A method for evaluating the remaining service life of bearings

Abstract

The present invention discloses a method for evaluating the remaining useful life of a bearing, which specifically relates to the field of bearing technology, and includes the following steps: applying a simulated inverter-driven motor common-mode voltage to an intact bearing until the bearing fails, so as to observe key events that severely damage the bearing; obtaining vibration, current and temperature data of the bearing during its operation to failure, and obtaining original vibration, current and temperature samples; determining discharge events in the original current samples based on a wavelet decomposition method; extracting key vibration characteristics in the original vibration samples based on a time-domain statistical moment method; obtaining a prediction result of the remaining useful life of the bearing based on temperature data, key vibration characteristics and discharge events, and using an extended Kalman filter method; using the surge in bearing discharge events as a clue to start estimating the RUL of the bearing, compared with RUL estimation starting from the bearing life, this new RUL estimation algorithm provides more accurate results and requires less computing time.

Description

Technical Field

[0001] The present invention belongs to the technical field of bearings, and in particular relates to a method for evaluating the remaining service life of a bearing. Background Art

[0002] Bearings are common components in mechanical equipment, carrying the rotational motion of the equipment. Therefore, their performance directly impacts the performance and reliability of the entire machine. Bearing fault diagnosis and prediction have received considerable attention in recent years. Bearing failures can be caused by a variety of factors, including overheating, excessive axial and radial loads, and electrical stresses such as bearing currents. During normal motor operation, all of these factors can accelerate bearing degradation and shorten the lifespan of motor bearings. Developing a method to assess motor bearing lifespan is crucial for optimizing the performance of motor bearings in equipment, ensuring safe, efficient, and long-lasting operation.

[0003] Among the various factors affecting motor bearing life, the most significant is the common-mode voltage generated by the inverter, which in turn induces shaft currents in the bearings. The most destructive of these various shaft currents is electrical discharge machining (EDM) current. EDM current can cause extensive damage to bearings, creating pits in the rotating elements and ultimately leading to bearing failure. Therefore, it is crucial to develop a method for assessing the remaining useful life of bearings to accurately diagnose and predict bearing faults. This provides a reliable basis for the design, use, and maintenance of motor bearings, ensuring proper operation and extending their service life. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for evaluating the remaining service life of a bearing, so as to solve the technical problems that the condition of the current motor bearing is difficult to evaluate and the failure and life of the motor bearing cannot be accurately predicted during actual operation.

[0005] In order to achieve the above object, a method for evaluating the remaining service life of a bearing is provided, and the evaluation method includes the following steps:

[0006] S1. Apply a common-mode voltage simulated by the inverter-driven motor to a healthy bearing until the bearing fails, in order to observe the critical events that severely damage the bearing.

[0007] S2. Acquire vibration, current, and temperature data of the bearing during its operation to failure, and obtain original vibration, current, and temperature samples;

[0008] S3, extract key vibration characteristics from the original vibration samples based on the statistical moment method in the time domain;

[0009] S4, determining discharge events in the original current sample based on the wavelet decomposition method;

[0010] S5. Based on temperature data, key vibration characteristics, and discharge events, and using the extended Kalman filter method, obtain the prediction result of the remaining life of the bearing;

[0011] S6. Make timely adjustment strategies based on the operating conditions of the motor bearings.

[0012] Furthermore, in step S2, the method of obtaining the vibration, current, and temperature data of the bearing during the process of running to failure and obtaining the original vibration, current, and temperature samples specifically includes:

[0013] The original temperature samples were measured by T-type thermocouples and obtained using a timed sampling method;

[0014] The original vibration sample is measured by placing an acceleration sensor in the horizontal direction of the bearing base, and the measurement interval and sampling time are fixed;

[0015] The original current samples are collected in real time by current sensors and voltage sensors.

[0016] Furthermore, the time domain statistical moment method in step S3 includes:

[0017] Select the root mean square frequency feature, the formula is as follows:

[0018]

[0019] Among them, n is the number of frequency samples, X fft,i is the i-th sample of the Fourier transform of the vibration signal.

