CN114091238A - Equipment life prediction method and device, electronic equipment and storage medium - Google Patents

Equipment life prediction method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114091238A
CN114091238A CN202111235647.9A CN202111235647A CN114091238A CN 114091238 A CN114091238 A CN 114091238A CN 202111235647 A CN202111235647 A CN 202111235647A CN 114091238 A CN114091238 A CN 114091238A
Authority
CN
China
Prior art keywords
determining
sequence
vibration
dimension
data 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.)
Pending
Application number
CN202111235647.9A
Other languages
Chinese (zh)
Inventor
张燧
傅望安
王海明
张育钧
高建忠
苏人奇
王青天
曾谁飞
李小翔
冯帆
杨永前
陈沐新
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huaneng Clean Energy Research Institute
Clean Energy Branch of Huaneng Zhejiang Energy Development Co Ltd
Original Assignee
Huaneng Clean Energy Research Institute
Clean Energy Branch of Huaneng Zhejiang Energy Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huaneng Clean Energy Research Institute, Clean Energy Branch of Huaneng Zhejiang Energy Development Co Ltd filed Critical Huaneng Clean Energy Research Institute
Priority to CN202111235647.9A priority Critical patent/CN114091238A/en
Publication of CN114091238A publication Critical patent/CN114091238A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/12—Timing analysis or timing optimisation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The application provides a method, a device, equipment and a storage medium for predicting the service life of the equipment, wherein the method comprises the following steps: determining a vibration data sequence and a corresponding characteristic data sequence of equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions; determining an eigen-mode data sequence and a trend sequence corresponding to the vibration characteristics on each dimension based on the characteristic data sequence; selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions; according to the trend sequence corresponding to the vibration characteristics on the target dimension, the residual service life of the equipment is determined, the maintenance cost of the equipment is reduced, the use safety and reliability of the equipment are improved, and meanwhile, the fault removal rate is improved.

Description

Equipment life prediction method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of device prediction technologies, and in particular, to a method and an apparatus for predicting a device life, an electronic device, and a storage medium.
Background
In the related art, in a new energy system, a large number of devices may damage the health of the devices due to long-term operation, environmental changes, frequent start and stop, and the like. Even when the regular maintenance time is not reached, equipment fails, the whole comprehensive energy system can be caused to be in a problem due to the phenomenon, and the safety is low and the maintenance cost is high.
Disclosure of Invention
The object of the present application is to solve at least to some extent one of the above mentioned technical problems.
Therefore, the method for predicting the service life of the equipment is provided, the eigenmode data sequence and the trend sequence corresponding to the vibration feature in each dimension are determined through the vibration data sequence and the feature data sequence of the equipment to be detected, the target dimension is selected based on the eigenmode data sequences and the trend sequences of multiple dimensions, the remaining service life of the equipment is determined according to the trend sequence corresponding to the target dimension, the maintenance cost of the equipment is reduced, and the safety, the reliability and the fault removal rate are improved.
An embodiment of a first aspect of the present application provides an apparatus life prediction method, including:
determining a vibration data sequence and a corresponding characteristic data sequence of equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions;
determining an eigen-mode data sequence and a trend sequence corresponding to the vibration characteristics in each dimension based on the characteristic data sequence;
selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions;
and determining the residual service life of the equipment according to the trend sequence corresponding to the vibration characteristics on the target dimension.
Optionally, the determining the vibration data sequence and the corresponding characteristic data sequence of the device to be detected in the preset time period includes:
acquiring a vibration data sequence of the equipment to be detected in a preset time period;
determining the type of the equipment and vibration characteristics of multiple dimensions corresponding to the type;
performing feature extraction processing on vibration data corresponding to each time point in the vibration data sequence based on the vibration data and the vibration data in a preset sub-time period before the time point, and determining the vibration features of the multiple dimensions of the time point;
determining the characteristic data sequence based on the vibration characteristics of the plurality of dimensions at each time point.
Optionally, the determining, based on the characteristic data sequence, an eigenmode data sequence and a trend sequence corresponding to the vibration characteristic in each dimension includes:
for each dimension, determining a characteristic sequence corresponding to the vibration characteristics on the dimension and an eigenmode data sequence based on the characteristic data sequence;
and determining a trend sequence on the dimension based on the characteristic sequence corresponding to the vibration characteristics on the dimension and the eigenmode data sequence.
