Device life prediction method and device, equipment and storage medium

Abstract

The invention relates to a device life prediction method and device, equipment and a storage medium, and the method comprises the steps: obtaining the historical use data of a to-be-predicted device, and enabling the historical use data to be historical data representing the operation state of the to-be-predicted device; determining a current feature value of the target statistical feature of the historical use data; and predicting the residual service life of the to-be-predicted device based on the current characteristic value and the failure threshold value of the target statistical characteristic. The service life prediction of each to-be-predicted device is based on the own historical use data, and the sensitivity of the target statistical characteristics to the degradation degree of the device makes the device more suitable for the prediction of the remaining service life, so that the prediction result is closer to the real result, the prediction deviation and the maintenance lag occurrence rate are reduced, the product yield is improved, and the product quality is improved. And the productivity loss is reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent manufacturing, and in particular to a device life prediction method, device, equipment and storage medium. Background Art

[0002] In recent years, with the accelerated development of computer, communication and consumer electronic products (referred to as 3C electronic products), many new intelligent manufacturing models that can be replicated and promoted have gradually been formed. For key components of product production and processing equipment, it is usually necessary to predict the remaining service life to guide the maintenance and use of the components.

[0003] However, when using the prediction method of related technology to predict the remaining service life of a device, there is a problem of large deviation between the predicted result and the actual result, which will lead to delayed device maintenance, insufficient effectiveness, low product production yield and high production capacity loss. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a device lifetime prediction method, apparatus, equipment and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a device lifetime prediction method is provided, the device lifetime prediction method comprising:

[0006] Acquire historical usage data of the device to be predicted, wherein the historical usage data is historical data characterizing the device operation status of the device to be predicted;

[0007] determining a current characteristic value of a target statistical characteristic of the historical usage data;

[0008] Based on the current feature value and the failure threshold of the target statistical feature, the remaining service life of the component to be predicted is predicted.

[0009] In some embodiments of the present disclosure, determining a current feature value of a target statistical feature of the historical usage data includes:

[0010] Based on the historical usage data, construct a characteristic function, wherein the characteristic function is used to characterize the relationship between the number of operations of the device to be predicted and the characteristic value of the target statistical feature;

[0011] Based on the characteristic function and the current operation times of the component to be predicted, a current characteristic value corresponding to the target statistical characteristic is determined.

[0012] In some embodiments of the present disclosure, constructing a feature function based on the historical usage data includes:

[0013] Preprocessing the historical usage data to obtain a first data set, wherein the first data set includes a plurality of first data groups, each of which includes target force data of a single operation of the component to be predicted;

[0014] Determining an initial characteristic value, a degradation parameter, and a fluctuation parameter based on the target statistical characteristic and the first data set;

[0015] The characteristic function is constructed based on the initial characteristic value, the degradation parameter and the fluctuation parameter.

[0016] In some embodiments of the present disclosure, the predicting the remaining useful life of the component to be predicted based on the current feature value and the failure threshold of the target statistical feature includes:

[0017] Determining a remaining useful life probability density based on the current characteristic value, the failure threshold, the degradation parameter, and the fluctuation parameter;

[0018] Based on the remaining useful life probability density, the remaining useful life is determined.

[0019] In some embodiments of the present disclosure, the historical usage data includes a plurality of second data groups, each of which includes original force data of a single operation of the device to be predicted, and the preprocessing of the historical usage data to obtain the first data set includes:

[0020] Resampling each of the second data groups to obtain a plurality of third data groups, wherein the number of data in each of the third data groups is the same;

[0021] Differentiating the data in each of the third data groups to obtain a plurality of fourth data groups;

[0022] The absolute value of each data in the fourth data group is taken to obtain the first data set.

[0023] In some embodiments of the present disclosure, determining the initial characteristic value, the degradation parameter and the fluctuation parameter based on the target statistical feature and the first data set includes:

[0024] Based on the first data set, determining a characteristic value of the target statistical characteristic corresponding to each of the first data groups;

[0025] Determine the eigenvalue corresponding to the first data group of the first group as the initial eigenvalue;

[0026] The degradation parameter and the fluctuation parameter are determined based on the initial characteristic values ​​corresponding to each of the first data groups.

[0027] In some embodiments of the present disclosure, before determining the current characteristic value of the target statistical characteristic of the historical usage data, the device life prediction method further includes:

[0028] Acquiring sample data, wherein the sample data includes historical usage data of the failed device;

[0029] Based on the sample data, the target statistical feature and a failure threshold of the target statistical feature are determined.

[0030] In some embodiments of the present disclosure, determining the target statistical feature and the failure threshold of the target statistical feature based on the sample data includes:

[0031] Preprocessing the sample data to obtain a second data set, wherein the second data set includes a plurality of fifth data groups, each of the fifth data groups includes target force data of a single operation of the failed device;

[0032] Based on the second data set, determining characteristic values ​​of a plurality of statistical characteristics corresponding to each of the fifth data groups;

[0033] determining the target statistical feature based on feature values ​​of a plurality of statistical features corresponding to each of the fifth data groups;

[0034] The failure threshold is determined based on the target statistical feature.

[0035] In some embodiments of the present disclosure, the sample data includes a plurality of sixth data groups, each of the sixth data groups includes original force data of a single operation of the failed device, and the preprocessing of the sample data to obtain the second data set includes:

[0036] Resampling each of the sixth data groups to obtain a plurality of seventh data groups, wherein the number of data in each of the seventh data groups is the same;

[0037] Differentiating the data in each of the seventh data groups to obtain a plurality of eighth data groups;

[0038] The absolute value of each data in the eighth data group is taken to obtain the second data set.

[0039] In some embodiments of the present disclosure, determining the target statistical feature based on the feature values ​​of the plurality of statistical features corresponding to each of the fifth data groups includes:

[0040] Determining a plurality of evaluation index values ​​corresponding to each of the statistical features based on the feature values ​​of the plurality of statistical features corresponding to each of the fifth data groups;

[0041] The target statistical feature is determined based on the multiple evaluation index values ​​corresponding to each of the statistical features.

[0042] In some embodiments of the present disclosure, the multiple evaluation index values ​​include a trend index value, a monotonicity index value, and a robustness index value, and the determining the target statistical feature based on the multiple evaluation index values ​​corresponding to each of the statistical features includes:

[0043] Determine a trend index mean, a monotonicity index mean, and a robustness index mean based on the trend index value, the monotonicity index value, and the robustness index value corresponding to each of the statistical features;

[0044] Based on the trend index value, the monotonicity index value and the robustness index value corresponding to each of the statistical features, determine the total value of the evaluation index corresponding to each of the statistical features, the total value of the evaluation index being the sum of the trend index value, the monotonicity index value and the robustness index value corresponding to each of the statistical features;

[0045] The statistical feature whose trend index value, monotonicity index value and robustness index value are respectively greater than the trend index mean value, the monotonicity index mean value and the robustness index mean value and whose total value of the evaluation index is the largest is determined as the target statistical feature.

[0046] In some embodiments of the present disclosure, the multiple statistical features include a combination of any multiple of multiple time domain features and / or multiple frequency domain features.

[0047] According to a second aspect of an embodiment of the present disclosure, a device lifetime prediction apparatus is provided, the device lifetime prediction apparatus comprising:

[0048] A first acquisition module, the first acquisition module is used to acquire historical usage data of the device to be predicted, wherein the historical usage data is historical data representing the device operation status of the device to be predicted;

[0049] a first determining module, the first determining module being used to determine a current feature value of a target statistical feature of the historical usage data;

[0050] A second determination module is used to predict the remaining useful life of the component to be predicted based on the current feature value and the failure threshold of the target statistical feature.

