CN115356109A - Rolling bearing fault identification method and system - Google Patents
Rolling bearing fault identification method and system Download PDFInfo
- Publication number
- CN115356109A CN115356109A CN202211271086.2A CN202211271086A CN115356109A CN 115356109 A CN115356109 A CN 115356109A CN 202211271086 A CN202211271086 A CN 202211271086A CN 115356109 A CN115356109 A CN 115356109A
- Authority
- CN
- China
- Prior art keywords
- signal
- vibration
- information entropy
- target
- rolling bearing
- 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.)
- Granted
Links
- 238000005096 rolling process Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims abstract description 22
- 230000000737 periodic effect Effects 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims description 5
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000001133 acceleration Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
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
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a rolling bearing fault identification method and a system, which relate to the field of artificial intelligence, and the method comprises the following steps: acquiring all vibration signals of a rolling bearing to be detected from the beginning to the current time period; obtaining the information entropy fluctuation range of the vibration signals by using the variance and the local information entropy corresponding to each vibration signal; acquiring a vibration signal corresponding to local information entropy in an information entropy fluctuation range of the vibration signal and recording the vibration signal as an initial target vibration signal; obtaining a plurality of target vibration signals belonging to the same periodicity by using the time difference between any two initial target vibration signals; carrying out curve fitting on the local information entropy of the same periodic target vibration signal to obtain a fitting curve; clustering the slope of each point on each fitting curve to obtain multiple kinds of slopes, and determining whether the current rolling bearing is abnormal or not by using the difference value between the mean values of the slopes of the various kinds.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a rolling bearing fault identification method and system.
Background
Rolling bearing is one of common spare parts among the mechanical equipment for reduce the loss that the friction brought between axle and the axle in the operation in-process, and can play fine supporting role to the part normal operation between axle and the axle, when the bearing among the mechanical equipment damages, can lead to the operation precision of axle to reduce, and lead to partial part stress concentration to cause the part to damage, and then make whole equipment unable use, influence production efficiency, probably cause the incident even.
At present, most of the collected vibration signals of the rolling bearing are utilized to identify faults of the rolling bearing, similarity measurement is carried out on the vibration signals of the rolling bearing in the current time period and the vibration signals of the rolling bearing in the initial normal period, and whether the rolling bearing is abnormal or not is judged according to a set threshold value of a similarity measurement result.
Disclosure of Invention
The invention provides a rolling bearing fault identification method and system, which are used for automatically analyzing vibration signals of a rolling bearing to obtain a current rolling bearing fault identification result.
The invention discloses a rolling bearing fault identification method, which adopts the following technical scheme:
acquiring all vibration signals of a rolling bearing to be detected from the beginning to the current time period;
selecting a signal segment with set time length as a target signal segment of the vibration signal by taking each vibration signal as a center;
obtaining the local information entropy of each vibration signal by using the signal values of all the vibration signals in the target signal segment of each vibration signal;
acquiring the variance of the signal values of all the vibration signals in the target signal segment of each vibration signal, and obtaining the information entropy fluctuation range of the vibration signals by using the variance and the local information entropy corresponding to each vibration signal;
acquiring a vibration signal corresponding to local information entropy in an information entropy fluctuation range of the vibration signal and recording the vibration signal as an initial target vibration signal;
dividing the initial target vibration signals into a plurality of different periodic target vibration signals by using the time difference between any two initial target vibration signals;
performing curve fitting on the local information entropy of each target vibration signal belonging to the same periodicity to obtain a fitting curve;
clustering the slope of each point on each fitting curve to obtain multiple kinds of slopes, and determining whether the current rolling bearing is abnormal or not by using the difference value between the mean values of the slopes of each kind.
Further, the length of the target signal segment is larger than the rotation period of the rolling bearing.
Further, the step of obtaining the information entropy fluctuation range of the vibration signal by using the variance and the local information entropy corresponding to each vibration signal comprises:
respectively obtaining the mean value of the variances of all the vibration signals and the mean value of the local information entropy as a target variance and a target local information entropy;
subtracting the target variance from the target local information entropy to serve as the minimum value of the information entropy fluctuation range of the vibration signal;
the target local information entropy plus the target variance is used as the maximum value of the information entropy fluctuation range of the vibration signal;
and taking an interval formed by the maximum value and the minimum value of the information entropy fluctuation range as the information entropy fluctuation range of the vibration signal.