Optionally, selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration features in multiple dimensions, including:
for each dimension, determining evaluation parameter information corresponding to the dimension based on an eigenmode data sequence and a trend sequence corresponding to the vibration characteristics on the dimension;
and selecting the target dimension based on the evaluation parameter information corresponding to the plurality of dimensions.
Optionally, the evaluation parameter information is a total number value obtained by weighted summation of values of a preset number of evaluation parameters corresponding to the dimension; the evaluation parameter includes at least one of the following parameters: relevance, single scheduling and robustness;
selecting the target dimension based on the evaluation parameter information corresponding to the plurality of dimensions includes:
and selecting the dimension with the maximum corresponding total number value to be determined as the target dimension.
Optionally, the determining the remaining service life of the device according to the trend sequence corresponding to the vibration feature on the target dimension includes:
inputting the trend data of each time point in the trend sequence into a pre-trained life prediction model, and determining the trend data of each time point in the future;
determining a target future time point when the corresponding trend data reaches a fault trend threshold value corresponding to the target dimension;
and determining the residual service life according to the target future time point and the preset time period.
The method for predicting the service life of the equipment comprises the steps of determining a vibration data sequence and a corresponding characteristic data sequence of the equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions; determining an eigen-mode data sequence and a trend sequence corresponding to the vibration characteristics on each dimension based on the characteristic data sequence; selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions; and determining the residual service life of the equipment according to the trend sequence corresponding to the vibration characteristics on the target dimension, reducing the maintenance cost of the equipment and improving the safety, reliability and troubleshooting rate.
An embodiment of a second aspect of the present application provides an apparatus for predicting a lifetime of a device, including:
the device comprises a first determining module, a second determining module and a judging module, wherein the first determining module is used for determining a vibration data sequence and a corresponding characteristic data sequence of equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions;
the second determination module is used for determining an eigen module data sequence and a trend sequence corresponding to the vibration characteristics in each dimension based on the characteristic data sequence;
the selection module is used for selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions;
and the third determining module is used for determining the residual service life of the equipment according to the trend sequence corresponding to the vibration characteristics on the target dimension.
Optionally, the first determining module is specifically configured to,
acquiring a vibration data sequence of the equipment to be detected in a preset time period;
determining the type of the equipment and vibration characteristics of multiple dimensions corresponding to the type;
performing feature extraction processing on vibration data corresponding to each time point in the vibration data sequence based on the vibration data and the vibration data in a preset sub-time period before the time point, and determining the vibration features of the multiple dimensions of the time point;
determining the characteristic data sequence based on the vibration characteristics of the plurality of dimensions at each time point.
Optionally, the second determining module is specifically configured to,
for each dimension, determining a characteristic sequence corresponding to the vibration characteristics on the dimension and an eigenmode data sequence based on the characteristic data sequence;
and determining a trend sequence on the dimension based on the characteristic sequence corresponding to the vibration characteristics on the dimension and the eigenmode data sequence.
Optionally, the selection module is specifically configured to,
for each dimension, determining evaluation parameter information corresponding to the dimension based on an eigenmode data sequence and a trend sequence corresponding to the vibration characteristics on the dimension;
and selecting the target dimension based on the evaluation parameter information corresponding to the plurality of dimensions.
Optionally, the evaluation parameter information is a total number value obtained by weighted summation of values of a preset number of evaluation parameters corresponding to the dimension; the evaluation parameter includes at least one of the following parameters: relevance, single scheduling and robustness;
the selection module is specifically configured to select the dimension with the largest total number value to determine the dimension as the target dimension.
Optionally, the third determining module is specifically configured to,
inputting the trend data of each time point in the trend sequence into a pre-trained life prediction model, and determining the trend data of each time point in the future;
determining a target future time point when the corresponding trend data reaches a fault trend threshold value corresponding to the target dimension;
determining the remaining service life according to the target future time point and the preset time period
The device life prediction device of the embodiment of the application determines the vibration data sequence and the corresponding characteristic data sequence of the device to be detected in the preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions; determining an eigen-mode data sequence and a trend sequence corresponding to the vibration characteristics on each dimension based on the characteristic data sequence; selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions; and determining the residual service life of the equipment according to the trend sequence corresponding to the vibration characteristics on the target dimension, reducing the maintenance cost of the equipment and improving the safety, reliability and troubleshooting rate.
An embodiment of a third aspect of the present application provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the program implementing the method of device lifetime prediction according to the first aspect.
A fourth aspect of the present application is directed to a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the device lifetime prediction method according to the first aspect.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a method for predicting a lifetime of a device according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of another method for predicting the lifetime of a device according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of another method for predicting the lifetime of a device according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a joint training model being trained;
fig. 5 is a schematic structural diagram of an apparatus life prediction device according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
A device life prediction method, an apparatus, an electronic device, and a non-transitory computer-readable storage medium according to embodiments of the present application are described below with reference to the accompanying drawings.
The device life prediction method provided by the present application is described in detail below with reference to fig. 1.
Fig. 1 is a schematic flowchart of a method for predicting a lifetime of a device according to an embodiment of the present disclosure.
The execution subject of the embodiment of the present application is the device life prediction apparatus provided by the present application, and the device life prediction apparatus may be configured in an electronic device, so that the electronic device may execute a device life prediction function.
The electronic device may be any device having a computing capability, for example, a Personal Computer (PC), a mobile terminal, a server, and the like, and the mobile terminal may be a hardware device having various operating systems, touch screens, and/or display screens, such as an in-vehicle device, a mobile phone, a tablet Computer, a Personal digital assistant, and a wearable device.
As shown in fig. 1, the device life prediction method includes the following steps:
step 101, determining a vibration data sequence and a corresponding characteristic data sequence of equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions.
The vibration data sequence may include vibration data of the device to be detected at each time point within a preset time period. Wherein the vibration data may include at least one of: the operation age, historical maintenance data and current operation data of the equipment to be detected. Wherein the current operating data may include at least one of the following vibration parameters: temperature, pressure, energy consumption data.
The characteristic data sequence may include characteristic data of the device to be detected at each time point within a preset time period.
In the embodiment of the application, a vibration Data sequence of the device to be detected within a preset time period can be collected by using an SCADA (Supervisory Control And Data Acquisition, Data Acquisition And monitoring Control system).
The device life prediction apparatus executing the process of step 101 may, for example, acquire a vibration data sequence of the device to be detected within a preset time period; determining the type of the equipment and vibration characteristics of multiple dimensions corresponding to the type; performing feature extraction processing on vibration data corresponding to each time point in the vibration data sequence based on the vibration data and the vibration data in a preset sub-time period before the time point, and determining vibration features of multiple dimensions of the time point; and determining a characteristic data sequence based on the vibration characteristics of multiple dimensions of each time point.
In the embodiment of the application, for vibration data corresponding to each time point in a vibration data sequence, feature extraction processing is performed on the basis of the vibration data and the vibration data in a preset sub-time period before the time point, before vibration features of multiple dimensions of the time point are determined, whether numerical values of multiple vibration parameters in the vibration data sequence meet corresponding fault conditions needs to be determined, when all vibration parameters do not meet corresponding fault conditions, feature extraction processing is performed on the basis of the vibration data, and vibration features of multiple dimensions of the time point are determined.
The fault condition may be whether the value of the vibration parameter exceeds a preset threshold, and if the value of the vibration parameter exceeds the preset threshold, the equipment to be detected is determined to be faulty and is directly reported.
If the vibration data sequence has phenomena such as missing or abnormal values, the expert experience can be combined, and for the static equipment, for example, a regression method can be used to interpolate the numerical value and remove the abnormal value, wherein, for example, the least square method or the polynomial regression method can be used to realize the interpolation.
And 102, determining an eigenmode data sequence and a trend sequence corresponding to the vibration characteristics in each dimension based on the characteristic data sequence.
The eigenmode data sequence refers to eigenmode data corresponding to vibration characteristics in each dimension, which is calculated based on the characteristic data sequence by using an IMF (Intrinsic Mode Functions).
Wherein, the trend sequence refers to trend data at each time point in a preset time period.