[0051] According to a third aspect of an embodiment of the present disclosure, a device lifetime prediction apparatus is provided, the device lifetime prediction apparatus comprising:

[0052] processor;

[0053] a memory for storing processor-executable instructions;

[0054] Wherein, the processor is configured to:

[0055] Acquire historical usage data of the device to be predicted, wherein the historical usage data is historical data characterizing the device operation status of the device to be predicted;

[0056] determining a current characteristic value of a target statistical characteristic of the historical usage data;

[0057] Based on the current feature value and the failure threshold of the target statistical feature, the remaining service life of the component to be predicted is predicted.

[0058] According to a fourth aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of a device life prediction device, the device life prediction device is enabled to perform a device life prediction method. The device life prediction method includes:

[0059] Acquire historical usage data of the device to be predicted, wherein the historical usage data is historical data characterizing the device operation status of the device to be predicted;

[0060] determining a current characteristic value of a target statistical characteristic of the historical usage data;

[0061] Based on the current feature value and the failure threshold of the target statistical feature, the remaining service life of the component to be predicted is predicted.

[0062] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by obtaining the historical usage data of the device to be predicted, determining the current characteristic value of the target statistical feature of the historical usage data, and then predicting the remaining service life of the device to be predicted based on the current characteristic value and the failure threshold of the target statistical feature, the prediction of the device life is achieved. The life prediction of each device to be predicted is based on its own historical usage data, and the sensitivity of the target statistical feature to the degree of device degradation makes it more suitable for the prediction of the remaining service life, so that the prediction result is closer to the actual result, reducing the prediction deviation and the occurrence rate of maintenance lag, improving the product yield, and reducing the loss of production capacity.

[0063] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0065] Figure 1 The figure is a flow chart of a device lifetime prediction method according to an exemplary embodiment.

[0066] Figure 2 The flowchart of determining a current feature value of a target statistical feature of historical usage data according to an exemplary embodiment is shown.

[0067] Figure 3 The flowchart of constructing a characteristic function based on historical usage data is shown according to an exemplary embodiment.

[0068] Figure 4 The present invention is a flowchart showing a method for predicting the remaining useful life of a component to be predicted based on a current feature value and a failure threshold of a target statistical feature according to an exemplary embodiment.

[0069] Figure 5 The present invention is a flowchart of preprocessing historical usage data to obtain a first data set according to an exemplary embodiment.

[0070] Figure 6 The present invention is a flowchart showing a method for determining an initial characteristic value, a degradation parameter and a fluctuation parameter based on a target statistical characteristic and a first data set according to an exemplary embodiment.

[0071] Figure 7 The figure is a flow chart of a device lifetime prediction method according to another exemplary embodiment.

[0072] Figure 8 It is a flowchart showing, according to an exemplary embodiment, determining a target statistical feature and a failure threshold of the target statistical feature based on sample data.

[0073] Fig. 9 The present invention is a flowchart of preprocessing sample data to obtain a second data set according to an exemplary embodiment.

[0074] Fig.10 The flowchart of determining a target statistical feature based on feature values ​​of a plurality of statistical features corresponding to each fifth data group is shown according to an exemplary embodiment.

[0075] Fig.11 The present invention is a flowchart of determining a target statistical feature based on a plurality of evaluation index values ​​corresponding to each statistical feature according to an exemplary embodiment.

[0076] Fig.12 is a comparison diagram of a predicted value of the remaining useful life and an actual value according to an exemplary embodiment.

[0077] Fig.13 The figure is a flow chart of a device lifetime prediction method according to another exemplary embodiment.

[0078] Fig.14 It is a block diagram of a device for predicting device lifetime according to an exemplary embodiment.

[0079] Fig.15 is a block diagram of a device for predicting device lifetime according to another exemplary embodiment.

[0080] Fig.16 The figure is a block diagram of a device for predicting device lifetime according to an exemplary embodiment.

[0081] In the figure:

[0082] 10-first acquisition module; 20-first determination module; 30-second determination module; 40-second acquisition module; 50-third determination module; 101-processing component; 102-memory; 103-power component; 104-multimedia component; 105-audio component; 106-input / output interface; 107-sensor component; 108-communication component; 109-processor. DETAILED DESCRIPTION

[0083] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0084] With the rapid development of 3C product manufacturing, some new intelligent manufacturing models that can be replicated and promoted have gradually been formed. They are advanced production models that achieve lean goals such as improving production quality and reliability, improving production efficiency and energy efficiency. For example, electronic products such as mobile phones are mostly made up of several small parts that are screwed together. Nowadays, automatic screw locking devices are mostly used to achieve fully automatic locking operations. As a key component of the automatic screw locking device, the remaining service life of the screw bit needs to be predicted to guide maintenance personnel to arrange maintenance operations.

[0085] In the related art, the actual number of times a device is operated is usually counted, and the difference between the actual number of times of operation and the permitted number of operations in the device's factory specification is subtracted, and the difference is used as the remaining service life prediction value of the device. However, the prediction method of the related art to predict the remaining service life of the device relies on the empirical summary of the permitted number of operations, and cannot take into account the external random factors and individual differences of each device during actual use. There is a significant deviation between the predicted results and the actual results, resulting in delayed maintenance based on the predicted results, insufficient effectiveness, low product production yield and high capacity loss.

[0086] Based on this, the exemplary embodiment of the present disclosure provides a device life prediction method, which realizes the prediction of device life by obtaining the historical usage data of the device to be predicted, determining the current characteristic value of the target statistical feature of the historical usage data, and then predicting the remaining service life of the device to be predicted based on the current characteristic value and the failure threshold of the target statistical feature. The life prediction of each device to be predicted is based on its own historical usage data, and the sensitivity of the target statistical feature to the degree of device degradation makes it more suitable for the prediction of the remaining service life, so that the prediction result is closer to the actual result, reducing the prediction deviation and the occurrence rate of maintenance lag, improving the product yield, and reducing the production capacity loss.

[0087] In an exemplary embodiment, reference Figure 1 As shown, a device life prediction method is provided, and the device life prediction method includes:

[0088] S100: Acquire historical usage data of a component to be predicted, where the historical usage data is historical data representing an operating status of the component to be predicted.

[0089] In step S100, the device to be predicted may be, for example, a key device for producing equipment such as processing and assembly, and the device to be predicted may have performance degradation such as wear under high-frequency use operations. The historical usage data of the device to be predicted is at least part of the usage data from the time the device to be predicted is put into use to the current moment. The historical usage data may be all the usage data of the device to be predicted, or may be part of the data extracted from all the usage data by, for example, interval sampling, and may characterize the device operating state of the device to be predicted. Exemplarily, the historical usage data may be force data such as torque and pressure that can characterize the device operating state during the use of the device to be predicted, or may be other high-frequency data such as vibration, current, sound, etc. that can reflect the device operating state during the use of the device to be predicted.

[0090] S200: Determine a current feature value of a target statistical feature of historical usage data.

[0091] In step S200, the historical usage data has a variety of statistical features that can characterize its data and attribute characteristics. The target statistical feature can be, for example, a statistical feature extracted from many statistical features. Each statistical feature can represent a data calculation method and can reflect the characteristics associated with the historical usage data. Exemplarily, the target statistical feature can be, for example, any one of the statistical features such as mean, standard deviation, and root mean square. The target statistical feature can, for example, have a strong trend, monotonicity, and small volatility, so as to be suitable for the prediction of the remaining service life and be more sensitive to the degree of degradation of the device to be predicted. The target statistical feature can, for example, be determined in the device life prediction process, and can also be set in advance before the device life prediction.

[0092] The current characteristic value of the target statistical characteristic of the historical usage data can be determined according to the historical usage data and the target statistical characteristic, and the current characteristic value is the characteristic value of the target statistical characteristic at the current time or the current number of operations. The current characteristic value can be directly represented by a numerical value, or indirectly represented by assigning a value to a function.

[0093] S300: predicting the remaining useful life of the component to be predicted based on the current characteristic value and the failure threshold of the target statistical characteristic.

[0094] In step S300, the target statistical feature has a corresponding failure threshold, and the device fails after the characteristic value representing the target statistical feature reaches the failure threshold. The failure threshold can be determined, for example, during the device life prediction process, or can be determined in advance before the device life prediction. Based on the current characteristic value and the failure threshold, the remaining service life of the device to be predicted can be predicted, and the remaining service life of the device to be predicted can be, for example, the remaining use time or the remaining number of uses.

[0095] In this embodiment, the prediction of device life is achieved by obtaining the historical usage data of the device to be predicted, determining the current characteristic value of the target statistical feature of the historical usage data, and then predicting the remaining service life of the device to be predicted based on the current characteristic value and the failure threshold of the target statistical feature. The life prediction of each device to be predicted is based on its own historical usage data, and the sensitivity of the target statistical feature to the degree of device degradation makes it more suitable for the prediction of the remaining service life. It fully considers the external random factors and individual differences of the device to be predicted during actual use, so that the prediction result is closer to the real result, reduces the prediction deviation and maintenance lag occurrence rate, improves the product yield, and reduces the production capacity loss.

[0096] In some embodiments, reference Figure 2 As shown, the current characteristic value of the target statistical characteristic of the historical usage data is determined, including:

[0097] S210 . Construct a characteristic function based on the historical usage data, where the characteristic function is used to characterize the relationship between the number of operations of the device to be predicted and the characteristic value of the target statistical characteristic.

[0098] In step S210, a characteristic function is constructed based on the historical usage data. Where t represents the number of operations of the device to be predicted, and the characteristic function The relationship between the number of operations of the device to be predicted and the characteristic value of the target statistical feature is used as the degradation model of the device to be predicted.

[0099] S220: Determine a current feature value corresponding to the target statistical feature based on the feature function and the current operation times of the component to be predicted.

[0100] In step S220, the characteristic function And the current operation number t1 of the device to be predicted, bring the current operation number t1 into the characteristic function In the above example, determine the current feature value corresponding to the target statistical feature

[0101] In this embodiment, a characteristic function is constructed based on historical usage data to characterize the relationship between the number of operations of the device to be predicted and the characteristic value of the target statistical feature, and the current characteristic value corresponding to the target statistical feature can be determined based on the characteristic function and the current number of operations of the device to be predicted, thereby achieving the determination of the current characteristic value and providing a basis for the subsequent prediction of the remaining service life of the device to be predicted. The construction of the characteristic function is based on the historical usage data of the device to be predicted itself, and the current characteristic value of the target statistical feature is determined based on the current number of operations of the device to be predicted, which fully considers the external random factors and individual differences of the device to be predicted during actual use, so that the determination of the current characteristic value is consistent with the usage of the device to be predicted itself and has a strong timeliness, thereby improving the prediction accuracy of the remaining service life of the device to be predicted.

[0102] In some embodiments, reference Figure 3 As shown, based on historical usage data, a feature function is constructed, including:

[0103] S211 , preprocess the historical usage data to obtain a first data set, where the first data set includes a plurality of first data groups, each of which includes target force data of a single operation of the component to be predicted.

[0104] In step S211, the historical usage data is preprocessed to enhance the fluctuation of different distribution characteristics of the historical usage data, and obtain a preprocessed first data set. The first data set includes multiple first data groups, each of which includes target force data for a single operation of the device to be predicted. For example, the number of first data groups can be the current operation number of the device to be predicted, and each first data group includes multiple target force data for a single operation of the device to be predicted. The target force data can be, for example, the torque data of the screw when the screwdriver is tightened with the screw.

[0105] S212: Determine initial eigenvalues, degradation parameters, and fluctuation parameters based on the target statistical characteristics and the first data set.

[0106] In step S212, based on the target statistical features and the first data set, an initial feature value is determined. Degeneration parameter v and fluctuation parameter σ, initial eigenvalue is the initial value corresponding to the target statistical feature, the degradation parameter v and the fluctuation parameter σ are the parameters describing the degradation rate and the volatility intensity respectively.

[0107] S213. Construct a characteristic function based on the initial eigenvalue, the degradation parameter and the fluctuation parameter.

[0108] In step S213, according to the initial eigenvalue The degradation parameter v and the fluctuation parameter σ can construct the characteristic function For example, the characteristic function Determined as the following formula:

[0109]

[0110] Among them, t and τ have the same actual meaning, both representing the number of operations of the device to be predicted, and B(t) is the standard Brownian motion formula. After determining the current number of operations t1 of the device to be predicted, the current number of operations t1 can be substituted into the characteristic function In the above example, determine the current feature value corresponding to the target statistical feature

[0111] In this embodiment, by preprocessing the historical usage data of the device to be predicted, the first data set can be obtained to combine and enhance the fluctuations of different distribution characteristics of the historical usage data. The initial characteristic value, degradation parameter and fluctuation parameter can be determined according to the target statistical characteristics and the first data set, and the characteristic function is constructed according to the initial characteristic value, degradation parameter and fluctuation parameter, so as to achieve the determination of the characteristic function and provide a basis for the subsequent determination of the current characteristic value corresponding to the target statistical characteristics. The parameters required for constructing the characteristic function are determined according to the first data set and the target statistical characteristics, and the external random factors and individual differences of the device to be predicted in the actual use process are fully considered, so that the determination of the current characteristic value is consistent with the use of the device to be predicted and has a strong timeliness, thereby improving the prediction accuracy of the remaining service life of the device to be predicted.

[0112] In some embodiments, reference Figure 4 As shown, based on the current characteristic value and the failure threshold of the target statistical characteristic, the remaining service life of the component to be predicted is predicted, including:

[0113] S310, determining the remaining useful life probability density based on the current characteristic value, failure threshold, degradation parameter and fluctuation parameter.

[0114] In step S310, the probability density of the remaining useful life can be determined according to the current characteristic value, failure threshold, degradation parameter and fluctuation parameter according to the random process theory. For example, the probability density of the remaining useful life f RUL (τ) is determined as follows:

[0115]

[0116] in, is the characteristic function of the current eigenvalue, Γ is the failure threshold, v and σ are the degradation parameter and fluctuation parameter respectively.

[0117] S320: Determine the remaining useful life based on the remaining useful life probability density.

[0118] In step S320, the remaining service life of the component to be predicted can be determined according to the remaining service life probability density, and the remaining service life of the component to be predicted is represented by the number of operations. For example, the remaining service life probability density can be expected, and the expected value is used as the remaining service life of the component to be predicted.

[0119] In this embodiment, the remaining service life probability density can be determined according to the current characteristic value, failure threshold, degradation parameter and fluctuation parameter, and the remaining service life of the device to be predicted can be obtained by calculating the expectation of the remaining service life probability density, thereby realizing the life prediction of the device. The remaining service life probability density is constructed based on the current characteristic value, failure threshold, degradation parameter and fluctuation parameter, and fully considers the external random factors and individual differences of the device to be predicted during actual use, so that the prediction result is closer to the real result, reduces the prediction deviation and maintenance lag occurrence rate, improves the product yield, and reduces the production capacity loss.

[0120] In some embodiments, the historical usage data includes a plurality of second data groups, each of which includes raw force data of a single operation of the device to be predicted. Figure 5 As shown, the historical usage data is preprocessed to obtain a first data set, including:

[0121] S211-1. Resample each second data group to obtain multiple third data groups, where the number of data in each third data group is the same.

