Equipment residual life prediction method and equipment considering degradation index coupling effect

Abstract

The invention discloses an equipment residual life prediction method and equipment considering a degradation index coupling effect, and relates to the technical field of equipment state monitoring and prediction. Monitoring signals are acquired, and high-dimensional features are extracted from the monitoring signals to construct a high-dimensional feature set; two high-dimensional features with the maximum correlation are screened out to serve as degradation indexes for representing the degradation state of the equipment; the degradation index is converted into a reference working condition by using an adaptive signal conversion algorithm to obtain a working condition adaptive degradation index, so that the problem of difficulty in residual life prediction caused by working condition change is solved; a nonlinear binary Wiener process is constructed to describe the interdependence relationship between the adaptive degradation indexes of the two working conditions, and the Monte Carlo simulation technology is utilized to simulate the coupling degradation indexes to obtain the prediction of the residual life of the equipment. The influence of the coupling effect of different degradation indexes on the residual life is considered while the influence of the working condition change on the degradation indexes is adaptively eliminated, so that the accurate residual life of the equipment is realized.

Description

Technical Field

[0001] This invention relates to the field of equipment condition monitoring and prediction technology, specifically to a method and device for predicting the remaining service life of equipment that takes into account the coupling effect of degradation indicators. Background Technology

[0002] In modern industry, the efficient and safe operation of various equipment is crucial for production activities. During their lifespan, equipment is inevitably affected by various factors, among which changes in operating conditions are a key factor. Frequent changes in operating conditions significantly impact equipment degradation data, thereby affecting the prediction of remaining life. Traditional remaining life prediction methods often model based on a single degradation index; however, this method struggles to comprehensively reflect the actual degradation process of equipment under complex operating conditions. Furthermore, under time-varying operating conditions, the impact of operating condition changes on degradation indices and the coupling effects between different degradation indices pose significant challenges to the accurate prediction of remaining life. Therefore, how to adaptively eliminate the impact of operating condition changes on degradation indices under time-varying operating conditions, and fully consider the coupling effects between different degradation indices, thereby achieving accurate prediction of equipment remaining life, is a pressing technical challenge that needs to be addressed.

[0003] In summary, the following problems still exist in the existing technology: 1. How to adaptively eliminate the impact of operating condition changes on the amplitude of degradation data when operating conditions change frequently during the equipment's life cycle, so as to improve the accuracy of remaining life prediction; 2. How to fully consider the coupling effect between different degradation indicators during the modeling process, so as to more comprehensively reflect the degradation process of equipment and achieve accurate prediction of equipment remaining life. Summary of the Invention

[0004] Based on the problems raised in the background technology above, the purpose of this invention is to provide a method and device for predicting the remaining service life of equipment that considers the coupling effect of degradation indicators, and to solve the problem of how to adaptively eliminate the influence of changes in operating conditions on degradation indicators under time-varying operating conditions, while considering the influence of the coupling effect of different degradation indicators on the remaining service life.

[0005] This invention is achieved through the following technical solution: The first aspect of this invention provides a method for predicting the remaining service life of equipment considering the coupling effect of degradation indices, comprising the following steps: Step S1: Acquire monitoring signals, extract high-dimensional features from the monitoring signals, and construct a high-dimensional feature set; Step S2: Perform correlation analysis on the high-dimensional feature set and select the two high-dimensional features with the highest correlation as degradation indicators to characterize the degradation state of the equipment. Step S3: Use an adaptive signal conversion algorithm to convert the degradation index to the baseline working condition to obtain the working condition adaptive degradation index; Step S4: Input the adaptive degradation index of the working condition into the pre-constructed nonlinear binary Wiener process degradation model to perform binary Wiener degradation analysis and obtain the coupled degradation index; Step S5: Use Monte Carlo simulation technology to simulate the coupling degradation index and obtain the equipment remaining life prediction results.

[0006] In the above technical solution, monitoring signals are first acquired from multi-source sensors, and high-dimensional features are extracted from the monitoring signals to construct a high-dimensional feature set. Then, based on correlation analysis, two highly correlated features are selected from the high-dimensional feature set as degradation indicators to characterize the degradation state. These two degradation indicators are highly representative features of the equipment degradation state.

