CN115879359B - Electronic component life prediction method, electronic device and storage medium - Google Patents
Electronic component life prediction method, electronic device and storage medium Download PDFInfo
- Publication number
- CN115879359B CN115879359B CN202210708428.6A CN202210708428A CN115879359B CN 115879359 B CN115879359 B CN 115879359B CN 202210708428 A CN202210708428 A CN 202210708428A CN 115879359 B CN115879359 B CN 115879359B
- Authority
- CN
- China
- Prior art keywords
- prediction model
- prediction
- time
- value
- time sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012549 training Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 16
- 230000009467 reduction Effects 0.000 claims description 15
- 230000036541 health Effects 0.000 claims description 4
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Abstract
The application discloses a method, a device, electronic equipment and a storage medium for predicting the service life of an electronic element, wherein the method for predicting the service life of the electronic element comprises the following steps: acquiring an influence factor time sequence set and a life value sequence of the electronic element; inputting a target prediction step number, the influence factor time sequence set and the life value sequence into a time sequence prediction model, wherein the time sequence prediction model comprises a single-step prediction model and a multi-step prediction model, the life of the electronic element is predicted through the single-step prediction model and the multi-step prediction model, a time prediction value corresponding to the life value sequence is obtained, and the target prediction step number is an integer larger than 1; and when the time predicted value is greater than or equal to a preset threshold value, early warning is carried out. According to the method and the device, the service life of the electronic element is predicted and early-warned based on data mining, so that the method and the device are flexible and accurate, and the user can conveniently maintain the electronic element daily.
Description
Technical Field
The present invention relates to the field of data prediction technologies, and in particular, to a method and apparatus for predicting lifetime of an electronic element, an electronic device, and a storage medium.
Background
eMMC (Embedded Multi Media Card) is an embedded memory standard specification defined by the MMC society and mainly aimed at products such as mobile phones and tablet computers. The service life of the eMMC is detected in real time mainly by adopting a monitoring technology by the current service life maintenance means of the vehicle-mounted eMMC, and the method alarms when the service life reaches a set threshold value by detecting the service life condition of the eMMC at the current moment. However, the threshold value in this technique is set according to the rated lifetime, and the lifetime is reduced due to the eMMC being affected by other related factors, and if the threshold value is set improperly, a premature or late alarm is generated, which is liable to cause excessive or insufficient maintenance.
Disclosure of Invention
In view of the above problems, the present application proposes a method, an apparatus, an electronic device, and a storage medium for predicting lifetime of an electronic component.
In a first aspect, embodiments of the present application provide a method for predicting lifetime of an electronic component, the method including: acquiring an influence factor time sequence set and a life value sequence of the electronic element; inputting a target prediction step number, the influence factor time sequence set and the life value sequence into a time sequence prediction model, wherein the time sequence prediction model comprises a single-step prediction model and a multi-step prediction model, the life of the electronic element is predicted through the single-step prediction model and the multi-step prediction model, a time prediction value corresponding to the life value sequence is obtained, and the target prediction step number is an integer larger than 1; and when the time predicted value is greater than or equal to a preset threshold value, early warning is carried out.
In a second aspect, embodiments of the present application provide an electronic component lifetime prediction device, the device including: the system comprises an acquisition module, a time prediction module and an early warning module, wherein the acquisition module is used for acquiring an influence factor time sequence set and a life value sequence of an electronic element; the time prediction module is used for inputting a target prediction step number, the influence factor time sequence set and the life value sequence into a time sequence prediction model, wherein the time sequence prediction model comprises a single-step prediction model and a multi-step prediction model, the life of the electronic element is predicted through the single-step prediction model and the multi-step prediction model, a time prediction value corresponding to the life value sequence is obtained, and the target prediction step number is an integer larger than 1; and the early warning module is used for carrying out early warning when the time predicted value is greater than or equal to a preset threshold value.
In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to perform the electronic component lifetime prediction method provided in the first aspect above.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored therein program code that is callable by a processor to perform the electronic component lifetime prediction method provided in the first aspect above.