[0122] In step S211-1, each second data group includes the original force data of a single operation of the device to be predicted. For example, each second data group can be, for example, the torque data of the screws when the same batch head is tightened each time. As the number of test points is different each time the screws are tightened, the number of data in each second data group is also different. Each second data group is resampled, and the resampling can include upsampling and downsampling, for example, upsampling can be performed on the second data group whose data quantity is less than the preset quantity, and downsampling can be performed on the second data group whose data quantity exceeds the preset quantity, so that the number of data in each second data group is the preset number, and multiple third data groups are obtained. The preset number can be, for example, the mean of the number of data in each second data group. For example, the preset number is 1800.

[0123] S211 - 2. Differentiate the data in each third data group to obtain multiple fourth data groups.

[0124] In step S211 - 2 , the data in each third data group is differentiated, that is, each data in each third data group is subtracted from the previous data, to obtain a plurality of fourth data groups corresponding to each third data group.

[0125] S211 - 3. Take the absolute value of the data in each fourth data group to obtain a first data set.

[0126] In step S211-3, the absolute value of the data in each fourth data group is taken to obtain the first data group corresponding to each fourth data group. The multiple first data groups constitute the first data set, and the conversion from the original force data to the target force data is completed. It can be understood that the above conversion process is for the data in each second data group, and the number of data groups is not changed. Each first data group, second data group, third data group and fourth data group corresponds to the data of each operation of the device to be predicted.

[0127] In this embodiment, each second data group is resampled, differentiated and averaged in turn, and the third data group, the fourth data group and the first data group are obtained in turn, the determination of the first data set is realized, and the conversion of the original force data of a single operation to the target force data is completed. By resampling each second data group, the deviation in the subsequent current characteristic value determination process can be reduced. By calculating the difference and the mean, the target force data of the screwdriver bits with different degrees of wear can more easily reflect different distribution characteristics, thereby improving the prediction accuracy of the remaining service life of the component to be predicted.

[0128] In some embodiments, reference Figure 6 As shown, based on the target statistical characteristics and the first data set, the initial characteristic value, the degradation parameter and the fluctuation parameter are determined, including:

[0129] S212-1. Based on the first data set, determine the characteristic value of the target statistical characteristic corresponding to each first data group.

[0130] In step S212 - 1 , based on the first data set, the feature value of the target statistical feature corresponding to each first data group is determined to form a feature value sequence with a sequence length equal to the number of first data groups.

[0131] S212-2. Determine the eigenvalue corresponding to the first data group as the initial eigenvalue.

[0132] In step S212-2, the eigenvalue corresponding to the first group of the first data group, that is, the first eigenvalue in the eigenvalue sequence, is determined as the initial eigenvalue The initial eigenvalues ​​are realized of determination.

[0133] S212-3. Determine degradation parameters and fluctuation parameters based on the characteristic values ​​corresponding to each first data group.

[0134] In step S212-3, the degradation parameter v and the fluctuation parameter σ are determined according to the eigenvalues ​​corresponding to each first data group, that is, the eigenvalue sequence. For example, the estimated value of the degradation parameter can be obtained by maximum likelihood estimation. and the estimated values ​​of the volatility parameters and the estimated value of the degradation parameter and the estimated values ​​of the volatility parameters As the degradation parameter v and fluctuation parameter σ respectively. The estimated value of the degradation parameter can be Determined as the following formula:

[0135]

[0136] And the estimated value of the volatility parameter Determined as the following formula:

[0137]

[0138] in, represents a differential sequence obtained by differentiating the characteristic values ​​corresponding to each first data group, that is, the characteristic value sequence, and its sequence length is N. Δt represents the acquisition interval of the characteristic values ​​corresponding to each first data group. Since each first data group corresponds to the target force data of each operation of the device to be predicted, that is, Δt=1, for Any element in

[0139] In this embodiment, by determining the characteristic value of the target statistical characteristic corresponding to each first data group, the characteristic value corresponding to the first data group can be determined as the initial characteristic value, and the degradation parameter and the fluctuation parameter are determined according to the characteristic value corresponding to each first data group, so that the initial characteristic value, the degradation parameter and the fluctuation parameter are determined, and the basis is provided for the subsequent construction of the characteristic function and the determination of the current characteristic value. The initial characteristic value, the degradation parameter and the fluctuation parameter are all determined according to the first data set, and the external random factors and the individual differences of the predicted device in the actual use process are fully considered, so that the determination of the current characteristic value is in line with the use of the predicted device itself and has a strong timeliness, thereby improving the prediction accuracy of the remaining service life of the predicted device.

[0140] In some embodiments, reference Figure 7 As shown, before determining the current characteristic value of the target statistical characteristic of the historical usage data, the device life prediction method further includes:

[0141] S400: Obtain sample data, where the sample data includes historical usage data of failed components.

[0142] In step S400, historical usage data of the failed device is obtained. The failed device may be, for example, a device of the same type and model as the device to be predicted, so that the service life of the failed device can reflect the service life of the device to be predicted to a certain extent. The historical usage data of the failed device is at least part of the usage data from the time the failed device is put into use to the time of failure. The historical usage data may be all usage data of the failed device, or may be part of the data extracted from all usage data by, for example, interval sampling, etc., which can characterize the device operating state of the failed device. Exemplarily, the historical usage data may be force data such as torque and pressure during the use of the failed device that can characterize the device operating state, or may be other high-frequency data such as vibration, current, sound, etc. during the use of the device to be predicted that can reflect the device operating state. The type of historical usage data of the failed device is the same as the type of historical usage data of the device to be predicted.

[0143] S500: Determine target statistical features and failure thresholds of the target statistical features based on sample data.

[0144] In step S500, target statistical features and failure thresholds of target statistical features suitable for life prediction can be determined based on sample data, providing a basis for subsequently determining the current feature value of the target statistical feature and the failure threshold based on the current feature value and the target statistical feature to predict the remaining service life of the component to be predicted.

[0145] In this embodiment, by obtaining sample data including historical usage data of failed devices, the target statistical features and the failure threshold of the target statistical features can be determined according to the sample data, providing a determined target statistical feature and failure threshold for the subsequent life prediction process. The target statistical features and failure threshold determined according to the sample data of the failed device can make the target statistical features applicable to the remaining service life prediction of the device to be predicted, and the failure threshold can characterize the threshold of the target statistical feature value corresponding to the failure of the same device, so that the prediction result is closer to the actual failure situation of the same device, and thus the prediction result is closer to the real result, reducing the prediction deviation and the occurrence rate of maintenance lag, improving the product yield, and reducing the production capacity loss.

[0146] In some embodiments, reference Figure 8 As shown, based on the sample data, the target statistical features and the failure threshold of the target statistical features are determined, including:

[0147] S510 , preprocessing the sample data to obtain a second data set, where the second data set includes a plurality of fifth data groups, each of which includes target force data of a single operation of the failed device.

[0148] In step S510, the sample data is preprocessed to enhance the fluctuation of different distribution characteristics of the sample data, and a preprocessed second data set is obtained. The second data set includes a plurality of fifth data groups, each of which includes target force data of a single operation of a failed device. Exemplarily, the number of fifth data groups may be, for example, the total number of operations of the failed device, and each of the fifth data groups includes a plurality of target force data of a single operation of the failed device, and the target force data may be, for example, torque data of a screw when a screwdriver is tightened with a screw.

[0149] S520: Based on the second data set, determine feature values ​​of multiple statistical features corresponding to each fifth data group.