[0007] Because operating conditions change frequently throughout the equipment's lifespan, and these changes often affect the amplitude of degradation data, predicting the remaining life of equipment under time-varying operating conditions becomes more difficult. To address this, this method divides operating conditions into baseline and non-baseline operating conditions. The baseline operating condition typically uses the initial operating condition, while non-baseline operating conditions include all varying operating conditions other than the baseline. An adaptive signal transformation algorithm is used to transform degradation indices from non-baseline operating conditions to the baseline operating condition, resulting in an adaptive degradation index for the operating condition. This overcomes the difficulty in predicting remaining life caused by changes in operating conditions.

[0008] A nonlinear bivariate Wiener process with stochastic effects is constructed to describe the interdependence between two adaptive degradation indices under different operating conditions, in order to find the coupling relationship between the degradation indices. Finally, Monte Carlo simulation is used to simulate the coupled degradation indices and obtain the equipment remaining life prediction. While adaptively eliminating the influence of operating condition changes on degradation indices, the influence of the coupling effect of different degradation indices on the remaining life is considered, thereby achieving accurate equipment remaining life.

[0009] In one optional embodiment, the degradation index is converted to a baseline operating condition using an adaptive signal conversion algorithm, including the following steps: Step S31: Obtain the sampling time points under changing operating conditions, and perform linear interpolation on the degradation index under the baseline operating conditions based on the sampling time points to obtain the estimated value of the degradation index. Step S32: Calculate the sum of squared errors between the degradation index and the estimated value of the degradation index, and minimize the sum of squared errors to obtain the function that minimizes the sum of squared errors; Step S33: Optimize the function that minimizes the sum of squared errors using a two-dimensional search optimization algorithm to obtain the relationship estimate; Step S34: Substitute the estimated relationship value into the degradation index under the changing working conditions to obtain the working condition adaptive degradation index.

[0010] In one optional embodiment, the condition-adaptive degradation index is input into a pre-built nonlinear bivariate Wiener process degradation model for bivariate Wiener degradation analysis to obtain a coupled degradation index, including: Step S41: Perform a logarithmic transformation on the adaptive degradation index of the working condition to obtain the adaptive degradation index of the changing working condition. Step S42: Use the binary Wiener process in the nonlinear binary Wiener process degradation model to describe the correlation of the adaptive degradation index under changing operating conditions, and obtain the coupled degradation index; wherein, the increment of the adaptive degradation index under changing operating conditions in the binary Wiener process within any time interval follows a two-dimensional normal distribution, and the two-dimensional normal distribution is the coupled degradation index of the adaptive degradation index under changing operating conditions.

[0011] In an optional embodiment, step S4 further includes the following steps: Historical data is acquired, and the parameters of the nonlinear binary Wiener process degradation model are estimated using the historical data to obtain the estimated values ​​of the model parameters. Based on the estimated model parameters, the random parameters in the nonlinear binary Wiener process degradation model are updated using Bayes' theorem.

[0012] In one optional embodiment, parameter estimation of the nonlinear binary Wiener process degradation model using the historical data includes the following steps: The historical data is filtered for availability to obtain available historical data; wherein, availability filtering includes: selecting N available historical data from the historical data, and among the N available historical data, the nth equipment degradation index is within the specified time frame. It is available online. Indicates the number of available degradation indicators; Calculate the historical binary index increment data of the nth equipment degradation index, and use the historical binary index increment data to perform unbiased estimation of the mean and covariance matrix in the nonlinear binary Wiener process degradation model based on the multivariate normality theory to obtain the unbiased estimation parameters. Bootstrap samples are generated from the historical data, and the hyperparameters in the nonlinear binary Wiener process degradation model are estimated by bootstrap using the bootstrap samples to obtain the estimated values ​​of the bootstrap hyperparameters.

[0013] In an alternative embodiment, the time The time interval between adjacent time points is the same, and the time interval is set to... .

[0014] It should be noted that in this embodiment, the parameters of the nonlinear bivariate Wiener process degradation model are estimated and updated. The bivariate normal distribution after parameter estimation and the updated bivariate normal distribution are used in Monte Carlo simulations, respectively.