According to the scheme, the service life of the electronic element and the information related to the service life of the electronic element are converted into time sequences, all the time sequences are input into the time sequence prediction model, the time sequence prediction model dynamically predicts the service life of the electronic element based on data mining through the service life value sequence of the electronic element and the influence factor time sequence set, the service life of the electronic element is predicted and early-warned, the method is flexible and accurate, and the user can conveniently maintain the electronic element daily.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart illustrating a method for predicting lifetime of an electronic component according to an embodiment of the present application.
Fig. 2 is a flowchart of a training method of a single-step prediction model in an electronic component lifetime prediction method according to an embodiment of the present application.
Fig. 3 is a schematic flow chart of step S220 in an embodiment of the present application.
Fig. 4 is a flowchart illustrating a training method of a multi-step prediction model in the electronic component lifetime prediction method according to an embodiment of the present application.
Fig. 5 is a flowchart illustrating a method for predicting lifetime of electronic components according to an exemplary embodiment of the present application.
Fig. 6 is a flowchart illustrating a method for predicting lifetime of an electronic component according to another embodiment of the present application.
Fig. 7 shows a schematic flow chart of step S430 in the embodiment of the present application.
Fig. 8 shows a schematic process flow diagram of the NAR and NARX dynamic network in the embodiment of the application.
Fig. 9 shows a block diagram of the electronic component lifetime prediction device provided in the embodiment of the present application.
Fig. 10 shows a block diagram of an electronic device for performing the electronic component lifetime prediction method according to the embodiment of the present application.
Fig. 11 shows a storage medium provided by an embodiment of the present application for storing or carrying program code for implementing a method of predicting lifetime of electronic components according to an embodiment of the present application.
Detailed Description
In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application.
The inventor finds that the maintenance of the eMMC only stays in the real-time detection of the service life of the eMMC at present, belongs to the technical field of fault monitoring, can only realize the post-maintenance after the fault occurs, easily causes excessive maintenance or insufficient maintenance, and specifically has the following defects:
1, the method can only detect the service life interval value of the eMMC in real time by reading the service life interval value provided by the eMMC chip in real time, and cannot provide accurate service life;
2, the method is essentially a fault monitoring technology, can only detect the current life state in real time, can not predict the service life of the eMMC, further can not provide necessary early warning time for subsequent maintenance decisions, and does not have intelligent predictive maintenance capability.
In order to solve the above problems, the inventor proposes a method, an apparatus, an electronic device, and a storage medium for predicting lifetime of an electronic component, where lifetime of the electronic component and information related to lifetime of the electronic component are all converted into time sequences, and all the time sequences are input into a time sequence prediction model, and the time sequence prediction model dynamically predicts a lifetime value sequence of the electronic component and a time sequence set of influencing factors, so that real-time prediction can be performed on the electronic component under different conditions, and the time sequence prediction model is set as a threshold fault model, and when a predicted value reaches a preset threshold, the predicted value is pre-warned, thereby facilitating daily maintenance of the electronic component by a user. The specific electronic component lifetime prediction method is described in detail in the following examples.
Referring to fig. 3, fig. 3 is a flowchart illustrating a method for predicting lifetime of an electronic device according to an embodiment of the present application. In a specific embodiment, the electronic component lifetime prediction method is applied to an electronic component lifetime prediction apparatus 500 as shown in fig. 9 and an electronic device 100 (fig. 10) provided with the electronic component lifetime prediction apparatus 500.
The specific flow of the embodiment will be described below by taking an electronic device as an example, and it will be understood that the electronic device applied in the embodiment may be an on-vehicle smart terminal, a smart phone, a computer, a wearable smart device, etc., which is not limited herein. The following details about the flowchart shown in fig. 3, the electronic component lifetime prediction method specifically may include the following steps:
step S110: a set of time series of impact factors for the electronic component and a series of lifetime values are obtained.
In this embodiment of the present application, the time series set of influence factors refers to a time series composed of influence factors related to lifetime of electronic components, where the influence factors may be applied write times, applied write traffic, storage unit types, number of bad blocks, monitoring health, and the like. The influencing factors may also be temperature, humidity, vehicle travel, etc.
The lifetime value sequence may be a real-time read of a lifetime query instruction sent to the eMMC chip. The data form of the lifetime value sequence may be yt= [0.91,0.8,0.79,0.6, … ], where yt is the lifetime value sequence.