[0150] In step S520, characteristic values ​​of multiple statistical features corresponding to each fifth data group are determined according to the second data set, forming characteristic value sequences of multiple different statistical features whose sequence lengths are all the same as the number of fifth data groups. Each statistical feature can characterize a data calculation method and can reflect the characteristics of certain data characteristics. For example, characteristic values ​​of statistical features such as mean, standard deviation, and root mean square can be determined for each fifth data group.

[0151] S530: Determine a target statistical feature based on the feature values ​​of the multiple statistical features corresponding to each fifth data group.

[0152] In step S530, according to the feature values ​​of multiple statistical features corresponding to each fifth data group, that is, the feature value sequence of multiple different statistical features, the target statistical feature can be extracted from the multiple statistical features, thereby achieving the determination of the target statistical feature.

[0153] S540: Determine a failure threshold based on target statistical characteristics.

[0154] In step S540, based on the target statistical characteristics, the characteristic values ​​of the target statistical characteristics corresponding to each fifth data group can be determined, and the characteristic values ​​of the target statistical characteristics corresponding to the last group of fifth data groups, i.e., the last operation before failure, are determined as the failure threshold of the target statistical characteristics, thereby realizing the determination of the failure threshold.

[0155] In this embodiment, by preprocessing the historical usage data of failed devices, the fluctuation of different distribution characteristics of the second data set and the enhanced sample data can be obtained. The characteristic values ​​of multiple statistical features corresponding to each fifth data group can be determined according to the second data set, and the target statistical features and failure thresholds can be determined according to the characteristic values ​​of multiple statistical features corresponding to each fifth data group, thereby realizing the extraction of target statistical features and the determination of failure thresholds. The target statistical features extracted from multiple statistical features are suitable for the prediction of the remaining service life of the device to be predicted, and the failure threshold can characterize the threshold of the target statistical feature value corresponding to the failure of the same device, so that the prediction result is closer to the actual failure situation of the same device, thereby making the prediction result closer to the real result, reducing the prediction deviation and the occurrence rate of maintenance lag, improving the product yield, and reducing the production capacity loss.

[0156] In some embodiments, reference Fig. 9 As shown, the sample data includes a plurality of sixth data groups, each of which includes original force data of a single operation of a failed device. The sample data is preprocessed to obtain a second data set, including:

[0157] S511. Resample each sixth data group to obtain multiple seventh data groups, and the number of data in each seventh data group is the same.

[0158] In step S511, each sixth data group includes the original force data of a single operation of the failed device. For example, each sixth data group may be the torque data of the screw when the same batch head is tightened each time. As the test point is different each time the screw is tightened, the number of data in each sixth data group is different. Each sixth data group is resampled, and the resampling may include upsampling and downsampling, for example, the sixth data group with less than a preset number of data may be upsampled, and the sixth data group with more than a preset number of data may be downsampled, so that the number of data in each sixth data group is the preset number, and multiple seventh data groups are obtained. The preset number may be, for example, the mean of the number of data in each sixth data group.

[0159] S512, performing differentiation on the data in each seventh data group to obtain multiple eighth data groups.

[0160] In step S512, the data in each seventh data group is differentiated, that is, each data in each seventh data group is subtracted from the previous data, to obtain a plurality of eighth data groups corresponding to each seventh data group.

[0161] S513, taking the absolute value of the data in each eighth data group to obtain a second data set.

[0162] In step S513, the absolute value of the data in each eighth data group is taken to obtain the fifth data group corresponding to each eighth data group. Multiple fifth data groups constitute the second data set, completing the conversion of the original force data to the target force data. It can be understood that the above conversion process is for the data in each sixth data group, and the number of data groups is not changed. Each fifth data group, sixth data group, seventh data group and eighth data group corresponds to the data of each operation of the failed device.

[0163] In this embodiment, the sixth data groups are resampled, differentiated and averaged in turn, and the seventh data group, the eighth data group and the fifth data group are obtained in turn, the second data set is determined, and the conversion of the original force data of a single operation to the target force data is completed. By resampling the sixth data groups, the deviation in the subsequent target statistical feature determination process can be reduced. By calculating the difference and the mean, the target force data of the screwdriver bits with different wear degrees can more easily reflect different distribution characteristics, thereby improving the prediction accuracy of the remaining service life of the component to be predicted.

[0164] In some embodiments, reference Fig.10 As shown, based on the feature values ​​of multiple statistical features corresponding to each fifth data group, the target statistical feature is determined, including:

[0165] S531. Determine a plurality of evaluation index values ​​corresponding to each statistical feature based on the feature values ​​of the plurality of statistical features corresponding to each fifth data group.

[0166] In step S531, multiple evaluation index values ​​corresponding to each statistical feature are determined according to the feature values ​​of multiple statistical features corresponding to each fifth data group, and each evaluation index value is used to characterize whether each statistical feature is suitable for predicting the remaining useful life of the component to be predicted.

[0167] S532: Determine the target statistical feature based on multiple evaluation index values ​​corresponding to each statistical feature.

[0168] In step S532, based on the multiple evaluation index values ​​corresponding to the statistical features, a target statistical feature that is most suitable for predicting the remaining useful life of the component to be predicted is extracted from the multiple statistical features.

[0169] In this embodiment, according to the characteristic values ​​of multiple statistical features corresponding to each fifth data group, multiple evaluation index values ​​corresponding to each statistical feature are determined, and the evaluation index value can be used to characterize whether each statistical feature is suitable for the remaining service life prediction of the device to be predicted, and the target statistical feature is extracted from the multiple statistical features according to the evaluation index value, thereby realizing the determination of the target statistical feature and providing a basis for the subsequent determination of the current characteristic value. The target statistical feature extracted from the multiple statistical features is suitable for the remaining service life prediction of the device to be predicted, and the prediction result is closer to the actual failure situation of the same device, thereby making the prediction result closer to the real result, reducing the prediction deviation and the occurrence rate of maintenance lag, improving the product yield, and reducing the production capacity loss.

[0170] In some embodiments, the multiple evaluation index values ​​include a trend index value, a monotonicity index value, and a robustness index value, which are used to evaluate the trend, monotonicity, and robustness of the characteristic values ​​of each statistical feature, respectively. Exemplarily, the trend index value Tred(H) can be determined as follows:

[0171]

[0172] The monotonicity index value Mon(H) is determined as follows:

[0173]

[0174] And the robustness index value Rob(H) is determined as follows:

[0175]

[0176] Wherein, K is the length of any statistical feature H, that is, the number of characteristic values ​​of the statistical feature corresponding to each fifth data group, h k and t k are the kth eigenvalue of the eigenvalue of the statistical feature and its sequence number, and are the median of the eigenvalues ​​and the median of the number of eigenvalues ​​of the statistical feature, dH is the difference sequence of the eigenvalues ​​of the statistical feature, No.of represents the counting operator, H R It represents the smoothed residual after smoothing the characteristic value of the statistical feature. It can be understood that for different statistical features, there are corresponding trend index values ​​Tred(H), monotonicity index values ​​Mon(H) and robustness index values ​​Rob(H).

[0177] refer to Fig.11 As shown, based on multiple evaluation index values ​​corresponding to each statistical feature, the target statistical feature is determined, including:

[0178] S532-1. Based on the trend index value, monotonicity index value and robustness index value corresponding to each statistical feature, determine the trend index mean, monotonicity index mean and robustness index mean.

[0179] In step S532-1, the trend index value, monotonicity index value and robustness index value corresponding to each statistical feature are averaged as the trend index mean, monotonicity index mean and robustness index mean. For example, the number of statistical features is 5, namely H1, H2, H3, H4 and H5, and the corresponding trend indexes are also 5, namely Tred(H1), Tred(H2), Tred(H3), Tred(H4) and Tred(H5). The average of the 5 trend indexes is taken and the average is taken as the trend index mean. Similarly, the monotonicity index mean and the robustness index mean can be obtained.

[0180] S532-2. Based on the trend index value, monotonicity index value and robustness index value corresponding to each statistical feature, determine the total value of the evaluation index corresponding to each statistical feature, the total value of the evaluation index being the sum of the trend index value, monotonicity index value and robustness index value corresponding to each statistical feature.

[0181] In step S532 - 2 , the trend index value, monotonicity index value and robustness index value corresponding to each statistical feature are summed up respectively to serve as the total evaluation index value corresponding to each statistical feature.

[0182] S532-3. The statistical feature whose trend index value, monotonicity index value and robustness index value are respectively greater than the trend index mean value, monotonicity index mean value and robustness index mean value and whose total value of evaluation index is the largest is determined as the target statistical feature.

[0183] In step S523-3, if the trend index value corresponding to any statistical feature among the multiple statistical features is less than the trend index mean, or the corresponding monotonicity index value is less than the monotonicity index mean, or the corresponding robustness index value is less than the robustness index mean, then the statistical feature is excluded. Then, the statistical feature of the total value of the evaluation index among the multiple statistical features remaining after the exclusion is determined as the target statistical feature.

[0184] The target statistical features are extracted from multiple different statistical features according to the above method. Compared with other statistical features, the extracted target statistical features have stronger trend, better monotonicity, less fluctuation, and are more suitable for predicting the remaining service life of the device to be predicted. Fig.12As shown, the predicted value of the remaining service life determined by the above method is compared with the actual value. The horizontal axis in the figure is the number of current operations, and the vertical axis is the number of operations of the remaining service life. The remaining service life prediction result is very close to the actual result, which can reduce the prediction deviation and the occurrence rate of maintenance lag, improve product yield, and reduce production capacity loss.

[0185] In this embodiment, by determining as the target statistical feature a statistical feature whose trend index value, monotonicity index value and robustness index value are respectively greater than the trend index mean, monotonicity index mean and robustness index mean and whose total value of evaluation index is the largest, the target statistical feature is extracted from multiple statistical features, so that the target statistical feature is more suitable for predicting the remaining service life of the component to be predicted, and the prediction result is closer to the actual failure situation of the same component, thereby making the prediction result closer to the real result, reducing prediction deviation and maintenance delay incidence, improving product yield and reducing production capacity loss.

[0186] In some embodiments, the statistical feature may include a combination of any multiple of the time domain features, or the statistical feature may include a combination of any multiple of the frequency domain features, or the statistical feature may include a combination of any multiple of the time domain features and the frequency domain features.

[0187] Among them, the time domain features may include, for example, mean, standard deviation, root mean square, etc., and the frequency domain features may include, for example, spectral centroid, spectral kurtosis, etc. Standard deviation σ x The calculation formula is as follows:

[0188]

[0189] RMS x rms The calculation formula is as follows:

[0190]

[0191] The calculation formula of the spectral center of gravity f1 is as follows:

[0192]

[0193] The calculation formula of spectral kurtosis f2 is as follows:

[0194]

[0195] Among them, x(n) is the value of the nth data in each fifth data group, s(l) is the frequency domain data after Fourier transform of the absolute value sequence data, and l∈{1,…,L}, L is the sequence length after Fourier transform, and p(l) is the frequency value corresponding to s(l).

[0196] In this embodiment, by setting a variety of statistical features, target statistical features can be extracted from sufficient statistical features, and the operating data of the device can be analyzed from multiple different dimensions, so that the extracted target statistical features are more suitable for predicting the remaining service life of the device to be predicted, and the prediction results are closer to the actual failure conditions of the same device, thereby making the prediction results closer to the actual results, reducing prediction deviations and the occurrence rate of maintenance delays, improving product yields, and reducing production capacity losses.

[0197] In some embodiments, the component to be predicted includes a bit of a screw locking device.

[0198] The device to be predicted may be, for example, a screwdriver bit of a screw locking device such as an automatic screw locking machine, which is used to apply the torque output by the motor of the screw locking device to the screw to complete the screw locking operation. When the device to be predicted is a screwdriver bit of a screw locking device, each first data group includes real-time torque data on the screw when the screwdriver bit performs a single screw locking operation.

[0199] In this embodiment, the component to be predicted includes a screw bit of a screw locking device. The remaining service life of the screw bit can be predicted through the above-mentioned component life prediction method, thereby guiding maintenance personnel to arrange maintenance work in advance, reducing the frequency of locking defects such as stripping, improving the stability of the product's locking screws, and further improving the product yield.

[0200] In an exemplary embodiment, reference Fig.13 As shown, a device life prediction method is provided, and the device life prediction method includes:

[0201] S1. Obtain sample data;

[0202] S2, resampling each sixth data group to obtain a plurality of seventh data groups;

[0203] S3, performing differential analysis on the data in each seventh data group to obtain a plurality of eighth data groups;

[0204] S4, taking the absolute value of the data in each eighth data group to obtain a second data set;

[0205] S5. Determine, based on the second data set, characteristic values ​​of a plurality of statistical characteristics corresponding to each fifth data group;

[0206] S6. Determine a plurality of evaluation index values ​​corresponding to each statistical feature based on the feature values ​​of the plurality of statistical features corresponding to each fifth data group;

[0207] S7. Determine the trend index mean, the monotonicity index mean, and the robustness index mean based on the trend index value, the monotonicity index value, and the robustness index value corresponding to each statistical feature;

[0208] S8. Determine the total value of the evaluation index corresponding to each statistical feature based on the trend index value, monotonicity index value and robustness index value corresponding to each statistical feature;

[0209] S9, determining the statistical feature whose trend index value, monotonicity index value and robustness index value are respectively greater than the trend index mean value, monotonicity index mean value and robustness index mean value and whose total value of evaluation index is the largest as the target statistical feature;

[0210] S10, determining a failure threshold based on target statistical characteristics;

[0211] S11, obtaining historical usage data of the device to be predicted;

[0212] S12, resampling each second data group to obtain a plurality of third data groups;

[0213] S13, performing differential analysis on the data in each third data group to obtain a plurality of fourth data groups;

[0214] S14, taking the absolute value of the data in each fourth data group to obtain a first data set;

[0215] S15. Determine, based on the first data set, a characteristic value of a target statistical characteristic corresponding to each first data group;

[0216] S16, determining the eigenvalue corresponding to the first data group as the initial eigenvalue;

[0217] S17, determining a degradation parameter and a fluctuation parameter based on the characteristic values ​​corresponding to each first data group;

[0218] S18, constructing a characteristic function based on the initial eigenvalue, the degradation parameter and the fluctuation parameter;

[0219] S19, determining a current characteristic value corresponding to the target statistical characteristic based on the characteristic function and the current operation number of the device to be predicted;

[0220] S20, determining the remaining service life probability density based on the current characteristic value, failure threshold, degradation parameter and fluctuation parameter;

[0221] S21. Determine the remaining useful life based on the remaining useful life probability density.

[0222] In this embodiment, the prediction of device life is achieved by obtaining the historical usage data of the device to be predicted, determining the current characteristic value corresponding to the target statistical feature based on the historical usage data and the target statistical feature, and then predicting the remaining service life of the device to be predicted based on the current characteristic value and the failure threshold of the target statistical feature. The life prediction of each device to be predicted is based on its own historical usage data, and the sensitivity of the target statistical feature to the degree of device degradation makes it more suitable for the prediction of the remaining service life. It fully considers the external random factors and individual differences of the device to be predicted during actual use, so that the prediction result is closer to the real result, reduces the prediction deviation and the occurrence rate of maintenance delay, improves the product yield, and reduces the loss of production capacity.

[0223] In an exemplary embodiment, reference Fig.14 As shown, a device life prediction device is provided, which includes a first acquisition module 10, a first determination module 20 and a second determination module 30. The first acquisition module 10 is used to acquire historical usage data of the device to be predicted, and the historical usage data is historical data that characterizes the operating state of the device to be predicted. The first determination module 20 is used to determine the current feature value of the target statistical feature of the historical usage data, and the second determination module 30 is used to predict the remaining service life of the device to be predicted based on the current feature value and the failure threshold of the target statistical feature.

[0224] In this embodiment, the historical usage data of the device to be predicted is obtained by the first acquisition module 10, and the current characteristic value of the target statistical feature of the historical usage data is determined by the first determination module 20, and then the remaining service life of the device to be predicted is predicted according to the current characteristic value and the failure threshold of the target statistical feature by the second determination module 30, so as to realize the prediction of the device life. The life prediction of each device to be predicted is based on its own historical usage data, and the sensitivity of the target statistical feature to the degree of device degradation makes it more suitable for the prediction of the remaining service life, and fully considers the external random factors and individual differences of the device to be predicted in the actual use process, so that the prediction result is closer to the real result, reduces the prediction deviation and the occurrence rate of maintenance lag, improves the product yield, and reduces the loss of production capacity.

[0225] In one embodiment, the first determination module 20 is also used to: construct a characteristic function based on historical usage data, the characteristic function is used to characterize the relationship between the number of operations of the device to be predicted and the characteristic value of the target statistical feature; based on the characteristic function and the current number of operations of the device to be predicted, determine the current characteristic value corresponding to the target statistical feature.

[0226] In one embodiment, the first determination module 20 is also used to: pre-process the historical usage data to obtain a first data set, the first data set includes multiple first data groups, each first data group includes target force data of a single operation of the component to be predicted; determine initial eigenvalues, degradation parameters and fluctuation parameters based on target statistical characteristics and the first data set; and construct a characteristic function based on the initial eigenvalues, degradation parameters and fluctuation parameters.

[0227] In one embodiment, the first determination module 20 is also used to: resample each second data group to obtain multiple third data groups, the number of data in each third data group is the same; differentiate the data in each third data group to obtain multiple fourth data groups; take the absolute value of the data in each fourth data group to obtain the first data set.

[0228] In one embodiment, the first determination module 20 is also used to: determine the characteristic value of the target statistical feature corresponding to each first data group based on the first data set; determine the characteristic value corresponding to the first group of first data groups as the initial characteristic value; and determine the degradation parameter and the fluctuation parameter based on the characteristic value corresponding to each first data group.

[0229] In one embodiment, the second determination module 30 is further used to: determine the remaining useful life probability density based on the current characteristic value, the failure threshold, the degradation parameter and the fluctuation parameter; and determine the remaining useful life based on the remaining useful life probability density.

[0230] In some embodiments, reference Fig.15 As shown, the device life prediction apparatus further includes a second acquisition module 40 and a third determination module 50. The second acquisition module 40 is used to acquire sample data, the sample data including historical usage data of failed devices. The third determination module 50 is used to determine the target statistical feature and the failure threshold of the target statistical feature based on the sample data.

[0231] In this embodiment, sample data including historical usage data of failed devices is obtained through the second acquisition module 40, and the target statistical feature and the failure threshold of the target statistical feature can be determined according to the sample data through the third determination module 50, providing a determined target statistical feature and failure threshold for the subsequent life prediction process. The target statistical feature and failure threshold determined according to the sample data of the failed device can make the target statistical feature applicable to the remaining service life prediction of the device to be predicted, and the failure threshold can characterize the threshold of the target statistical feature value corresponding to the failure of the same device, so that the prediction result is closer to the actual failure situation of the same device, and thus the prediction result is closer to the real result, reducing the prediction deviation and the occurrence rate of maintenance lag, improving the product yield, and reducing the loss of production capacity.

[0232] In one embodiment, the third determination module 50 is also used to: pre-process the sample data to obtain a second data set, the second data set includes multiple fifth data groups, each fifth data group includes target force data of a single operation of the failed device; based on the second data set, determine the characteristic values ​​of multiple statistical features corresponding to each fifth data group; based on the characteristic values ​​of multiple statistical features corresponding to each fifth data group, determine the target statistical feature; based on the target statistical feature, determine the failure threshold.

[0233] In one embodiment, the third determination module 50 is also used to: resample each sixth data group to obtain multiple seventh data groups, and the number of data in each seventh data group is the same; differentiate the data in each seventh data group to obtain multiple eighth data groups; take the absolute value of the data in each eighth data group to obtain a second data set.

[0234] In one embodiment, the third determination module 50 is further used to: determine multiple evaluation index values ​​corresponding to each statistical feature based on the feature values ​​of multiple statistical features corresponding to each fifth data group; determine the target statistical feature based on the multiple evaluation index values ​​corresponding to each statistical feature.

[0235] In one embodiment, the third determination module 50 is also used to: determine the trend indicator mean, the monotonicity indicator mean and the robustness indicator mean based on the trend indicator value, the monotonicity indicator value and the robustness indicator value corresponding to each statistical feature; determine the total value of the evaluation index corresponding to each statistical feature based on the trend indicator value, the monotonicity indicator value and the robustness indicator value corresponding to each statistical feature, the total value of the evaluation index being the sum of the trend indicator value, the monotonicity indicator value and the robustness indicator value corresponding to each statistical feature; determine the statistical feature whose trend indicator value, monotonicity indicator value and robustness indicator value are respectively greater than the trend indicator mean, the monotonicity indicator mean and the robustness indicator mean and whose total value of the evaluation index is the largest as the target statistical feature.

[0236] In an exemplary embodiment, a device lifetime prediction apparatus is provided, referring to Fig.16 As shown, the device lifetime prediction apparatus may include one or more of the following components: a processing component 101 , a memory 102 , a power component 103 , a multimedia component 104 , an audio component 105 , an input / output (I / O) interface 106 , a sensor component 107 , and a communication component 108 .

[0237] The processing component 101 generally controls the overall operation of the device life prediction device, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 101 may include one or more processors 109 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 101 may include one or more modules to facilitate the interaction between the processing component 101 and other components. For example, the processing component 101 may include a multimedia module to facilitate the interaction between the multimedia component 104 and the processing component 101.

[0238] The memory 102 is configured to store various types of data to support the operation of the device lifetime prediction device. Examples of such data include instructions for any application or method operating on the device lifetime prediction device, contact data, phone book data, messages, pictures, videos, etc. The memory 102 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0239] The power component 103 provides power to various components of the device life prediction apparatus. The power component 103 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device life prediction apparatus.

[0240] The multimedia component 104 includes a screen that provides an output interface between the device life prediction device and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 104 includes a front camera and / or a rear camera. When the device life prediction device is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0241] The audio component 105 is configured to output and / or input audio signals. For example, the audio component 105 includes a microphone (MIC), and when the device life prediction device is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 102 or sent via the communication component 108. In some embodiments, the audio component 105 also includes a speaker for outputting audio signals.

[0242] I / O interface 106 provides an interface between processing component 101 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0243] The sensor assembly 107 includes one or more sensors for providing various aspects of status assessment for the device life prediction device. For example, the sensor assembly 107 can detect the on / off state of the device life prediction device, the relative positioning of components, such as the display and keypad of the device life prediction device, and the sensor assembly 107 can also detect the position change of the device life prediction device or a component of the device life prediction device, the presence or absence of user contact with the device life prediction device, the orientation or acceleration / deceleration of the device life prediction device, and the temperature change of the device life prediction device. The sensor assembly 107 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 107 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 107 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0244] The communication component 108 is configured to facilitate wired or wireless communication between the device life prediction device and other devices. The device can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 108 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 108 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0245] In an exemplary embodiment, the device life prediction device can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned device life prediction method applied to the device life prediction device.

[0246] In an exemplary embodiment, a non-temporary computer-readable storage medium including instructions is also provided, such as a memory 102 including instructions, and the above instructions can be executed by a processor 109 of the device life prediction device to complete the above-mentioned device life prediction method applied to the device life prediction device. For example, the non-temporary computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a tape, a floppy disk, and an optical data storage device. When the instructions in the storage medium are executed by the processor of the device life prediction device, the device life prediction device is enabled to perform the device life prediction method shown in the above-mentioned embodiment.

[0247] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0248] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A device life prediction method, characterized in that: The device life prediction method comprises: Acquire historical usage data of the device to be predicted, wherein the historical usage data is historical data characterizing the device operation status of the device to be predicted; The statistical feature determines a current feature value of a target statistical feature of the historical usage data; Based on the current feature value and the failure threshold of the target statistical feature, the remaining service life of the component to be predicted is predicted.

2. The device lifetime prediction method according to claim 1, characterized in that: The determining of the current characteristic value of the target statistical characteristic of the historical usage data includes: Based on the historical usage data, construct a characteristic function, wherein the characteristic function is used to characterize the relationship between the number of operations of the device to be predicted and the characteristic value of the target statistical feature; Based on the characteristic function and the current operation times of the component to be predicted, a current characteristic value corresponding to the target statistical characteristic is determined.

3. The device lifetime prediction method according to claim 2, characterized in that: The constructing of a characteristic function based on the historical usage data includes: Preprocessing the historical usage data to obtain a first data set, wherein the first data set includes a plurality of first data groups, each of which includes target force data of a single operation of the component to be predicted; Determining an initial characteristic value, a degradation parameter, and a fluctuation parameter based on the target statistical characteristic and the first data set; The characteristic function is constructed based on the initial characteristic value, the degradation parameter and the fluctuation parameter.

4. The device lifetime prediction method according to claim 3, characterized in that: The predicting the remaining useful life of the component to be predicted based on the current feature value and the failure threshold of the target statistical feature includes: Determining a remaining useful life probability density based on the current characteristic value, the failure threshold, the degradation parameter, and the fluctuation parameter; Based on the remaining useful life probability density, the remaining useful life is determined.

5. The device lifetime prediction method according to claim 3, characterized in that: The historical usage data includes a plurality of second data groups, each of which includes original force data of a single operation of the device to be predicted. The historical usage data is preprocessed to obtain a first data set, including: Resampling each of the second data groups to obtain a plurality of third data groups, wherein the number of data in each of the third data groups is the same; Differentiating the data in each of the third data groups to obtain a plurality of fourth data groups; The absolute value of each data in the fourth data group is taken to obtain the first data set.

6. The device lifetime prediction method according to claim 3, characterized in that: The determining of initial characteristic values, degradation parameters and fluctuation parameters based on the target statistical characteristics and the first data set includes: Based on the first data set, determining a characteristic value of the target statistical characteristic corresponding to each of the first data groups; Determine the eigenvalue corresponding to the first data group of the first group as the initial eigenvalue; The degradation parameter and the fluctuation parameter are determined based on the characteristic values ​​corresponding to each of the first data groups.

7. The device lifetime prediction method according to any one of claims 1 to 6, characterized in that: Before determining the current characteristic value of the target statistical characteristic of the historical usage data, the device life prediction method further includes: Acquiring sample data, wherein the sample data includes historical usage data of the failed device; Based on the sample data, the target statistical feature and a failure threshold of the target statistical feature are determined.

8. The device lifetime prediction method according to claim 7, characterized in that: The determining, based on the sample data, the target statistical feature and the failure threshold of the target statistical feature includes: Preprocessing the sample data to obtain a second data set, wherein the second data set includes a plurality of fifth data groups, each of the fifth data groups includes target force data of a single operation of the failed device; Based on the second data set, determining feature values ​​of a plurality of statistical features corresponding to each of the fifth data groups; Determining the target statistical feature based on feature values ​​of a plurality of statistical features corresponding to each of the fifth data groups; The failure threshold is determined based on the target statistical feature.

9. The device lifetime prediction method according to claim 8, characterized in that: The sample data includes a plurality of sixth data groups, each of which includes original force data of a single operation of the failed device. The preprocessing of the sample data to obtain a second data set includes: Resampling each of the sixth data groups to obtain a plurality of seventh data groups, wherein the number of data in each of the seventh data groups is the same; Differentiating the data in each of the seventh data groups to obtain a plurality of eighth data groups; The absolute value of each data in the eighth data group is taken to obtain the second data set.

10. The device lifetime prediction method according to claim 8, characterized in that: The determining the target statistical feature based on the feature values ​​of the plurality of statistical features corresponding to each of the fifth data groups comprises: Determining a plurality of evaluation index values ​​corresponding to each of the statistical features based on the feature values ​​of the plurality of statistical features corresponding to each of the fifth data groups; The target statistical feature is determined based on a plurality of evaluation index values ​​corresponding to each of the statistical features.

11. The device lifetime prediction method according to claim 10, characterized in that: The multiple evaluation index values ​​include a trend index value, a monotonicity index value, and a robustness index value, and the target statistical feature is determined based on the multiple evaluation index values ​​corresponding to each of the statistical features, including: Determine a trend index mean, a monotonicity index mean, and a robustness index mean based on the trend index value, the monotonicity index value, and the robustness index value corresponding to each of the statistical features; Based on the trend index value, the monotonicity index value and the robustness index value corresponding to each of the statistical features, determine the total value of the evaluation index corresponding to each of the statistical features, the total value of the evaluation index being the sum of the trend index value, the monotonicity index value and the robustness index value corresponding to each of the statistical features; The statistical feature whose trend index value, monotonicity index value and robustness index value are respectively greater than the trend index mean value, the monotonicity index mean value and the robustness index mean value and whose total value of the evaluation index is the largest is determined as the target statistical feature.

12. The device lifetime prediction method according to claim 8, characterized in that: The multiple statistical features include any combination of multiple time domain features and / or multiple frequency domain features.

13. A device for predicting device lifetime, characterized in that: The device life prediction device comprises: A first acquisition module, the first acquisition module is used to acquire historical usage data of the device to be predicted, wherein the historical usage data is historical data representing the device operation status of the device to be predicted; a first determining module, the first determining module being used to determine a current feature value of a target statistical feature of the historical usage data; A second determination module is used to predict the remaining useful life of the component to be predicted based on the current feature value and the failure threshold of the target statistical feature.

14. A device for predicting device lifetime, characterized in that: The device life prediction device comprises: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Acquire historical usage data of the device to be predicted, wherein the historical usage data is historical data characterizing the device operation status of the device to be predicted; determining a current characteristic value of a target statistical characteristic of the historical usage data; Based on the current feature value and the failure threshold of the target statistical feature, the remaining service life of the component to be predicted is predicted.

15. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of a device life prediction device, the device life prediction device is enabled to execute a device life prediction method, the device life prediction method comprising: Acquire historical usage data of the device to be predicted, wherein the historical usage data is historical data characterizing the device operation status of the device to be predicted; determining a current characteristic value of a target statistical characteristic of the historical usage data; Based on the current feature value and the failure threshold of the target statistical feature, the remaining service life of the component to be predicted is predicted.

Images