Further, the step of dividing the initial target vibration signal into a plurality of different periodic target vibration signals using the time difference between any two initial target vibration signals includes:
acquiring a time difference between any two initial target vibration signals;
and dividing the vibration signals with the time difference equal to the rotation period and with the time interval of the rotation period into the same periodic target vibration signals.
Further, the slope of each point on the fitting curve is subjected to k-means algorithm two classification to obtain two types of slopes.
Further, the step of determining whether the current rolling bearing has the abnormality by using the difference value between the mean values of the slopes of each type comprises the following steps:
obtaining the mean value of all the slope rates in each class, and obtaining the difference value between the mean values of the two classes of slope rates;
when the difference value is larger than a preset abnormal threshold value, the rolling bearing is considered to have a fault;
and when the difference value is not greater than a preset abnormal threshold value, the rolling bearing is considered to have no fault.
A rolling bearing fault identification system comprising:
a data acquisition module: the device comprises a signal section, a signal section and a signal section, wherein the signal section is used for acquiring all vibration signals of a rolling bearing to be detected from the beginning to the current time period, and the signal section with set time length is selected as a target signal section of the vibration signals by taking each vibration signal as a center;
a data processing module: the method comprises the steps of obtaining the local information entropy of each vibration signal by using the signal values of all the vibration signals in the target signal segment of the vibration signal; acquiring the variance of the signal values of all the vibration signals in the target signal segment of each vibration signal, and obtaining the information entropy fluctuation range of the vibration signals by using the variance and the local information entropy corresponding to each vibration signal;
a data extraction module: the method comprises the steps of obtaining a vibration signal corresponding to local information entropy in an information entropy fluctuation range of the vibration signal, and recording the vibration signal as an initial target vibration signal; dividing the initial target vibration signals into a plurality of different periodic target vibration signals by using the time difference between any two initial target vibration signals;
a detection and identification module: the method comprises the steps of performing curve fitting on local information entropy of each target vibration signal belonging to the same periodicity to obtain a fitting curve; and clustering the slope of each point on each fitting curve to obtain multiple types of slopes, and determining whether the current rolling bearing is abnormal or not by using the difference value between the mean values of the slopes of each type.
The invention has the beneficial effects that: according to the rolling bearing fault identification method and system, the information entropy fluctuation range is determined through the variance and the local information entropy, the vibration signals in the information entropy fluctuation range in all the vibration signals are extracted through the information entropy fluctuation range, the local information entropy is expanded into the information entropy fluctuation range through the variance, the information entropy fluctuation range serves as a fault tolerance range of data acquisition errors, and therefore normal points can be reserved as far as possible when noise points are removed; screening an initial target vibration signal by using the information entropy fluctuation range to obtain a vibration signal with partial noise points removed; then, the periodic vibration signals are screened out through the rotation period, and the vibration signals without periodic regular noise can be filtered out, so that the subsequent fault identification result is more accurate; after the interference of noise points is removed, curve fitting is carried out on the local information entropies of all the vibration signals, whether the rolling bearing in the current time period is abnormal or not is judged by utilizing the slope, and automatic analysis of rolling bearing fault identification is achieved.
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 embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the general steps of an embodiment of a rolling bearing fault identification method of the present invention;
fig. 2 is a schematic structural diagram of a rolling bearing fault identification system 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 making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
An embodiment of a rolling bearing fault identification method of the present invention, as shown in fig. 1, includes:
s1, acquiring all vibration signals of a rolling bearing to be detected from the beginning to the current time period; and selecting a signal segment with set time length as a target signal segment of the vibration signal by taking each vibration signal as a center.
Specifically, a micro acceleration sensor is arranged at a mechanical part where the rolling bearing is installed and is used for collecting vibration signals of the rolling bearing. All vibration signals from the beginning of running of the rolling bearing to the current moment are collected by the micro acceleration sensor.
The method comprises the steps that each vibration signal is used as the center of a time window, the time window with the time sequence length larger than the rotation period of a rolling bearing is selected, the rotation period of the rolling bearing is the vibration period of the vibration signal, the vibration signal is periodic data, and therefore in order to reduce errors, the time sequence length is set to be larger than the vibration period, namely, the time sequence length is larger than the rotation period.
All of the vibration signals in the time window of each vibration signal are collectively referred to as a target signal segment of the vibration signal.
