Method and device for predicting service life of cable based on Weibull distribution, terminal equipment and storage medium

Abstract

The invention discloses a Weibull distribution-based cable life prediction method and apparatus, a terminal device and a storage medium. The method comprises the steps of obtaining operation time of a to-be-predicted cable; substituting the operation time of the to-be-predicted cable into a preset life prediction model, so that the life prediction model determines the life of the to-be-predicted cable according to the operation time of the to-be-predicted cable; wherein the life prediction model is determined by the following steps: acquiring life data of a cable sample and preprocessing the life data; constructing an initial grey prediction model according to the preprocessed data; repeatedly executing the parameter updating operation of the grey prediction model to obtain a final grey prediction model; constructing a cumulative distribution function, and performing formula transformation to obtain a life prediction model with an expression in the same form as that of the final grey prediction model; and determining parameters of the life prediction model, and generating a final life prediction model. And predicting the service life of the cable through the final service life prediction model.

Description

Technical Field

[0001] The present application relates to the technical field of cable life prediction, and in particular to a method, device, terminal equipment and storage medium for predicting cable life based on Weibull distribution. Background Art

[0002] As an indispensable cornerstone of the power transmission network, the reliability and stability of cable operation are key factors in maintaining the healthy operation of the entire power grid. The prediction of cable life provides power companies with a powerful tool to gain insight into and solve potential risks in the cable system in advance, effectively reduce power grid fluctuations and power outages caused by cable aging or sudden failures, and significantly improve the reliability and stability of the power grid. At the same time, through cable life prediction, more accurate and efficient preventive maintenance measures can be taken, so as to tailor a reasonable maintenance schedule to ensure that necessary inspections and repairs are carried out when the cable performance begins to decline or the precursors of failure appear. This strategy not only effectively avoids the inconvenience caused by unexpected power outages to social production and residents' lives, but also greatly reduces the high costs caused by emergency repairs, achieving dual guarantees of economic benefits and safe operation. In most cases, the two-parameter Weibull distribution model is usually selected according to the characteristics of the cable life data to describe the cable life distribution. However, the existing cable life prediction methods rely on data integrity and sufficient sample size. Due to the limitations of actual conditions, it is often difficult to obtain a large amount of detailed life data, especially the accumulation of aging data. Therefore, the existing traditional technical methods often face the problem of insufficient data. Summary of the invention

[0003] The embodiment of the present invention provides a method, device, terminal equipment and storage medium for predicting cable life based on Weibull distribution. The present invention can predict the life of a cable to be predicted when the amount of cable data is insufficient.

[0004] An embodiment of the present invention provides a method for predicting cable life based on Weibull distribution, comprising:

[0005] Obtaining the running time of the cable to be predicted;

[0006] Substituting the operating time of the cable to be predicted into a preset life prediction model, so that the life prediction model determines the life of the cable to be predicted according to the operating time of the cable to be predicted;

[0007] Wherein, the life prediction model is determined by the following method:

[0008] Obtain life data of several cable samples, sort each life data by time length to obtain an original sequence, and perform accumulation processing on the original sequence to generate an initial accumulated sequence;

[0009] Construct the initial grey prediction model according to the original sequence and the initial cumulative series;

[0010] Repeat the parameter updating operation of the grey prediction model until the grey prediction model meets the preset accuracy requirement, and obtain the final grey prediction model; the parameter updating operation includes: inputting the first data item in the original sequence into the current grey prediction model, so that the current grey prediction model generates the first prediction data; removing the first data item of the original cumulative sequence, and adding the first prediction data to the end of the original cumulative sequence, to obtain the updated cumulative sequence; updating the parameters of the grey prediction model according to the updated cumulative sequence and the original sequence;

[0011] According to the running time of each cable sample, a cumulative distribution function is constructed, and the cumulative distribution function is transformed into a formula to obtain a life prediction model having an expression in the same form as the final grey prediction model;

[0012] The threshold parameters, scale parameters and shape parameters of the life prediction model are determined according to the parameters of the final grey prediction model to generate the final life prediction model.

[0013] Furthermore, the life data of several cable samples are obtained, and each life data is sorted by time length to obtain an original sequence, and the original sequence is accumulated to generate an initial accumulated sequence, including:

[0014] Arrange the cable life data in ascending order according to the duration to generate the original sequence;

[0015] The original sequence is accumulated using the following calculation formula to generate the initial cumulative sequence:

[0016]

[0017] Where, X (1) (j) is the jth data of the initial cumulative sequence, X (0) (i) is the i-th data in the original sequence, and j is the total number of accumulated data in the original sequence.

[0018] Furthermore, the grey prediction model includes:

[0019]

[0020] Where, X (1) (j+1) is the j+1th data of the initial cumulative sequence, X (0) (1) is the first data of the original sequence, a is the development grayscale, and u is the endogenous control gray number.

[0021] Furthermore, the following method is used to determine whether the grey prediction model meets the preset accuracy requirements:

[0022] According to the posterior difference ratio calculation formula, calculate the posterior difference ratio corresponding to the grey prediction model;

[0023] Determining whether the posterior difference ratio is less than a preset posterior difference ratio;

[0024] If yes, it is determined that the grey prediction model meets the preset accuracy requirement, otherwise it is determined that the grey prediction model does not meet the preset accuracy requirement;

[0025] Among them, the calculation formula of the posterior difference ratio is:

[0026]

[0027] C=S2 / S1

[0028] In the formula, e(i) is the residual of the i-th data, is the predicted i-th data, is the variance of the original sequence, is the variance of the corresponding residual sequence calculated from the original sequence, n is the total number of data in the original sequence, is the average value of all data in the original sequence, is the average value of all data of the corresponding residual sequence calculated from the original sequence, and C is the posterior difference ratio.

[0029] Furthermore, the cumulative distribution function includes:

[0030]

[0031] Where x is the operation time of the cable, γ is the threshold parameter, β is the scale parameter, δ is the shape parameter, and F(x) is the probability of cable failure.

[0032] Furthermore, the life prediction model includes:

[0033]

[0034] In the formula, For the service life of the cable,

[0035] Furthermore, after determining the threshold parameter, scale parameter and shape parameter of the life prediction model according to the parameters of the final grey prediction model and generating the final life prediction model, it also includes:

[0036] According to the calculation formula of residual test, the absolute error and relative error of the life prediction model are calculated;

[0037] Determine whether the absolute error and the relative error are less than a preset error value;

[0038] If yes, it is determined that the life prediction model meets the preset accuracy requirement, otherwise it is determined that the life prediction model does not meet the preset accuracy requirement;

[0039] Among them, the calculation formulas for absolute error and relative error are:

[0040]

[0041] Where Δ is the absolute error and Φ is the relative error.

[0042] According to the calculation formula of the correlation test, the correlation value of the life prediction model is calculated;

[0043] Determining whether the correlation value is greater than a preset correlation value;

[0044] If yes, it is determined that the life prediction model has passed the correlation test, otherwise it is determined that the life prediction model has not passed the correlation test;

[0045] The calculation formula of the correlation test is:

[0046]

[0047] Where r is the correlation value, min{(Δi)} is the minimum absolute error, max{(Δi)} is the maximum absolute error, ρ is the resolution, and Δi is the absolute error of the i-th data in the original sequence.

[0048] Another embodiment of the present invention provides a prediction device for cable life based on Weibull distribution, comprising: a cable operation data acquisition module, a cable life calculation module, and a life prediction model construction module, wherein the life prediction model construction module comprises: an original data processing unit, a grey prediction model construction unit, a grey prediction model parameter updating unit, a life prediction model construction unit, and a life prediction model parameter determination unit;

[0049] The cable operation data acquisition module is used to obtain the operation time of the cable to be predicted;

[0050] The cable life calculation module is used to substitute the operation time of the cable to be predicted into a preset life prediction model, so that the life prediction model determines the life of the cable to be predicted according to the operation time of the cable to be predicted;

[0051] The raw data processing unit is used to obtain the life data of several cable samples, and to sort the life data by time to obtain an initial raw sequence, and to perform accumulation processing on the raw sequence to generate an initial accumulated sequence;

[0052] The grey prediction model construction unit is used to construct an initial grey prediction model according to the initial original sequence and the initial accumulated sequence;

[0053] The grey prediction model parameter updating unit is used to repeatedly perform the grey prediction model parameter updating operation until the grey prediction model meets the preset accuracy requirement, thereby obtaining a final grey prediction model; the parameter updating operation includes: inputting the first data item in the original sequence into the current grey prediction model, so that the current grey prediction model generates the first prediction data; removing the first data item of the current cumulative sequence, and adding the first prediction data to the end of the current cumulative sequence, thereby obtaining an updated cumulative sequence; and updating the grey prediction model parameters according to the updated cumulative sequence and the original sequence.

[0054] The life prediction model construction unit is used to construct a cumulative distribution function according to the operating time of each cable sample, and perform formula transformation on the cumulative distribution function to obtain a life prediction model with an expression in the same form as the grey prediction model;

[0055] The life prediction model parameter determination unit is used to determine the threshold parameters, scale parameters and shape parameters of the life prediction model according to the parameters of the grey prediction model to generate a final life prediction model.

[0056] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for predicting cable life based on Weibull distribution as described in any one of the above embodiments is implemented.

[0057] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a method for predicting cable life based on Weibull distribution as described in any of the above embodiments.

[0058] The following beneficial effects are achieved by implementing the embodiments of the present invention:

[0059] An embodiment of the present invention provides a method for predicting the life of a cable based on Weibull distribution. The method obtains the operating time of the cable to be predicted; substitutes the operating time of the cable to be predicted into a preset life prediction model, so that the life prediction model determines the life of the cable to be predicted according to the operating time of the cable to be predicted; wherein the life prediction model is determined in the following manner: obtaining life data of cable samples for preprocessing; constructing an initial grey prediction model based on the preprocessed data; repeatedly executing the parameter update operation of the grey prediction model to obtain a final grey prediction model; constructing a cumulative distribution function, performing formula transformation, and obtaining a life prediction model with an expression in the same form as the final grey prediction model; determining the parameters of the life prediction model to generate a final life prediction model. Compared with the prior art, the present invention obtains a high-precision prediction value of the cable life based on the existing cable sample data by constructing a gray prediction model, supplements the existing sample data, and updates the parameters of the gray prediction model. Then, according to the final gray prediction model, a life prediction model is constructed, the parameter values ​​of the life prediction model are determined, the operating time of the cable to be predicted is input into the life prediction model, and the life prediction value of the cable to be predicted is calculated, which solves the problem of predicting the life of the cable to be tested when the life data of the cable sample is insufficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of a method for predicting cable life based on Weibull distribution provided by one embodiment of the present invention.

[0061] Figure 2 It is a structural schematic diagram of a device for predicting cable life based on Weibull distribution provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0064] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0065] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0066] like Figure 1 FIG. 1 is a flow chart of a method for predicting cable life based on Weibull distribution provided by an embodiment of the present invention, comprising the following steps:

[0067] Step S1, obtaining the running time of the cable to be predicted;

[0068] In the present invention, by acquiring the operating time data of the cable to be predicted, data preparation is provided for the subsequent calculation of the service life of the cable to be predicted.

[0069] Step S2, substituting the operating time of the cable to be predicted into a preset life prediction model, so that the life prediction model determines the life of the cable to be predicted according to the operating time of the cable to be predicted;

[0070] In the present invention, the operating time data of the cable to be predicted is input into a preset life prediction model, and the life of the cable to be predicted is calculated according to the formula of the life prediction model.

[0071] Wherein, the steps of determining the life prediction model are:

[0072] Step S21, obtaining life data of a number of cable samples, and sorting each life data by time length to obtain an original sequence, and performing accumulation processing on the original sequence to generate an initial accumulation sequence;

[0073] In the present invention, by acquiring the existing cable laying time data and cable failure time data, the specific operating time data of the cable in the entire life cycle is calculated, and it is used as the life data of the cable sample. Then, according to the specific duration of each life data, the life is arranged in ascending order from short to long to obtain a sorted sequence, that is, the above-mentioned original sequence.

[0074] In a preferred embodiment, the life data of several cable samples are obtained, and each life data is sorted by time length to obtain an original sequence, and the original sequence is accumulated to generate an initial accumulated sequence, including:

[0075] Arrange the cable life data in ascending order according to the duration to generate the original sequence;

[0076] The original sequence is accumulated using the following calculation formula to generate the initial cumulative sequence:

[0077]

[0078] Where, X (1) (j) is the jth data of the initial cumulative sequence, X (0) (i) is the i-th data in the original sequence, and j is the total number of accumulated data in the original sequence.

[0079] Specifically, after obtaining the original sequence, the original sequence is accumulated to obtain an initial accumulated sequence, the first data item in the initial accumulated sequence is consistent with the first data item of the original sequence, the second data item in the initial accumulated sequence is the sum of the first data item and the second data item of the original sequence, the third data item in the initial accumulated sequence is the sum of the first data item, the second data item and the third data item of the original sequence, and so on.

[0080] Step S22, constructing an initial grey prediction model according to the original sequence and the initial accumulated series;

[0081] In the present invention, an initial grey prediction model is constructed according to the original sequence and the initial accumulated series, and an expression of the initial grey prediction model is obtained;

[0082] In a preferred embodiment, the grey prediction model includes:

[0083]

[0084] Where, X (1) (j+1) is the j+1th data of the initial cumulative sequence, X (0) (1) is the first data of the original sequence, a is the development grayscale, and u is the endogenous control gray number;

[0085] Specifically, the specific construction process of the grey prediction model includes:

[0086] Construct the first-order differential equation of a variable for grey prediction, the expression is:

[0087]

[0088] By solving the differential equation, we can get the grey prediction model:

[0089]

[0090] Based on the original sequence and the initial cumulative series, the parameter vector is estimated by the least square method to meet the following conditions, and the initial values ​​of the two parameters of the development gray scale and endogenous control gray number of the initial grey prediction model are obtained:

[0091] [au] T =[B T B] -1 B T Y;

[0092] In the formula,

[0093] After constructing the above initial grey prediction model, it is necessary to update the values ​​of the two parameters of the development grey scale and endogenous control grey number of the initial grey prediction model until the grey prediction model meets the preset accuracy requirements. The specific parameter updating steps are as follows:

[0094] Step S23, repeatedly executing the parameter updating operation of the grey prediction model until the grey prediction model meets the preset accuracy requirement, and obtaining the final grey prediction model; the parameter updating operation includes: inputting the first data item in the original sequence into the current grey prediction model, so that the current grey prediction model generates the first prediction data; removing the first data item of the original cumulative sequence, and adding the first prediction data to the end of the original cumulative sequence, to obtain the updated cumulative sequence; updating the parameters of the grey prediction model according to the updated cumulative sequence and the original sequence;

[0095] In the present invention, the first data in the original sequence is input into the initial grey prediction model to obtain the first prediction data, which is recorded as the first prediction data. The first prediction data is added to the end of the original cumulative sequence, and the first data item of the original cumulative sequence is removed to generate an updated cumulative sequence. Based on the original sequence and the updated cumulative sequence, according to the specific construction process of the grey prediction model, the two parameters of the development grayscale and the endogenous control gray number of the grey prediction model are updated to obtain new parameter values, thereby obtaining the corresponding updated grey prediction model. The first parameter update is completed through the above steps, and then the updated cumulative sequence is used as the current original cumulative sequence, and the updated grey prediction model is used as the current initial grey prediction model. The above parameter updating operation is repeatedly performed until the grey prediction model meets the preset accuracy requirements, and the final values ​​of the two parameters of the development grayscale and the endogenous control gray number and the final grey prediction model are obtained.

[0096] Among them, the following methods are used to determine whether the grey prediction model meets the preset accuracy requirements:

[0097] According to the posterior difference ratio calculation formula, calculate the posterior difference ratio corresponding to the grey prediction model;

[0098] Determining whether the posterior difference ratio is less than a preset posterior difference ratio;

[0099] If yes, it is determined that the grey prediction model meets the preset accuracy requirement, otherwise it is determined that the grey prediction model does not meet the preset accuracy requirement;

[0100] Among them, the calculation formula of the posterior difference ratio is:

[0101]

[0102] C = S2 / S1;

[0103] In the formula, e(i) is the residual of the i-th data, is the predicted i-th data, is the variance of the original sequence, is the variance of the corresponding residual sequence calculated from the original sequence, n is the total number of data in the original sequence, is the average value of all data in the original sequence, is the average value of all data of the corresponding residual sequence calculated from the original sequence, and C is the posterior difference ratio;

[0104] Specifically, the smaller the posterior difference ratio is, the higher the accuracy of the grey prediction model is, indicating that although the original data is very discrete, the difference between the calculated value obtained by the model and the actual value is not too discrete.

[0105] Step S24, constructing a cumulative distribution function according to the running time of each cable sample, performing formula transformation on the cumulative distribution function, and obtaining a life prediction model having the same expression form as the final grey prediction model;

[0106] In the present invention, according to the running time of each cable sample, a cumulative distribution function (Weibull) including threshold parameters, scale parameters and shape parameters is constructed, and the calculation formula of the cumulative distribution function is transformed into a life prediction model with the same expression form as the final grey prediction model, providing a model basis for determining the parameters of the life prediction model in subsequent steps;

[0107] The specific construction process of the life prediction model is described by the following examples:

[0108] In a preferred embodiment, the cumulative distribution function comprises:

[0109]

[0110] Where x is the operation time of the cable, γ is the threshold parameter, β is the scale parameter, δ is the shape parameter, and F(x) is the probability of cable failure.

[0111] In another preferred embodiment, the life prediction model comprises:

[0112]

[0113] In the formula, For the service life of the cable,

[0114] Specifically, the transformation process of the life prediction model includes:

[0115] Construct the cumulative distribution function:

[0116] Let R(x)=1-F(x),

[0117] After transformation, the life prediction model is obtained:

[0118] After obtaining the specific life prediction model, the values ​​of the three parameters, namely, the threshold parameter, the scale parameter and the shape parameter, are determined by the following steps:

[0119] Step S25, determining the threshold parameters, scale parameters and shape parameters of the life prediction model according to the parameters of the final grey prediction model, and generating the final life prediction model.

[0120] In the present invention, the life prediction model and the final grey prediction model have the same expression form, so that the values ​​of the threshold parameter, the scale parameter and the shape parameter can be calculated accordingly, thereby obtaining the final life prediction model, and the operation time of the cable to be predicted is input into the final life prediction model, and the life prediction value of the cable to be predicted is obtained by calculation;

[0121] Among them, the threshold parameter represents the minimum operating time before the cable starts to consider its life or failure probability;

[0122] The scale parameter is a parameter that affects the scale or range of the distribution. It determines the width or extent of the distribution curve. A larger scale parameter value means that the cable life is relatively dispersed, while a smaller scale parameter value means that the cable life is relatively concentrated.

[0123] The shape parameter determines the shape of the distribution curve. When the shape parameter is less than 1, the distribution curve is decreasing. When the shape parameter is equal to 1, the distribution becomes an exponential distribution. When the shape parameter is greater than 1, the distribution curve is increasing.

[0124] In a preferred embodiment, after determining the threshold parameter, scale parameter and shape parameter of the life prediction model according to the parameters of the final grey prediction model and generating the final life prediction model, the method further includes:

[0125] According to the calculation formula of residual test, the absolute error and relative error of the life prediction model are calculated;

[0126] Determine whether the absolute error and the relative error are less than a preset error value;

[0127] If yes, it is determined that the life prediction model meets the preset accuracy requirement, otherwise it is determined that the life prediction model does not meet the preset accuracy requirement;

[0128] Among them, the calculation formulas for absolute error and relative error are:

[0129]

[0130] In the formula, Δ is the absolute error and Φ is the relative error;

[0131] According to the calculation formula of the correlation test, the correlation value of the life prediction model is calculated;

[0132] Determining whether the correlation value is greater than a preset correlation value;

[0133] If yes, it is determined that the life prediction model has passed the correlation test, otherwise it is determined that the life prediction model has not passed the correlation test;

[0134] The calculation formula of the correlation test is:

[0135]

[0136] Where r is the correlation value, min{(Δi)} is the minimum absolute error, max{(Δi)} is the maximum absolute error, ρ is the resolution, and Δi is the absolute error of the i-th data in the original sequence;

[0137] Specifically, the core of the residual test is to measure the deviation between the original failure data series and the model prediction value, which is achieved by calculating the absolute error and relative error. The smaller these error values ​​are, the closer the model's prediction results are to the actual data, thus proving that the model's prediction accuracy is higher. The correlation test aims to quantify the degree of correlation between the original failure data series and the predicted value. If the calculated correlation value is higher than the preset threshold, it means that the model has passed the correlation test.

[0138] Based on the above method embodiment, the present invention provides a corresponding device embodiment;

[0139] like Figure 2 FIG. 1 is a schematic diagram of a device for predicting cable life based on Weibull distribution according to an embodiment of the present invention, comprising:

[0140] A cable operation data acquisition module, a cable life calculation module, and a life prediction model construction module, wherein the life prediction model construction module includes: an original data processing unit, a grey prediction model construction unit, a grey prediction model parameter updating unit, a life prediction model construction unit, and a life prediction model parameter determination unit;

[0141] The cable operation data acquisition module is used to obtain the operation time of the cable to be predicted;

[0142] The cable life calculation module is used to substitute the operation time of the cable to be predicted into a preset life prediction model, so that the life prediction model determines the life of the cable to be predicted according to the operation time of the cable to be predicted;

[0143] The raw data processing unit is used to obtain the life data of several cable samples, and to sort the life data by time to obtain an initial raw sequence, and to perform accumulation processing on the raw sequence to generate an initial accumulated sequence;

[0144] The grey prediction model construction unit is used to construct an initial grey prediction model according to the initial original sequence and the initial accumulated sequence;

[0145] The grey prediction model parameter updating unit is used to repeatedly perform the parameter updating operation of the grey prediction model until the grey prediction model meets the preset accuracy requirement, thereby obtaining a final grey prediction model; the parameter updating operation includes: inputting the first data item in the original sequence into the current grey prediction model, so that the current grey prediction model generates the first prediction data; removing the first data item of the current cumulative sequence, and adding the first prediction data to the end of the current cumulative sequence, thereby obtaining an updated cumulative sequence; and updating the parameters of the grey prediction model according to the updated cumulative sequence and the original sequence;

[0146] The life prediction model construction unit is used to construct a cumulative distribution function according to the operating time of each cable sample, and perform formula transformation on the cumulative distribution function to obtain a life prediction model with an expression in the same form as the grey prediction model;

[0147] The life prediction model parameter determination unit is used to determine the threshold parameters, scale parameters and shape parameters of the life prediction model according to the parameters of the grey prediction model to generate a final life prediction model.

[0148] It can be understood that the above-mentioned device item embodiment corresponds to the method item embodiment of the present invention, which can implement a cable life prediction method based on Weibull distribution provided by any of the above-mentioned method item embodiments of the present invention.

[0149] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0150] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0151] Another preferred embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a method for predicting cable life based on Weibull distribution as described in any one of the above embodiments.

[0152] It should be noted that the terminal device mentioned here can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that, for example, it may also include input and output devices, network access devices, buses, etc.

[0153] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0154] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0155] Another preferred embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a method for predicting cable life based on Weibull distribution as described in any one of the present invention.

[0156] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0157] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for predicting cable life based on Weibull distribution, characterized in that: include: Obtaining the running time of the cable to be predicted; Substituting the operating time of the cable to be predicted into a preset life prediction model, so that the life prediction model determines the life of the cable to be predicted according to the operating time of the cable to be predicted; Wherein, the life prediction model is determined by the following method: Obtain life data of several cable samples, sort each life data by time length to obtain an original sequence, and perform accumulation processing on the original sequence to generate an initial accumulated sequence; Construct the initial grey prediction model according to the original sequence and the initial cumulative series; Repeat the parameter updating operation of the grey prediction model until the grey prediction model meets the preset accuracy requirement, and obtain the final grey prediction model; the parameter updating operation includes: inputting the first data item in the original sequence into the current grey prediction model, so that the current grey prediction model generates the first prediction data; removing the first data item of the original cumulative sequence, and adding the first prediction data to the end of the original cumulative sequence, to obtain the updated cumulative sequence; updating the parameters of the grey prediction model according to the updated cumulative sequence and the original sequence; According to the running time of each cable sample, a cumulative distribution function is constructed, and the cumulative distribution function is transformed into a formula to obtain a life prediction model having an expression in the same form as the final grey prediction model; The threshold parameters, scale parameters and shape parameters of the life prediction model are determined according to the parameters of the final grey prediction model to generate the final life prediction model.

2. The method for predicting cable life based on Weibull distribution according to claim 1, characterized in that: The method of obtaining life data of a number of cable samples, and sorting each life data by time length to obtain an original sequence, and performing accumulation processing on the original sequence to generate an initial accumulated sequence includes: Arrange the cable life data in ascending order according to the duration to generate the original sequence; The original sequence is accumulated using the following calculation formula to generate the initial cumulative sequence: Where, X (1) (j) is the jth data of the initial cumulative sequence, X (0) (i) is the i-th data in the original sequence, and j is the total number of accumulated data in the original sequence.

3. A method for predicting cable life based on Weibull distribution as claimed in claim 2, characterized in that: The grey prediction model comprises: Where, X (1) (j+1) is the j+1th data of the initial cumulative sequence, X (0) (1) is the first data of the original sequence, a is the development grayscale, and u is the endogenous control gray number.

4. A method for predicting cable life based on Weibull distribution as claimed in claim 3, characterized in that: The following methods are used to determine whether the grey prediction model meets the preset accuracy requirements: According to the posterior difference ratio calculation formula, calculate the posterior difference ratio corresponding to the grey prediction model; Determining whether the posterior difference ratio is less than a preset posterior difference ratio; If yes, it is determined that the grey prediction model meets the preset accuracy requirement, otherwise it is determined that the grey prediction model does not meet the preset accuracy requirement; Among them, the calculation formula of the posterior difference ratio is: C=S2 / S1 In the formula, e(i) is the residual of the i-th data, is the predicted i-th data, is the variance of the original sequence, is the variance of the corresponding residual sequence calculated from the original sequence, n is the total number of data in the original sequence, is the average value of all data in the original sequence, is the average value of all data of the corresponding residual sequence calculated from the original sequence, and C is the posterior difference ratio.

5. The method for predicting cable life based on Weibul distribution according to claim 1, characterized in that: The cumulative distribution function comprises: Where x is the operation time of the cable, γ is the threshold parameter, β is the scale parameter, δ is the shape parameter, and F(x) is the probability of cable failure.

6. A method for predicting cable life based on Weibull distribution as claimed in claim 5, characterized in that: The life prediction model comprises: In the formula, For the service life of the cable, 7. The method for predicting cable life based on Weibul distribution according to claim 4, characterized in that: After determining the threshold parameters, scale parameters and shape parameters of the life prediction model according to the parameters of the final grey prediction model and generating the final life prediction model, it also includes: According to the calculation formula of residual test, the absolute error and relative error of the life prediction model are calculated; Determine whether the absolute error and the relative error are less than a preset error value; If yes, it is determined that the life prediction model meets the preset accuracy requirement, otherwise it is determined that the life prediction model does not meet the preset accuracy requirement; Among them, the calculation formulas for absolute error and relative error are: In the formula, Δ is the absolute error and Φ is the relative error; According to the calculation formula of the correlation test, the correlation value of the life prediction model is calculated; Determining whether the correlation value is greater than a preset correlation value; If yes, it is determined that the life prediction model has passed the correlation test, otherwise it is determined that the life prediction model has not passed the correlation test; The calculation formula of the correlation test is: Where r is the correlation value, min{(Δi)} is the minimum absolute error, max{(Δi)} is the maximum absolute error, ρ is the resolution, and Δi is the absolute error of the i-th data in the original sequence.

8. A device for predicting cable life based on Weibull distribution, characterized in that: include: A cable operation data acquisition module, a cable life calculation module, and a life prediction model construction module, wherein the life prediction model construction module includes: an original data processing unit, a grey prediction model construction unit, a grey prediction model parameter updating unit, a life prediction model construction unit, and a life prediction model parameter determination unit; The cable operation data acquisition module is used to obtain the operation time of the cable to be predicted; The cable life calculation module is used to substitute the operation time of the cable to be predicted into a preset life prediction model, so that the life prediction model determines the life of the cable to be predicted according to the operation time of the cable to be predicted; The raw data processing unit is used to obtain the life data of several cable samples, and to sort the life data by time to obtain an initial raw sequence, and to perform accumulation processing on the raw sequence to generate an initial accumulated sequence; The grey prediction model construction unit is used to construct an initial grey prediction model according to the initial original sequence and the initial accumulated sequence; The grey prediction model parameter updating unit is used to repeatedly perform the grey prediction model parameter updating operation until the grey prediction model meets the preset accuracy requirement, thereby obtaining a final grey prediction model; the parameter updating operation includes: inputting the first data item in the original sequence into the current grey prediction model, so that the current grey prediction model generates the first prediction data; removing the first data item of the current cumulative sequence, and adding the first prediction data to the end of the current cumulative sequence, thereby obtaining an updated cumulative sequence; and updating the grey prediction model parameters according to the updated cumulative sequence and the original sequence. The life prediction model construction unit is used to construct a cumulative distribution function according to the operating time of each cable sample, and perform formula transformation on the cumulative distribution function to obtain a life prediction model with an expression in the same form as the grey prediction model; The life prediction model parameter determination unit is used to determine the threshold parameters, scale parameters and shape parameters of the life prediction model according to the parameters of the grey prediction model to generate a final life prediction model.

9. A terminal device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for predicting cable life based on Weibul l distribution as claimed in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a method for predicting cable life based on Weibul l distribution as described in any one of claims 1 to 7.

Images