Step S120: inputting a target prediction step number, the influence factor time sequence set and the life value sequence into a time sequence prediction model, wherein the time sequence prediction model comprises a single-step prediction model and a multi-step prediction model, the life of the electronic element is predicted through the single-step prediction model and the multi-step prediction model, a time prediction value corresponding to the life value sequence is obtained, and the target prediction step number is an integer larger than 1.
The target prediction step number may be set by the user according to the actual requirement, for example, if the user wants to obtain the remaining life time of the electronic component after ten days, the target prediction step number is set to 10, and the time series prediction model predicts according to the target prediction step number input by the user, and obtains a plurality of time prediction values corresponding to each day.
The time sequence prediction model comprises a single-step prediction model and a multi-step prediction model, wherein the single-step prediction model is obtained by training an initial single-step prediction model based on an influence factor time sequence set and a life value sequence, and the multi-step prediction model is obtained by training the initial multi-step prediction model based on the life value sequence.
Referring to fig. 2, in some embodiments, the method of training the single-step predictive model may include:
step S210: and acquiring the influence factor time sequence set.
Step S220: and performing dimension reduction processing on the influence factor time sequence set to obtain a comprehensive variable time sequence set.
The dimension reduction process is an operation of converting high-dimensional data into low-dimensional data. The high-dimensional data input means that life impact factors of the electronic element comprise the number of writing times of application, the writing flow of application, the type of storage unit, the number of bad blocks, the monitoring health degree and the like, and the impact factors are input into the model at the same time. There may be complex nonlinear relationships between high-dimensional data, and there may be problems such as data redundancy. The high-dimensional data is converted into the low-dimensional data through the dimension reduction processing, so that not only can the complex nonlinear relation among the high-dimensional data be solved, but also the problem of data redundancy can be solved.
Specifically, referring to fig. 3, the step of performing the dimension reduction processing on the influence factor time series set to obtain the integrated variable time series set may include: step S222 to step S224 will be described in detail below with respect to the flow shown in fig. 3.
Step S222: acquiring the influence factor time sequence set;
step S224: and carrying out principal component analysis and dimension reduction on the influence factor time sequence set to obtain the comprehensive variable time sequence set.
PCA (principal components analysis), principal component analysis, also called principal component analysis, aims to convert multiple indices into a few comprehensive indices by using the idea of dimension reduction. And the PCA data dimension reduction method is utilized to solve the problem of high-dimension data redundancy. The total contribution rate of the main components is required to reach 85% in general, since a plurality of main components are extracted based on the total contribution rate of the main components.
Step S230: and inputting the comprehensive variable time sequence set and the life value sequence into an initial single-step prediction model for training to obtain the single-step prediction model.
In the embodiment of the application, the single-step prediction model may be an NARX neural network model, which is a nonlinear autoregressive neural network model based on the out-of-band source input. NARX is a model used to describe nonlinear discrete systems. The NARX neural network structure comprises an input layer, an hidden layer and an output layer. The number of input layer nodes is set according to the number of input values, and the number of output layer nodes is set according to the number of predicted values. The NARX neural network adds a delay and feedback mechanism, so that the memory capacity of historical data is enhanced, and the NARX neural network is a dynamic neural network. NARX is suitable for time series prediction and is applied to solve nonlinear series prediction problems in various fields.
Referring to fig. 4, in some embodiments, a method of training the multi-step predictive model may include:
step S310: and acquiring the life value sequence.
Step S320: and inputting the life value sequence into an initial multi-step prediction model for training to obtain the multi-step prediction model.
The life value sequence is a life value of the electronic element, and the multi-step prediction model is trained through the life value of the electronic element, so that a plurality of prediction values aiming at the life value sequence are obtained, and real-time prediction of the multi-step prediction model is realized.
In the embodiment of the application, the multi-step prediction model can be an NAR network model, and the NAR network model can better realize short-time real-time prediction and has the advantages of easiness in realization, strong nonlinearity and the like. Real-time prediction of the service life of the electronic element is realized through the NAR network model, so that the condition-dependent maintenance capability of a user on the electronic element can be improved, the safety of data stored in the electronic element is effectively ensured, and the maintenance cost of the electronic element is reduced.