[0020] Furthermore, the method for determining the discharge event in the original current sample based on the wavelet decomposition method in step S4 specifically includes:

[0021] S4-1: Wavelet decomposition decomposes the signal into different scales and frequency bands through multi-resolution analysis. The specific steps are as follows:

[0022] (1) Select Haar as the small fundamental wave function;

[0023] (2) Select the number of decomposition levels based on the sampling frequency and signal characteristics;

[0024] (3) Use discrete wavelet transform to decompose the original current signal into low-frequency (approximate part) and high-frequency (detail part) components;

[0025] S4-2: The specific steps for extracting discharge event features are:

[0026] (1) Locate the frequency range of the discharge event. The discharge event usually manifests as a high-frequency component, and locate its level in the wavelet decomposition;

[0027] (2) Extract high-frequency features and extract characteristic signals from the high-frequency detail coefficients obtained by decomposition;

[0028] (3) Calculate the energy characteristics. The energy of the discharge event is concentrated in the high frequency. Calculate the energy of the high frequency coefficient of each layer, and highlight the layer with energy jump, which may be a discharge event.

[0029] (4) Find the mutation point and use the threshold method to locate the mutation point in the high-frequency coefficient;

[0030] S4-3: The specific steps for determining a discharge event are:

[0031] (1) Reconstruct the signal by performing wavelet reconstruction on the high-frequency components containing the discharge event to restore the time domain signal of the frequency band;

[0032] (2) Analyze the time domain waveform of the reconstructed signal in combination with the time characteristics to determine whether there is a short-term pulse that meets the characteristics of the discharge event;

[0033] (3) Statistical characteristics: Statistical analysis is performed on multiple collected data to verify the repeatability and distribution characteristics of the discharge events.

[0034] Furthermore, in step S5, the method for obtaining the prediction result of the remaining life of the bearing based on the temperature data, key vibration characteristics and discharge events and using the extended Kalman filter method specifically includes:

[0035] S5-1: Based on the discharge event, a historical record of discharge events in a specified time of m minutes is established, the number of discharges is accumulated within a certain period of time, and a linear function a+bt is fitted to the current discharge event in the last m minutes. The normalized mean square error between this fitted line and the actual data points is calculated. If the normalized mean square error exceeds the preset threshold, the event flag is triggered, the inflow point of the current discharge event is found, and an appropriate threshold is set to capture the occurrence of high discharge inflow points;

[0036] S5-2: Using a sharp increase in bearing discharge events within a short period of time as an indicator, the remaining service life prediction begins. The training of the extended Kalman filter begins after m minutes, and then the discharge events are tracked over time to detect the current inflow discharge event. If this inflow event is realized, the remaining service life of the bearing will be predicted based on vibration using the extended Kalman filter.

[0037] Furthermore, based on the calculated root mean square frequency characteristics, the best fitting exponential function is determined to be ae bt form.

[0038] Furthermore, a method for predicting the remaining service life of a bearing based on vibration using an extended Kalman filter specifically includes:

[0039] (1) Perform curve fitting on the training data, extract the root mean square frequency characteristics and establish the best fitting form as ae bt The exponential function of is used as the observation model B;

[0040] (2) Based on the new measurement point, dynamically update the Kalman filter parameters and continue to perform an estimate of the remaining useful life of the

[0041] (3) Based on the Kalman filter parameters and fault threshold, the remaining service life of the bearing is predicted.