[0015] In one alternative embodiment, the coupling degradation index is simulated using Monte Carlo simulation techniques, including the following steps: Step S51: Obtain the bivariate normal distribution after parameter estimation in the nonlinear bivariate Wiener process degradation model, and sample the future drift term parameters from the bivariate normal distribution after parameter estimation. Step S52: Obtain the updated binary normal distribution in the nonlinear binary Wiener process degradation model, and sample the future degradation increment from the updated binary normal distribution based on the future drift term parameter; Step S53: Calculate the future degradation trajectory using the future degradation increment; Step S54: Construct a failure threshold, compare the future degradation trajectory with the failure threshold, and if the future degradation trajectory is less than the failure threshold, repeat steps S51 to S54.

[0016] A second aspect of the present invention provides an equipment remaining life prediction system that considers the coupling effect of degradation indices, comprising: The feature construction module is used to acquire monitoring signals, extract high-dimensional features from the monitoring signals, and construct a high-dimensional feature set. The indicator screening module is used to perform correlation analysis on the high-dimensional feature set and screen out the two high-dimensional features with the highest correlation as degradation indicators characterizing the degradation state of the equipment. An adaptive conversion module is used to convert the degradation index to a baseline operating condition using an adaptive signal conversion algorithm, thereby obtaining an adaptive degradation index for the operating condition. The coupling module is used to input the adaptive degradation index of the operating condition into a pre-built nonlinear binary Wiener process degradation model for binary Wiener degradation analysis to obtain the coupled degradation index. The simulation module is used to simulate the coupling degradation index using Monte Carlo simulation technology to obtain the equipment's remaining life prediction results.

[0017] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements a method for predicting the remaining life of equipment that takes into account the coupling effect of degradation indices.

[0018] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for predicting the remaining life of equipment taking into account the coupling effect of degradation indices.

[0019] Compared with the prior art, the present invention has the following advantages and beneficial effects: 1. This invention utilizes an adaptive signal conversion algorithm to convert degradation indices from other non-baseline operating conditions to baseline operating conditions, thereby obtaining an adaptive degradation index for operating conditions, thus overcoming the problem of difficulty in predicting remaining life caused by changes in operating conditions. 2. A nonlinear bivariate Wiener process with stochastic effects is constructed to describe the interdependence between two adaptive degradation indices under different operating conditions, in order to find the coupling relationship between the degradation indices. Finally, Monte Carlo simulation technology is used to simulate the coupled degradation indices to obtain the equipment remaining life prediction. While adaptively eliminating the influence of changes in operating conditions on the degradation indices, the influence of the coupling effect of different degradation indices on the remaining life is considered, thereby achieving accurate equipment remaining life. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 A flowchart illustrating the equipment remaining life prediction method considering the coupling effect of degradation indices, provided in an embodiment of the present invention. Figure 2 Distribution diagram of equipment remaining life prediction results provided in embodiments of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0022] This invention provides a method for predicting the remaining service life of equipment that considers the coupling effect of degradation indices, such as... Figure 1 As shown, the method includes the following steps: Step S1: Acquire monitoring signals, extract high-dimensional features from the monitoring signals, and construct a high-dimensional feature set; Step S2: Perform correlation analysis on the high-dimensional feature set and select the two high-dimensional features with the highest correlation as degradation indicators to characterize the degradation state of the equipment. Step S3: Use an adaptive signal conversion algorithm to convert the degradation index to the baseline working condition to obtain the working condition adaptive degradation index; Step S4: Input the adaptive degradation index of the working condition into the pre-constructed nonlinear binary Wiener process degradation model to perform binary Wiener degradation analysis and obtain the coupled degradation index; Step S5: Use Monte Carlo simulation technology to simulate the coupling degradation index and obtain the equipment remaining life prediction results.

[0023] It should be noted that there are currently two problems in predicting the remaining life of equipment under varying operating conditions: First, the operating conditions change frequently throughout the equipment's lifespan, and these changes often affect the amplitude of degradation data, making the prediction of the remaining life of equipment under time-varying operating conditions more difficult. Second, modeling based on a single degradation index is insufficient to comprehensively reflect the equipment's degradation process. Therefore, under time-varying operating conditions, it is crucial to adaptively eliminate the impact of operating condition changes on degradation indices while considering the coupling effect of different degradation indices on the remaining life, thereby achieving accurate prediction of the remaining life of equipment.

[0024] To address the problems existing in the prior art, this embodiment provides a method for predicting the remaining service life of equipment considering the coupling effect of degradation indicators. In this method, monitoring signals are first acquired from multi-source sensors, and high-dimensional features are extracted from the monitoring signals to construct a high-dimensional feature set. Then, based on correlation analysis, two highly correlated features are selected from the high-dimensional feature set as degradation indicators characterizing the degradation state. These two degradation indicators are highly representative features of the equipment's degradation state.

[0025] Because operating conditions change frequently throughout the equipment's lifespan, and these changes often affect the amplitude of degradation data, predicting the remaining life of equipment under time-varying operating conditions becomes more difficult. To address this, this method divides operating conditions into baseline and non-baseline operating conditions. The baseline operating condition typically uses the initial operating condition, while non-baseline operating conditions include all varying operating conditions other than the baseline. An adaptive signal transformation algorithm is used to transform degradation indices from non-baseline operating conditions to the baseline operating condition, resulting in an adaptive degradation index for the operating condition. This overcomes the difficulty in predicting remaining life caused by changes in operating conditions.

[0026] A nonlinear bivariate Wiener process with stochastic effects is constructed to describe the interdependence between two adaptive degradation indices under different operating conditions, in order to find the coupling relationship between the degradation indices. Finally, Monte Carlo simulation is used to simulate the coupled degradation indices and obtain the equipment remaining life prediction. While adaptively eliminating the influence of operating condition changes on degradation indices, the influence of the coupling effect of different degradation indices on the remaining life is considered, thereby achieving accurate equipment remaining life.

[0027] In this embodiment, Pearson correlation analysis can be used for screening in the correlation analysis method. Specifically, the screening process is as follows: Correlation analysis is performed between the characteristics under the baseline operating condition and the equipment degradation state or time series. The Pearson correlation coefficient between the characteristics and the equipment degradation state is calculated to obtain the correlation matrix. The calculation formula for the correlation analysis is as follows: ,in, The equipment is in a degraded state. Let be the correlation matrix, i=1,2,...,h; j=1,2,...,D, h is the number of sensor signal channels, and D is the number of features for each channel. Represents the covariance function. Standard deviation, Features.

[0028] By synthesizing the correlation matrices of N historical equipment, two features with high correlation are selected and used as degradation indicators to characterize the degradation state of the equipment. and express.

[0029] In one optional embodiment, the degradation index is converted to a baseline operating condition using an adaptive signal conversion algorithm, including the following steps: Step S31: Obtain the sampling time points under changing operating conditions, and perform linear interpolation on the degradation index under the baseline operating conditions based on the sampling time points to obtain the estimated value of the degradation index. Step S32: Calculate the sum of squared errors between the degradation index and the estimated value of the degradation index, and minimize the sum of squared errors to obtain the function that minimizes the sum of squared errors; Step S33: Optimize the function that minimizes the sum of squared errors using a two-dimensional search optimization algorithm to obtain the relationship estimate; Step S34: Substitute the estimated relationship value into the degradation index under the changing working conditions to obtain the working condition adaptive degradation index.

[0030] It should be noted that the purpose of this step is to design an adaptive signal conversion algorithm to eliminate the impact of operating condition changes on degradation indicators. Specifically, considering the influence of operating condition changes on the slope and amplitude of degradation indicators, an error sum of squares minimization algorithm is used to convert degradation indicators under different operating conditions to those under a baseline operating condition.

[0031] In this embodiment, the first degradation index is used. For example, the relationship between the degradation index under the baseline working condition and the index under other working conditions can be expressed as: ,in, for The degradation index of the cutting tool under baseline conditions at any given time, where K represents the current time. In working conditions The degradation index below, and The parameters are used to adjust the relationship between degradation indices under the baseline condition and indices under other conditions.

[0032] Specifically, the sampling time points under the varying operating condition p are obtained, and linear interpolation is performed within the amplitude range of the degradation index under the baseline operating condition to obtain the estimated value of the degradation index under the baseline operating condition. .

[0033] Calculate the sum of squared errors between the degradation index and its estimated value, and then estimate the adjustment parameters by minimizing the sum of squared errors function, which is calculated as follows: ,in, Let be the sum of squared errors function. This represents the set of sampling times for the nth device under condition p. For the nth piece of equipment The degradation index of the equipment under reference operating conditions, where K represents the current time. For the nth equipment condition The degradation index under the given conditions is estimated at the baseline operating condition. For the nth piece of equipment in operating condition The degradation index below.

[0034] The estimated value is obtained by minimizing the sum of squared errors function using a two-dimensional search optimization algorithm. ,Will and Substituting the estimated value into the relationship between the degradation index under the baseline working condition and the index under other working conditions, we obtain the value of the degradation index under working condition p, i.e., the transformed degradation index. y 1 ( t Similarly, for the second degradation index... The above transformation operations yield the transformed degradation index. y 2 ( t These two degradation indicators will be used for subsequent remaining life prediction.

[0035] In one optional embodiment, the condition-adaptive degradation index is input into a pre-built nonlinear bivariate Wiener process degradation model for bivariate Wiener degradation analysis to obtain a coupled degradation index, including: Step S41: Perform a logarithmic transformation on the adaptive degradation index of the working condition to obtain the adaptive degradation index of the changing working condition. Step S42: Use the binary Wiener process in the nonlinear binary Wiener process degradation model to describe the correlation of the adaptive degradation index under changing operating conditions, and obtain the coupled degradation index; wherein, the increment of the adaptive degradation index under changing operating conditions in the binary Wiener process within any time interval follows a two-dimensional normal distribution, and the two-dimensional normal distribution is the coupled degradation index of the adaptive degradation index under changing operating conditions.

[0036] It should be noted that modeling based on a single degradation index is insufficient to fully reflect the degradation process of equipment. Therefore, the purpose of this step is to describe the interdependence of degradation indices using a nonlinear bivariate Wiener process with stochastic effects, and to model the degradation process of equipment using two degradation indices, thereby comprehensively reflecting the degradation process of equipment.

[0037] The stochastic degradation model of the nonlinear binary Wiener process is as follows: Where y(t) represents the value of the degradation index after transformation at time t. For degradation rate, The diffusion term characterizes the random fluctuations of the degradation process, where For standard Brownian motion, For the diffusion term parameters.

[0038] To simplify calculations, the adaptive degradation index of the operating condition is logarithmically transformed. y 1 ( t )and y 2 ( t ) is transformed into an adaptive degradation index x1 for the transformed operating condition. t ) and x2 ( t The correlation between the two degradation indices is then described using a binary Wiener process. Specifically, the values ​​x1 of the two degradation indices after logarithmic transformation are... t ) and x2 ( t ) at any t and between The increment follows the mean. variance is bivariate normal distribution .

[0039] Right now , Among them, a, b, c, d and These are all parameters of a nonlinear Wiener process stochastic degradation model.

[0040] In an optional embodiment, step S4 further includes the following steps: Historical data is acquired, and the parameters of the nonlinear binary Wiener process degradation model are estimated using the historical data to obtain the estimated values ​​of the model parameters. Based on the estimated model parameters, the random parameters in the nonlinear binary Wiener process degradation model are updated using Bayes' theorem.

[0041] In one optional embodiment, parameter estimation of the nonlinear binary Wiener process degradation model using the historical data includes the following steps: The historical data is filtered for availability to obtain available historical data; wherein, availability filtering includes: selecting N available historical data from the historical data, and among the N available historical data, the nth equipment degradation index is within the specified time frame. It is available online. Indicates the number of available degradation indicators; Calculate the historical binary index increment data of the nth equipment degradation index, and use the historical binary index increment data to perform unbiased estimation of the mean and covariance matrix in the nonlinear binary Wiener process degradation model based on the multivariate normality theory to obtain the unbiased estimation parameters. Bootstrap samples are generated from the historical data, and the hyperparameters in the nonlinear binary Wiener process degradation model are estimated by bootstrap using the bootstrap samples to obtain the estimated values ​​of the bootstrap hyperparameters.

[0042] In an alternative embodiment, the time The time interval between adjacent time points is the same, and the time interval is set to... .

[0043] It should be noted that in this embodiment, the parameters of the nonlinear bivariate Wiener process degradation model are estimated and updated. The bivariate normal distribution after parameter estimation and the updated bivariate normal distribution are used in Monte Carlo simulations, respectively.