Step S130: and when the time predicted value is greater than or equal to a preset threshold value, early warning is carried out.
For example, the life prediction set is { y (t+1), y (t+2), …, y (t+k) },a k-th predicted value of the time sequence; y is thr For the service life failure alarm threshold of the electronic component, when +.>And (3) early warning is carried out by the time sequence prediction model.
Furthermore, the early warning is performed, and the remaining time of the service life of the electronic element corresponding to the kth step predicted value at the moment can be output.
Specifically, referring to fig. 5, fig. 5 is a schematic flow chart of a method for predicting lifetime of an electronic device according to an exemplary embodiment of the present application. Firstly, performing dimension reduction processing on an influence factor time sequence set, and training an NARX model by using the influence factor time sequence set after the dimension reduction processing and a life value sequence, thereby obtaining a single-step prediction model. The multi-step predictive model only requires a sequence of life values to train it. The time series prediction model is obtained through a single-step prediction model and a multi-step prediction model. Inputting real-time data of the electronic element into a time sequence prediction model, obtaining a plurality of prediction results through a prediction algorithm, comparing the prediction results with a threshold value, and predicting and alarming the life value of the electronic element by the time sequence prediction model if the prediction results reach the set threshold value.
Specifically, referring to fig. 6, in some embodiments, predicting the lifetime of the electronic component by the single-step prediction model and the multi-step prediction model may include:
step S410: a set of time series of impact factors for the electronic component and a series of lifetime values are obtained.
Step S420: and inputting a target prediction step number, the influence factor time sequence set and the life value sequence into a time sequence prediction model, wherein the time sequence prediction model comprises a single-step prediction model and a multi-step prediction model.
Step S430: and outputting a single-step predicted value through the single-step prediction model based on the influence factor time sequence set and the life value sequence.
The single-step prediction model is used for carrying out single-step prediction on the service life based on the service life value sequence and the influence factor time sequence set, the influence factor time sequence at the moment is obtained after the dimension reduction by the PCA technology, and the dynamic prediction of the time prediction model relative to the time sequence under the influence factor of the electronic element is realized, so that the single-step prediction value is closer to the real service life value.
Step S440: and obtaining a target predicted step number, a real-time step number and the single-step predicted value.
Step S450: and outputting a multi-step prediction result through the multi-step prediction model based on the target prediction step number, the real-time step number and the single-step prediction value.
The input of the multi-step prediction model not only comprises the target prediction step number and the real-time step number, but also comprises a single-step prediction value predicted by the single-step prediction model, and the single-step prediction value is used as an observation value of multi-step prediction for iterative prediction, so that a multi-step prediction result can be obtained. The multi-step prediction result output by the multi-step prediction model is more real.
Referring to fig. 7, in some embodiments, outputting the multi-step prediction result by the multi-step prediction model based on the real-time step number and the single-step prediction value may include:
step S432: comparing the real-time number of steps with the target predicted number of steps.
And comparing the real-time step number with the target predicted step number in real time, and judging the relation between the real-time step number and the target predicted step number.
Step S434: if the real-time step number does not reach the target predicted step number, adding the single-step predicted value into the tail part of the life value sequence to obtain a new life value sequence; adding 1 to the real-time step number; and carrying out single-step prediction on the new life value sequence through the multi-step prediction model to obtain a single-step prediction result, and returning to the step of comparing the real-time step number with the target prediction step number.
The single-step prediction algorithm is a special multi-step prediction algorithm, and the multi-step prediction value is a set of multiple single-step prediction values in practice.
Since the single-step prediction algorithm predicts a lifetime value sequence and an influence factor time sequence set, the multi-step prediction algorithm only predicts the target prediction algorithm. The single-step predicted value obtained by the single-step predicted algorithm is added into the life value sequence to ensure that the first multi-step predicted value is the single-step predicted value in the single-step predicted algorithm, so as to ensure that the predicted value obtained by the multi-step predicted algorithm is related to the life value sequence and the influence factor time sequence set, thereby ensuring the accuracy of data.