[0042] Furthermore, the Kalman filter parameters are dynamically updated based on the new measurement point, and the The methods for estimating the remaining useful life include:

[0043] In the extended Kalman filter, the state transition model and observation model are shown in the following formulas:

[0044] x k =f(x k-1 ,u k-1 )+w k-1

[0045] z k =h(x k )+v k

[0046] Among them, x k is the state to be estimated, f is the nonlinear function of the state, h is the measurement function, u k is the input, z k is the measurement of sample k at time instant, w k and v k The covariance matrix is ​​Q k and R k , zero-mean Gaussian noise;

[0047] Once f and h have been determined, they must be locally linearized around the estimated state by computing their respective Jacobians, yielding matrices F and H, respectively;

[0048] in, It describes how small changes in the state vector around time k affect the state at time k+1; It describes how small changes in the state vector affect the observables;

[0049] If the state transition model is defined by the continuous-time state equation dx / dt = Ax(t) + Lw(t), where A and L are matrices representing the model, x is the state vector, and w is a vector with power spectral density Q c Gaussian white noise, and then use To discretize it, where δt k is the time step to find the state transition matrix F; the matrix L is used to calculate Q k :

[0050]

[0051] Where τ represents the integral variable of the matrix exponential function, and T represents the transpose of the matrix L;

[0052] The first step of the extended Kalman filter is prediction, using the predicted state estimate and the error covariance matrix

[0053]

[0054] Assuming there is no input, when a measurement value is received, the difference is updated to the extended Kalman filter, using the relationship between the predicted value and the measured value:

[0055]

[0056] Among them, K k is the Kalman gain; represents the transpose of the observation matrix at time k;

[0057] In order to predict the remaining service life of a bearing, a failure threshold is defined:

[0058]

[0059] Among them, γ i is the value of the training set at each failure, K is the number of training datasets, and is determined using a dataset containing only vibration data.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] This life assessment method uses the surge in bearing discharge events as a clue to start estimating the bearing's RUL. Compared with RUL estimation starting from the bearing's life, this new RUL estimation algorithm provides more accurate results and requires less computation time. The method also provides some insights into the bearing's hidden health status by linking the accumulated discharge volume with the bearing vibration.

[0062] Based on the implementation methods provided in the above aspects, this application can also be further combined to provide more implementation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0064] Figure 1 This is a flow chart of the method for evaluating the remaining service life of a bearing according to the present invention. DETAILED DESCRIPTION

[0065] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention. Unless otherwise specified, the technical means used in the embodiments are conventional means well known to those skilled in the art.

[0066] The embodiment of the present invention provides a method for evaluating the remaining service life of a bearing. Figure 1 , Figure 1 A flowchart of a method for evaluating the remaining useful life of a bearing provided by an embodiment of the present invention. The evaluation method includes the following steps:

[0067] S1. Apply a common-mode voltage simulated by the inverter-driven motor to a healthy bearing until the bearing fails, in order to observe the critical events that severely damage the bearing.

[0068] S2. Acquire vibration, current, and temperature data of the bearing during its operation to failure, and obtain original vibration, current, and temperature samples;

[0069] S3, extract key vibration characteristics from the original vibration samples based on the statistical moment method in the time domain;

[0070] S4, determining discharge events in the original current sample based on the wavelet decomposition method;

[0071] S5. Based on temperature data, key vibration characteristics, and discharge events, and using the extended Kalman filter (EKF) method, the remaining life (RUL) of the bearing is predicted.

[0072] S6. Make timely adjustment strategies based on the operating conditions of the motor bearings.

[0073] A method for estimating the remaining useful life of a bearing, provided by an embodiment of the present invention, uses surges in bearing discharge events as a clue to begin estimating the bearing's RUL. Compared to RUL estimation based on the bearing's lifespan, this new RUL estimation algorithm provides more accurate results and requires less computation time. This method also provides insights into the bearing's hidden health status by linking accumulated discharges with bearing vibration.

[0074] In one embodiment, in step S1, an actual intact bearing is subjected to electrical stress during the operation of its bearing shaft to ensure that the bearing starts to run until the bearing fails, so as to observe the key events that seriously damage the bearing. The applied voltage is intended to simulate the common mode voltage from the inverter-driven motor, thereby allowing EDM current to flow through the bearing, and this current is used as the main cause of accelerated bearing aging.