In this embodiment of the application, the device life prediction apparatus may execute the process of step 102, for example, to determine, for each dimension, a feature sequence and an eigen-mode data sequence corresponding to the vibration feature in the dimension based on the feature data sequence; and determining a trend sequence in the dimension based on the characteristic sequence corresponding to the vibration characteristics in the dimension and the eigenmode data sequence.
And 103, selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics in multiple dimensions.
In the embodiment of the present application, taking the vibration parameters of the device to be detected as an example, the vibration characteristics of multiple dimensions that can be extracted may include at least one of the following characteristics: root of mean square deviation, kurtosis on a single vibration parameter; entropy, energy between a plurality of vibration parameters; based on the features of trigonometric functions. The characteristics based on the trigonometric function are shown in formula (1) and formula (2), different vibration characteristics can be selected according to different scenes, and the method is not limited in the application.
Figure BDA0003317580930000091
Figure BDA0003317580930000092
Wherein x isjFor the elements in the data set X, j is 1, …, and n, i is a constant, and an appropriate number is selected according to the scene and experience, which is not limited in the present application. Equation (1) is the standard deviation of the hyperbolic inverse sinusoid of data set X, and equation (2) is the arctangent standard deviation of data set X.
And 104, determining the residual service life of the equipment according to the trend sequence corresponding to the vibration characteristics on the target dimension.
The device life prediction apparatus executing the process of step 104 may, for example, input the trend data of each time point in the trend sequence into a life prediction model trained in advance, and determine the trend data of each time point in the future; determining a target future time point when the corresponding trend data reaches a fault trend threshold value corresponding to the target dimension; and determining the remaining service life according to the target future time point and the preset time period.
The method for predicting the service life of the equipment provided by the embodiment of the application comprises the steps of determining a vibration data sequence and a corresponding characteristic data sequence of the equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions; determining an eigen-mode data sequence and a trend sequence corresponding to the vibration characteristics on each dimension based on the characteristic data sequence; selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions; according to the trend sequence corresponding to the vibration characteristics on the target dimension, the residual service life of the equipment is determined, the maintenance cost of the equipment is reduced, the use safety and reliability of the equipment are improved, and meanwhile, the fault removal rate is improved.
As a possible implementation manner of the embodiment of the present application, the method for predicting the service life of the device provided by the present application is further described with reference to fig. 2.
Fig. 2 is a schematic flowchart of another device life prediction method according to an embodiment of the present disclosure. As shown in fig. 2, the specific steps are as follows:
step 201, determining evaluation parameter information corresponding to the dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics of the dimension for each dimension.
The evaluation parameter information is a total number value obtained by weighted summation of values of a preset number of evaluation parameters corresponding to the dimensionality; the evaluation parameters include at least one of the following parameters: correlation, single scheduling, and robustness.
Step 202, selecting a target dimension based on the evaluation parameter information corresponding to the plurality of dimensions.
In the embodiment of the application, according to a total numerical value obtained by weighted summation of values of a preset number of evaluation parameters corresponding to the dimensionality, the dimensionality with the maximum corresponding total numerical value is selected to be determined as the target dimensionality.
According to the equipment life prediction method, for each dimension, evaluation parameter information corresponding to the dimension is determined based on an eigenmode data sequence and a trend sequence corresponding to vibration characteristics on the dimension; based on the evaluation parameter information corresponding to the multiple dimensions, the target dimension is selected, the maintenance cost of the equipment is reduced, the use safety and reliability of the equipment are improved, and meanwhile, the fault removal rate is improved.
As a possible implementation manner of the embodiment of the present application, with reference to fig. 3, another device Life prediction method provided by the present application is illustrated, where collected data may be processed by collecting data, and Remaining Life is output by modeling with RUL (Remaining Useful Life), and a flowchart of the another device Life prediction method provided by the embodiment of the present application is shown in fig. 3.
In the embodiment of the present application, taking an optimal metric algorithm as an example, the collected data is processed, and in order to evaluate the optimal metric of the feature data, first, the degradation value of the feature parameter is separated, for example, a smoothing method may be used, as shown in formula (3).