And adding 1 to the real-time step number, ending the cycle when the real-time step number is the same as the target prediction step number, and outputting a plurality of predicted values to ensure that the number of the finally output plurality of predicted values is the same as the target prediction step number, so as to avoid data omission and inaccurate data prediction.
Step S436: and if the new real-time step number reaches the target prediction step number, outputting a plurality of single-step prediction results obtained by the multi-step prediction model.
Step S460: and when the time predicted value is greater than or equal to a preset threshold value, early warning is carried out.
The steps S410, S420, S460 may be described in detail with reference to the steps S110, S120, S130, which are not described herein.
In this embodiment, the single-step prediction model includes a NARX network, and the multi-step prediction model includes a NAR network. Specifically, referring to fig. 8, in the prediction process, a single-step prediction is performed through a target prediction step number, a lifetime value sequence and an influence factor time sequence set input by a user, so as to obtain and output a single-step prediction value. And judging the target predicted step number, and if the target predicted step number is 1 and the single-step predicted value reaches a threshold value set by a time sequence prediction model, carrying out early warning on the single-step predicted step number by the model. If the target predicted step number is an integer greater than 1, the real-time step number initial value in the multi-step prediction algorithm is made to be 1, and 1 adding processing is performed, at this time, the single-step predicted value is used as the last value in the new life value sequence, the multi-step prediction algorithm gradually excavates the new life value sequence until the real-time step number is equal to the target predicted step number, and a plurality of single-step predicted values are output. If one or more single-step predicted values in the output single-step predicted values reach a threshold value, fault early warning is carried out, and the single-step predicted values are output.
According to the scheme, the service life of the electronic element and the information related to the service life of the electronic element are converted into time sequences, all the time sequences are input into the time sequence prediction model, the time sequence prediction model can predict the electronic element in real time according to the service life value sequences of the electronic element and the time sequence sets of influencing factors, the time sequence prediction model is set as a threshold fault model, when the predicted value reaches a preset threshold, the predicted value is early-warned, the residual service life value of the electronic element is output, and the daily maintenance of the electronic element by a user is facilitated.
Referring to fig. 9, a block diagram of an electronic component lifetime prediction apparatus 500 according to an embodiment of the present application is shown. The electronic component lifetime prediction apparatus 500 is applied to the above-described electronic device, and the electronic component lifetime prediction apparatus 500 includes: the device comprises an acquisition module 510, a time prediction module 520 and an early warning module 530, wherein the acquisition module 510 is configured to acquire an influence factor time sequence set and a life value sequence of an electronic component, the life value sequence comprises a life value sequence of the electronic component, and the influence factor time sequence set comprises an influence factor time sequence; the time prediction module 520 is configured to input a target prediction step number, the impact factor time sequence set, and the lifetime value sequence into a time sequence prediction model, where the time sequence prediction model includes a single-step prediction model and a multi-step prediction model, and predict the lifetime of the electronic component through the single-step prediction model and the multi-step prediction model to obtain a time prediction value corresponding to the lifetime value sequence, where the target prediction step number is an integer greater than 1; and the early warning module 530 is configured to perform early warning and output a remaining time of the lifetime of the electronic component when the time prediction value is greater than or equal to a preset threshold value.
In some embodiments of the present application, the temporal prediction module 520 further includes: the influence factor time sequence set acquisition module is used for acquiring the influence factor time sequence set, wherein the influence factor time sequence set comprises the use times of the electronic element, environment data and health degree data of the electronic element; the dimension reduction module is used for carrying out dimension reduction processing on the influence factor time sequence set to obtain a comprehensive variable time sequence set; and the model training module is used for inputting the comprehensive variable time sequence set and the life value sequence into an initial single-step prediction model for training to obtain the single-step prediction model.
In some embodiments of the present application, the dimension reduction module includes: acquiring the influence factor time sequence set; and the influence factor time sequence set acquisition module is used for acquiring the comprehensive variable time sequence set.
In some embodiments of the present application, the model training module comprises: the life value sequence acquisition module is used for acquiring the life value sequence; and the multi-step prediction model training module is used for inputting the life value sequence into an initial multi-step prediction model for training to obtain the multi-step prediction model.