[0075] In one embodiment, the method of obtaining vibration, current, and temperature data of the bearing during operation to failure in step S2 to obtain original vibration, current, and temperature samples specifically includes:

[0076] The original temperature samples are obtained by measuring with a T-type thermocouple and using a timed sampling method; the original vibration samples are measured by placing an acceleration sensor horizontally on the bearing base, and the measurement interval and sampling time are fixed; the original current samples are collected in real time using current sensors and voltage sensors.

[0077] In one embodiment, in step S4, key bearing vibration characteristics are extracted from the bearing vibration data based on statistical moments in the time domain. At the beginning of operation, the vibration amplitude is at its lowest point. At the end of operation, when the bearing begins to fail, the vibration amplitude increases exponentially. Some common features that capture trends in bearing vibration data are statistical moments from the time domain, such as variance, and root mean square frequency from the frequency domain. This method uses the root mean square frequency, and the formula is as follows:

[0078]

[0079] Among them, n is the number of frequency samples, X fft,i is the i-th sample of the Fourier transform of the vibration signal.

[0080] In one embodiment, the method for determining the discharge event in the original current sample based on the wavelet decomposition method in step S3 specifically includes:

[0081] S3-1: Wavelet decomposition decomposes the signal into different scales and frequency bands through multi-resolution analysis. The specific steps are as follows:

[0082] (1) Wavelet decomposition decomposes the signal into different scales and frequency bands through multi-resolution analysis (MRA), which facilitates the extraction of the characteristics of discharge events;

[0083] (2) Select the number of decomposition levels based on the sampling frequency and signal characteristics;

[0084] (3) Use discrete wavelet transform to decompose the original current signal into low-frequency (approximate part) and high-frequency (detail part) components;

[0085] S3-2: The specific steps for extracting discharge event features are:

[0086] (1) Locate the frequency range of the discharge event. The discharge event usually manifests as a high-frequency component, and locate its level in the wavelet decomposition;

[0087] (2) Extract high-frequency features and extract characteristic signals from the high-frequency detail coefficients obtained by decomposition;

[0088] (3) Calculate the energy characteristics. The energy of the discharge event is concentrated in the high frequency. Calculate the energy of the high frequency coefficient of each layer, and highlight the layer with energy jump, which may be a discharge event.

[0089] (4) Find the mutation point and use the threshold method to locate the mutation point in the high-frequency coefficient;

[0090] S3-3: The specific steps for determining a discharge event are:

[0091] (1) Reconstruct the signal by performing wavelet reconstruction on the high-frequency components containing the discharge event to restore the time domain signal of the frequency band;

[0092] (2) Analyze the time domain waveform of the reconstructed signal in combination with the time characteristics to determine whether there is a short-term pulse that meets the characteristics of the discharge event;

[0093] (3) Statistical characteristics: Statistical analysis is performed on multiple collected data to verify the repeatability and distribution characteristics of the discharge events.

[0094] Specifically, the detection and tracking of EDM (Electro-spark machining) current: During actual bearing operation, the bearing has three states: ohmic, capacitive, and discharge. As the bearing degrades, it begins to switch between the three electrical states. When a spike appears in the current waveform recorded within a time period, it indicates that a discharge event has occurred.

[0095] A large influx of bearing discharge events within a short period of time can cause significant, irreversible damage to the bearing, thereby accelerating failure.

[0096] This method uses a wavelet decomposition-based method to detect discharge events in the original current sample: First, each current sample is decomposed by Haar wavelet. Assume that the decomposition level is 8. The reason for choosing Haar wavelet is that it is very similar to the square wave properties of bearing current data and is an ideal choice for detecting discontinuous wavelets. In the wavelet domain, each discharge event can be observed in the signal reconstructed in the subspace spanned by a given 8-level wavelet function. The following is the 8-level wavelet function:

[0097]