X(tk)＝XT(tk)+XR(tk) (3)
Wherein, X (t)k) Is tkDegradation value at time, XT(tk) Is a trend value, XR(tk) Is the remaining value.
In the embodiment of the present application, the optimal metric algorithm may include at least one of the following evaluation parameters: correlation (Corr), single scheduling (Mon), robustness (robustness, Rob). As shown in equation (4), equation (5) and equation (6).
Figure BDA0003317580930000111
Figure BDA0003317580930000112
Figure BDA0003317580930000113
Wherein, K is the total number of observation time, T is the set of all observation times, δ () is a simple unit transition function (simple unit step function), which has mature function and can be directly called.
In the embodiment of the present application, taking an optimal metric algorithm as an example, after processing collected data, when performing RUL on optimal metric values of a large number of obtained feature parameters, all parameters need to be selected, and the most effective data is selected. Can be obtained from equation (7).
Figure BDA0003317580930000121
Where J is the objective function and Ω is all the candidate featuresTotal set, ωiWeights for three evaluation parameters. Finally, the maximum value J is calculated, and the maximum value J is the maximum value of the characteristic parameter.
In the embodiment of the present application, the trend analysis is performed based on the parameter of the maximum value J, and for example, the trend analysis may be performed by using a linear regression method, a polynomial regression method, a neural network model, or the like. If a plurality of parameters with larger J values are selected, all characteristic parameters can be fused, for example, DS evidence theory (also called DS theory) and LSTM (Long Short Term Memory network) can be used for fusion, and then regression analysis is performed on the fusion. Wherein t is corresponded based on the parameterkThe value of the time can be subjected to regression analysis.
In the embodiment of the application, the characteristic parameters and the values at the corresponding moments are trained, finally, the equipment degradation value at the future moment is predicted through the input of real-time data, when the degradation value reaches a preset degradation alarm threshold value at a future moment, an alarm is given in advance, the predicted moment is output as a result, and the residual service life of the equipment is obtained.
According to the equipment service life prediction method, the collected data are processed through the collected data, the residual service life is output through RUL modeling, the maintenance cost of the equipment is reduced, the use safety and reliability of the equipment are improved, and meanwhile the fault removal rate is improved.
Based on the above example, an exemplary implementation of training the co-trained models may be that all data is distributed to different machines, each machine downloads the models from a server, then training the model using local data, then returning to the server the parameters that need to be updated, the server aggregating the returned parameters on each machine, updating the model, and then feeding back the latest model to each machine, as shown in fig. 4, which illustrates, as follows, that each of the participants downloads the latest model from server a, and the participators use the local data to train the model, encrypt the gradient and upload to the server A, the server A gathers the gradient of each user to update the model parameter, the server A returns the updated model to each participator, the more the number of the participants is, the more the samples of the models in the server are, the stronger the adaptability of the models is, and finally, each participant updates the respective model.
The application provides an equipment service life prediction method, which comprises the steps of determining a vibration data sequence and a corresponding characteristic data sequence of equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions; determining an eigen-mode data sequence and a trend sequence corresponding to the vibration characteristics on each dimension based on the characteristic data sequence; selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions; according to the trend sequence corresponding to the vibration characteristics on the target dimension, the residual service life of the equipment is determined, the maintenance cost of the equipment is reduced, the use safety and reliability of the equipment are improved, and meanwhile, the fault removal rate is improved.
Corresponding to the device life prediction methods provided by the above several embodiments, an embodiment of the present application further provides a device life prediction apparatus. Since the device life prediction apparatus provided in the embodiments of the present application corresponds to the device life prediction methods provided in the foregoing several embodiments, the implementation of the device life prediction method is also applicable to the device life prediction apparatus provided in the embodiments, and will not be described in detail in the embodiments.
Fig. 5 is a schematic structural diagram of an apparatus life prediction device according to an embodiment of the present application.
As shown in fig. 5, the device life prediction apparatus 50 may include: a first determining module 51, a second determining module 52, a selecting module 53 and a third determining module 54.
The first determining module 51 is configured to determine a vibration data sequence of the device to be predicted within a preset time period and a corresponding characteristic data sequence; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions;
a second determining module 52, configured to determine, based on the feature data sequence, an eigen-mode data sequence and a trend sequence corresponding to the vibration feature in each dimension;
a selection module 53, configured to select a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration features in multiple dimensions;
and a third determining module 54, configured to determine the remaining service life of the device according to the trend sequence corresponding to the vibration feature in the target dimension.
As a possible implementation manner of the embodiment of the present application, the first determining module 51 is specifically configured to,
acquiring a vibration data sequence of equipment to be detected in a preset time period;
determining the type of the equipment and vibration characteristics of multiple dimensions corresponding to the type;
performing feature extraction processing on vibration data corresponding to each time point in the vibration data sequence based on the vibration data and the vibration data in a preset sub-time period before the time point, and determining vibration features of multiple dimensions of the time point;
and determining a characteristic data sequence based on the vibration characteristics of multiple dimensions of each time point.
As another possible implementation manner of the embodiment of the present application, the second determining module 52 is specifically configured to,
determining a characteristic sequence corresponding to vibration characteristics on each dimension and an eigenmode data sequence based on the characteristic data sequence aiming at each dimension;
and determining a trend sequence in the dimension based on the characteristic sequence corresponding to the vibration characteristics in the dimension and the eigenmode data sequence.
As another possible implementation manner of the embodiment of the present application, the selecting module 53 is specifically configured to,
for each dimension, determining evaluation parameter information corresponding to the dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the dimension;
and selecting the target dimension based on the evaluation parameter information corresponding to the plurality of dimensions.
As another possible implementation manner of the embodiment of the application, the evaluation parameter information is a total number value obtained by weighted summation of values of a preset number of evaluation parameters corresponding to the dimensionality; the evaluation parameters include at least one of the following parameters: relevance, single scheduling and robustness;
the selecting module 53 is specifically configured to select the dimension with the largest total number value as the target dimension.
As another possible implementation manner of the embodiment of the present application, the third determining module 54 is specifically configured to,
inputting the trend data of each time point in the trend sequence into a pre-trained life prediction model, and determining the trend data of each time point in the future;
determining a target future time point when the corresponding trend data reaches a fault trend threshold value corresponding to the target dimension;
and determining the remaining service life according to the target future time point and the preset time period.
The device life prediction device provided by the embodiment of the application determines the vibration data sequence and the corresponding characteristic data sequence of the device to be detected in the preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions; determining an eigen-mode data sequence and a trend sequence corresponding to the vibration characteristics on each dimension based on the characteristic data sequence; selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions; according to the trend sequence corresponding to the vibration characteristics on the target dimension, the residual service life of the equipment is determined, the maintenance cost of the equipment is reduced, the use safety and reliability of the equipment are improved, and meanwhile, the fault removal rate is improved.
In order to implement the foregoing embodiments, the present application further provides an electronic device, and fig. 6 is a schematic structural diagram of the electronic device provided in the embodiments of the present application. The electronic device includes:
memory 1001, processor 1002, and computer programs stored on memory 1001 and executable on processor 1002.
The processor 1002, when executing the program, implements the device life prediction method provided in the above-described embodiment.
Further, the electronic device further includes:
a communication interface 1003 for communicating between the memory 1001 and the processor 1002.
A memory 1001 for storing computer programs that may be run on the processor 1002.
Memory 1001 may include high-speed RAM memory and may also include non-volatile memory (e.g., at least one disk memory).
The processor 1002 is configured to implement the device life prediction method according to the foregoing embodiment when executing the program.
If the memory 1001, the processor 1002, and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001, and the processor 1002 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 6, but this is not intended to represent only one bus or type of bus.
Optionally, in a specific implementation, if the memory 1001, the processor 1002, and the communication interface 1003 are integrated on one chip, the memory 1001, the processor 1002, and the communication interface 1003 may complete communication with each other through an internal interface.
The processor 1002 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
In order to implement the foregoing embodiments, the present application further proposes a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the device life prediction method provided in the foregoing embodiments.
In order to implement the foregoing embodiments, the present application further provides a computer program product, which when executed by an instruction processor in the computer program product, implements the device lifetime prediction method provided in the foregoing embodiments.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (14)

1. A method for predicting a lifetime of a device, comprising:
determining a vibration data sequence and a corresponding characteristic data sequence of equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions;
determining an eigen-mode data sequence and a trend sequence corresponding to the vibration characteristics in each dimension based on the characteristic data sequence;
selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions;
and determining the residual service life of the equipment according to the trend sequence corresponding to the vibration characteristics on the target dimension.
2. The method according to claim 1, wherein the determining the vibration data sequence and the corresponding characteristic data sequence of the device to be detected within a preset time period comprises:
acquiring a vibration data sequence of the equipment to be detected in a preset time period;
determining the type of the equipment and vibration characteristics of multiple dimensions corresponding to the type;
performing feature extraction processing on vibration data corresponding to each time point in the vibration data sequence based on the vibration data and the vibration data in a preset sub-time period before the time point, and determining the vibration features of the multiple dimensions of the time point;
determining the characteristic data sequence based on the vibration characteristics of the plurality of dimensions at each time point.
3. The method of claim 1, wherein determining a sequence of eigenmode data and a sequence of trends for the vibration signature in each dimension based on the sequence of signature data comprises:
for each dimension, determining a characteristic sequence corresponding to the vibration characteristics on the dimension and an eigenmode data sequence based on the characteristic data sequence;
and determining a trend sequence on the dimension based on the characteristic sequence corresponding to the vibration characteristics on the dimension and the eigenmode data sequence.
4. The method of claim 1, wherein selecting the target dimension based on the eigenmode data sequences corresponding to the vibration features in the plurality of dimensions and the trend sequence comprises:
for each dimension, determining evaluation parameter information corresponding to the dimension based on an eigenmode data sequence and a trend sequence corresponding to the vibration characteristics on the dimension;
and selecting the target dimension based on the evaluation parameter information corresponding to the plurality of dimensions.
5. The method according to claim 4, wherein the evaluation parameter information is a total number value obtained by weighted summation of values of a preset number of evaluation parameters corresponding to the dimension; the evaluation parameter includes at least one of the following parameters: relevance, single scheduling and robustness;
selecting the target dimension based on the evaluation parameter information corresponding to the plurality of dimensions includes:
and selecting the dimension with the maximum corresponding total number value to be determined as the target dimension.
6. The method of claim 1, wherein determining the remaining service life of the device according to the trend sequence corresponding to the vibration feature in the target dimension comprises:
inputting the trend data of each time point in the trend sequence into a pre-trained life prediction model, and determining the trend data of each time point in the future;
determining a target future time point when the corresponding trend data reaches a fault trend threshold value corresponding to the target dimension;
and determining the residual service life according to the target future time point and the preset time period.
7. An apparatus for predicting a lifetime of a device, comprising:
the device comprises a first determining module, a second determining module and a judging module, wherein the first determining module is used for determining a vibration data sequence and a corresponding characteristic data sequence of equipment to be detected in a preset time period; wherein each feature data in the feature data sequence comprises vibration features in a plurality of dimensions;
the second determination module is used for determining an eigen module data sequence and a trend sequence corresponding to the vibration characteristics in each dimension based on the characteristic data sequence;
the selection module is used for selecting a target dimension based on the eigenmode data sequence and the trend sequence corresponding to the vibration characteristics on the multiple dimensions;
and the third determining module is used for determining the residual service life of the equipment according to the trend sequence corresponding to the vibration characteristics on the target dimension.
8. The apparatus of claim 7, wherein the first determining module is specifically configured to,
acquiring a vibration data sequence of the equipment to be detected in a preset time period;
determining the type of the equipment and vibration characteristics of multiple dimensions corresponding to the type;
performing feature extraction processing on vibration data corresponding to each time point in the vibration data sequence based on the vibration data and the vibration data in a preset sub-time period before the time point, and determining the vibration features of the multiple dimensions of the time point;
determining the characteristic data sequence based on the vibration characteristics of the plurality of dimensions at each time point.
9. The apparatus of claim 7, wherein the second determining module is specifically configured to,
for each dimension, determining a characteristic sequence corresponding to the vibration characteristics on the dimension and an eigenmode data sequence based on the characteristic data sequence;
and determining a trend sequence on the dimension based on the characteristic sequence corresponding to the vibration characteristics on the dimension and the eigenmode data sequence.
10. The apparatus according to claim 7, characterized in that the selection module is specifically configured to,
for each dimension, determining evaluation parameter information corresponding to the dimension based on an eigenmode data sequence and a trend sequence corresponding to the vibration characteristics on the dimension;
and selecting the target dimension based on the evaluation parameter information corresponding to the plurality of dimensions.
11. The apparatus according to claim 10, wherein the evaluation parameter information is a total number value obtained by weighted summation of values of a preset number of evaluation parameters corresponding to the dimension; the evaluation parameter includes at least one of the following parameters: relevance, single scheduling and robustness;
the selection module is specifically configured to select the dimension with the largest total number value to determine the dimension as the target dimension.
12. The apparatus of claim 7, wherein the third determination module is specifically configured to,
inputting the trend data of each time point in the trend sequence into a pre-trained life prediction model, and determining the trend data of each time point in the future;
determining a target future time point when the corresponding trend data reaches a fault trend threshold value corresponding to the target dimension;
and determining the residual service life according to the target future time point and the preset time period.
13. An electronic device, comprising:
memory, processor and computer program stored on the memory and executable on the processor, the processor implementing the device lifetime prediction method according to any of claims 1-6 when executing the program.
14. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the device lifetime prediction method of any one of claims 1-6.
CN202111235647.9A 2021-10-22 2021-10-22 Equipment life prediction method and device, electronic equipment and storage medium Pending CN114091238A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111235647.9A CN114091238A (en) 2021-10-22 2021-10-22 Equipment life prediction method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111235647.9A CN114091238A (en) 2021-10-22 2021-10-22 Equipment life prediction method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114091238A true CN114091238A (en) 2022-02-25

Family

ID=80297798

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111235647.9A Pending CN114091238A (en) 2021-10-22 2021-10-22 Equipment life prediction method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114091238A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115655764A (en) * 2022-10-27 2023-01-31 圣名科技(广州)有限责任公司 Vibration trend analysis method and device, electronic equipment and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115655764A (en) * 2022-10-27 2023-01-31 圣名科技(广州)有限责任公司 Vibration trend analysis method and device, electronic equipment and storage medium
CN115655764B (en) * 2022-10-27 2023-08-25 圣名科技(广州)有限责任公司 Vibration trend analysis method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN109239075B (en) Battery detection method and device
CN111427753B (en) Capacity prediction device based on ARIMA model and control method thereof
JP7003159B2 (en) Failure prediction system and failure prediction method
JP6815480B2 (en) Methods and systems for discovering precursor substrings in time series
CN107480028B (en) Method and device for acquiring usable residual time of disk
CN114021784A (en) Method and device for determining residual service life of equipment and electronic equipment
CN108009692A (en) Maintenance of equipment information processing method, device, computer equipment and storage medium
CN110688617B (en) Fan vibration abnormity detection method and device
JP6711323B2 (en) Abnormal state diagnosis method and abnormal state diagnosis device
CN113868953B (en) Multi-unit operation optimization method, device and system in industrial system and storage medium
CN110837852A (en) Fault diagnosis method and device for rolling mill gearbox and terminal equipment
WO2023169274A1 (en) Data processing method and device, and storage medium and processor
CN109643087B (en) System and method for selecting controllable parameters for operational safety of a device
CN114091238A (en) Equipment life prediction method and device, electronic equipment and storage medium
KR101960755B1 (en) Method and apparatus of generating unacquired power data
CN117076258A (en) Remote monitoring method and system based on Internet cloud
CN114021744A (en) Method and device for determining residual service life of equipment and electronic equipment
KR102110319B1 (en) System for generating learning data
CN113593074B (en) Method and device for generating monitoring video
CN114881321A (en) Mechanical component failure prediction method, device, electronic device and storage medium
CN114117734A (en) Equipment life detection method and device, electronic equipment and storage medium
JP6627258B2 (en) System model generation support device, system model generation support method, and program
CN114083987A (en) Battery monitoring parameter correction method and device and computer equipment
CN112798949A (en) Pumped storage unit generator temperature early warning method and system
CN116579573B (en) Electromechanical spare part guarantee analysis method meeting maintenance requirements

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