In some embodiments of the present application, the temporal prediction module 520 further includes: the single-step prediction value output module is used for outputting a single-step prediction value through the single-step prediction model based on the influence factor time sequence set and the life value sequence; the data acquisition module is used for acquiring the target predicted step number, the real-time step number and the single-step predicted value; and the multi-step prediction result output module is used for outputting the multi-step prediction result through the multi-step prediction model based on the target prediction step number, the real-time step number and the single-step prediction value.
In some embodiments of the present application, the multi-step prediction result output module includes: the comparison module is used for comparing the real-time step number with the target prediction step number; the multi-step prediction module is used for adding the single-step predicted value to the tail part of the life value sequence to obtain a new life value sequence if the real-time step number does not reach the target predicted step number; adding 1 to the real-time step number; performing single-step prediction on the new life value sequence through the multi-step prediction model to obtain a single-step prediction result, and returning to the step of comparing the real-time step number with the target prediction step number; and the single-step prediction result output modules are used for outputting a plurality of single-step prediction results obtained by the multi-step prediction model if the new real-time step number reaches the target prediction step number.
In some embodiments of the present application, the single-step predictive model includes a NARX network and the multi-step predictive model includes a NAR network.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus and modules described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
In several embodiments provided herein, the coupling of the modules to each other may be electrical, mechanical, or other.
In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.
In summary, according to the scheme provided by the application, the features are compressed in a preset proportion according to the feature weight coefficient of the target feature set in the trained information extraction model, so that the optimal feature set is obtained and is used as the feature set in the compressed information extraction model, the service life prediction of the electronic element is realized, the memory ratio of the information extraction model in the electronic equipment is reduced, and meanwhile, the processing speed of named entity recognition can be improved.
Referring to fig. 10, a block diagram of an electronic device according to an embodiment of the present application is shown. The electronic device 100 may be an electronic device capable of running an application program, such as a smart phone, a tablet computer, a smart watch, smart glasses, a notebook computer, etc. The electronic device 100 in this application may include one or more of the following components: a processor 110, a memory 120, and one or more application programs, wherein the one or more application programs may be stored in the memory 120 and configured to be executed by the one or more processors 110, the one or more program(s) configured to perform the method as described in the foregoing method embodiments.
Processor 110 may include one or more processing cores. The processor 110 utilizes various interfaces and lines to connect various portions of the overall electronic device 100, perform various functions of the electronic device 100, and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 120, and invoking data stored in the memory 120. Alternatively, the processor 110 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 110 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 110 and may be implemented solely by a single communication chip.
The Memory 120 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Memory 120 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 120 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described below, etc. The storage data area may also store data created by the electronic device 100 in use (e.g., phonebook, audiovisual data, chat log data), and the like.
Referring to fig. 11, a block diagram of a computer readable storage medium according to an embodiment of the present application is shown. The computer readable medium 600 has stored therein program code which can be invoked by a processor to perform the methods described in the method embodiments described above.
The computer readable storage medium 600 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium 600 comprises a non-volatile computer readable medium (non-transitory computer-readable storage medium). The computer readable storage medium 600 has storage space for program code 610 that performs any of the method steps described above. The program code can be read from or written to one or more computer program products. Program code 610 may be compressed, for example, in a suitable form.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, one of ordinary skill in the art will appreciate that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (9)
1. A method for predicting lifetime of an electronic component, the method comprising:
acquiring an influence factor time sequence set and a life value sequence of the electronic element;
inputting a target prediction step number, the influence factor time sequence set and the life value sequence into a time sequence prediction model, wherein the time sequence prediction model comprises a single-step prediction model and a multi-step prediction model, the life of the electronic element is predicted through the single-step prediction model and the multi-step prediction model, a time prediction value corresponding to the life value sequence is obtained, the target prediction step number is an integer greater than 1, the single-step prediction model is obtained by training an initial single-step prediction model through the influence factor time sequence set and the life value sequence, and the multi-step prediction model is obtained by training an initial multi-step prediction model through the life value sequence;
when the time predicted value is greater than or equal to a preset threshold value, early warning is carried out;
inputting the target prediction step number, the influencing factor time sequence set and the life value sequence into a time sequence prediction model, wherein the time sequence prediction model comprises a single-step prediction model and a multi-step prediction model, predicting the life of the electronic element through the single-step prediction model and the multi-step prediction model to obtain a time prediction value corresponding to the life value sequence, and the method comprises the following steps: outputting a single-step predicted value through the single-step prediction model based on the influence factor time sequence set and the life value sequence; obtaining a target predicted step number, a real-time step number and the single-step predicted value; and outputting a multi-step prediction result through the multi-step prediction model based on the target prediction step number, the real-time step number and the single-step prediction value.
