reduce the need for manual intervention and complex modeling, and adapt to various complex and uncertain current data environments.

[0003] The patent application document with the publication number CN115099624A currently discloses a multi-attribute decision-making system based on intuitive fuzzy entropy and interval fuzzy entropy, including a decision information acquisition module, a fuzzy entropy calculation module, and a decision result generation module; the decision information acquisition module is used to obtain several decision information matrices of the target and transmit them to the fuzzy entropy calculation module; the fuzzy entropy calculation module processes the decision information matrix to obtain the decision maker's hesitation weight coefficient and the benefit attribute hesitation weight coefficient, and transmits them to the decision result generation module; the decision result generation module calculates the comprehensive evaluation result of each decision information matrix according to the decision maker's hesitation weight coefficient and the benefit attribute hesitation weight coefficient, and obtains the optimal decision according to the comprehensive evaluation result of the decision information matrix.

[0004] When the fuzzy entropy method performs anomaly detection on current data, it determines whether the current data is abnormal by analyzing the variable value of the fuzzy entropy value corresponding to the current data and the previous current data. The fuzzy entropy value of the current data is calculated by first obtaining the window of the current data, obtaining several sub-windows of the current data according to the window of the current data, and finally averaging the fuzzy membership between all sub-windows of the current data. However, when collecting current data flowing through metal alloys, due to external electromagnetic fields, especially radiation from high-frequency electronic devices, it may interfere with the current acquisition system, resulting in noise in the collected current data. Then, when there is noise data in some sub-windows of the current data, the accuracy of the fuzzy membership mean of the subsequently obtained sub-window and other sub-windows will be reduced, and the abnormal detection result of the current data will be distorted. Summary of the invention

[0005] In order to solve the technical problem that noise appears in the collected current data due to interference from external electromagnetic fields, a fuzzy entropy algorithm is used, which reduces the accuracy of the fuzzy membership mean of each subwindow of current data obtained with other subwindows, resulting in distortion of the abnormal detection result of current data. The present invention provides a metal alloy current sensing resistor detection data processing method and system.

[0006] In a first aspect, the present invention provides a method for processing detection data of a metal alloy current sensing resistor, which adopts the following technical solution:

[0007] A method for processing detection data of a metal alloy current-sensing resistor comprises the following steps:

[0008] Collect current data and voltage drop data; obtain each sub-window of each current data; obtain the stability of each sub-window of each current data , Represents the stability of the jth sub-window of the i-th current data; Represents the similarity between the jth subwindow of the i-th current data and other subwindows; as well as Respectively represent the square root mean of the data in the j-th sub-window of the i-th current data and the mean of the data; Represents a hyperparameter; exp() represents an exponential function with a natural constant as the base; || represents the absolute value symbol; obtain the authenticity of each sub-window of each current data:

[0009] , represents the authenticity of the jth sub-window of the i-th current data; Represents the number of data in the jth subwindow of the i-th current data; as well as Represent the arrangement sequence number of the dth data in the jth subwindow of the ith current data and the ith voltage drop data respectively; Represents the stability of the jth sub-window of the i-th voltage drop data; norm() represents the normalization function;

[0010] According to the authenticity, a reference window of each current data is obtained; according to the reference window of each current data, a fuzzy entropy value of each current data is obtained, and then a plurality of abnormal data are obtained.

[0011] The innovation of the present invention lies in that by analyzing the numerical change characteristics of the current data flowing through the metal alloy and the voltage drop data at both ends of the alloy, the authenticity of each subwindow of each current data is obtained and the subwindows with poor authenticity are screened out based on it. The subwindows with large noise can be identified and eliminated, which can effectively improve the accuracy of fuzzy entropy calculation, thereby improving the effect of anomaly detection and avoiding the adverse effects of noise data on the calculation of fuzzy entropy values.

[0012] Preferably, the sub-windows for obtaining each current data include:

[0013] The number of sampling moments N is preset, and the current data at N sampling moments before the sampling moment corresponding to each current data is used as the window of each current data;

[0014] The length of the preset sub-window is M, and each data in the window of the i-th current data is recorded as each initial data. If any initial data and the M-1 data thereafter are data in the window of the i-th current data, then the initial data and the M-1 data thereafter are taken as a sub-window of the i-th current data. Similarly, each sub-window of the i-th current data is obtained.

[0015] This facilitates subsequent analysis of the numerical characteristics of the data in each subwindow of each current data, obtains the stability of each subwindow of each current data, and further identifies the window containing noise data.