S2, obtaining the local information entropy of each vibration signal by using the signal values of all vibration signals in the target signal segment of each vibration signal; and acquiring the variance of the signal values of all the vibration signals in the target signal section of each vibration signal, and obtaining the information entropy fluctuation range of the vibration signals by using the variance and the local information entropy corresponding to each vibration signal.
If data abnormality exists in the historical vibration data of the rolling bearing, the vibration signal data can be relatively disordered, even if the rolling bearing is normally used, vibration can be generated, noise can also occur during signal acquisition, and therefore fault detection on the rolling bearing is influenced; the more chaotic the vibration signal in the target signal segment is, namely the more irregular the change of the signal value is, the larger the entropy value is, the more likely the phenomenon is caused by the fault of the rolling bearing, and the signal value refers to the signal data of the vibration signal acquired by the miniature acceleration sensor, namely the acceleration signal value of the vibration signal.
Specifically, the local information entropy of each vibration signal segment is calculated by using the signal value of each vibration signal in the target signal segment of each vibration signal, that is, the information entropy of the signal value in the segment is calculated by using the probability of occurrence of the signal values of all vibration signals in the target signal segment, and is used as the local information entropy of the target signal segment, the local information entropy of the target signal segment is used as the local information entropy of the corresponding vibration signal, the calculation of the information entropy is the prior art, and is not described herein again, and the local information entropy of each vibration signal is obtained by using a method for obtaining the local information entropy of the vibration signal.
The vibration signal acquisition may be subjected to more noise, so that even a normal signal with the same periodicity fluctuates, and a vibration signal with the same periodicity refers to a vibration signal belonging to the same corresponding position in different vibration periods, for example, a peak signal of each vibration period belongs to the same periodicity, because there is interference of a noise signal in the acquired vibration signal, and there is a certain degree of error in the signal acquisition process, if the periodicity of the vibration signal is determined by using a rule that vibration signals with completely equal local entropies belong to the same periodic vibration signal, an effective periodicity cannot be found due to the noise interference, and local information entropies calculated by the vibration signals belonging to the same periodicity are not completely equal, so that a certain fault tolerance range is required to reduce the influence of noise. Namely, the vibration signals belonging to the same periodicity are determined by calculating the fluctuation range of the information entropy of each vibration signal, so that more vibration signals possibly belonging to the same periodicity can be reserved, and the periodicity result is more accurate.
Specifically, the variance of the signal values of all vibration signals in the target signal segment of each vibration signal is calculated, the mean value of the variances of all vibration signals is obtained as the target variance, and the mean value of the local information entropies of all vibration signals is obtained as the target local information entropy; subtracting the target variance from the target local information entropy to serve as the minimum value of the information entropy fluctuation range of the vibration signal, adding the target variance to the target local information entropy to serve as the maximum value of the information entropy fluctuation range of the vibration signal, and taking the interval formed by the maximum value and the minimum value of the information entropy fluctuation range as the information entropy fluctuation range of the vibration signal, namely the information entropy fluctuation range is
Wherein, in the step (A),
the target local information entropy representing the vibration signal,
representing the target variance of the vibration signal.
It should be noted that if the local information entropy fluctuation of the peripheral vibration signal of the vibration signal is large, the instability is larger, and the corresponding information entropy value tolerance should be larger, so that the variance is used to adjust the local information entropy of the vibration signal to obtain the information entropy fluctuation range.
S3, obtaining a vibration signal corresponding to a local information entropy in an information entropy fluctuation range of the vibration signal and marking as an initial target vibration signal; the time difference between any two initial target vibration signals is used to divide the initial target vibration signals into a plurality of different periodic target vibration signals.
Specifically, the vibration signals belonging to the information entropy fluctuation range in all the vibration signals are obtained as initial target vibration signals, and the vibration signals with part of noise points removed are obtained.
Because the bearing is under the unchangeable condition of rotational speed, the time of rotating a week is also unchangeable, and the rolling bearing does not possess self-healing ability promptly, so can exist always after the rolling bearing breaks down, and probably along with long-time use, the rolling bearing trouble anomaly can be more and more obvious, and local information entropy value can grow, and the rolling bearing trouble anomaly can present periodicity, and the noise has stronger unstable factor, consequently can utilize the periodicity of vibration signal's local information entropy, rejects the noise point.
Specifically, the time difference between any two initial target vibration signals is obtained, all the initial target vibration signals with the time difference equal to the rotation period and the time interval of the rotation period are obtained as the target vibration signals belonging to the same periodicity, and all the initial target vibration signals are traversed to obtain all the target vibration signals with the periodicity.
All the obtained target vibration signals are normal signals and abnormal signals in all the vibration signals after the noise point is removed.
S4, performing curve fitting on the local information entropy of each target vibration signal belonging to the same periodicity to obtain a fitting curve; clustering the slope of each point on each fitting curve to obtain slopes of multiple categories, and determining whether the current rolling bearing is abnormal or not by using the difference value between the mean values of the slopes of the categories.
And the abnormal signal can be screened out by using the local information entropy of the vibration signals with the same periodicity. Specifically, least square curve fitting is carried out on the local information entropies of the vibration signals belonging to the same periodicity, so as to obtain a fitting curve. If the rolling bearing has a fault, the fault abnormality becomes more and more obvious along with the long-time use of the rolling bearing, and the value of the local information entropy becomes larger, so that the fitting curve of the local information entropy is approximate to a monotonously increasing curve.
If the increasing rate of the fitted curve is slow and relatively consistent, the local information entropy of the vibration signal caused by normal wear of the rolling bearing is considered to be gradually increased; if a part with a locally high increasing speed appears in the fitting curve of the local information entropy, the rolling bearing is indicated to have a fault.
Specifically, slope values of all points on a fitting curve are obtained, a k-means algorithm is used for carrying out binary classification on all slopes to obtain slopes of two categories, the slopes of the two categories are respectively averaged, the obtained average values are differentiated to obtain slope difference values of the two categories, an abnormal threshold value r =0.5 is set, r is a hyperparameter, an implementer can carry out adjustment according to a specific implementation scene, and if the slope difference values are larger than the abnormal threshold value 0.5, the vibration signal of the current rolling bearing is considered to be abnormal, namely the rolling bearing has a fault; if the slope difference value is not greater than the abnormal threshold value 0.5, the vibration signal of the current rolling bearing is considered to be abnormal, namely the rolling bearing is not in fault.
The invention also discloses a rolling bearing fault identification system, as shown in fig. 2, the system comprises: the device comprises a data acquisition module, a data processing module, a data extraction module and a detection identification module. The data acquisition module is used for acquiring all vibration signals of the rolling bearing to be detected from the beginning of operation to the current time period, and selecting a signal segment with set duration as a target signal segment of the vibration signals by taking each vibration signal as a center; the data processing module is used for obtaining the local information entropy of each vibration signal by using the signal values of all the vibration signals in the target signal segment of each vibration signal; acquiring the variance of the signal values of all the vibration signals in the target signal segment of each vibration signal, and obtaining the information entropy fluctuation range of the vibration signals by using the variance and the local information entropy corresponding to each vibration signal; the data extraction module is used for acquiring a vibration signal corresponding to local information entropy in an information entropy fluctuation range of the vibration signal and recording the vibration signal as an initial target vibration signal; dividing the initial target vibration signals into a plurality of different periodic target vibration signals by using the time difference between any two initial target vibration signals; the detection and identification module is used for performing curve fitting on the local information entropy of each target vibration signal belonging to the same periodicity to obtain a fitting curve; and clustering the slope of each point on each fitting curve to obtain multiple types of slopes, and determining whether the current rolling bearing is abnormal or not by using the difference value between the mean values of the slopes of each type.