2. The method of claim 1, wherein the method of training the single-step predictive model comprises:
acquiring the influence factor time sequence set, wherein the influence factor time sequence set comprises one or a combination of more of the use times of the electronic element, environment data and health degree data of the electronic element;
performing dimension reduction processing on the influence factor time sequence set to obtain a comprehensive variable time sequence set;
and inputting the comprehensive variable time sequence set and the life value sequence into an initial single-step prediction model for training to obtain the single-step prediction model.
3. The method according to claim 2, wherein the performing the dimension reduction on the influence factor time series set to obtain a comprehensive variable time series set includes:
acquiring the influence factor time sequence set;
and carrying out principal component analysis and dimension reduction on the influence factor time sequence set to obtain the comprehensive variable time sequence set.
4. The method of claim 2, wherein the method of training the multi-step predictive model comprises:
acquiring the life value sequence;
and inputting the life value sequence into an initial multi-step prediction model for training to obtain the multi-step prediction model.
5. The method of claim 1, wherein outputting a multi-step prediction result by the multi-step prediction model based on the real-time step number and the single-step prediction value comprises:
comparing the real-time step number with the target predicted step number;
if the real-time step number does not reach the target predicted step number, adding the single-step predicted value into the tail part of the life value sequence to obtain a new life value sequence; adding 1 to the real-time step number; performing single-step prediction on the new life value sequence through the multi-step prediction model to obtain a single-step prediction result, and returning to the step of comparing the real-time step number with the target prediction step number;
and if the real-time step number reaches the target prediction step number, outputting a plurality of single-step prediction results obtained by the multi-step prediction model.
6. The method of claim 1, wherein the single-step predictive model comprises a NARX network and the multi-step predictive model comprises a NAR network.
7. An electronic component lifetime prediction device, comprising: the system comprises an acquisition module, a time prediction module and an early warning module, wherein,
the acquisition module is used for acquiring an influence factor time sequence set and a life value sequence of the electronic element;
the time prediction module is used for inputting a target prediction step number, the influence factor time sequence set and the life value sequence into a time sequence prediction model, the time sequence prediction model comprises a single-step prediction model and a multi-step prediction model, the life of the electronic element is predicted through the single-step prediction model and the multi-step prediction model to obtain a time prediction value corresponding to the life value sequence, the target prediction step number is an integer greater than 1, the single-step prediction model is obtained by training an initial single-step prediction model through the influence factor time sequence set and the life value sequence, and the multi-step prediction model is obtained by training an initial multi-step prediction model through the life value sequence;
the early warning module is used for carrying out early warning and outputting the residual time of the service life of the electronic element when the time predicted value is greater than or equal to a preset threshold value;
the time prediction module is further used for outputting a single-step prediction value through the single-step prediction model based on the influence factor time sequence set and the life value sequence; obtaining a target predicted step number, a real-time step number and the single-step predicted value; and outputting a multi-step prediction result through the multi-step prediction model based on the target prediction step number, the real-time step number and the single-step prediction value.