[0098] Where n is the length of the signal, d 8,k is the 8th layer wavelet coefficient, ψ is the wavelet function, which is Haar wavelet in this case; this reconstruction or projection of the subspace will produce a significant peak when the current discharge event occurs; on the contrary, the current sample without a discharge event has no obvious peak; in order to determine whether a fault has occurred, a threshold T = μ(D8) + 4σ(D8) is selected, where D8 = [D8(1)D8(2)...D8(N)] is the vector of projected signal samples in the subspace, μ is the mean, and σ is the standard deviation; whenever the reconstructed signal crosses the threshold, T is classified as a bearing discharge event;

[0099]

[0100] DE(K) is a switching function that outputs 1 or 0 depending on whether D8(k) exceeds the threshold T;

[0101] These discharge events were then tracked over time to obtain a cumulative sum; at some point during the run, the number of discharge events per minute increased, and after a critical period in the discharge event profile, the amplitude of the vibration also began to increase exponentially.

[0102] In one embodiment, the method for obtaining the prediction result of the remaining life of the bearing based on the temperature data, key vibration characteristics and discharge events and using the extended Kalman filter method in step S5 specifically includes:

[0103] S5-1: Based on the discharge event, a historical record of discharge events in a specified time of m minutes is established, the number of discharges is accumulated within a certain period of time, and a linear function a+bt is fitted to the current discharge event in the last m minutes. The normalized mean square error (NMSE) between this fitted line and the actual data points is calculated. If the normalized mean square error exceeds the preset threshold, the event flag is triggered, the inflow point of the current discharge event is found, and an appropriate threshold is set to capture the occurrence of high discharge inflow points;

[0104] S5-2: Using a sharp increase in bearing discharge events within a short period of time as an indicator, the remaining service life prediction begins. The training of the extended Kalman filter begins after m minutes, and then the discharge events are tracked over time to detect the current inflow discharge event. If this inflow event is realized, the remaining service life of the bearing will be predicted based on vibration using the extended Kalman filter.

[0105] In one embodiment, the best fitting exponential function is determined to be ae based on the calculated root mean square frequency characteristics. bt form.

[0106] In one embodiment, a method for predicting the remaining useful life of a bearing based on vibration using an extended Kalman filter specifically includes:

[0107] (1) Perform curve fitting on the training data, extract the root mean square frequency characteristics and establish the best fitting form as ae bt The exponential function of is used as the observation model h;

[0108] (2) Based on the new measurement point, dynamically update the Kalman filter parameters and continue to perform an estimate of the remaining useful life of the

[0109] (3) Based on the Kalman filter parameters and fault threshold, the remaining service life of the bearing is predicted.

[0110] In one embodiment, the Kalman filter parameters are dynamically updated based on the new measurement point, and the Kalman filter is continued based on the The methods for estimating the remaining useful life include:

[0111] In the extended Kalman filter, the state transition model and observation model are shown in the following formulas:

[0112] x k =f(x k-1 ,u k-1 )+w k-1

[0113] z k =h(x k )+v k

[0114] in, is the state to be estimated, f is the nonlinear function of the state, h is the measurement function (nonlinear function of the state), u k is the input, z k is the measurement of sample k at time instant, w k and v k The covariance matrix is ​​Q k and R k , zero-mean Gaussian noise;

[0115] Once f and h have been determined, they must be locally linearized around the estimated state by computing their respective Jacobians, yielding matrices F and H, respectively;

[0116] in, It describes how small changes in the state vector around time k affect the state at time k+1. It describes how small changes in the state vector affect the observable.

[0117] If the state transition model is defined by the continuous-time state equation dx / dt = Ax(t) + Lw(t), where A and L are matrices representing the model, x is the state vector, and w is a vector with power spectral density Q c Gaussian white noise, and then use (δt k is the time step) to discretize it to find the state transition matrix F; the matrix L is used to calculate Q k ;

[0118]

[0119] Where τ represents the integral variable of the matrix exponential function, and T represents the transpose of the matrix L;

[0120] The first step of EKF is prediction, using the predicted state estimate and the error covariance matrix

[0121]

[0122] Assuming there is no input, when a measurement is received, the difference is updated to the EKF, using the relationship between the predicted value and the measured value:

[0123]

[0124] Among them, K k is the Kalman gain; represents the transpose of the observation matrix at time k;

[0125] To predict the RUL of a bearing, a failure threshold is defined:

[0126]

[0127] where γi is the value of the training set at each failure, K is the number of training datasets, and is determined using a dataset containing only vibration data.

[0128] Specifically, first, curve fitting is performed on the training data to extract appropriate observations and establish the model h. For the root mean square frequency feature, the best fitting form is ae bt exponential function; secondly, select the state variable as x = [abω], where dω / dt = b; also assume that a and b are updated linearly: da / dt = w a and db / dt=w b , where w a and w b is a Gaussian white process; the continuous-time state equation used in this method is:

[0129]

[0130] in:

[0131]

[0132] To predict the RUL of a bearing, a failure threshold is defined:

[0133]

[0134] where γ i is the value of each independent training set at the time of failure, K is the number of training data sets, and is determined using a data set containing only vibration data; secondly, initialize the EKF and repeatedly run the prediction step until ae bt The value reaches the failure threshold The time to reach the threshold is taken as RUL. Finally, the EKF parameters are updated with each new measurement point, and the process continues based on RUL estimation.

[0135] The method of step S5 is summarized as follows: the training of the EKF starts after m minutes, and then the discharge events are tracked over time to detect the current inflow event. Once this event is achieved, the RUL estimation based on the vibration through the EKF is started.

[0136] Finally, make timely adjustment strategies based on the operating conditions of the motor bearings.

[0137] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for evaluating the remaining service life of a bearing, characterized in that: The evaluation method comprises the following steps: S1. Apply a common-mode voltage simulated by the inverter-driven motor to a healthy bearing until the bearing fails, in order to observe the critical events that severely damage the bearing. S2. Acquire the vibration, current, and temperature data of the bearing during its operation to failure, and obtain the original vibration, current, and temperature samples; S3. extracting key vibration characteristics from the original vibration sample based on a statistical moment method in the time domain; S4. Determine the discharge event in the original current sample based on a wavelet decomposition method; S5. Based on the temperature data, key vibration characteristics, and discharge events, and using an extended Kalman filter method, obtain a prediction result of the remaining life of the bearing; S6. Make timely adjustment strategies based on the operating conditions of the motor bearings; The method of obtaining the prediction result of the remaining life of the bearing based on the temperature data, key vibration characteristics and discharge events and using the extended Kalman filter method in step S5 specifically includes: S5-1: Based on the discharge event, a historical record of discharge events within a specified time of m minutes is established, the number of discharges is accumulated within a certain period of time, and a linear function a+bt is fitted to the current discharge event within the last m minutes. The normalized mean square error between the fitted line and the actual data points is calculated. If the normalized mean square error exceeds a preset threshold, an event flag is triggered, and the inflow point of the current discharge event is found. An appropriate threshold is set to capture the occurrence of a high discharge inflow point; S5-2: Using a sharp increase in bearing discharge events within a short period of time as an indicator, the remaining service life prediction begins. The training of the extended Kalman filter begins after m minutes, and then the discharge events are tracked over time to detect the current inflow discharge event. If this inflow event is realized, the remaining service life of the bearing will be predicted based on vibration using the extended Kalman filter.

2. The method for evaluating the remaining service life of a bearing according to claim 1, characterized in that: The method of obtaining the vibration, current, and temperature data of the bearing during the process of running to failure in step S2 to obtain the original vibration, current, and temperature samples specifically includes: The original temperature sample is measured by a T-type thermocouple and obtained using a timed sampling method; The original vibration sample is measured by placing an acceleration sensor in the horizontal direction of the bearing base, and the measurement interval and sampling time are fixed; The raw current samples are collected in real time by current sensors and voltage sensors.

3. The method for evaluating the remaining service life of a bearing according to claim 1, wherein: The time-domain statistical moment method described in step S3 includes: Select the root mean square frequency feature, the formula is as follows: ； Where n is the number of frequency samples, is the first Fourier transform of the vibration signal samples.

4. The method for evaluating the remaining service life of a bearing according to claim 1, wherein: The method for determining the discharge event in the original current sample based on the wavelet decomposition method in step S4 specifically includes: S4-1: The wavelet decomposition decomposes the signal into different scales and frequency bands through multi-resolution analysis. The specific steps are as follows: (1) Select Haar as the small fundamental wave function; (2) Select the number of decomposition layers based on the sampling frequency and signal characteristics; (3) Decompose the original current signal into low-frequency and high-frequency components using discrete wavelet transform; S4-2: The specific steps for extracting discharge event features are: (1) Locate the frequency range of the discharge event. The discharge event is manifested as a high-frequency component, and locate its level in the wavelet decomposition; (2) Extract high-frequency features and extract characteristic signals from the high-frequency detail coefficients obtained by decomposition; (3) Calculate the energy characteristics. The energy of the discharge event is concentrated in the high frequency. Calculate the energy of the high frequency coefficient of each layer. The layer with the most prominent energy jump is likely to be a discharge event. (4) Find the mutation point and use the threshold method to locate the mutation point in the high-frequency coefficient; S4-3: The specific steps for determining a discharge event are: (1) Reconstruct the signal by performing wavelet reconstruction on the high-frequency components containing the discharge event to restore the time domain signal of this frequency band; (2) Analyze the time domain waveform of the reconstructed signal based on the time characteristics to determine whether there is a short-term pulse that meets the characteristics of the discharge event; (3) Statistical characteristics: Statistical analysis is performed on multiple collected data to verify the repeatability and distribution characteristics of discharge events.

5. The method for evaluating the remaining service life of a bearing according to claim 3, wherein: Based on the calculation of the RMS frequency characteristics, it is determined that the best fitting exponential function is ae bt form.

6. The method for evaluating the remaining service life of a bearing according to claim 1, wherein: The method for predicting the remaining service life of a bearing based on vibration by using an extended Kalman filter in step S5-2 specifically includes: (1) Perform curve fitting on the training data, extract the root mean square frequency characteristics and establish the best fitting form as ae bt The exponential function of B ; (2) Based on the new measurement point, dynamically update the Kalman filter parameters and continue to perform an estimate of the remaining useful life of the It is expressed as the fault threshold; (3) Based on the Kalman filter parameters and fault threshold, the remaining service life of the bearing is predicted.

7. The method for evaluating the remaining service life of a bearing according to claim 6, characterized in that: Based on the new measurement point, the Kalman filter parameters are dynamically updated, and the The methods for estimating the remaining useful life include: In the extended Kalman filter, the state transition model and observation model are shown in the following formulas: ； in, is the state to be estimated, f is a nonlinear function of the state, h Measurement function, is the input, It is a time sample k The measurement, and The covariance matrices are and Zero-mean Gaussian noise; once f and h It has been determined that they must be locally linearized around the estimated state by computing their respective Jacobians, yielding the matrices F and H ; in, , which describes how small changes in the state vector around time k affect time k+1 Status; , which describes how a small change in the state vector affects the observable; If the state transition model is represented by the continuous-time state equation to define, where A and L is the matrix representing the model, x is the state vector, w It has a power spectral density Q c Gaussian white noise, and then use To discretize it, is the time step to find the state transition matrix F ;matrix L Used for calculation : ； in, τ represents the integral variable of the matrix exponential function, T Representative pair matrix L The transpose of The first step of the extended Kalman filter is prediction, using the predicted state estimate and the error covariance matrix : ； Assuming there is no input, when a measurement value is received, the difference is updated to the extended Kalman filter, using the relationship between the predicted value and the measured value: ； in, is the Kalman gain; Indicates time k The transpose of the observation matrix at ; In order to predict the remaining service life of a bearing, a failure threshold is defined: ； in, is the value of the training set at each failure, K is the number of training datasets and is determined using a dataset containing only vibration data.

Images