In summary, the invention provides a rolling bearing fault identification method and system, which jointly determine an information entropy fluctuation range through a variance and a local information entropy, extract vibration signals in the information entropy fluctuation range from all vibration signals by using the information entropy fluctuation range, and expand the local information entropy into the information entropy fluctuation range by using the variance, wherein the information entropy fluctuation range is used as a fault tolerance range of data acquisition errors, so that normal points can be kept as far as possible when noise points are removed; screening an initial target vibration signal by using the information entropy fluctuation range to obtain a vibration signal with partial noise points removed; then, the periodic vibration signals are screened out through the rotation period, and the vibration signals without periodic regular noise can be filtered out, so that the subsequent fault identification result is more accurate; after the interference of noise points is removed, curve fitting is carried out on the local information entropies of all the vibration signals, whether the rolling bearing in the current time period is abnormal or not is judged by utilizing the slope, and automatic analysis of rolling bearing fault identification is realized.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A rolling bearing fault identification method is characterized in that:
acquiring all vibration signals of a rolling bearing to be detected from the beginning to the current time period;
selecting a signal segment with set duration as a target signal segment of each vibration signal by taking each vibration signal as a center;
obtaining the local information entropy of each vibration signal by using the signal values of all the vibration signals in the target signal segment of each vibration signal;
acquiring the variance of the signal values of all the vibration signals in the target signal segment of each vibration signal, and obtaining the information entropy fluctuation range of the vibration signals by using the variance and the local information entropy corresponding to each vibration signal;
acquiring a vibration signal corresponding to local information entropy in an information entropy fluctuation range of the vibration signal and recording the vibration signal as an initial target vibration signal;
dividing the initial target vibration signals into a plurality of different periodic target vibration signals by using the time difference between any two initial target vibration signals;
performing curve fitting on the local information entropy of each target vibration signal belonging to the same periodicity to obtain a fitting curve;
clustering the slope of each point on each fitting curve to obtain multiple kinds of slopes, and determining whether the current rolling bearing is abnormal or not by using the difference value between the mean values of the slopes of each kind.
2. The rolling bearing fault identification method according to claim 1, wherein the length of the target signal segment is greater than a rotation period of the rolling bearing.
3. The rolling bearing fault identification method according to claim 1, wherein the step of obtaining the information entropy fluctuation range of the vibration signal by using the variance and the local information entropy corresponding to each vibration signal comprises:
respectively obtaining the mean value of the variances of all the vibration signals and the mean value of the local information entropy as a target variance and a target local information entropy;
subtracting the target variance from the target local information entropy to serve as the minimum value of the information entropy fluctuation range of the vibration signal;
the target local information entropy and the target variance are used as the maximum value of the information entropy fluctuation range of the vibration signal;
and taking an interval formed by the maximum value and the minimum value of the information entropy fluctuation range as the information entropy fluctuation range of the vibration signal.
4. The rolling bearing fault identification method according to claim 1, wherein the step of dividing the initial target vibration signal into a plurality of different periodic target vibration signals using the time difference between any two initial target vibration signals comprises:
acquiring a time difference between any two initial target vibration signals;
and dividing the vibration signals with the time difference equal to the rotation period and the time interval equal to the rotation period into the same periodic target vibration signals.
5. The rolling bearing fault identification method according to claim 1, wherein two types of slopes are obtained by performing k-means algorithm two classification on the slope of each point on the fitting curve.
6. The rolling bearing fault identification method according to claim 5, wherein the step of determining whether the current rolling bearing is abnormal by using the difference value between the mean values of each slope comprises the following steps:
obtaining the mean value of all the slope rates in each class, and obtaining the difference value between the mean values of the two classes of slope rates;
when the difference value is larger than a preset abnormal threshold value, the rolling bearing is considered to have a fault;
and when the difference value is not greater than a preset abnormal threshold value, the rolling bearing is considered to have no fault.
7. A rolling bearing fault identification system, comprising:
a data acquisition module: the device comprises a signal section, a signal section and a signal section, wherein the signal section is used for acquiring all vibration signals of a rolling bearing to be detected from the beginning to the current time period, and the signal section with set time length is selected as a target signal section of the vibration signals by taking each vibration signal as a center;
a data processing module: the method comprises the steps of obtaining the local information entropy of each vibration signal by using the signal values of all the vibration signals in the target signal segment of the vibration signal; acquiring the variance of the signal values of all the vibration signals in the target signal segment of each vibration signal, and obtaining the information entropy fluctuation range of the vibration signals by using the variance and the local information entropy corresponding to each vibration signal;
a data extraction module: the vibration signal corresponding to the local information entropy in the information entropy fluctuation range for obtaining the vibration signal is marked as an initial target vibration signal; dividing the initial target vibration signals into a plurality of different periodic target vibration signals by using the time difference between any two initial target vibration signals;
a detection identification module: the method comprises the steps of performing curve fitting on local information entropy of each target vibration signal belonging to the same periodicity to obtain a fitting curve; clustering the slope of each point on each fitting curve to obtain multiple kinds of slopes, and determining whether the current rolling bearing is abnormal or not by using the difference value between the mean values of the slopes of each kind.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211271086.2A CN115356109B (en) | 2022-10-18 | 2022-10-18 | Rolling bearing fault identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211271086.2A CN115356109B (en) | 2022-10-18 | 2022-10-18 | Rolling bearing fault identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115356109A true CN115356109A (en) | 2022-11-18 |
| CN115356109B CN115356109B (en) | 2023-12-26 |
Family
ID=84007925
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211271086.2A Active CN115356109B (en) | 2022-10-18 | 2022-10-18 | Rolling bearing fault identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115356109B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104468728A (en) * | 2014-11-06 | 2015-03-25 | 北京邮电大学 | Service selecting method based on information entropy and variance |
| US20180011065A1 (en) * | 2013-07-02 | 2018-01-11 | Computational Systems, Inc. | Machine Fault Prediction Based on Analysis of Periodic Information in a Signal |
| CN108645620A (en) * | 2018-07-26 | 2018-10-12 | 北京工业大学 | A kind of Fault Diagnosis of Rolling Element Bearings method based on comentropy and Multiscale Morphological |
| CN108760300A (en) * | 2018-04-19 | 2018-11-06 | 西安工业大学 | A method of intelligent fault diagnosis being carried out to it according to bearing vibration signal |
| CN114705426A (en) * | 2022-01-06 | 2022-07-05 | 杭州爱华仪器有限公司 | Early fault diagnosis method for rolling bearing |
-
2022
- 2022-10-18 CN CN202211271086.2A patent/CN115356109B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180011065A1 (en) * | 2013-07-02 | 2018-01-11 | Computational Systems, Inc. | Machine Fault Prediction Based on Analysis of Periodic Information in a Signal |
| CN104468728A (en) * | 2014-11-06 | 2015-03-25 | 北京邮电大学 | Service selecting method based on information entropy and variance |
| CN108760300A (en) * | 2018-04-19 | 2018-11-06 | 西安工业大学 | A method of intelligent fault diagnosis being carried out to it according to bearing vibration signal |
| CN108645620A (en) * | 2018-07-26 | 2018-10-12 | 北京工业大学 | A kind of Fault Diagnosis of Rolling Element Bearings method based on comentropy and Multiscale Morphological |
| CN114705426A (en) * | 2022-01-06 | 2022-07-05 | 杭州爱华仪器有限公司 | Early fault diagnosis method for rolling bearing |
Non-Patent Citations (1)
| Title |
|---|
| 朱文君等: "构造概念格的权值优化改进算法", 《传感器与微系统》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115356109B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106714109B (en) | WiFi fingerprint database updating method based on crowdsourcing data | |
| CN114781467B (en) | Fault detection method based on vibration similarity | |
| CN113284143B (en) | Die casting deburring precision detection system based on image data processing | |
| CN110738255A (en) | device state monitoring method based on clustering algorithm | |
| CN117191305B (en) | State evaluation method and system for highway bridge | |
| CN110715808A (en) | Fault detection method and device | |
| CN112818766A (en) | High-altitude parabolic detection alarm method and system based on computer vision | |
| CN113551927A (en) | Mechanical equipment fault early warning method and system based on vibration signals | |
| CN110474862B (en) | Network traffic anomaly detection method and device | |
| CN114881960A (en) | Feature enhancement-based cloth linear defect detection method and system | |
| CN115220396A (en) | Intelligent monitoring method and system for numerical control machine tool | |
| CN115356109A (en) | Rolling bearing fault identification method and system | |
| CN108446162B (en) | Method and system for monitoring JVM Full GC event | |
| CN117194177A (en) | Method for improving detection accuracy of slow disk of storage system | |
| CN116304963B (en) | Data processing system suitable for geological disaster early warning | |
| CN115741218B (en) | Machine tool fault early warning method and system based on machining image analysis | |
| US20170160302A1 (en) | Automatic Threshold Detection for Tachometer Signals | |
| CN115295016A (en) | Equipment running state monitoring method, device, equipment and storage medium | |
| CN115495274A (en) | Exception handling method based on time sequence data, network equipment and readable storage medium | |
| CN111025288B (en) | Security radar monitoring device and system | |
| CN114879033A (en) | Motor fault detection method, system and storage medium | |
| CN114564469A (en) | Method and system for processing collected data | |
| CN115511106B (en) | Method, device and readable storage medium for generating training data based on time sequence data | |
| CN115017014B (en) | Highway electromechanical monitoring system and method | |
| CN117370898B (en) | Electronic data safety control system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |