CN118153757A

CN118153757A - Method and device for predicting service life of electric element, electronic equipment and storage medium

Info

Publication number: CN118153757A
Application number: CN202410309286.5A
Authority: CN
Inventors: 房元; 张长涛; 李威; 曲振宁; 慈伟程; 顾家闻; 王伯军; 张研
Original assignee: FAW Group Corp
Current assignee: FAW Group Corp
Priority date: 2024-03-18
Filing date: 2024-03-18
Publication date: 2024-06-07

Abstract

The invention discloses a life prediction method and device of an electrical element, electronic equipment and a storage medium. Wherein the method comprises the following steps: acquiring a plurality of characteristic data sets of the electric element in response to receiving a life prediction instruction of the electric element, wherein the plurality of characteristic data sets are used for representing a plurality of characteristic values of the electric element and a plurality of data sets formed by acquisition time points of the plurality of characteristic values; updating initial parameters in the process degradation model based on a plurality of characteristic data sets to obtain an adjusted process degradation model, wherein the process degradation model is used for describing a process of which characteristic values change along with time, and the initial parameters are used for representing parameters to be updated in the process degradation model; and predicting the characteristic data sets by using the adjusted process degradation model to obtain the residual service life of the electric element. The invention solves the technical problem of lower efficiency of life prediction of the electrical element in the related technology.

Description

Method and device for predicting service life of electric element, electronic equipment and storage medium

Technical Field

The present invention relates to the field of electrical component monitoring, and in particular, to a lifetime prediction method and apparatus for an electrical component, an electronic device, and a storage medium.

Background

The life prediction is carried out on the electric element, namely, the expected time for the electric element to continue to work normally after the electric element is used for a period of time is predicted, so that a user can be helped to plan equipment maintenance and replacement plans better, and the reliability and safety of the equipment are improved.

At present, in the related art, a laboratory accelerated life test or a general life prediction model is often adopted to predict the life of an electrical element, so that the time consumption of the prediction process for predicting the life of the electrical element is long or the accuracy of the obtained prediction result is low, namely the efficiency of predicting the life of the electrical element is low.

In view of the above problems, no effective solution has been proposed at present.

Disclosure of Invention

The embodiment of the invention provides a life prediction method and device for an electric element, electronic equipment and a storage medium, which are used for at least solving the technical problem of low efficiency of life prediction for the electric element in the related technology.

According to an aspect of an embodiment of the present invention, there is provided a lifetime prediction method of an electrical element, including: acquiring a plurality of characteristic data sets of the electric element in response to receiving a life prediction instruction of the electric element, wherein the plurality of characteristic data sets are used for representing a plurality of characteristic values of the electric element and a plurality of data sets formed by acquisition time points of the plurality of characteristic values; updating initial parameters in the process degradation model based on a plurality of characteristic data sets to obtain an adjusted process degradation model, wherein the process degradation model is used for describing a process of which characteristic values change along with time, and the initial parameters are used for representing parameters to be updated in the process degradation model; and predicting the characteristic data sets by using the adjusted process degradation model to obtain the residual service life of the electric element.

Optionally, acquiring an initial characteristic value of the electrical element in an initial state, wherein the initial state is used for representing an initial state that the characteristic value of the electrical element is unchanged; a process degradation model is constructed based on the process model and the initial feature values, wherein the process model is used for describing a process that the feature values are changed by environmental factors.

Optionally, acquiring a plurality of characteristic data sets of the electrical component includes: acquiring a first circuit parameter of the electric element at a first detection point and acquiring a second circuit parameter of the electric element at a second detection point, wherein the first detection point and the second detection point are respectively positioned at two sides of the electric element corresponding to the detection point to be detected, and the detection point to be detected is used for representing a position required to detect for life prediction of the electric element; determining a characteristic value of the to-be-detected point based on the first circuit parameter and the second circuit parameter; collecting characteristic values of a to-be-detected point based on a preset frequency to obtain a plurality of characteristic values; the plurality of feature data sets are composed based on the plurality of feature values and the acquisition time points of the plurality of feature values.

Optionally, determining the characteristic value of the point to be detected based on the first circuit parameter and the second circuit parameter includes: acquiring a first voltage value and a first current value in a first circuit parameter, and acquiring a second voltage value and a second current value in a second circuit parameter; determining a contact resistance value of the to-be-detected point based on the first voltage value, the first current value, the second voltage value and the second current value; and determining the characteristic value of the to-be-detected point based on the contact resistance value.

Optionally, predicting the plurality of feature data sets using the adjusted process degradation model to obtain a remaining service life of the electrical component, including: acquiring a time point to be tested of the residual service life of the electrical element; determining a target characteristic data set from a plurality of characteristic data sets based on the time point to be detected, wherein the target characteristic data set is used for representing a data set consisting of the time point to be detected and characteristic values corresponding to the time point to be detected in the plurality of characteristic data sets; obtaining residual life probability distribution of the electrical element based on the adjusted process degradation model and a preset failure threshold, wherein the residual life probability distribution is used for representing probability distribution of faults of the electrical element along with time change; substituting the target characteristic data set into the residual life probability distribution for processing to obtain the residual life of the electrical element at the time point to be detected.

