CN114742093A - Rolling bearing fault diagnosis method and device based on time-frequency curve extraction and classification - Google Patents
Rolling bearing fault diagnosis method and device based on time-frequency curve extraction and classification Download PDFInfo
- Publication number
- CN114742093A CN114742093A CN202210259001.2A CN202210259001A CN114742093A CN 114742093 A CN114742093 A CN 114742093A CN 202210259001 A CN202210259001 A CN 202210259001A CN 114742093 A CN114742093 A CN 114742093A
- Authority
- CN
- China
- Prior art keywords
- time
- frequency
- curve
- fault
- 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.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 34
- 238000005096 rolling process Methods 0.000 title claims abstract description 30
- 238000000605 extraction Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 25
- 239000002131 composite material Substances 0.000 claims abstract description 29
- 238000012423 maintenance Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 230000001133 acceleration Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000009467 reduction Effects 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 2
- 238000011418 maintenance treatment Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a time-varying working condition composite fault diagnosis method and device based on time-frequency curve extraction and classification; the device comprises a signal acquisition module, a signal processing module and a signal processing module, wherein the signal acquisition module is used for detecting and acquiring a vibration signal of a rolling bearing through an acceleration sensor; the signal preprocessing module is used for preprocessing the acquired vibration signals of the rolling bearing; the characteristic extraction module is used for extracting fault characteristics of the vibration signals subjected to noise reduction; the state recognition module is used for carrying out fault matching and recognition on the extracted fault characteristics, inputting the trained model and carrying out damage degree recognition; and the fault diagnosis and early warning module is used for reminding equipment maintenance personnel to perform corresponding treatment on the equipment. The invention can visually reflect the operation condition of the equipment, provide reliable equipment operation information for equipment maintenance personnel in time and effectively ensure the operation of the equipment, thereby reducing the fault downtime of the equipment and reducing the scheduled maintenance time and the unscheduled maintenance time.
Description
Technical Field
The invention belongs to the technical field of mechanical fault diagnosis, and particularly relates to a time-varying working condition rolling bearing composite fault diagnosis method and device based on time-frequency curve extraction and classification.
Background
The rotating machine is used as indispensable operation equipment in the fields of chemical industry, petroleum, manufacturing, aerospace and the like, and the application scene of the rotating machine is gradually wide. With the rapid development of scientific technology, the modern industrial production mode is revolutionized, the automation, digitization and intelligence levels of rotary machinery are continuously improved, the equipment scale is larger, and the operation working conditions are more complex.
The rolling bearing is used as a key part of a rotating part and a fixed part of the rotary mechanical connecting device, plays an important role in the operation of the rotary mechanical connecting device, and the operation state of the rolling bearing directly influences the performance of the whole device. Once an injury-type fault occurs, especially a compound fault which generates multiple fault couplings, the whole system is likely to be broken down, and serious damage is caused. Therefore, bearing fault monitoring and diagnosis technical research is developed, fault characteristics of equipment are found and identified in time, fault tracing and detection are achieved, accurate understanding and mastering of generation and evolution processes of bearing faults are facilitated, the method plays a vital role in aspects of bearing performance state understanding, potential fault finding as early as possible, equipment safety and stability service guarantee, accident avoidance, manpower and financial loss reduction and the like, is a key for rotary machine fault diagnosis, and has great significance in research of multi-source fault diagnosis and monitoring of rotary machines under complex working conditions.
Time-varying operating conditions are also common in rotary machines, and at the start-stop stage of the equipment, the key parts of the rotary machine can bear varying loads, and the mapping relation between the signal characteristics and the failure modes becomes more complex. The composite fault under the variable-speed working condition is formed by mixing a plurality of different single faults, signal components are mutually coupled and interfered, different fault characteristics are different in strength and weakness, the components of the fault characteristics are less prominent, and the difficulty in extracting the fault characteristics is increased. The traditional diagnosis method based on the tachometer is not beneficial to practical application, so that the method diagnoses the composite fault of the rolling bearing under the time-frequency working condition through time-frequency curve extraction and classification on the basis of time-frequency analysis, and simultaneously identifies and evaluates the running state of the rolling bearing and makes a response.
Disclosure of Invention
In order to solve the technical problems, the invention provides a time-varying working condition rolling bearing composite fault diagnosis method and a time-varying working condition rolling bearing composite fault diagnosis device based on time-frequency curve extraction and classification, which are used for diagnosing and evaluating fault parts and damage degrees based on vibration signals generated when a fault occurs under the time-varying working condition of a rolling bearing, and giving early warning to equipment maintenance personnel in time to remove the fault and ensure the safe operation of rotary mechanical equipment;
a time-frequency curve extraction and classification based composite fault diagnosis method for a rolling bearing under time-varying working conditions comprises the following steps:
s1: acquiring a composite fault vibration signal of the rolling bearing under a time-varying working condition through a signal acquisition module;
s2: carrying out wavelet threshold denoising on the acquired vibration signals through a preprocessing module circuit to realize denoising processing of the signals;
s3: performing Hilbert envelope demodulation and fast short-time Fourier transform on the vibration signals subjected to noise reduction to obtain a time-frequency image;
s4: extracting a time-frequency curve in the obtained time-frequency image by using a multi-time-frequency curve extraction algorithm based on rapid path optimization;
s5: classifying the time-frequency curves by adopting a time-frequency curve classification criterion;
s6: matching the classified curves with fault characteristic coefficients, and identifying damage degrees of the faults which are successfully matched;
preferably, if the classified time-frequency curve in S6 matches with the failure characteristic coefficient, the early warning module prompts that the part fails; if the damage evaluation result exceeds the threshold value, the early warning module gives an alarm, and equipment maintenance is used for maintaining and processing the equipment;
preferably, the time-frequency curve classification criterion adopts a mean value ratio and a standard deviation;
preferably, the mean ratio is determined by whether the average ratio of the extracted instantaneous frequency of the curve to be determined to the Instantaneous Fault Characteristic Frequency (IFCF) or the Instantaneous Shaft Rotation Frequency (ISRF) is an integer, i.e., whether the extracted instantaneous frequency and the extracted Instantaneous Fault Characteristic Frequency (IFCF) or the average ratio of the extracted Instantaneous Shaft Rotation Frequency (ISRF) are harmonic relations, i.e., whether the extracted instantaneous frequency and the extracted instantaneous shaft rotation frequency belong to the same type of curve; first, the frequency average value of each curve should be calculated, and then the curve f with the minimum frequency average value is takenp(τn) A is as the radicalLine, calculating the average ratio R of other curves to the base linea，RaThe calculation formula is as follows:
if the relative error between the average ratio and the expected integral multiple value is less than or equal to 10 percent, preliminarily judging whether the two curves belong to the same class or not;
preferably, the standard deviation compares the standard deviation of the ith curve to be classified divided by the corresponding multiple with the standard deviation between the selected base lines to determine whether they belong to the same class, and the two standard deviation values can be expressed as:
if the relative error of the two standard deviations is less than or equal to 10%, the two standard deviations are further regarded as the same type of curve, and if the relative error is not greater than the 10%, the curve is divided into unrelated curves;
preferably, after the time-frequency curves are classified by the S5, related curves and unrelated curve classes of different classes are obtained; for fault diagnosis, only the relevant curve classes need to be considered; the category containing the minimum instantaneous frequency mean baseline is ISRF and harmonic wave category thereof; since the class may not contain ISRF, in order to reduce the error of ISRF estimation, a weighted average of all curves of the class is taken as a new baseline, and the new baseline is an instantaneous frequency curve of the ISRF, or a second harmonic curve of the ISRF, or one of third harmonic curves of the ISRF;
preferably, after the new baseline is obtained, the average ratio of the baseline to the new baseline in other categories is matched with a Fault Characteristic Coefficient (FCC) (or 1/3 × FCC, 1/2 × FCC), and if the matching is successful, it is determined that a fault corresponding to the FCC has occurred; due to the limited resolution of the time-frequency plot and the accuracy of a given size, the calculated average ratio may not match the FCC completely; therefore, the matching is considered to be within the allowable relative error range, i.e. the matching is considered to be successful.
Another objective of the present invention is to provide a time-varying condition rolling bearing composite fault diagnosis apparatus based on time-frequency curve extraction and classification, comprising:
the signal acquisition module is used for acquiring time-varying working condition composite fault vibration signals through an acceleration sensor, and the acceleration sensor is installed in the axial direction, the radial direction and the vertical direction;
the signal preprocessing module is used for preprocessing the acquired diaphragm pump vibration signals, including filtering, demodulation, time-frequency conversion and time-frequency curve extraction of the signals, so that subsequent state identification is facilitated;
the fault diagnosis module is used for extracting the extracted time-frequency curve, classifying the extracted time-frequency curve by adopting a classification criterion, and performing fault matching and identification on the extracted time-frequency curve and a fault characteristic coefficient;
and the damage assessment and early warning module is used for assessing the damage degree of the matched fault and sending out an early warning signal to remind equipment maintenance personnel to pay attention to and process the matched fault.
The invention has the beneficial effects that:
the invention relates to a time-frequency curve extraction and classification based composite fault diagnosis method and device for a rolling bearing under time-varying working conditions, which are provided for composite fault vibration signals under the time-varying working conditions of the rolling bearing; by using the fault diagnosis device, the running state monitoring and diagnosis of the rolling bearing can be realized, reliable equipment running information is provided for equipment maintenance personnel in time, and the equipment fault downtime is reduced. The time-frequency curve extraction and classification method is adopted to diagnose the composite fault of the rolling bearing under the time-varying working conditions, the installation of a tachometer in the traditional method is avoided, and the method has the characteristics of simplicity and convenience.
Drawings
FIG. 1 is a basic framework diagram of the present invention;
FIG. 2 is a block diagram of the hardware design of the system of the present invention for system fault diagnosis and alarm configuration;
FIG. 3 is a time domain signal plot of a composite fault under time varying conditions of the present invention;
FIG. 4 is a time-frequency diagram of a composite fault signal under time-varying conditions of the present invention;
FIG. 5 is a time-frequency curve obtained by the extraction of the present invention.
Fig. 6 is a diagram of the classification result of the present invention.
Detailed Description
In order to clearly and completely describe the technical scheme and the effect of the invention, the following embodiments are used for detailed description;
example 1
A time-frequency curve extraction and classification based composite fault diagnosis method for a rolling bearing under time-varying working conditions comprises the following steps:
s1: acquiring a composite fault vibration signal of the rolling bearing under a time-varying working condition through a signal acquisition module;
s2: carrying out wavelet threshold filtering denoising on the acquired vibration signals through a preprocessing module circuit to realize denoising processing of the signals;
s3: performing Hilbert envelope demodulation and short-time Fourier transform on the vibration signals subjected to noise reduction to obtain time-frequency images;
s4: extracting a time-frequency curve in the obtained time-frequency image by using a time-frequency curve extraction algorithm based on rapid path optimization;
s5: classifying the time-frequency curves by adopting a time-frequency curve classification criterion;
s6: matching the classified curves with fault characteristic coefficients, and identifying damage degrees of the faults which are successfully matched;
preferably, if the classified time-frequency curve in S6 matches with the failure feature coefficient, the early warning module prompts that the part fails; if the damage assessment result exceeds the threshold value, the early warning module gives an alarm, and equipment maintenance is performed on the equipment;
preferably, the time-frequency curve classification criterion adopts a mean value ratio and a standard deviation;
preferably, the average ratio is an instantaneous frequency according to the extracted curve to be judgedWhether the average ratio of the rate to the Instantaneous Fault Characteristic Frequency (IFCF) or the Instantaneous Shaft Rotation Frequency (ISRF) is an integer or not can be preliminarily judged, namely whether the average ratio of the rate to the Instantaneous Fault Characteristic Frequency (IFCF) or the Instantaneous Shaft Rotation Frequency (ISRF) belongs to a harmonic relation or not can be preliminarily judged, and whether the average ratio of the rate to the Instantaneous Fault Characteristic Frequency (IFCF) or the Instantaneous Shaft Rotation Frequency (ISRF) belongs to the same curve or not can be preliminarily judged; first, the frequency average value of each curve should be calculated, and then the curve f with the minimum frequency average value is takenp(τn) Using _jas a base line, calculating the average ratio R of other curves to the base linea，RaThe calculation formula is as follows:
if the relative error between the average ratio and the expected integral multiple value is less than or equal to 10 percent, preliminarily judging whether the two curves belong to the same class or not;
preferably, the standard deviation compares the standard deviation of the ith curve to be classified divided by the corresponding multiple with the standard deviation between the selected base lines to determine whether they belong to the same class, and the two standard deviation values can be expressed as:
if the relative error of the two standard deviations is less than or equal to 10%, the two standard deviations are further regarded as the same type of curve, and if the relative error is not greater than the 10%, the curve is divided into unrelated curves;
preferably, after the S5 classifies the multiple time-frequency curves, different categories of related curves and unrelated curve categories are obtained; for fault diagnosis, only the relevant curve classes need to be considered; the category containing the minimum instantaneous frequency mean baseline is ISRF and harmonic wave category thereof; since the class may not contain ISRF, in order to reduce the error of ISRF estimation, a weighted average of all curves in the class is taken as a new baseline, and the new baseline is an instantaneous frequency curve of ISRF, or a second harmonic curve of ISRF, or one of third harmonic curves of ISRF;
preferably, after the new baseline is obtained, the average ratio of the baseline to the new baseline in other categories is matched with a Fault Characteristic Coefficient (FCC) (or 1/3 × FCC, 1/2 × FCC), and if the matching is successful, it is determined that a fault corresponding to the FCC has occurred; due to the limited resolution of the time-frequency plot and the accuracy of a given size, the calculated average ratio may not match the FCC completely; therefore, the matching is considered to be within the allowable relative error range, i.e. the matching is considered to be successful.
Example 2
A time-varying working condition rolling bearing composite fault diagnosis device based on time-frequency curve extraction and classification comprises the following components:
the signal acquisition module is used for acquiring time-varying working condition composite fault vibration signals through an acceleration sensor, and the acceleration sensor is installed in the axial direction, the radial direction and the vertical direction;
the signal preprocessing module is used for preprocessing the acquired diaphragm pump vibration signals, including filtering, demodulation, time-frequency conversion and time-frequency curve extraction of the signals, so that subsequent state identification is facilitated;
the fault diagnosis module is used for extracting the extracted time-frequency curve, classifying the extracted time-frequency curve by adopting a classification criterion, and performing fault matching and identification on the extracted time-frequency curve and a fault characteristic coefficient;
and the damage assessment and early warning module is used for assessing the damage degree of the matched fault and sending out an early warning signal to remind equipment maintenance personnel to pay attention to and process the matched fault.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (8)
1. A time-varying working condition rolling bearing composite fault diagnosis method based on time-frequency curve extraction and classification is characterized by comprising the following steps:
s1: acquiring a composite fault vibration signal of the rolling bearing under a time-varying working condition through a signal acquisition module;
s2: carrying out wavelet threshold denoising on the acquired vibration signals through a preprocessing module circuit to realize denoising processing of the signals;
s3: performing Hilbert envelope demodulation and short-time Fourier transform on the vibration signals subjected to noise reduction to obtain time-frequency images;
s4: extracting a time-frequency curve in the obtained time-frequency image by using a time-frequency curve extraction algorithm based on rapid path optimization;
s5: classifying the time-frequency curves by adopting the constructed time-frequency curve classification criterion;
s6: and matching the classified curves with fault characteristic coefficients, and identifying the damage degree of the successfully matched fault.
2. The time-frequency curve extraction and classification-based composite fault diagnosis method for the rolling bearing under the time-varying working conditions according to claim 1, wherein if the classified time-frequency curve in the S6 is matched with a fault characteristic coefficient, an early warning module prompts that the part has a fault; and if the damage evaluation result exceeds the threshold value, the early warning module gives an alarm, and equipment maintenance personnel carries out maintenance treatment on the equipment.
3. The time-frequency curve extraction and classification time-varying working condition rolling bearing composite fault diagnosis method based on the fast path optimization as claimed in claim 1, wherein the time-frequency curve classification criterion adopts a mean value ratio and a standard deviation.
4. The time-frequency curve extraction and classification-based composite fault diagnosis method for the rolling bearing under the time-varying working conditions as claimed in claim 3, wherein the mean value ratio is determined by whether the average ratio of the instantaneous frequency of the extracted curve to be determined to the Instantaneous Fault Characteristic Frequency (IFCF) or the Instantaneous Shaft Rotation Frequency (ISRF) is an integer or not, so that whether the extracted curve and the Instantaneous Fault Characteristic Frequency (IFCF) or the Instantaneous Shaft Rotation Frequency (ISRF) belong to a harmonic relation or not can be preliminarily determined, namely whether the extracted curve and the instantaneous fault characteristic frequency (ISRF) belong to the same curve; first, the frequency average value of each curve should be calculated, and then the curve f with the minimum frequency average value is takenp(τn) Using _jas a base line, calculating the average ratio R of other curves to the base linea，RaThe calculation formula is as follows:
if the relative error between the average ratio and the desired integer multiple value is less than or equal to 10%, it is preliminarily determined whether the two curves belong to the same class.
5. The time-frequency curve extraction and classification-based composite fault diagnosis method for the rolling bearing under the time-varying working conditions according to claim 3, wherein the standard deviation is compared with the standard deviation between the standard deviation obtained by dividing the ith curve to be classified by the corresponding multiple and the selected baseline to judge whether the ith curve to be classified belongs to the same class, and the two standard deviation values can be expressed as:
if the relative error of the two standard deviations is less than or equal to 10%, the curve is further considered as the same type of curve, and if the relative error is not more than 10%, the curve is divided into unrelated curves.
6. The time-frequency curve extraction and classification-based composite fault diagnosis method for the rolling bearing under the time-varying working conditions according to claim 1, wherein after the time-frequency curves are classified in the S5, related curves and unrelated curve classes of different classes are obtained; for fault diagnosis, only the relevant curve classes need to be considered; the category containing the minimum instantaneous frequency mean baseline is ISRF and harmonic wave category thereof; since the class may not contain ISRF, in order to reduce the error of ISRF estimation, a weighted average of all curves in the class is taken as a new baseline, and the new baseline is one of an instantaneous frequency curve of ISRF, or a second harmonic curve of ISRF, or a third harmonic curve of ISRF.
7. The time-frequency curve extraction and classification-based composite fault diagnosis method for the rolling bearing under the time-varying working conditions as claimed in claim 6, wherein after the new baseline is obtained, the average ratio of the baseline and the new baseline in other categories is adopted to be matched with a certain Fault Characteristic Coefficient (FCC) (or 1/3 xFCC, 1/2 xFCC), and if the matching is successful, the fault corresponding to the FCC can be determined; due to the limited resolution of the time-frequency plot and the accuracy of a given size, the calculated average ratio may not match the FCC completely; therefore, the matching is considered to be within the allowable relative error range, i.e. the matching is considered to be successful.
8. The utility model provides a time-varying working condition antifriction bearing composite fault diagnosis device based on time frequency curve draws and categorised which characterized in that includes:
the signal acquisition module is used for acquiring time-varying working condition composite fault vibration signals through an acceleration sensor, and the acceleration sensor is installed in the axial direction, the radial direction and the vertical direction;
the signal preprocessing module is used for preprocessing the acquired diaphragm pump vibration signals, including filtering, demodulation, time-frequency conversion and time-frequency curve extraction of the signals, so that subsequent state identification is facilitated;
the fault diagnosis module is used for extracting the extracted time-frequency curve, classifying the extracted time-frequency curve by adopting a classification criterion, and performing fault matching and identification on the extracted time-frequency curve and a fault characteristic coefficient;
and the damage assessment and early warning module is used for assessing the damage degree of the matched fault and sending out an early warning signal to remind equipment maintenance personnel to pay attention to and process the matched fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210259001.2A CN114742093A (en) | 2022-03-16 | 2022-03-16 | Rolling bearing fault diagnosis method and device based on time-frequency curve extraction and classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210259001.2A CN114742093A (en) | 2022-03-16 | 2022-03-16 | Rolling bearing fault diagnosis method and device based on time-frequency curve extraction and classification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114742093A true CN114742093A (en) | 2022-07-12 |
Family
ID=82277515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210259001.2A Pending CN114742093A (en) | 2022-03-16 | 2022-03-16 | Rolling bearing fault diagnosis method and device based on time-frequency curve extraction and classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114742093A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115081491A (en) * | 2022-08-18 | 2022-09-20 | 深圳市乐闵科技有限公司 | Running state fault diagnosis method for sanitary towel production equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103048137A (en) * | 2012-12-20 | 2013-04-17 | 北京航空航天大学 | Fault diagnosis method of rolling bearing under variable working conditions |
| CN104568444A (en) * | 2015-01-28 | 2015-04-29 | 北京邮电大学 | Method for extracting fault characteristic frequencies of train rolling bearings with variable rotational speeds |
| CN110617964A (en) * | 2019-07-29 | 2019-12-27 | 中国铁道科学研究院集团有限公司城市轨道交通中心 | Synchronous compression transformation order ratio analysis method for fault diagnosis of rolling bearing |
| CN110991564A (en) * | 2019-12-24 | 2020-04-10 | 安徽工业大学 | Variable working condition bearing fault diagnosis method based on multi-scale dispersion entropy deviation mean value and nonlinear mode decomposition |
-
2022
- 2022-03-16 CN CN202210259001.2A patent/CN114742093A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103048137A (en) * | 2012-12-20 | 2013-04-17 | 北京航空航天大学 | Fault diagnosis method of rolling bearing under variable working conditions |
| CN104568444A (en) * | 2015-01-28 | 2015-04-29 | 北京邮电大学 | Method for extracting fault characteristic frequencies of train rolling bearings with variable rotational speeds |
| CN110617964A (en) * | 2019-07-29 | 2019-12-27 | 中国铁道科学研究院集团有限公司城市轨道交通中心 | Synchronous compression transformation order ratio analysis method for fault diagnosis of rolling bearing |
| CN110991564A (en) * | 2019-12-24 | 2020-04-10 | 安徽工业大学 | Variable working condition bearing fault diagnosis method based on multi-scale dispersion entropy deviation mean value and nonlinear mode decomposition |
Non-Patent Citations (3)
| Title |
|---|
| 彭博等: "快速路径的多时频曲线时变转速轴承故障诊断", 制造技术与机床, no. 09, 30 September 2020 (2020-09-30), pages 149 - 150 * |
| 王思豪等: "一种改进的MP-WVD滚动轴承信号时频分析方法", 电子测量与仪器学报, vol. 34, no. 12, 31 December 2020 (2020-12-31), pages 133 - 143 * |
| 许雪梅: "微弱信号检测及无损探测技术研究", 31 July 2021, 湖南科学技术出版社, pages: 116 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115081491A (en) * | 2022-08-18 | 2022-09-20 | 深圳市乐闵科技有限公司 | Running state fault diagnosis method for sanitary towel production equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lei et al. | New clustering algorithm-based fault diagnosis using compensation distance evaluation technique | |
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| Song et al. | Step-by-step fuzzy diagnosis method for equipment based on symptom extraction and trivalent logic fuzzy diagnosis theory | |
| Pandarakone et al. | Deep neural network based bearing fault diagnosis of induction motor using fast Fourier transform analysis | |
| Li et al. | Bearing fault feature selection method based on weighted multidimensional feature fusion | |
| CN111259990B (en) | Seawater pump fault monitoring device and diagnosis method based on multi-source information fusion | |
| CN111365251B (en) | Intelligent diagnosis method for faults of centrifugal pump unit | |
| CN106441896A (en) | Characteristic vector extraction method for rolling bearing fault mode identification and state monitoring | |
| CN110954354B (en) | Equipment fault diagnosis method and device | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN108398265A (en) | A kind of online fault detection method of rolling bearing | |
| Lu et al. | Bearing fault diagnosis based on clustering and sparse representation in frequency domain | |
| CN114742093A (en) | Rolling bearing fault diagnosis method and device based on time-frequency curve extraction and classification | |
| CN110749443B (en) | Rolling bearing fault diagnosis method and system based on high-order origin moment | |
| CN117759491A (en) | Wind turbine generator set bolt fault monitoring method | |
| CN116257747A (en) | Early abnormality detection method for rotor system of fusion kurtosis and convolution self-encoder | |
| CN113032915B (en) | Method and device for evaluating health state of spindle bearing of manufacturing equipment | |
| CN112706901B (en) | Semi-supervised fault diagnosis method for main propulsion system of semi-submerged ship | |
| CN112525337B (en) | Pretreatment method for vibration monitoring data of mechanical press | |
| CN111947927B (en) | Rolling bearing fault detection method based on chromaticity theory | |
| Li et al. | Correlation warping radius tracking for condition monitoring of rolling bearings under varying operating conditions | |
| CN115186692A (en) | Intelligent fault diagnosis method based on empirical mode decomposition and image conversion | |
| Yang et al. | Fault diagnosis of rotating machinery using denoising-integrated sparse autoencoder based health state classification | |
| Lorenz et al. | Vibration Data Analysis for Fault Detection in Manufacturing Systems-A Systematic Literature Review | |
| Raj | An Improved Accuracy and Efficiency Based Defect Detection Method for Industrial Signal Processing |
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 |