[0044] In this embodiment, parameter estimation for a nonlinear binary Wiener process degradation model specifically includes: First, acquire historical data, then select N usable historical data points, and finally determine the nth equipment degradation index within a given time frame. The above is available, among which, Indicates the number of available degradation indicators.

[0045] Then, the incremental data of the historical binary degradation index of the nth piece of equipment. Represented as Where the interval between two adjacent time points is the same, it is set as .

[0046] Based on multivariate normality theory, unbiased estimation of the mean and covariance matrices in the nonlinear binary Wiener process degradation model is performed using historical binary index incremental data to obtain unbiased estimation parameters. The calculation process is as follows: ; ;in, This represents the estimation results of the mean in the binary Wiener process degradation model. This is the estimation result of the covariance in the binary Wiener process degradation model. Therefore, we can obtain: .

[0047] Stochastic hyperparameter estimation of the drift term. Due to the randomness of the service environment of individual equipment, different individuals exhibit variability in their degradation paths. To describe this phenomenon, we consider... a c follows the mean variance is The normal distribution, i.e. , .

[0048] Next, for a The hyperparameters of c are estimated. First, from historical data... H bootstrap samples are generated. The bootstrap samples are then combined to obtain... a and C bootstrap estimation and Where i = 1, 2, ..., H. Since a Since c and c follow a normal distribution, their log-likelihood function can be expressed as: ; .

[0049] The hyperparameter estimates of a and c can be obtained through maximum probability estimation. .

[0050] Furthermore, based on Bayes' theorem and combined with online degradation indices, the random parameters in the model are analyzed. An update is performed to update the two-dimensional Wiener process stochastic degradation model; Based on Bayesian theory posterior distribution It can be represented as: .

[0051] Then the posterior distribution This can be further expressed as: .

[0052] For convenience, let .

[0053] Based on this, we can further deduce: .

[0055] The final result is: Among them, A, B, D, E, F, and G are all intermediate parameters and have no practical significance.

[0056] In one alternative embodiment, the coupling degradation index is simulated using Monte Carlo simulation techniques, including the following steps: Step S51: Obtain the bivariate normal distribution after parameter estimation in the nonlinear bivariate Wiener process degradation model, and sample the future drift term parameters from the bivariate normal distribution after parameter estimation. Step S52: Obtain the updated binary normal distribution in the nonlinear binary Wiener process degradation model, and sample the future degradation increment from the updated binary normal distribution based on the future drift term parameter; Step S53: Calculate the future degradation trajectory using the future degradation increment; Step S54: Construct a failure threshold, compare the future degradation trajectory with the failure threshold, and if the future degradation trajectory is less than the failure threshold, repeat steps S51 to S54.

[0057] It should be noted that obtaining Parameters of the drift term at time step: from the bivariate normal distribution Mid-sampling yields the drift term parameters for the j-th future step. .

[0058] Obtaining future degradation increments based on future drift term parameters: from a binary normal distribution The increment for the j-th step is obtained by sampling. .

[0059] Calculate the future degradation trajectory using future degradation increments: ,in, and For the future j-step degradation trajectory and For the future J-1 step degradation trajectory.

[0060] Build failure threshold and Failure determination is based on failure thresholds: if or Then let ; Otherwise, j = j + 1, and return S52.

[0061] The procedure is as follows: if or ( and (Failure threshold); ;

[0062] break; else; j = j + 1, return S52.

[0063] After repeating steps S51 to S54 L times to obtain L simulated remaining lifetime prediction results, the distribution of remaining lifetime and important indicators such as mean, median, and confidence interval can be obtained through simulation. Approximate estimate, where, Indicates remaining lifespan.

[0064] Furthermore, this embodiment uses full-life tool milling data to verify the method proposed in this embodiment.

[0065] First, features of each channel's data are extracted from the time domain, frequency domain, and time-frequency domain. The time domain features include five dimensional features: mean, variance, root mean square (RMS), absolute mean, and peak value; and six dimensionless features: waveform index, peak index, impulse index, margin, skewness, and kurtosis. The frequency domain signal consists of a full-band signal and sub-band signals, from which eleven features are extracted: spectral sum, spectral mean, spectral variance, spectral entropy, RMS, spectral kurtosis, spectral skewness, spectral shape mean, spectral shape variance, third moment, and fourth moment. Eight time-frequency domain features are generated through Haar wavelet packet transform and three-level decomposition.

[0066] By calculating the Pearson correlation coefficients between various features and tool wear values, highly representative features were selected as degradation indices. In Working Condition 1, the variance of the X-axis vibration signal in the 1000-2000Hz frequency band (correlation coefficient 0.964) and the time-domain variance of the Y-axis vibration signal (correlation coefficient 0.940) were selected as degradation indices. In Working Condition 2, the variances of the X-axis cutting force signal and the X-axis vibration signal in the 1000-2000Hz frequency band (correlation coefficients 0.949 and 0.937, respectively) were selected as degradation indices. Using the proposed signal transformation method, the degradation indices were transformed to the baseline machining parameters. Furthermore, the transformed signals were further smoothed using a moving average algorithm to reduce the influence of random noise; the moving average algorithm window size was set to 3.

[0067] like Figure 2 As shown, Figure 2 (a) is a distribution diagram of the results for the tool at sampling point 0. Figure 2 (b) is a distribution diagram of the tool at 220 sampling points. Figure 2 (c) is a distribution diagram of the tool at 110 sampling points. Figure 2 (d) is a distribution diagram of the tool at 330 sampling points. The four parts described above are plotted respectively at four sampling time points (t). k The approximate remaining lifetime distribution prediction results for (=0, 110, 220, 330) are shown. It can be seen that as degradation data accumulates, the variance of the remaining lifetime gradually decreases, and the point estimation results (mean) become closer and closer to the true value.

[0068] This invention provides an equipment remaining life prediction system that considers the coupling effect of degradation indicators. This system is used to implement the equipment remaining life prediction method that considers the coupling effect of degradation indicators as provided in the above embodiments.

[0069] Specifically, equipment remaining life prediction systems that consider the coupling effect of degradation indices include: The feature construction module is used to acquire monitoring signals, extract high-dimensional features from the monitoring signals, and construct a high-dimensional feature set. The indicator screening module is used to perform correlation analysis on the high-dimensional feature set and screen out the two high-dimensional features with the highest correlation as degradation indicators characterizing the degradation state of the equipment. An adaptive conversion module is used to convert the degradation index to a baseline operating condition using an adaptive signal conversion algorithm, thereby obtaining an adaptive degradation index for the operating condition. The coupling module is used to input the adaptive degradation index of the operating condition into a pre-built nonlinear binary Wiener process degradation model for binary Wiener degradation analysis to obtain the coupled degradation index. The simulation module is used to simulate the coupling degradation index using Monte Carlo simulation technology to obtain the equipment's remaining life prediction results.

[0070] This invention also provides an electronic device, such as... Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23, and an output device 24; the number of processors 21 in the computer device can be one or more. Figure 3 Taking a processor 21 as an example; the processor 21, memory 22, input device 23, and output device 24 in an electronic device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0071] The memory 22, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules. The processor 21 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 22, thereby implementing the equipment remaining life prediction method considering the coupling effect of degradation indicators described in the above embodiments.

[0072] The memory 22 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 22 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory, or other non-volatile solid-state storage device. In some instances, the memory 22 may further include memory remotely located relative to the processor 21, which can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0073] Input device 23 can be used to receive user input such as ID and password. Output device 24 is used to output the network configuration page.

[0074] This invention also provides a computer-readable storage medium, wherein the computer-executable instructions, when executed by a computer processor, are used to implement a method for predicting the remaining life of equipment considering the coupling effect of degradation indicators as provided in the above embodiments.

[0075] The storage medium containing computer-executable instructions provided in the embodiments of the present invention is not limited to the method operations provided in the above embodiments, but can also perform related operations in the equipment remaining life prediction method considering the coupling effect of degradation indexes provided in any embodiment of the present invention.

[0076] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting the residual life of equipment considering the coupling effect of degradation indicators, characterized in that, The method comprises the following steps: Step S1, obtaining a monitoring signal, extracting high-dimensional features from the monitoring signal, and constructing a high-dimensional feature set; Step S2, performing correlation analysis on the high-dimensional feature set, and screening out two high-dimensional features with the largest correlation as degradation indexes representing the degradation state of the equipment; Step S3, converting the degradation indexes to a reference working condition by using an adaptive signal conversion algorithm to obtain working condition adaptive degradation indexes; Step S4, inputting the working condition adaptive degradation indexes into a pre-constructed nonlinear bivariate Wiener process degradation model to perform bivariate Wiener degradation analysis, and obtaining coupled degradation indexes; Step S5, simulating the coupled degradation indexes by using a Monte Carlo simulation technique to obtain equipment residual life prediction results. 2.The method of claim 1, wherein, The method for converting the degradation indexes to the reference working condition by using the adaptive signal conversion algorithm comprises the following steps: Step S31, obtaining a sampling time point under a changed working condition, performing linear interpolation on the degradation indexes under the reference working condition based on the sampling time point to obtain degradation index estimation values; Step S32, calculating the error sum of squares between the degradation indexes and the degradation index estimation values, minimizing the error sum of squares to obtain a minimized error sum of squares function; Step S33, optimizing the minimized error sum of squares function by using a two-dimensional search optimization algorithm to obtain a relationship estimation value; Step S34, substituting the relationship estimation value into the degradation indexes under the changed working condition to obtain working condition adaptive degradation indexes. 3.The equipment residual life prediction method considering coupling effects of degradation indicators according to claim 1, wherein, The method for finding the mutual dependence relationship of the working condition adaptive degradation indexes by using the nonlinear bivariate Wiener process degradation model comprises: Step S41, performing logarithmic transformation on the working condition adaptive degradation indexes to obtain transformed working condition adaptive degradation indexes; Step S42, describing the correlation of the transformed working condition adaptive degradation indexes by using a bivariate Wiener process in the nonlinear bivariate Wiener process degradation model to obtain coupled degradation indexes; wherein the increment of the transformed working condition adaptive degradation indexes in any time interval in the bivariate Wiener process obeys a bivariate normal distribution, and the bivariate normal distribution is the coupled degradation index of the transformed working condition adaptive degradation indexes. 4.The method of claim 3, wherein, The step S4 further comprises the following steps: Obtaining historical data, and performing parameter estimation on the nonlinear bivariate Wiener process degradation model by using the historical data to obtain model parameter estimation values; Based on the model parameter estimation values, updating the random parameters in the nonlinear bivariate Wiener process degradation model by using the Bayes theorem.

5. The method of claim 4, wherein the degradation index coupling effect is considered. The method for performing parameter estimation on the nonlinear bivariate Wiener process degradation model by using the historical data comprises the following steps: The historical data is subjected to availability screening to obtain availability historical data; wherein the availability screening comprises: screening N available historical data from the historical data, and the nth equipment degradation index in the N available historical data is available at time , represents the number of available degradation indexes. Calculating historical bivariate index increment data of the nth equipment degradation index, and performing unbiased estimation on the mean and the covariance matrix in the nonlinear bivariate Wiener process degradation model by using the historical bivariate index increment data based on multivariate normal theory to obtain unbiased estimation parameters; Generating bootstrap samples from the historical data, and performing bootstrap estimation on the hyperparameters in the nonlinear bivariate Wiener process degradation model in combination with the bootstrap samples to obtain bootstrap hyperparameter estimation values.

6. The method for predicting the remaining life of equipment considering the coupling effect of degradation indicators according to claim 5, characterized in that, The time The interval time between adjacent time points is the same, and the interval time is set as . 7.The method of claim 1, wherein, The coupling degradation index is simulated by using a Monte Carlo simulation technique, including the following steps: In step S51, a bivariate normal distribution after parameter estimation in the nonlinear bivariate Wiener process degradation model is obtained, and a future drift term parameter is sampled from the bivariate normal distribution after parameter estimation; In step S52, a bivariate normal distribution after updating in the nonlinear bivariate Wiener process degradation model is obtained, and a future degradation increment is sampled from the bivariate normal distribution after updating based on the future drift term parameter; In step S53, a future degradation trajectory is calculated by using the future degradation increment; In step S54, a failure threshold is constructed, the future degradation trajectory is compared with the failure threshold, and if the future degradation trajectory is less than the failure threshold, steps S51 to S54 are repeated.

8. An electronic device, comprising: The equipment residual life prediction method considering coupling effects of degradation indexes comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the equipment residual life prediction method considering coupling effects of degradation indexes according to any one of claims 1 to 7 when executing the computer program.

Images