Optionally, updating the initial parameters in the process degradation model based on the plurality of feature data sets to obtain an adjusted process degradation model, including: processing the plurality of characteristic data sets by using a process degradation model to obtain a plurality of parameters; screening the plurality of parameters based on a preset variance threshold to obtain a plurality of first preselected parameters, wherein variances of the plurality of first preselected parameters are within a preset range, and the preset range is determined based on the preset variance threshold; adjusting the plurality of first preselected parameters based on the plurality of characteristic data sets and the process degradation model to obtain target parameters; and replacing the initial parameters in the process degradation model by the target parameters to obtain an adjusted process degradation model.

Optionally, screening the plurality of parameters based on a preset variance threshold to obtain a plurality of first preselected parameters, including: acquiring target variances of a plurality of parameters; comparing the preset variance threshold with the target variance to obtain a comparison result, wherein the comparison result is used for indicating whether the target variance is within a preset range; and screening the plurality of parameters based on the comparison result to obtain a plurality of first preselected parameters.

Optionally, adjusting the plurality of first preselected parameters based on the plurality of characteristic data sets and the process degradation model to obtain the target parameters includes: determining an average of the first plurality of preselected parameters; replacing initial parameters in the process degradation model with average values to obtain a preselected process degradation model; and adjusting the average value based on a first characteristic data set in the characteristic data sets and a preselected process degradation model to obtain a target parameter.

Optionally, adjusting the average value based on a first characteristic data set of the plurality of characteristic data sets and the preselected process degradation model to obtain the target parameter includes: substituting the first characteristic data set into a preselected process degradation model for processing to obtain a reference characteristic data set; determining a similarity between the first feature data set and the reference feature data set; and adjusting the average value based on the similarity to obtain the target parameter.

According to another aspect of the embodiment of the present invention, there is also provided a lifetime prediction device of an electrical element, including: an acquisition module for acquiring a plurality of characteristic data sets of the electric element in response to receiving a life prediction instruction of the electric element, wherein the plurality of characteristic data sets are used for representing a plurality of characteristic values of the electric element and a plurality of data sets formed by acquisition time points of the plurality of characteristic values; the updating module is used for updating initial parameters in the process degradation model based on the plurality of characteristic data sets to obtain an adjusted process degradation model, wherein the process degradation model is used for describing the process of the change of the characteristic value along with time, and the initial parameters are used for representing parameters to be updated in the process degradation model; and the prediction module is used for predicting the plurality of characteristic data sets by utilizing the adjusted process degradation model to obtain the residual service life of the electric element.

According to another aspect of the embodiment of the present invention, there is also provided an electronic device, including: a memory storing an executable program; and a processor for running a program, wherein the program when run performs the methods of the various embodiments of the present invention.

According to another aspect of the embodiments of the present invention, there is also provided a computer readable storage medium including a stored executable program, where the executable program when run controls a device in which the computer readable storage medium is located to perform the method in the embodiments of the present invention.

According to another aspect of embodiments of the present invention, there is also provided a computer program product comprising a computer program which, when executed by a processor, implements the methods of the various embodiments of the invention.

According to another aspect of embodiments of the present invention, there is also provided a computer program product comprising a non-volatile computer readable storage medium storing a computer program which, when executed by a processor, implements the method in various embodiments of the invention.

According to another aspect of embodiments of the present invention, there is also provided a computer program which, when executed by a processor, implements the methods of the various embodiments of the invention.

In an embodiment of the present application, there is provided a life prediction method of an electrical component, including: acquiring a plurality of characteristic data sets of the electric element in response to receiving a life prediction instruction of the electric element, wherein the plurality of characteristic data sets are used for representing a plurality of characteristic values of the electric element and a plurality of data sets formed by acquisition time points of the plurality of characteristic values; updating initial parameters in the process degradation model based on a plurality of characteristic data sets to obtain an adjusted process degradation model, wherein the process degradation model is used for describing a process of which characteristic values change along with time, and the initial parameters are used for representing parameters to be updated in the process degradation model; the method and the device have the advantages that the adjusted process degradation model is utilized to predict the plurality of characteristic data sets to obtain the residual service life of the electric element, and easily notice that the process degradation model is updated and optimized through the plurality of characteristic data sets representing the characteristic value change relation of the electric element, so that the change process of the characteristic value of the electric element along with time can be reflected by the adjusted process degradation model more accurately, the accuracy of predicting the residual service life of the electric element can be improved, and meanwhile, compared with the prior art, a laboratory accelerated life test is not needed, the time consumption of the prediction process for predicting the service life of the electric element is saved, and the technical problem that the efficiency of predicting the service life of the electric element in the prior art is lower is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

Fig. 1 is a flowchart of a life prediction method of an electrical component according to an embodiment of the present invention;

FIG. 2 is a flow chart of an alternative method of updating initial parameters in a process degradation model in accordance with an embodiment of the present invention;

fig. 3 is a schematic view of a life predicting apparatus for an electric element according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

According to another aspect of embodiments of the present invention there is also provided a method of life prediction of an electrical component, it being noted that the steps shown in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and although a logical sequence is shown in the flowcharts, in some cases the steps shown or described may be performed in a different order than here.

Fig. 1 is a flowchart of a life prediction method of an electrical component according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:

Step S102, a plurality of characteristic data sets of the electric element are acquired in response to receiving a life prediction instruction of the electric element.

The plurality of characteristic data sets are used for representing a plurality of characteristic values of the electric element and a plurality of data sets formed by acquisition time points of the plurality of characteristic values.

The electrical components described above may refer to various components and devices used in electrical systems, and elements used for transmitting, converting, controlling and protecting electrical energy, and the electrical components may include, but are not limited to, resistors, capacitors, inductors, switches, harnesses, sockets, circuit breakers, relays, transformers, motors, etc., and the electrical components play an important role in the electrical systems, so that the transmission and control of electrical energy can be achieved, and safe and stable operation of the electrical systems can be ensured.

The above-mentioned lifetime prediction instruction may refer to an instruction or command for predicting the remaining lifetime of an electrical component, which is used to start a lifetime prediction process for the electrical component.

The above-mentioned characteristic data set may refer to a data set formed by a characteristic value of an electrical element and an acquisition time corresponding to the characteristic value, where the characteristic value of the electrical element may refer to some important performance parameters or characteristic characteristics of the electrical element under a specific working condition, and the characteristic value of the electrical element may include, but is not limited to, a resistance value, a current, a voltage, a power, a frequency, an impedance, a capacity, an inductance, and the like of the electrical element, where the characteristic value of the electrical element may be determined according to an actual requirement for life prediction of the electrical element, and is not limited herein.

In an alternative embodiment, the electrical component may be tested and measured by using a testing instrument, such as an oscilloscope, a multimeter, a network analyzer, etc., to obtain a characteristic value of the electrical component, for example, a characteristic of the component may be obtained by measuring parameters such as resistance, capacitance, inductance, etc.; the circuit simulation software can be used to simulate the electric elements in the circuit, the characteristics of the electric elements can be known by adjusting the parameters of the electric elements and observing the simulation results, so as to obtain the characteristic values of the electric elements, and the method for obtaining the characteristic values of the electric elements can be determined according to actual conditions and is not limited herein.

In another alternative embodiment, a plurality of characteristic data sets may be obtained based on a large data embedding point manner, specifically, a data embedding point scheme may be designed according to a characteristic value of an electrical element, and a data type, an acquisition frequency, a storage format and the like to be collected may be determined; according to the designed data embedding scheme, data acquisition equipment such as a sensor, a data acquisition device and the like is deployed for acquiring characteristic value data of the electrical element in real time; the acquired data is transmitted to the data storage equipment through a network, cloud storage or local storage can be selected, and the safety and reliability of the data are ensured; and processing and analyzing the collected large amount of electrical element characteristic value data, and performing characteristic extraction, data cleaning, pattern recognition and other operations by utilizing a data analysis tool and algorithm to obtain the characteristic value of the electrical element.

The characteristic value of the electrical element can change along with the use and loss of the electrical element, the change of the characteristic value of the electrical element can reflect the use and loss degree of the electrical element, the characteristic value of the electrical element is monitored and analyzed, the prediction of the residual service life of the electrical element can be realized, the acquisition quantity of the characteristic data sets can be determined according to actual needs, thousands of characteristic data sets can be acquired, millions of characteristic data sets can be acquired, the acquisition quantity of the characteristic data sets can be determined according to actual needs, and the method is not limited.

Step S104, updating initial parameters in the process degradation model based on the plurality of characteristic data sets to obtain an adjusted process degradation model.

The process degradation model is used for describing the process of the change of the characteristic value along with time, and the initial parameters are used for representing parameters to be updated in the process degradation model.

The process degradation model may refer to a model describing gradual degradation and damage of an electrical element during use, and may be used to predict the remaining service life and performance degradation of the electrical element so as to make an appropriate maintenance and replacement plan, and by modeling and analyzing the process degradation of the electrical element, the reliability and safety of the device may be improved.

The initial parameters may refer to parameters or coefficients that need to be adjusted or updated in the constructed process degradation model, and the initial parameters may include, but are not limited to, diffusion coefficients, drift coefficients, etc. in the process degradation model, and the initial parameters may be one parameter or coefficient, or may be multiple parameters or coefficients, where the initial parameters may be determined according to actual needs, and are not limited herein.

In an alternative embodiment, the process degradation model may be a Wiener process degradation model, where the Wiener process degradation model may be a model describing gradual degradation and aging of an electrical element during use, the Wiener process degradation model may be used to predict performance changes and service lives of the electrical element after a certain period of use, to help design and maintenance personnel perform reasonable prevention and maintenance, and the Wiener process degradation model may be combined with the use environment and working state of the electrical element and the characteristics of the element itself to model and analyze the degradation process of the electrical element, and the process degradation model may be determined according to practical situations, which is not limited herein.

When the process degradation model adopts a wiener process degradation model, initial parameters can be determined to be a diffusion coefficient and a drift coefficient, in the wiener process, the diffusion coefficient and the drift coefficient can be used for describing parameters of a characteristic value change process of an electric element in the use process of the electric element, wherein the diffusion coefficient can be parameters for describing the randomness degree of the characteristic value change of the electric element along with time, the diffusion coefficient reflects the average fluctuation degree of the characteristic value of the electric element in unit time, namely the change speed of a random variable, and the larger the diffusion coefficient is, the larger the fluctuation of the random variable is, and the change speed is faster; the drift coefficient may be a parameter describing a trend property of the characteristic value of the electrical element over time, the drift coefficient reflecting an average increasing or decreasing trend of the characteristic value of the electrical element in a unit time, i.e., an overall change direction of the characteristic value of the electrical element, the drift coefficient being positive indicating that the overall trend of the random variable increases upward, being negative indicating that the overall trend decreases downward, and being zero indicating that the overall trend has no significant directionality.

The process degradation model can be used for representing the time-dependent change process of the characteristic values of various electrical elements, and the initial parameters in the process degradation model can be adjusted or optimized based on a plurality of characteristic data sets of the electrical elements, so that the adjusted process degradation model can more accurately reflect the time-dependent change process of the characteristic values of the electrical elements, and the accuracy of the subsequent residual life prediction of the electrical elements is improved.

And S106, predicting the characteristic data sets by using the adjusted process degradation model to obtain the residual service life of the electric element.

The remaining service life may refer to an expected time for the electrical element to continue to normally operate after the electrical element has been used for a period of time, and the remaining service life may refer to a remaining service life of the electrical element at a current time, or may be a remaining service life of the electrical element predicted at a specific time, which is not limited herein.

In an alternative embodiment, since the characteristic value of the electrical element changes with use and loss of the electrical element, the change of the characteristic value of the electrical element may reflect the use and loss degree of the electrical element, the characteristic value of the electrical element may be monitored and analyzed based on the adjusted process degradation model, prediction of the remaining service life of the electrical element may be achieved, and the characteristic value of the electrical element may be continuously monitored over time, and the adjusted process degradation model may be continuously calibrated and adjusted to improve accuracy of the prediction.

The prediction of the remaining service life of the electrical element can help a user to better manage the maintenance of the equipment, through the prediction of the remaining service life of the electrical element, the user can discover potential faults and problems in advance, so that measures are timely taken to repair or replace the equipment, equipment shutdown and production delay caused by the faults of the electrical element are avoided, the prediction of the remaining service life can also help the user to optimize the maintenance plan of the equipment, unnecessary maintenance cost and shutdown time are reduced, and the reliability and stability of the equipment are improved.

The initial characteristic value may be an initial or original state in which the characteristic value of the electrical component is not changed, and may be a state in which the electrical component is not started to be used or no loss is generated.

The process model may refer to a process of describing that the characteristic value of the electrical element is changed by environmental factors, the characteristic value of the electrical element may be changed along with use of the electrical element, and reasons for the change may include factors such as normal wear of the electrical element, aging of materials, random interference of external environment, etc., and the factor that the electrical element is randomly interfered by the external environment may be represented by using the process model, which may be determined according to needs, and is not limited herein.

In an alternative embodiment, the process model may employ a wiener process, which may refer to a random process, also referred to as brownian motion, in which the value of a random variable randomly fluctuates according to time changes, and the process model may be employed to describe random phenomena and behavior of a random system, i.e., a process in which the wiener process is employed to represent a process in which the characteristic value of an electrical element is changed by an environmental factor, thereby implementing a representation and generalization of the process in which the characteristic value of the electrical element is changed by an environmental factor, and facilitating construction of a process degradation model of the electrical element.

Further, the characteristic value of the electrical element may change along with the use of the electrical element, the changing factors include random interference from external environment, and the like, so that the characteristic value of the electrical element does not strictly increase or decrease, and random fluctuation may occur in a certain range, the process model may use wiener process to represent the process that the characteristic value of the electrical element is changed by the environmental factor, and the following process degradation model may be established based on the process model and the initial characteristic value of the electrical element:

X(t)＝μt+X₀+σW(t)；

wherein X (t) may be used to represent the degradation or variation of the characteristic value of the electrical element, i.e. the variation of the characteristic value of the electrical element from the initial characteristic value, X ₀ may be used to represent the initial characteristic value of the electrical element, W (t) may be used to represent the wiener process, σ is used to represent the diffusion coefficient, μ is used to represent the drift coefficient, t is used to represent the time variable, where the degradation or variation of the characteristic value of the electrical element X (t) may obey a normal distribution:

ΔX～N(μ，Δtσ^2Δt)；

other methods may be used to construct the process degradation model based on the process model and the initial eigenvalues, and are not limited in this regard.

The number of the detection points to be detected may be one or more, and the types of the detection points to be detected may be determined according to the requirements of life prediction, the types of the electric elements, the types of the characteristic values of the electric elements, and the like, which are not limited herein.

The first circuit parameter and the second circuit parameter may refer to circuit parameter values for determining characteristic values of the electrical element, and the first circuit parameter and the second circuit parameter may be determined according to actual needs, which are not limited herein.

The preset frequency may be a preset collection frequency of the characteristic value of the electrical element, and the preset frequency may be a fixed value or a variable, where the preset frequency may be determined according to the actual requirement, and is not limited herein.

In an alternative embodiment, the to-be-detected points can be determined according to the structural characteristics, the working environment and the types of characteristic values of the electric elements, the residual service life of the electric elements, namely, the time that all parts of the electric elements can work normally can be predicted, at this time, the to-be-detected points can select positions on the electric elements which are easy to damage or wear, and the selected number and positions of the to-be-detected points can be determined according to actual needs, and are not limited herein; the application can form a plurality of characteristic data sets by the characteristic values of a plurality of different detection points and the acquisition time points of the characteristic values, and also can form a plurality of characteristic data sets by a plurality of characteristic values of the same detection point and the acquisition time points of the characteristic values, wherein the determination method of the characteristic data sets can be determined according to actual needs, and is not limited in this way.

Because the position with serious damage or abrasion degree on the electric element is often selected by taking the to-be-detected point into consideration, and if the detection equipment is adopted to directly detect the characteristic value of the to-be-detected point, the to-be-detected point is required to be connected with the detection equipment, the damage or abrasion degree of the to-be-detected point can be increased, and the residual service life of the electric element is further influenced.

In an alternative embodiment, the resistance value of the electrical element at the first detection point may be determined based on the first voltage value and the first current value of the first detection point, the resistance value of the electrical element at the second detection point may be determined based on the second voltage value and the second current value of the second detection point, the resistance value of the electrical element at the point to be detected, that is, the contact resistance value, may be determined based on the resistance value of the first detection point and the resistance value of the second detection point, and finally the contact resistance value may be determined as the characteristic value of the point to be detected.

In another alternative embodiment, the voltage value of the electrical element at the point to be detected may be determined based on the first voltage value of the first detection point and the second voltage value of the second detection point, the current value of the electrical element at the point to be detected may be determined based on the first current value of the first detection point and the second current value of the second detection point, finally, the contact resistance value may be determined based on the voltage value and the current value of the electrical element at the point to be detected, and the contact resistance value may be determined as the characteristic value of the point to be detected, where the characteristic value of the electrical element at the point to be detected may be obtained in other manners, which is not limited herein.

The above-mentioned time point to be measured may be determined according to the requirement for life prediction of the electrical component, which is not limited herein.

The preset failure threshold is used for indicating the threshold condition that the characteristic value reaches or meets when the electrical element fails, and the preset failure threshold can be inquired according to a factory manual of the electrical element and the like, and is not limited herein.

The above-mentioned remaining life probability distribution may refer to a probability distribution that the electrical element continues to operate for a certain period of time after the electrical element has operated for a certain period of time, and the remaining life probability distribution may include an exponential distribution, a normal distribution, etc., which are not limited herein, and the remaining life probability distribution may be used to predict the life of the electrical element, help to make a maintenance plan, and improve the reliability and safety of the device.

The target feature data set may be selected directly from the plurality of feature data sets based on the time point to be measured, or the corresponding feature value may be obtained based on the time point to be measured, the target feature data set may be reconstructed, and the target feature data set may be added to the plurality of feature data sets, and the method for obtaining the target feature data set is not limited herein.

In an alternative embodiment, when the expression of the process degradation model is X (t) =μt+x ₀ +σw (t), whether the electrical element fails or breaks down at the acquired time point t corresponding to the characteristic value can be determined through the comparison relation between the characteristic value of the electrical element and the preset failure threshold D, and the predicted time point when the electrical element fails or breaks down for the first time, that is, the remaining life deadline of the electrical element, namely, the time point when the characteristic value of the electrical element reaches the preset failure threshold for the first time can be taken as the remaining life deadline of the electrical element, so that the prediction of the remaining service life of the electrical element is realized.

Further, the distribution of the first time the characteristic value of the electrical element reaches the preset failure threshold time point may be an unreliable degree function of the electrical element, the unreliable degree function of the electrical element accords with the inverse gaussian distribution, and the expression of the probability density function f (t) of the unreliable degree function of the electrical element may be obtained as follows:

Thus, an expression of the electrical component uncertainty function R (t) can be obtained:

Wherein F (t) may be used to represent a primitive function of a probability density function F (t) of the unreliability function of the electrical element, Φ (t) may be used to represent a value corresponding to the parameter t under a standard normal distribution, t is used to represent a time variable, and D may be used to represent a preset failure threshold.

Based on the process degradation model of the electrical element, the unreliability function of the electrical element can obtain the remaining life probability distribution of the electrical element, and assuming that the degradation amount or the change amount X(s) =x of the characteristic value of the electrical element at the current time s, the expression of the remaining life E (T) of the electrical element can be obtained:

The remaining service life of the electrical component at the time point to be measured can also be determined in other ways, without limitation.

The above-mentioned preset variance threshold may be a preset threshold, which is used for screening a plurality of parameters, where the preset variance threshold may be determined according to an actual requirement of an electrical element, and is not limited herein.

In an alternative embodiment, the acquired plurality of feature data sets may be substituted into the process degradation model for processing to obtain a plurality of parameters, i.e., values of a plurality of initial parameters; the multiple parameters can be screened based on a preset variance threshold to obtain multiple first preselected parameters, namely values of multiple initial parameters obtained after screening; verifying and adjusting the first preselected parameters based on the characteristic data sets and the process degradation model to obtain target parameters, namely the adjusted or optimized initial parameters; finally, replacing the initial parameters based on the target parameters to obtain an adjusted process degradation model, and adjusting or optimizing the initial parameters in the process degradation model based on a plurality of characteristic data sets can be achieved through the steps, so that the adjusted process degradation model is more matched with the change process of the characteristic values of the electrical element, and the accuracy of residual life prediction of the electrical element is improved.

The above-mentioned target variance may refer to a variance value corresponding to each of the plurality of parameters, that is, a variance value corresponding to each of the plurality of parameters, where the target variance represents a degree of dispersion between each of the plurality of parameters and an average value of the plurality of parameters.

In an alternative embodiment, the filtering may be performed on the multiple parameters based on a preset variance threshold, and specifically, the filtering may be implemented on the multiple parameters based on a comparison relationship between a target variance corresponding to the multiple parameters and a preset range corresponding to the preset variance threshold, where the preset variance threshold may include a preset variance threshold upper limit value and a preset variance threshold lower limit value, and the preset variance threshold upper limit value and the preset variance threshold lower limit value form a preset range.

The first feature data set may be a set of feature data sets selected randomly or arbitrarily from a plurality of feature data sets.

In an alternative embodiment, the initial parameters in the process degradation model may be replaced by an average value of a plurality of first preselected parameters to obtain a preselected process degradation model, the first feature data set may be acquired a plurality of times, and the average value in the preselected process degradation model may be adjusted or optimized based on the first feature data set to obtain the target parameters.

The above-described reference feature data set may refer to a reference data set determined by the first feature data set, and the feature value acquisition time point or the feature value in the reference feature data set coincides with the first feature data set.

In an alternative embodiment, the feature value acquisition time point in the first feature data set may be substituted into the pre-selected process degradation model to obtain the reference feature value, the feature value acquisition time point and the reference feature value form the reference feature data set, and since the feature value acquisition time points in the first feature data set and the reference feature data set are consistent, the similarity between the first feature data set and the reference feature data set is determined, that is, the similarity between the feature value in the first feature data set and the reference feature value is determined, the average value in the pre-selected process degradation model is adjusted or optimized based on the determined similarity, generally, the higher the similarity between the feature value in the first feature data set and the reference feature value is, the smaller the average value in the pre-selected process degradation model is adjusted until the target parameter is obtained, and the initial parameter in the process degradation model is replaced by the target parameter, so that the adjusted process degradation model is more consistent with the change process of the feature value of the electrical element, thereby being beneficial to improving the accuracy of predicting the residual life of the electrical element.

FIG. 2 is a flowchart of an alternative method of updating initial parameters in a process degradation model, as shown in FIG. 2, in accordance with an embodiment of the present invention:

Step S202, a plurality of feature data sets are formed based on the plurality of feature values and the acquisition time points of the plurality of feature values.

Step S204, a plurality of characteristic data sets are processed by using the process degradation model, and a plurality of parameters are obtained.

Step S206, obtaining target variances of a plurality of parameters; comparing the preset variance threshold with the target variance to obtain a comparison result; and screening the plurality of parameters based on the comparison result to obtain a plurality of first preselected parameters.

Step S208, determining an average value of a plurality of first preselected parameters; and replacing the initial parameters in the process degradation model with average values to obtain a preselected process degradation model.

Step S210, substituting a preselected process degradation model into the preselected process degradation model for processing based on a first characteristic data set in the plurality of characteristic data sets to obtain a reference characteristic data set; determining a similarity between the first feature data set and the reference feature data set; and adjusting the average value based on the similarity to obtain the target parameter.

Example 2

According to another aspect of the embodiments of the present invention, there is further provided a lifetime prediction device for an electrical element, where the lifetime prediction device can execute the lifetime prediction method for an electrical element in the foregoing embodiments, and the specific implementation method and the preferred application scenario are the same as those in the foregoing embodiments, and are not described herein.

Fig. 3 is a schematic view of a life predicting apparatus for an electric element according to an embodiment of the present application, as shown in fig. 3, the apparatus including: an acquisition module 302, an update module 304, a prediction module 306.

Wherein, the acquiring module 302 is configured to acquire a plurality of feature data sets of the electrical component in response to receiving a lifetime prediction instruction of the electrical component, where the plurality of feature data sets are used to represent a plurality of feature values of the electrical component and a plurality of data sets formed by acquisition time points of the plurality of feature values; the updating module 304 is configured to update initial parameters in the process degradation model based on the plurality of feature data sets, to obtain an adjusted process degradation model, where the process degradation model is used to describe a process in which feature values change with time, and the initial parameters are used to represent parameters to be updated in the process degradation model; and the prediction module 306 is configured to predict the plurality of feature data sets by using the adjusted process degradation model, so as to obtain the remaining service life of the electrical element.

The acquisition module is further used for acquiring an initial characteristic value of the electrical element in an initial state, wherein the initial state is used for representing an initial state that the characteristic value of the electrical element is unchanged; a process degradation model is constructed based on the process model and the initial feature values, wherein the process model is used for describing a process that the feature values are changed by environmental factors.

In the above embodiment of the present application, the obtaining module includes: the device comprises a first acquisition unit, a first determination unit, an acquisition unit and a composition unit.

The first acquisition unit is used for acquiring a first circuit parameter of the electric element at a first detection point and acquiring a second circuit parameter of the electric element at a second detection point, wherein the first detection point and the second detection point are respectively positioned at two sides of the electric element corresponding to the detection point to be detected, and the detection point to be detected is used for indicating a position required to detect for life prediction of the electric element; the first determining unit is used for determining a characteristic value of the to-be-detected point based on the first circuit parameter and the second circuit parameter; the acquisition unit is used for acquiring the characteristic values of the to-be-detected points based on the preset frequency to obtain a plurality of characteristic values; the composing unit is configured to compose a plurality of feature data sets based on the plurality of feature values and the acquisition time points of the plurality of feature values.

In the above embodiment of the present application, the determining module includes: the device comprises an acquisition subunit, a first determination subunit and a second determination subunit.

The acquisition subunit is used for acquiring a first voltage value and a first current value in the first circuit parameter and acquiring a second voltage value and a second current value in the second circuit parameter; the first determining subunit is used for determining a contact resistance value of the to-be-detected point based on the first voltage value, the first current value, the second voltage value and the second current value; the second determination subunit is used for determining the characteristic value of the to-be-detected point based on the contact resistance value.

In the above embodiment of the present application, the determining module includes: the device comprises a second acquisition unit, a second determination unit, a third determination unit and a first processing unit.

The second acquisition unit is used for acquiring a time point to be detected of the residual service life of the electrical element; the second determining unit is used for determining a target characteristic data set from the plurality of characteristic data sets based on the time point to be detected, wherein the target characteristic data set is used for representing a data set which consists of the time point to be detected and characteristic values corresponding to the time point to be detected in the plurality of characteristic data sets; the third determining unit is used for obtaining the residual life probability distribution of the electric element based on the adjusted process degradation model and a preset failure threshold value, wherein the residual life probability distribution is used for representing the probability distribution of the electric element which breaks down along with the change of time; the first processing unit is used for substituting the target characteristic data set into the residual life probability distribution to process so as to obtain the residual service life of the electrical element at the time point to be tested.

In the above embodiment of the present application, the update module includes: the device comprises a second processing unit, a screening unit, an adjusting unit and a replacing unit.

The second processing unit is used for processing the plurality of characteristic data sets by using the process degradation model to obtain a plurality of parameters; the screening unit is used for screening the parameters based on a preset variance threshold to obtain a plurality of first preselected parameters, wherein variances of the first preselected parameters are within a preset range, and the preset range is determined based on the preset variance threshold; the adjusting unit is used for adjusting a plurality of first preselected parameters based on a plurality of characteristic data sets and the process degradation model to obtain target parameters; the replacing unit is used for replacing the initial parameters in the process degradation model by the target parameters to obtain an adjusted process degradation model.

The screening unit is also used for acquiring target variances of a plurality of parameters; comparing the preset variance threshold with the target variance to obtain a comparison result, wherein the comparison result is used for indicating whether the target variance is within a preset range; and screening the plurality of parameters based on the comparison result to obtain a plurality of first preselected parameters.

Wherein the adjusting unit is further configured to determine an average value of the plurality of first preselected parameters; replacing initial parameters in the process degradation model with average values to obtain a preselected process degradation model; and adjusting the average value based on a first characteristic data set in the characteristic data sets and a preselected process degradation model to obtain a target parameter.

The adjusting unit is also used for substituting the first characteristic data set into a preselected process degradation model for processing to obtain a reference characteristic data set; determining a similarity between the first feature data set and the reference feature data set; and adjusting the average value based on the similarity to obtain the target parameter.

Example 3

The embodiment of the application also provides electronic equipment, which comprises: a memory storing an executable program; and a processor for running a program, wherein the program when run performs the methods of the various embodiments of the present application.

The above-mentioned memory may refer to a device for storing data and programs inside a computer, and may include a memory, a hard disk, etc., where the memory may be used to temporarily store the running programs and data, the hard disk may be used to store the programs and data for a long period of time, and the memory may be used to enable the computer to read and write data, and execute the programs; the processor described above may be responsible for executing instructions in a computer program and performing data processing, and may be responsible for controlling and performing various operations, including arithmetic operations, logical operations, data transmission, and the like.

Example 4

Embodiments of the present application also provide a computer-readable storage medium including a stored executable program, wherein the executable program when run controls a device in which the computer-readable storage medium resides to perform the methods of the embodiments of the present application.

The computer storage medium may be a medium for storing a certain discrete physical quantity in a computer memory, and the computer storage medium mainly includes a semiconductor, a magnetic core, a magnetic drum, a magnetic tape, a laser disk, and the like; the computer readable storage medium may include a stored program which may be a set of instructions which can be recognized and executed by a computer, running on an electronic computer, and which may be an informative tool for meeting certain needs of a person.

Example 5

Embodiments of the application also provide a computer program product comprising a computer program which, when executed by a processor, implements the methods of the various embodiments of the application.

The computer program product may refer to a software program written, tested and distributed and may be run on a computer or other device, and may include application programs, operating systems, tools software, etc. for implementing specific functions or solving specific problems.

Example 6

Embodiments of the present application also provide a computer program product comprising a non-volatile computer readable storage medium for storing a computer program which, when executed by a processor, implements the methods of the various embodiments of the application.

The above-mentioned non-volatile computer readable storage medium may refer to a medium for storing data, where the non-volatile computer readable storage medium can keep data from being lost when power is off, and may be used for storing data stored for a long period of time, such as an operating system, an application program, and a user file, and the non-volatile storage medium may include a hard disk drive, a solid state disk, an optical disk, a flash memory storage device, and the like.

Example 7

Embodiments of the present application also provide a computer program which, when executed by a processor, implements the methods of the various embodiments of the application described above.

The above-described computer program may refer to a set of instructions for instructing a computer to perform a particular task or operation, may be written by a programmer using a particular programming language, and may include algorithms, data structures, logic, control flows, etc., and may be used for a variety of purposes, including application software, operating systems, etc.

In the foregoing embodiments of the present invention, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed technology may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, for example, may be a logic function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a Read-only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.

Claims

1. A life prediction method of an electrical component, comprising:

Acquiring a plurality of characteristic data sets of an electric element in response to receiving a life prediction instruction of the electric element, wherein the plurality of characteristic data sets are used for representing a plurality of characteristic values of the electric element and a plurality of data sets formed by acquisition time points of the plurality of characteristic values;

Updating initial parameters in a process degradation model based on the plurality of characteristic data sets to obtain an adjusted process degradation model, wherein the process degradation model is used for describing a process of the change of a characteristic value along with time, and the initial parameters are used for representing parameters to be updated in the process degradation model;

And predicting the plurality of characteristic data sets by using the adjusted process degradation model to obtain the residual service life of the electric element.

2. The method according to claim 1, wherein the method further comprises:

Acquiring an initial characteristic value of the electrical element in an initial state, wherein the initial state is used for representing an initial state that the characteristic value of the electrical element is unchanged;

The process degradation model is constructed based on a process model and the initial feature values, wherein the process model is used for describing a process that the feature values are changed by environmental factors.

3. The method of claim 1, wherein acquiring a plurality of characteristic data sets of the electrical component comprises:

acquiring a first circuit parameter of the electrical element at a first detection point and acquiring a second circuit parameter of the electrical element at a second detection point, wherein the first detection point and the second detection point are respectively positioned at two sides of the electrical element corresponding to a detection point to be detected, and the detection point to be detected is used for representing a position required to detect for life prediction of the electrical element;

determining a characteristic value of the to-be-detected point based on the first circuit parameter and the second circuit parameter;

collecting the characteristic values of the to-be-detected points based on a preset frequency to obtain a plurality of characteristic values;

the plurality of feature data sets are composed based on the plurality of feature values and the acquisition time points of the plurality of feature values.

4. A method according to claim 3, wherein determining the characteristic value of the point to be detected based on the first circuit parameter and the second circuit parameter comprises:

acquiring a first voltage value and a first current value in the first circuit parameter, and acquiring a second voltage value and a second current value in the second circuit parameter;

determining a contact resistance value of the to-be-detected point based on the first voltage value, the first current value, the second voltage value and the second current value;

And determining the characteristic value of the to-be-detected point based on the contact resistance value.

5. The method of claim 1, wherein predicting the plurality of feature data sets using the adjusted process degradation model results in a remaining useful life of the electrical component, comprising:

Acquiring a time point to be measured of the residual service life of the electrical element;

Determining a target characteristic data set from the plurality of characteristic data sets based on the time point to be measured, wherein the target characteristic data set is used for representing a data set which consists of characteristic values corresponding to the time point to be measured and the time point to be measured in the plurality of characteristic data sets;

Obtaining a residual life probability distribution of the electrical element based on the adjusted process degradation model and a preset failure threshold, wherein the residual life probability distribution is used for representing the probability distribution of the electrical element which is changed along with time and has faults;

Substituting the target characteristic data set into the residual life probability distribution for processing to obtain the residual life of the electrical element at the time point to be detected.

6. The method of claim 1, wherein updating initial parameters in the process degradation model based on the plurality of feature data sets to obtain an adjusted process degradation model comprises:

processing the plurality of characteristic data sets by using the process degradation model to obtain a plurality of parameters;

Screening the parameters based on a preset variance threshold to obtain a plurality of first preselected parameters, wherein variances of the first preselected parameters are within a preset range, and the preset range is determined based on the preset variance threshold;

adjusting the plurality of first preselected parameters based on the plurality of characteristic data sets and the process degradation model to obtain target parameters;

and replacing the initial parameters in the process degradation model by the target parameters to obtain the adjusted process degradation model.

7. The method of claim 6, wherein screening the plurality of parameters based on a preset variance threshold results in a plurality of first preselected parameters, comprising:

Acquiring target variances of the plurality of parameters;

Comparing the preset variance threshold with the target variance to obtain a comparison result, wherein the comparison result is used for indicating whether the target variance is within the preset range;

and screening the plurality of parameters based on the comparison result to obtain the plurality of first preselected parameters.

8. The method of claim 6, wherein adjusting the first plurality of preselected parameters based on the plurality of characteristic data sets and the process degradation model to obtain target parameters comprises:

Determining an average of the plurality of first preselected parameters;

Replacing the initial parameters in the process degradation model with the average values to obtain a preselected process degradation model;

And adjusting the average value based on a first characteristic data set in the characteristic data sets and the preselected process degradation model to obtain the target parameter.

9. The method of claim 8, wherein adjusting the average based on a first one of the plurality of feature data sets and the preselected process degradation model to obtain the target parameter comprises:

substituting the first characteristic data set into the preselected process degradation model for processing to obtain a reference characteristic data set;

Determining a similarity between the first feature data set and the reference feature data set;

And adjusting the average value based on the similarity to obtain the target parameter.

10. A life predicting apparatus for an electric element, comprising:

An acquisition module for acquiring a plurality of characteristic data sets of an electric element in response to receiving a life prediction instruction of the electric element, wherein the plurality of characteristic data sets are used for representing a plurality of characteristic values of the electric element and a plurality of data sets formed by acquisition time points of the plurality of characteristic values;

The updating module is used for updating initial parameters in the process degradation model based on the plurality of characteristic data sets to obtain an adjusted process degradation model, wherein the process degradation model is used for describing a process of the change of a characteristic value along with time, and the initial parameters are used for representing parameters to be updated in the process degradation model;

And the prediction module is used for predicting the plurality of characteristic data sets by using the adjusted process degradation model to obtain the residual service life of the electrical element.

11. An electronic device, comprising:

A memory storing an executable program;

a processor for executing the program, wherein the program executes the lifetime prediction method of an electrical component according to any one of claims 1 to 9 when executed.

12. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored executable program, wherein the executable program, when run, controls a device in which the storage medium is located to perform the lifetime prediction method of an electrical component according to any one of claims 1 to 9.

13. A computer program product comprising a computer program which, when executed by a processor, implements the method of life prediction of an electrical component according to any one of claims 1 to 9.