[0016] Preferably, obtaining the similarity between the j-th sub-window of the i-th current data and other sub-windows includes:

[0017] The mean of the fuzzy membership of the j-th subwindow of the i-th current data and each subwindow except the j-th subwindow is obtained, which is recorded as the similarity between the j-th subwindow of the i-th current data and other subwindows.

[0018] Preferably, the method for obtaining the arrangement sequence number includes:

[0019] Sort the data in the j-th subwindow of the i-th current data in ascending order to obtain the arrangement sequence number of each data in the j-th subwindow of the i-th current data;

[0020] The voltage drop data corresponding to the sampling moment of the i-th current data is recorded as the i-th voltage drop data. According to the acquisition method of each sub-window of each current data, each sub-window of the i-th voltage drop data is obtained, and the data in the j-sub-window of the i-th voltage drop data is sorted in ascending order to obtain the arrangement number of each data in the j-sub-window of the i-th voltage drop data.

[0021] This facilitates the subsequent acquisition of the authenticity of each sub-window of each current data.

[0022] Preferably, obtaining a reference window for each current data according to the authenticity includes:

[0023] A authenticity threshold T is preset. If the authenticity of the jth subwindow of the i-th current data is greater than or equal to the authenticity threshold T, the jth subwindow of the i-th current data is recorded as the reference window of the i-th current data to obtain each reference window of each current data.

[0024] The sub-windows with larger noise are eliminated to obtain the reference window, which can effectively improve the accuracy of fuzzy entropy calculation.

[0025] Preferably, the fuzzy entropy value of each current data is obtained according to the reference window of each current data, and then a plurality of abnormal data are obtained, including:

[0026] The abnormality level threshold T1 is preset, and the absolute value of the difference between the fuzzy entropy value of the i-th current data and the fuzzy entropy value of the i-1th current data is recorded as the abnormality level of the i-th current data. If the abnormality level of the i-th current data is greater than the abnormality level threshold T1, the i-th current data is abnormal data. At this time, the metal alloy current sensing resistor is abnormal at the sampling moment corresponding to the i-th current data, and the relevant technical personnel are notified to take corresponding measures.

[0027] Improved the accuracy of anomaly detection results.

[0028] Preferably, the collecting current data and voltage drop data includes:

[0029] Every ten seconds is a sampling moment. The current data flowing through the metal alloy and the voltage data at both ends of the metal alloy are collected by the current sensor and the voltage sensor. The collection is done for one hour in total to obtain the current data and two voltage data at each sampling moment. The absolute value of the difference between the two voltage data at each sampling moment is recorded as the voltage drop data at each sampling moment.

[0030] In a second aspect, the present invention provides a metal alloy current sensing resistor detection data processing system, which adopts the following technical solution:

[0031] A metal alloy current sensing resistor detection data processing system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned metal alloy current sensing resistor detection data processing method is implemented.

[0032] By adopting the above technical solution, the above-mentioned metal alloy current sensing resistor detection data processing method is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is manufactured according to the memory and the processor for easy use.

[0033] The present invention has the following technical effects: The purpose of the present invention is to obtain the authenticity of each sub-window of each current data and screen out sub-windows with poor authenticity based on the analysis of the numerical change characteristics of the current data flowing through the metal alloy and the voltage drop data at both ends of the alloy, so as to identify and eliminate sub-windows with large noise, effectively improve the accuracy of fuzzy entropy calculation, thereby improving the effect of anomaly detection and avoiding the adverse effects of noise data on the calculation of fuzzy entropy values. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0035] Figure 1 The present invention is a flowchart of a method for processing data of metal alloy current sensing resistor detection according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0037] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0038] The embodiment of the present invention discloses a method for processing detection data of a metal alloy current sensing resistor, referring to Figure 1 , comprising steps S1 to S4:

[0039] S1: Collect some current data and voltage drop data.

[0040] In the embodiment of the present invention, every ten seconds is a sampling moment, and the current data flowing through the metal alloy and the voltage data at both ends of the metal alloy are collected each time by the current sensor and the voltage sensor. The collection is done for one hour in total to obtain the current data and two voltage data at each sampling moment; the absolute value of the difference between the two voltage data at each sampling moment is recorded as the voltage drop data at each sampling moment.

[0041] S2: Obtain each sub-window of each current data; obtain the stability of each sub-window of each current data.

[0042] It should be noted that when the fuzzy entropy method performs anomaly detection on current data, it determines whether the current data is abnormal by analyzing the variable value of the fuzzy entropy value corresponding to the current data before it, and the fuzzy entropy value of the current data is calculated by first obtaining the window of the current data, obtaining several sub-windows of the current data according to the window of the current data, and finally averaging the fuzzy membership between all sub-windows of the current data; however, when collecting current data flowing through metal alloys, due to external electromagnetic fields, especially radiation from high-frequency electronic devices, it may interfere with the current acquisition system, resulting in noise in the collected current data. Then, when there is noise data in some sub-windows of the current data, the accuracy of the fuzzy membership mean of the subsequently obtained sub-window and other sub-windows will be reduced, and the abnormal detection result of the current data will be distorted.

[0043] Therefore, the present invention first needs to obtain several sub-windows of each current data, and then analyze the numerical change characteristics of the current data flowing through the metal alloy and the voltage drop data at both ends of the alloy to obtain the authenticity of each sub-window of each current data, and screen the sub-windows according to the authenticity, and eliminate the sub-windows with poor authenticity to obtain a reference window for each current data. Subsequently, the fuzzy entropy value of each current data is calculated based on the reference window of each current data to obtain a more accurate abnormality detection result. Therefore, the present invention first needs to obtain the window of each current data, and then obtain the sub-window of each current data to facilitate subsequent analysis.

[0044] In the embodiment of the present invention, the current data at N sampling moments before the sampling moment corresponding to each current data is used as the window of each current data; in the embodiment of the present invention, the preset number of sampling moments N=60, in other embodiments, the implementer can preset the value of N according to the specific implementation method;

[0045] The length of the preset sub-window is M. Each data in the window of the i-th current data is denoted as each initial data. If any initial data and the subsequent M - 1 data are all in the window of the i-th current data, then this initial data and the subsequent M - 1 data are used as a sub-window of the i-th current data. Similarly, each sub-window of the i-th current data is obtained. In the embodiment of the present invention, the length M of the preset sub-window is 20. In other embodiments, the implementer can preset the length of the sub-window according to the specific implementation situation.

[0046] It should be noted that if there are noise data in the sub-window of the current data, the data in the sub-window of the current data will fluctuate and become unstable. At this time, the sub-window needs to be deleted. Therefore, it is necessary to analyze the numerical performance of the data in the sub-window of the current data. When the root mean square of the data in the sub-window of the current data has a smaller difference from the mean value of the data, it indicates that the stability degree of the sub-window of the current data is relatively large; and the average value of the fuzzy membership degrees of each sub-window of the current data with all other sub-windows except itself can reflect the similarity in value between the sub-window of the current data and all other sub-windows except itself. The larger this value is, the more similar it is, and at this time, the stability degree of the sub-window of the current data is relatively large. When the stability degree of the sub-window is relatively large, it indicates that the possibility of noise data existing in the sub-window is relatively low.

[0047] Obtain the mean value of the fuzzy membership degrees of the j-th sub-window of the i-th current data with each sub-window except the j-th sub-window, and denote it as the similarity of the j-th sub-window of the i-th current data with other sub-windows; it should be noted that the acquisition of the fuzzy membership degree is a well-known technology, and in the embodiment of the present invention, it will not be elaborated too much.

[0048] In the embodiment of the present invention, obtain the stability degree of the j-th sub-window of the i-th current data:

[0049] ;

[0050] In the formula, represents the stability degree of the j-th sub-window of the i-th current data; represents the similarity of the j-th sub-window of the i-th current data with other sub-windows; represents the root mean square of the data in the j-th sub-window of the i-th current data; represents the mean value of the data in the j-th sub-window of the i-th current data; represents a hyperparameter. In the embodiment of the present invention, the preset hyperparameter = 0.01. Its existence is to avoid from being 0; exp() represents the exponential function with the natural constant as the base;

[0051] The smaller the value is, the more stable the data in the subwindow is, the lower the possibility of noise data is, and the greater the corresponding stability is; The larger the value is, the closer the numerical performance of the sub-window is to that of other windows except itself. The smaller the absolute value of the difference between the mean square root and the mean of the data in the sub-window is, the greater the credibility is. This can further explain that the data in the sub-window is more stable, the possibility of noise data is lower, and the corresponding stability is greater.

[0052] S3: According to the stability of each sub-window of each current data and the connection between the numerical changes of the current data and the voltage data, the authenticity of each sub-window of each current data is obtained; according to the authenticity, a reference window of each current data is obtained; according to the reference window of each current data, a fuzzy entropy value of each current data is obtained.

[0053] It should be noted that the influence of noise may cause some data with relatively abnormal numerical performance to be mistakenly regarded as normal data, and the acquisition of the stability of each subwindow of the current data is based on the numerical performance of the current data itself. Therefore, the accuracy of the stability of each subwindow of the current data is reduced. According to the scene investigation, the collected current data flowing through the metal alloy often has a certain connection with the voltage data at both ends of the alloy, that is, a positive correlation. This conclusion is based on Ohm's law, that is, when the resistance value remains unchanged, the greater the voltage, the greater the current. Therefore, in order to reduce the interference of noise data, the connection between the numerical changes of current data and voltage data is analyzed, and then the stability of each subwindow of each current data is combined to obtain the authenticity of each subwindow of each current data; if the connection between the subwindow of current data and the data in the corresponding subwindow of voltage drop data is strong, it means that the less noise data there is in the subwindow of current data, the stronger the credibility of the stability of the subwindow, and the stronger the corresponding authenticity.

[0054] In the embodiment of the present invention, the data in the j-th sub-window of the i-th current data are sorted in ascending order to obtain the arrangement sequence number of each data in the j-th sub-window of the i-th current data;

[0055] The voltage drop data corresponding to the sampling time of the i-th current data is recorded as the i-th voltage drop data, and each sub-window of the i-th voltage drop data is obtained. It should be noted that each sub-window of the i-th voltage drop data is aligned with the data timing in the sub-window of the i-th current data;

[0056] Sort the data in the j-th subwindow of the i-th voltage drop data in ascending order to obtain the arrangement sequence number of each data in the j-th subwindow of the i-th voltage drop data;

[0057] For example, a group of data is 8, 7, 5, 9, and after being arranged from small to large, the group of data is 5, 7, 8, 9, among which the arrangement number of the first data 8 in the group of data is 3, the arrangement number of the second data 7 in the group of data is 2, and the arrangement number of the third data 5 in the group of data is 1.

[0058] Get the truth of each subwindow of each current data:

[0059] ;

[0060] In the formula, represents the authenticity of the jth sub-window of the i-th current data; Represents the stability of the jth sub-window of the i-th current data; Represents the number of data in the jth subwindow of the i-th current data; Represents the arrangement sequence number of the dth data in the jth subwindow of the i-th current data; represents the arrangement number of the dth data in the jth subwindow of the i-th voltage drop data; represents the stability of the jth sub-window of the i-th voltage drop data; norm() represents the normalization function; exp() represents the exponential function with a natural constant as the base; || represents the absolute value symbol;

[0061] The larger the value of is, the greater the authenticity of the j-th sub-window corresponding to the i-th current data is; Represents the connection between the data in the jth subwindow of the i-th current data and the data in the jth subwindow of the i-th voltage drop data. The smaller the value, the greater the connection, indicating that the less noise data exists in the jth subwindow of the i-th current data, and the greater the authenticity of the jth subwindow of the i-th current data; The larger the value of , the greater the stability of the j-th sub-window of the ith voltage drop data, and the more authentic the connection between the j-th sub-window of the ith current data and the data in the j-th sub-window of the ith voltage drop data. It can further be explained that the less noise data exists in the j-th sub-window of the ith current data, the greater the authenticity of the j-th sub-window of the ith current data.

[0062] A authenticity threshold T is preset. If the authenticity of the j-th subwindow of the ith current data is greater than or equal to the authenticity threshold T, the j-th subwindow of the ith current data is recorded as the reference window of the ith current data, and each reference window of each current data is obtained. In an embodiment of the present invention, the authenticity threshold T is preset to 0.6. In other embodiments, the implementer may preset the value of the authenticity threshold T according to the specific implementation method.

[0063] The fuzzy entropy method is used to obtain the fuzzy entropy value of each current data according to the reference window of each current data.

[0064] S4: Obtain each abnormal data according to the fuzzy entropy value of each current data, and complete the judgment of the abnormal situation of the metal alloy current sensing resistor.

[0065] It should be noted that the fuzzy entropy value of each current data is obtained, so next, based on the change value between each current data and the fuzzy entropy value of the previous current data, it is determined whether there is an abnormality in the metal alloy current sensing resistor at the sampling moment corresponding to each current data point.

[0066] In an embodiment of the present invention, the absolute value of the difference between the fuzzy entropy value of the i-th current data and the fuzzy entropy value of the i-1th current data is recorded as the abnormality of the i-th current data. If the abnormality of the i-th current data is greater than the abnormality threshold, the i-th current data is abnormal data, indicating that the change between the fuzzy entropy value of the i-th current data and the previous current data exceeds the abnormal threshold, indicating that the metal alloy current sensing resistor is abnormal at the sampling time corresponding to the i-th current data, and it is necessary to notify the relevant technical personnel to take corresponding measures. The preset abnormality threshold T1=0.15, in other embodiments, the implementer can preset the abnormality threshold T1 according to the specific implementation method.

[0067] An embodiment of the present invention further discloses a metal alloy current sensing resistor detection data processing system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a metal alloy current sensing resistor detection data processing method according to the present invention is implemented.

[0068] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0069] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0070] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0071] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for processing detection data of a metal alloy current sensing resistor, characterized in that: Includes steps: Collect current data and voltage drop data; obtain each sub-window of each current data; obtain the stability of each sub-window of each current data , Represents the stability of the jth sub-window of the i-th current data; Represents the similarity between the jth subwindow of the i-th current data and other subwindows; as well as Respectively represent the square root mean value and the mean value of the data in the j-th sub-window of the i-th current data; Represents a hyperparameter; exp() represents an exponential function with a natural constant as the base; || represents the absolute value symbol; obtain the authenticity of each sub-window of each current data: , represents the authenticity of the jth sub-window of the i-th current data; Represents the number of data in the jth subwindow of the i-th current data; as well as Represent the arrangement sequence number of the dth data in the jth subwindow of the i-th current data and the i-th voltage drop data respectively; Represents the stability of the jth sub-window of the i-th voltage drop data; norm() represents the normalization function; According to the authenticity, obtaining a reference window for each current data; According to the reference window of each current data, the fuzzy entropy value of each current data is obtained, and then a number of abnormal data are obtained.

2. A method for processing metal alloy current sensing resistor detection data according to claim 1, characterized in that: The sub-windows for obtaining current data include: The number of sampling moments N is preset, and the current data at N sampling moments before the sampling moment corresponding to each current data is used as the window of each current data; The length of the preset sub-window is M, and each data in the window of the i-th current data is recorded as each initial data. If any initial data and the M-1 data thereafter are data in the window of the i-th current data, then the initial data and the M-1 data thereafter are taken as a sub-window of the i-th current data. Similarly, each sub-window of the i-th current data is obtained.

3. The method for processing metal alloy current sensing resistor detection data according to claim 1, characterized in that: The acquisition of the similarity between the j-th sub-window of the i-th current data and other sub-windows includes: The mean of the fuzzy membership of the j-th subwindow of the i-th current data and each subwindow except the j-th subwindow is obtained, which is recorded as the similarity between the j-th subwindow of the i-th current data and other subwindows.

4. The method for processing metal alloy current sensing resistor detection data according to claim 1, characterized in that: The method for obtaining the arrangement sequence number includes: Sort the data in the j-th subwindow of the i-th current data in ascending order to obtain the arrangement sequence number of each data in the j-th subwindow of the i-th current data; The voltage drop data corresponding to the sampling moment of the i-th current data is recorded as the i-th voltage drop data. According to the acquisition method of each sub-window of each current data, each sub-window of the i-th voltage drop data is obtained, and the data in the j-sub-window of the i-th voltage drop data is sorted in ascending order to obtain the arrangement number of each data in the j-sub-window of the i-th voltage drop data.

5. The method for processing metal alloy current sensing resistor detection data according to claim 1, characterized in that: The step of obtaining a reference window for each current data according to the authenticity includes: A authenticity threshold T is preset. If the authenticity of the jth subwindow of the i-th current data is greater than or equal to the authenticity threshold T, the jth subwindow of the i-th current data is recorded as the reference window of the i-th current data to obtain each reference window of each current data.

6. The method for processing metal alloy current sensing resistor detection data according to claim 1, characterized in that: The method of obtaining the fuzzy entropy value of each current data according to the reference window of each current data, and then obtaining a plurality of abnormal data, includes: The abnormality level threshold T1 is preset, and the absolute value of the difference between the fuzzy entropy value of the i-th current data and the fuzzy entropy value of the i-1th current data is recorded as the abnormality level of the i-th current data. If the abnormality level of the i-th current data is greater than the abnormality level threshold T1, the i-th current data is abnormal data. At this time, the metal alloy current sensing resistor is abnormal at the sampling moment corresponding to the i-th current data, and the relevant technical personnel are notified to take corresponding measures.

7. A method for processing metal alloy current sensing resistor detection data according to claim 1, characterized in that: The collecting current data and voltage drop data includes: Every ten seconds is a sampling moment. The current data flowing through the metal alloy and the voltage data at both ends of the metal alloy are collected by the current sensor and the voltage sensor. The collection is done for one hour in total to obtain the current data and two voltage data at each sampling moment. The absolute value of the difference between the two voltage data at each sampling moment is recorded as the voltage drop data at each sampling moment.

8. A metal alloy current sensing resistor detection data processing system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a metal alloy current sensing resistor detection data processing method according to any one of claims 1-7 is implemented.

Images