8. An electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to perform the method of any of claims 1-6.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program code, which is callable by a processor for executing the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210708428.6A CN115879359B (en) | 2022-06-21 | 2022-06-21 | Electronic component life prediction method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210708428.6A CN115879359B (en) | 2022-06-21 | 2022-06-21 | Electronic component life prediction method, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115879359A CN115879359A (en) | 2023-03-31 |
| CN115879359B true CN115879359B (en) | 2024-02-23 |
Family
ID=85769432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210708428.6A Active CN115879359B (en) | 2022-06-21 | 2022-06-21 | Electronic component life prediction method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879359B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886430A (en) * | 2019-01-24 | 2019-06-14 | 同济大学 | A kind of equipment health state evaluation and prediction technique based on industrial big data |
| CN111443294A (en) * | 2020-04-10 | 2020-07-24 | 华东理工大学 | Method and device for indirectly predicting remaining life of lithium ion battery |
| CN112307638A (en) * | 2020-11-09 | 2021-02-02 | 中南大学 | Capacitor life estimation method and device and electronic equipment |
| WO2022080377A1 (en) * | 2020-10-15 | 2022-04-21 | 昭和電工株式会社 | Lithium ion battery life span prediction method, discharge capacity retention rate prediction method, life span prediction program, discharge capacity retention rate prediction program, and information processing device |
| CN114510870A (en) * | 2022-01-07 | 2022-05-17 | 华东交通大学 | Method and device for predicting residual life of underground structure of urban rail transit |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11507716B2 (en) * | 2018-07-09 | 2022-11-22 | International Business Machines Corporation | Predicting life expectancy of machine part |
-
2022
- 2022-06-21 CN CN202210708428.6A patent/CN115879359B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886430A (en) * | 2019-01-24 | 2019-06-14 | 同济大学 | A kind of equipment health state evaluation and prediction technique based on industrial big data |
| CN111443294A (en) * | 2020-04-10 | 2020-07-24 | 华东理工大学 | Method and device for indirectly predicting remaining life of lithium ion battery |
| WO2022080377A1 (en) * | 2020-10-15 | 2022-04-21 | 昭和電工株式会社 | Lithium ion battery life span prediction method, discharge capacity retention rate prediction method, life span prediction program, discharge capacity retention rate prediction program, and information processing device |
| CN112307638A (en) * | 2020-11-09 | 2021-02-02 | 中南大学 | Capacitor life estimation method and device and electronic equipment |
| CN114510870A (en) * | 2022-01-07 | 2022-05-17 | 华东交通大学 | Method and device for predicting residual life of underground structure of urban rail transit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115879359A (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112436968B (en) | Network traffic monitoring method, device, equipment and storage medium | |
| CN111880856B (en) | Voice wakeup method and device, electronic equipment and storage medium | |
| CN111489517A (en) | Screw locking abnormity warning method and device, computer device and storage medium | |
| CN114169604A (en) | Performance index abnormality detection method, abnormality detection device, electronic apparatus, and storage medium | |
| CN112181919A (en) | Compression method, compression system, electronic equipment and storage medium | |
| CN114205212A (en) | Network security early warning method, device, equipment and readable storage medium | |
| CN115879359B (en) | Electronic component life prediction method, electronic device and storage medium | |
| CN113123955B (en) | Plunger pump abnormity detection method and device, storage medium and electronic equipment | |
| CN117391466A (en) | Novel early warning method and system for contradictory dispute cases | |
| CN110704614B (en) | Information processing method and device for predicting user group type in application | |
| CN111582589A (en) | Car rental insurance prediction method, device, equipment and storage medium | |
| CN115278757A (en) | Method and device for detecting abnormal data and electronic equipment | |
| CN110780820A (en) | Method and device for determining continuous storage space, electronic equipment and storage medium | |
| CN116245630A (en) | Anti-fraud detection method and device, electronic equipment and medium | |
| CN115080745A (en) | Multi-scene text classification method, device, equipment and medium based on artificial intelligence | |
| CN113449062B (en) | Track processing method, track processing device, electronic equipment and storage medium | |
| Gruenwedel et al. | Efficient foreground detection for real‐time surveillance applications | |
| CN114692987A (en) | Time sequence data analysis method, device, equipment and storage medium | |
| CN113762294A (en) | Feature vector dimension compression method, device, equipment and medium | |
| CN112231182A (en) | Internet of things equipment working condition data analysis method and device and computer equipment | |
| CN113208566A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN111178630A (en) | Load prediction method and device | |
| CN111274113B (en) | State prediction method and device and mobile terminal | |
| CN113487316B (en) | Distributed payment system security processing method and device | |
| CN114518849B (en) | Data storage method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |