CN115186707A - Simple gear box fault detection method - Google Patents
Simple gear box fault detection method Download PDFInfo
- Publication number
- CN115186707A CN115186707A CN202210803111.0A CN202210803111A CN115186707A CN 115186707 A CN115186707 A CN 115186707A CN 202210803111 A CN202210803111 A CN 202210803111A CN 115186707 A CN115186707 A CN 115186707A
- Authority
- CN
- China
- Prior art keywords
- value
- gear
- data
- calculating
- sensitive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a simple gear box fault detection method, which is used for solving the technical problems of high complexity and poor accuracy of the conventional gear fault detection method. According to the method, m groups of vibration signals of the gear box are continuously acquired at equal intervals and preprocessed, and sensitive characteristics of gear faults are screened out; data preprocessing is carried out on the data with the sensitive characteristics; equally dividing the front q groups of data into p intervals, calculating the slope value of the sensitive feature in the ith interval by using a least square method, and constructing a data matrix by using the slope value; calculating the weight value of the sensitive feature by using an entropy method; calculating a gear degradation index of an ith interval by using a sum-product method and using a weight value and a slope value, and calculating an alarm value of the gear degradation index based on a central limit theorem; calculating a gear degradation index for the rear r group data; if the gear degradation index is larger than or equal to w, judging that the gear has a fault; otherwise, the gear is not malfunctioning. The invention can automatically detect the health condition of the gear box and obviously improve the accuracy of identifying the gear fault.
Description
Technical Field
The invention relates to the technical field of equipment state monitoring and fault diagnosis, in particular to a simple gearbox fault detection method.
Background
The gear box is a key device with wide application in mechanical equipment, and is mainly applied to the prop industry of national civilians such as manufacturing industry, coal, petrifaction, electric power, water conservancy and the like. Through carrying out health monitoring to the gear box, can discover the early fault of gear box, lifting means intelligence fortune dimension level avoids unplanned shutdown, reduces trouble emergence number of times, and lifting means operating efficiency ensures that equipment safety and stability moves.
Generally, when a bearing or a gear in a gearbox fails, a worker can hardly distinguish and judge the failure according to experience, and an expert generally judges the failure type by analyzing an impact component of a vibration map or an accurate failure frequency position. In the field of intelligent manufacturing, a monitoring method for accurately and automatically identifying faults of a gearbox is urgently needed in intelligent operation and maintenance and unattended scenes of the gearbox. Therefore, a new method for automatically identifying the fault of the gearbox, which is simple and accurate, is needed to be provided, the health condition of the gearbox is automatically detected, the predictive maintenance mode of the equipment is promoted to fall to the ground, and the cost of an enterprise is reduced, the quality is improved and the efficiency is increased.
The gear fault diagnosis method based on the combination of the VMD entropy method and the VPMCD with the application number of 202010270912.6 combines the variational modal decomposition VMD and the variable prediction model mode identification VPMCD, so that the gear vibration signal is purified, most useless noise interference signal components are filtered, the signal information is highlighted, and the gear fault diagnosis method has higher fault identification accuracy and higher identification efficiency on the gear fault. However, the processing method is complicated, the calculation amount is large, and the real-time fault recognition cannot be performed.
Disclosure of Invention
Aiming at the technical problems of high complexity and poor accuracy of the existing gear fault detection method, the invention provides a simple gear box fault detection method which can automatically detect the health condition of a gear box and obviously improve the gear fault identification accuracy.
In order to achieve the purpose, the technical scheme of the invention is realized as follows: a simple gearbox fault detection method comprises the following steps:
step 1: under a rated working condition, continuously acquiring m groups of vibration signals x (t) of the gear box at equal intervals, preprocessing the vibration signals x (t), respectively calculating characteristic values in a time domain, a frequency domain and a time-frequency domain, and screening out s sensitive characteristics of gear faults;
step 2: respectively carrying out data preprocessing on each m groups of data of the s sensitive features to obtain n groups of data of the s sensitive features;
and 3, step 3: equally dividing the front q groups of data of s sensitive features into p intervals, wherein the interval length L = q/p, and calculating the slope value k of the jth sensitive feature in the ith interval by using a least square method ij Using the slope value k ij Constructing a data matrix K of the jth sensitive characteristic; wherein i =1,2,. Cndot, p; j =1,2, \8230;, s;
and 4, step 4: according to the data matrix K, calculating the weighted value of the jth sensitive feature by using an entropy method
And 5: calculating gear deterioration index of ith interval by using sum-product method
Calculating an alarm value w of the gear degradation index based on a central limit theorem;
and 6: for r = n-q group data after s sensitive characteristics, when the data length reaches L, calculating the gear degradation index according to the slope value and the weight value of each sensitive characteristic
If gear deterioration index
Judging that the gear has a fault; otherwise, the gear is not malfunctioning.
Preferably, the sensitive feature comprises a single peak P k Envelope value E v And impact engagement index value I m (ii) a The impact engagement index value I m Comprises the following steps:
in the formula, root mean square value R v More than 0.1,1 times of meshing frequency value G m ＞0.1，100＞I m ＞0；W v As an index of the waveform, P k Is a single peak value, and k, v and m are subscripts.
Preferably, the preprocessing in step 1 is to remove a random noise signal in the vibration signal x (t) by a white noise inspection method; the data preprocessing in the step 2 comprises rejecting equipment shutdown data and alarm data and calculating median; the step of rejecting the equipment shutdown data refers to deleting the characteristic value calculated when the rotating speed is 0; the elimination of the equipment alarm data refers to the deletion of a characteristic value calculated when a single peak value exceeds a preset alarm value; and the median calculation means that a median is obtained for every 10 groups of data after the shutdown data is removed from the m groups of data.
Preferably, the least square method is used for calculating the slope value k of the jth sensitive feature in the ith interval ij The method comprises the following steps:
constructing a data matrix Y in the ith interval for the jth sensitive feature ij Using least squares to perform a unary linear fit of X β ij ＝Y ij And, and:
in the formula, y 1 -y L Is the jth sensitive characteristicL groups of data in the ith interval;
according to the formula beta ij ＝(X T X) -1 X T Y ij The slope value k of the fitting curve in the interval is obtained ij 。
Preferably, the entropy method is: the entropy value of the jth sensitive feature is:
wherein k is ij The value of the slope of the jth sensitive feature in the ith interval is, and p is the number of intervals;
weight value of jth sensitive feature
Comprises the following steps:
preferably, if the slope value is less than 0, the absolute value of the slope value is taken; if the slope value of a row is equal to 0, then a value is added to the row data at the same time, and the default is 0.01.
Preferably, the method of calculating the gear degradation index is: gear deterioration index of the ith section is
Where s is the total number of sensitive features.
Preferably, the implementation method of the central limit theorem is as follows: calculating gear degradation index
Mean μ and standard deviation σ of (d); and solving an alarm value w of the gear degradation index according to a 3sigma principle as follows: w = μ +3 σ.
The invention has the beneficial effects that: the gear degradation index of the sensitive characteristics is calculated through a sum-product method, and a plurality of sensitive characteristics of the gear faults are put together for processing, so that compared with a single index, the diagnosis accuracy is higher; the gear degradation index alarm value is calculated by adopting a central limit theorem on the basis of normal data; according to the 3sigma principle, when a fault occurs, the gear degradation index can exceed the alarm value. The invention combines the characteristics of the gear box, automatically detects the health condition of the gear box, obviously improves the accuracy of gear fault identification, promotes the equipment to land in a predictive maintenance mode, and assists enterprises to reduce cost, improve quality and improve efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of the present invention.
Fig. 2 is a digital model of the device according to the embodiment of the present invention.
Fig. 3 is a waveform spectrum diagram before and after an actual failure of the gearbox according to the embodiment of the invention, wherein (a) is before the failure and (b) is after the failure.
FIG. 4 is a trend chart of the sensitivity characteristics of the gearbox before and after actual failure of the gearbox according to the embodiment of the invention.
FIG. 5 is a field view of a broken gear of a gearbox according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
As shown in FIG. 1, a simple gearbox fault detection method comprises the following steps:
step 1: under a rated working condition, m groups of original vibration signals x (t) of the gear box are continuously collected at equal intervals, each group of vibration signals are preprocessed, characteristic values are calculated in a time domain, a frequency domain and a time-frequency domain respectively, and s gear fault sensitivity characteristics are screened out.
Under a rated working condition, m groups of original vibration signals x (t) of the gear box are continuously acquired at equal intervals, and the sampling frequency is f s And the number of sampling points is N, preprocessing each group of vibration signals x (t), and then respectively calculating corresponding characteristic values in a time domain, a frequency domain and a time-frequency domain. The signal preprocessing process is to remove random noise signals by a white noise detection method and keep normal signals. The time-frequency domain characteristic value is obtained by subjecting the vibration signal x (t) to a series of processes such as a Butterworth filter, fourier transform and inverse transform, hilbert-Huang transform, and the like. Wherein the time domain feature comprises a single peak P k Root mean square value R v Waveform index W v (ii) a The frequency domain characteristics include a 1-fold mesh frequency value G m (ii) a The time-frequency domain feature comprises an envelope value E v And impact engagement index value I m 。
Impact value of mesh I m The calculation formula is as follows:
in the formula, root mean square value R v More than 0.1,1 times of meshing frequency value G m ＞0.1，100＞I m ＞0。W v As an index of the waveform, P k Is a single peak. The subscripts k, v, m denote the difference in peak, envelope and mesh frequency, respectively.
Selecting a Peak value P k Envelope value E v And impact engagement index value I m S =3 here, a sensitive feature of gear failure.
Under a rated working condition, m groups of original vibration signals x (t) (the sampling frequency is f) of a mill gearbox measuring point 5 are continuously acquired at equal intervals s =5120Hz, the number of sampling points is N = 8192), the digital model of the mill is as shown in fig. 2, the motor is powered onThe gear box is connected with the coal mill, and the gear box and the coal mill are connected through a gear and a gear shaft. Information on the device structure, the type of sensor mounted, and the position of the measurement point can be seen in fig. 2. Here, m =2098.
The gearbox gear parameters and meshing frequency are shown in table 1.
TABLE 1 Gear parameters and mesh frequency (Hz) of the gearbox
As shown in fig. 3, by comparing waveform frequency spectrograms before and after the gear box fault occurs, the impact characteristic of the waveform chart is obvious, and the change of a single peak is obvious; the amplitude of the sideband at the gear meshing frequency on the spectrogram changes obviously, namely the envelope value changes obviously.
As shown in fig. 4, a single peak P k Envelope value E v And impact engagement index I m The value varies significantly with the occurrence of gear failure, so a single peak value P is selected k Envelope value E v And impact engagement index value I m For gear failure sensitive features, here s =3.
Step 2: and respectively carrying out data preprocessing on each m group of data of the s sensitive features to obtain n groups of data of the s sensitive features.
The data preprocessing process comprises the steps of rejecting equipment shutdown data and alarm data and calculating median; the step of rejecting the equipment shutdown data refers to deleting the characteristic value calculated when the rotating speed is 0; the elimination of the equipment alarm data refers to the deletion of the calculated characteristic value when the single peak value exceeds a preset alarm value; and the median is calculated by removing the shutdown data from the m groups of data and acquiring a median for each 10 groups of data. The purpose of calculating the median is to improve the accuracy of gear fault recognition and avoid misjudgment caused by low signal acquisition quality at a certain moment.
Single peak value P k Envelope value E v And impact engagement index value I m The median trend graph of (a) is shown in fig. 4, where n =210. Selecting the front 90 groups of data as normal characteristic data of the gear box for calculating the gear degradation index valueA baseline value and an alarm value. The 90 sets of data were used to verify the gear degradation index value utility.
And step 3: equally dividing the front q groups of data of s sensitive features into p intervals, and calculating the slope value k of the ith interval by using a least square method i Constructing a data matrix k of the jth sensitive characteristic ij (ii) a Wherein i =1,2,.. P; j =1,2, \ 8230;, s.
Dividing n groups of data of a certain sensitive characteristic into p intervals with interval length L = n/p, constructing a data matrix in the ith interval, and performing unary linear fitting X beta = Y by using a least square method, namely solving a parameter beta by using a known matrix X and Y,
in the formula, y 1 -y L And the data is the L groups of data in the ith interval of the sensitive characteristic.
According to the formula β = (X) T X) -1 X T Y, calculating the slope k = beta of a fitting curve in the interval, and calculating the slope value k of the feature data in all the intervals of the sensitive feature by analogy i I =1,2. The effect of the partitions is to find the changes in the curve, i.e. between the partitions.
Repeating the above process to calculate all slope values k of s sensitive features in p intervals ij Constructing a data matrix k ij (i =1,2, \8230;, p; j =1,2, \8230;, s). Here, s =3,q =90,p =18,l =5.
And 4, step 4: according to the data matrix k ij Calculating the weighted value of the jth sensitive feature by using an entropy method
For data matrix k ij Calculating the weight of s sensitive features by using an entropy method
The calculation formula of the entropy value method is as follows:
wherein e is j Entropy value, k, of the j-th sensitive feature ij The value of the slope of the jth sensitive feature in the ith interval is p, the number of the intervals is p, and the number of the sensitive features is s.
If a certain slope value is less than 0, taking an absolute value of the slope value; if the slope value of a certain row is equal to 0, a value is added to the row of data at the same time, and the entropy calculation method cannot have negative numbers and defaults to 0.01.
The formula for calculating the weight value of the jth sensitive feature is as follows:
wherein, the first and the second end of the pipe are connected with each other,
is the weight value of the jth sensitive feature.
A single peak P as shown in Table 2 k Envelope value E v And impact engagement index value I m The weights of the three sensitive features are 0.213, 0.422 and 0.366, respectively.
TABLE 2 sensitive characteristic index parameters and calculated values
And 5: calculating a gear degradation index of an i-th zone using a sum-product method
And calculating an alarm value w of the gear degradation index based on the central limit theorem.
Index of gear deterioration
The calculation formula adopted is as follows:
wherein, the first and the second end of the pipe are connected with each other,
is the gear degradation index value of the ith interval.
Calculating a gear degradation index based on the central limit theorem
Mean μ and standard deviation σ of (d); and (3) solving an alarm value w of the gear degradation index according to a 3sigma principle, wherein a calculation formula is as follows:
w＝μ+3σ
as shown in table 2, the baseline value and the alarm value of the gear degradation index value were 0.065 and 0.163, respectively. The baseline value of the gear degradation index value is the mean value μ in order to calculate the degradation index alarm value.
And 6: for r groups of data after s sensitive features, r = n-q, when the data length reaches L, the slope k of each sensitive feature is used ij Combining weight values of sensitive features
Calculating a gear degradation index
If gear deterioration index
The gear is described to be in fault; otherwise, the gear is not malfunctioning. And when the data length does not reach L, continuing to wait until the data length reaches L.
Comparing fig. 4 and table 2, it is understood that the calculated gear deterioration index significantly changes when the tendency deteriorates. The gear deterioration index values in the 101 th to 105 th intervals and 176 th to 180 th intervals in fig. 4 are 0.687 and 0.415, respectively, which exceed the baseline value and the alarm value. Wherein, the interval 101-105 calculates the largest deterioration index value. As shown in fig. 5, the manual on-site shutdown maintenance confirms that the gear-breaking fault occurs in the gear box; through comparison with the on-site fault occurrence time, the interval just corresponds to the equipment fault occurrence time, and the gear degradation index can accurately identify faults such as gear breakage, tooth surface meshing and the like of the gear box.
In conclusion, the method provided by the invention can automatically detect the health condition of the gear box by combining the characteristics of the equipment, obviously improve the accuracy of gear fault identification, and has high engineering application value for assisting enterprises to realize predictive maintenance of the equipment.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (8)
1. A simple gearbox fault detection method is characterized by comprising the following steps:
step 1: under a rated working condition, continuously acquiring m groups of vibration signals x (t) of the gear box at equal intervals, preprocessing the vibration signals x (t), respectively calculating characteristic values in a time domain, a frequency domain and a time-frequency domain, and screening out s sensitive characteristics of gear faults;
step 2: respectively carrying out data preprocessing on each m group of data of the s sensitive features to obtain n groups of data of the s sensitive features;
and 3, step 3: equally dividing the front q groups of data of s sensitive features into p intervals, wherein the interval length L = q/p, and calculating the slope value k of the jth sensitive feature in the ith interval by using a least square method ij Using the slope value k ij Constructing a data matrix K of the jth sensitive feature; wherein i =1,2,.. P; j =1,2,. Said, s;
and 4, step 4: according to the data matrix K, calculating the weighted value of the jth sensitive feature by using an entropy method
And 5: calculating a gear degradation index of an i-th zone using a sum-product method
Calculating an alarm value w of the gear degradation index based on a central limit theorem;
step 6: for r = n-q group data after s sensitive features, when the data length reaches L, calculating the gear degradation index according to the slope value and the weighted value of each sensitive feature
If gear deterioration index
Judging that the gear has a fault; otherwise, the gear is not malfunctioning.
2. The simple gearbox fault detection method of claim 1, wherein the sensitive characteristic comprises a single peak value P k Envelope value E v And impact engagement index value I m (ii) a The impact engagement index value I m Comprises the following steps:
in the formula, root mean square value R v More than 0.1,1 times of meshing frequency value G m ＞0.1，100＞I m ＞0；W v As an index of the waveform, P k Is a single peak value, and k, v and m are subscripts.
3. The simple gearbox fault detection method as claimed in claim 1 or 2, wherein the preprocessing in step 1 is to remove random noise signals in the vibration signal x (t) by a white noise inspection method; the data preprocessing in the step 2 comprises removing equipment shutdown data and alarm data and calculating median; the step of rejecting the equipment shutdown data refers to deleting the characteristic value calculated when the rotating speed is 0; the elimination of the equipment alarm data refers to the deletion of a characteristic value calculated when a single peak value exceeds a preset alarm value; and the median is calculated by removing the shutdown data from the m groups of data and acquiring a median for each 10 groups of data.
4. The simple gearbox fault detection method as claimed in claim 3, wherein the least square method is used for calculating the slope value k of the jth sensitive feature in the ith interval ij The method comprises the following steps:
constructing a data matrix Y in the ith interval for the jth sensitive feature ij Using least squares to perform a unary linear fit of X β ij ＝Y ij And:
in the formula, y 1 -y L The L groups of data in the ith interval are used as the jth sensitive characteristic;
according to the formula beta ij ＝(X T X) -1 X T Y ij Determining the slope value k of the fitted curve in the interval ij 。
5. The simple gearbox fault detection method according to claim 1 or 4, characterized in that the entropy method is: the entropy value of the jth sensitive feature is:
wherein k is ij The value of the slope of the jth sensitive feature in the ith interval is, and p is the number of intervals;
weight value of jth sensitive feature
Comprises the following steps:
6. the simple gearbox fault detection method as recited in claim 5, wherein if the slope value is less than 0, then the absolute value of the slope value is taken; if the slope value of a row is equal to 0, then a value is added to the row data at the same time, and the default is 0.01.
7. The simplified gearbox fault detection method of claim 6, wherein the method of calculating a gear degradation index is: the gear deterioration index of the ith interval is
Where s is the total number of sensitive features.
8. The simple gearbox fault detection method according to claim 1 or 7, characterized in that the central limit theorem is implemented by the following method: calculating gear degradation index
Mean μ and standard deviation σ of (d); and solving an alarm value w of the gear degradation index according to a 3sigma principle as follows: w = μ +3 σ.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210803111.0A CN115186707A (en) | 2022-07-07 | 2022-07-07 | Simple gear box fault detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210803111.0A CN115186707A (en) | 2022-07-07 | 2022-07-07 | Simple gear box fault detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115186707A true CN115186707A (en) | 2022-10-14 |
Family
ID=83517161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210803111.0A Pending CN115186707A (en) | 2022-07-07 | 2022-07-07 | Simple gear box fault detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115186707A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117906946A (en) * | 2024-03-20 | 2024-04-19 | 江苏金恒信息科技股份有限公司 | Gear fault alarm method based on multi-scale peak searching |
-
2022
- 2022-07-07 CN CN202210803111.0A patent/CN115186707A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117906946A (en) * | 2024-03-20 | 2024-04-19 | 江苏金恒信息科技股份有限公司 | Gear fault alarm method based on multi-scale peak searching |
| CN117906946B (en) * | 2024-03-20 | 2024-05-31 | 江苏金恒信息科技股份有限公司 | Gear fault alarm method based on multi-scale peak searching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108388860B (en) | Aero-engine rolling bearing fault diagnosis method based on power entropy spectrum-random forest | |
| CN109506921B (en) | Fault diagnosis and early warning method for rotary machine | |
| Yang et al. | Vibration feature extraction techniques for fault diagnosis of rotating machinery: a literature survey | |
| CN108805059B (en) | Sparse regularization filtering and self-adaptive sparse decomposition gearbox fault diagnosis method | |
| Lei et al. | Gear crack level identification based on weighted K nearest neighbor classification algorithm | |
| CN109214355B (en) | Mechanical monitoring data abnormal section detection method based on kernel estimation LOF | |
| CN105181019A (en) | Computer program product for early fault early-warning and analysis of rotation type machine | |
| CN111170103B (en) | Equipment fault identification method | |
| CN109469896B (en) | Industrial boiler fault diagnosis method and system based on time series analysis | |
| DE102009026128A1 (en) | System and method for detecting stall and surge | |
| Guo et al. | An enhanced modulation signal bispectrum analysis for bearing fault detection based on non-Gaussian noise suppression | |
| CN105865794A (en) | Engine misfire fault diagnosis method based on short-time Fourier transformation and principal component analysis | |
| CN111927717B (en) | System and method for online monitoring noise of transmission chain of fan engine room | |
| CN115186707A (en) | Simple gear box fault detection method | |
| CN116893036A (en) | Plunger pump leakage diagnosis method with smooth acceleration signal sequence time window characteristics | |
| CN116877452B (en) | Non-positive-displacement water pump running state monitoring system based on Internet of things data | |
| DE102010005525A1 (en) | Method for condition monitoring of a machine and monitoring device therefor | |
| CN114754899A (en) | Fault diagnosis method and system for temperature sensor of scavenging box of marine main engine | |
| CN114184375A (en) | Intelligent diagnosis method for common faults of gear box | |
| CN112798044A (en) | Remote intelligent monitoring system for transmission chain of wind turbine generator | |
| CN113049251A (en) | Bearing fault diagnosis method based on noise | |
| TWI398629B (en) | Equipment supervision method | |
| Tajiani et al. | RUL prediction of bearings using empirical wavelet transform and Bayesian approach | |
| CN113447264B (en) | Online acoustic monitoring and diagnosing method for tooth breakage fault of planetary gear box | |
| WO2021128985A1 (en) | Device fault recognition systen and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |