CN113591248A - Bearing fault diagnosis method in mine hoist transmission part - Google Patents
Bearing fault diagnosis method in mine hoist transmission part Download PDFInfo
- Publication number
- CN113591248A CN113591248A CN202110908516.6A CN202110908516A CN113591248A CN 113591248 A CN113591248 A CN 113591248A CN 202110908516 A CN202110908516 A CN 202110908516A CN 113591248 A CN113591248 A CN 113591248A
- Authority
- CN
- China
- Prior art keywords
- bearing
- fault
- formula
- information entropy
- covariance matrix
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000005540 biological transmission Effects 0.000 title claims abstract description 13
- 238000003745 diagnosis Methods 0.000 title abstract description 14
- 230000001133 acceleration Effects 0.000 claims abstract description 10
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000003750 conditioning effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000001143 conditioned effect Effects 0.000 claims 1
- 238000005096 rolling process Methods 0.000 abstract description 9
- 239000000284 extract Substances 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 abstract description 3
- 230000003595 spectral effect Effects 0.000 description 4
- 238000005065 mining Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a bearing fault diagnosis method in a mine hoist transmission part, which comprises the steps of collecting vibration signals of a bearing in a normal state and a fault state through a vibration acceleration sensor, and converting the collected analog signals into digital signals; then, the digital signals are subjected to an ensemble empirical mode decomposition sample entropy characteristic extraction method to obtain information entropy H (X) of the bearing in a normal state and a fault statei) And Hf1（Xi) And to H (X)i) And Hf1（Xi) And comparing to diagnose the bearing fault. The vibration acceleration sensor extracts the collected related digital signals by adopting an ensemble empirical mode decomposition methodAccording to the method, EEMD decomposition is carried out to obtain a data residual ri between the actual output of the sensor and the expected output, corresponding information entropy is obtained through calculation of the residual ri, and fault diagnosis of the rolling bearing can be realized through comparison of the information entropy, so that the reliability and the safety of the whole transmission part of the mine hoist are improved.
Description
Technical Field
The invention belongs to the technical field of bearing fault diagnosis, and relates to a bearing fault diagnosis method in a transmission part of a mine hoist.
Background
The mine hoist is a transport machine which is used in mining engineering profession and establishes a connection between underground work and ground above the well. In a mine, a mine hoist is an automatic machine for working under the coal mine and working on the ground above the mine. The mine hoist mainly comprises a three-phase motor, a speed reducer, a winding drum (or a sliding friction wheel), a braking system, a depth warning mark software management system, a mobile speed measuring speed limiting system, an operation software system and the like.
At present, a related algorithm which is mainly based on machine learning is successfully applied to the detection of the abnormal condition of the bearing in the mining machine hoist, but the method easily ignores some possible early faults of the rolling bearing, so that the safety and reliability problems of the whole mining machine hoist system occur.
Disclosure of Invention
The invention aims to provide a bearing fault diagnosis method in a mine hoist transmission component, which can diagnose early faults of a bearing and aims to solve the problem that the early faults of the bearing are difficult to diagnose in the prior art.
Therefore, the invention adopts the following technical scheme:
a bearing fault diagnosis method in a mine hoist transmission component comprises the following steps:
(1) collecting vibration analog signals of a bearing in a normal state and a fault state through a vibration acceleration sensor, and converting the collected analog signals into digital signals;
(2) the method for extracting entropy characteristics of the digital signals by adopting a set empirical mode decomposition sample entropy obtains the information entropy H (X) of the bearing in a normal statei) And information entropy H under fault conditionf1（Xi）；
(3) Comparing the information entropy of the bearing in the normal state with that in the fault state: h (X)i）- Hf1（Xi）。
Further, in the step (1), the acquired vibration analog signal is converted into a digital signal through signal conditioning and a/D conversion, and then the digital signal is processed in real time.
Further, in the step (2), data is extracted from the digital signal after real-time processing by using an ensemble empirical mode decomposition method, and a data residual r between the actual output of the sensor and the expected output is obtainediBy data residual riCalculating the information entropy H (X) of the vibration acceleration sensor in the normal state and the fault state of the bearingi) And Hf1（Xi) The calculation formula is as follows:
in the formula, the covariance matrix of multivariate normal distribution is shown, and n is a data dimension.
Further, the formula (1) introduces H (X)i）-Hf1（Xi) To obtain
In the formula: is a function of the probability density at which the bearing fails.
Further, the formula (2) conforms to the expression of K-L divergence, i.e.
Further, the introduction of the mahalanobis transform to the calculation formula (1) results in an improved formula:
in the formula: is a covariance matrix of multivariate normal distribution, and n is a data dimension.
Introducing equation (4) into equation (3) yields:
in the formula: the covariance matrix of the bearing data when the fault does not occur is the covariance matrix of the bearing when the fault occurs.
The invention has the beneficial effects that:
(1) the vibration acceleration sensor is used for collecting the bearing operation to enable the relevant data to be converted into digital signals, the obtained relevant digital signals are subjected to data extraction by adopting an ensemble empirical mode decomposition method to obtain corresponding information entropies, and fault diagnosis of the rolling bearing can be realized by comparing the information entropies, so that the reliability and the safety of the whole transmission part of the mine hoist are improved.
(2) The information entropy is converted into the K-L divergence, so that the operation steps are further saved, and the calculation is more convenient and faster.
(3) The vibration acceleration sensor is arranged on the bearing, corresponding vibration signals are collected and converted into digital signals, subsequent processing is facilitated, the number of required mounting equipment is small, and cost is low.
Drawings
FIG. 1 is a time domain diagram of a bearing raw signal;
FIG. 2 is a time domain diagram of the IMF components;
FIG. 3 is a plot of power spectral density of different IMF components;
FIG. 4 is a graph of divergence values for different fault types K-L for different sensitive components for the same fault diameter.
FIG. 5 is a K-L divergence value graph of inner ring faults under different diameters under the same fault type.
Detailed Description
The invention is described in detail below with reference to the following figures and examples:
a bearing fault diagnosis method in a mine hoist transmission component comprises the following steps:
(1) the vibration acceleration sensor is arranged on the bearing, vibration signals (the time domain of the acquired original signals is shown in figure 1) in a normal state, an inner ring fault, a rolling body (ball) fault and an outer ring fault state are respectively acquired under the sampling frequency of 12k, the acquired analog signals are subjected to signal conditioning through the MAX3082 high-speed transceiver and are converted into standard signals, then the standard signals are subjected to A/D conversion to be converted into digital signals, and the converted digital signals are communicated to the TMS320DM642DSP processor to be processed in real time.
(2) Extracting data from the digital signal after real-time processing by adopting an ensemble empirical mode decomposition method to obtain a data residual ri between the actual output and the expected output of the sensor, and calculating the information entropy H (X) of the vibration acceleration sensor in the normal state and the fault state of the bearing through rii) And Hf1（Xi) Wherein the calculation formula is as follows:
in order to save computing resources, the traditional information entropy formula needs to be redesigned, and the improved information entropy formula obtained by introducing the mahalanobis transformation is as follows:
in the formula: is a covariance matrix of multivariate normal distribution, and n is a data dimension.
The difference in entropy between the normal state and the fault state of the bearing can be expressed as:
in the formula: is a function of the probability density at which the sensor experiences drift failure.
The observation of the formula result shows that the formula just conforms to the expression of K-L divergence, and the expression of K-L can be expressed as:
introducing K-L divergence for fault diagnosis, but because of the problem of high computational complexity caused by difficult estimation of a residual probability density function in the K-L divergence, carrying formula (2) into formula (4) to obtain a new K-L divergence expression:
in the formula: is the covariance matrix of the sensor when no fault occurs, is the sensor X when fault occursiThe covariance matrix of (2).
In order to judge whether the result is accurate, the rolling bearing fault diagnosis platform of the university of kassejour is taken as an example, and the specific experimental parameters are as follows:
when the failure diameter of a bearing at the driving end is 0.1778mm under the condition of a sampling frequency of 12K, EEMD decomposition is carried out on original signals of different failure types when the motor load is 3 horsepower, and K-L divergence (standard entropy) and correlation coefficients between IMF components after EEMD decomposition and the original failure signals are shown in the table 1;
| IMF1 | IMF2 | IMF3 | IMF4 | IMF5 | IMF6 | IMF7 | IMF8 | |
| divergence of K-L | -1.2757 | 0.2053 | 0.2040 | 0.7232 | 1.4958 | 1.8410 | 2.1212 | 2.6916 |
| Correlation coefficient | 0.2951 | 0.0153 | 0.0153 | 0.0054 | 0.0012 | 5.80438 | 3.3140 | 1.0591 |
From table 1, it can be seen that in the method of distinguishing the sensitive components according to the correlation coefficients, (reference related literature study: ISSAE and XGBoost based rolling bearing failure diagnosis study [ J ] electromechanical engineering, 2021,38(06): 704-711) sets the sensitive component threshold value to 0.1 times the maximum correlation coefficient value according to the literature, and thus, the threshold value is 0.5804, so that the sensitive IMF components are sequentially IMF1, IMF2, IMF3, IMF4 and IMF5 according to the correlation coefficient values, and the sensitive components are distinguished according to the K-L divergence, and thus, the sensitive components have a significant difference between IMF4 and IMF5, and thus, by setting the threshold value d =1, it can be seen that IMF1, IMF2, IMF3 and IMF4 are all smaller than the set threshold values, and thus, it can be determined that the four components are the sensitive components.
As shown in fig. 3, since the sensitive components identified by the correlation coefficient and K-L divergence method are different, the sensitive components are further determined by comparing the power spectral density maps of the determined sensitive components, and it can be seen from the power spectral density maps of the IMF components that the IMF4 component is similar to the power spectral density map of the IMF5 component, so that the IMF5 can be determined as a false sensitive component, and thus it can be seen that the extraction of the sensitive components based on K-L divergence is an effective method, and therefore, the last sensitive components are IMF1, IMF2, IMF3 and IMF 4.
This gives rise to the K-L divergence values for different fault types for different sensitive components at the same fault diameter, as shown in fig. 4, and for the inner ring faults for different fault diameters at different sensitive components, also at a motor load of 3 horsepower, as shown in fig. 5.
From the above fig. 4, it can be seen that under the condition that the fault diameter is 0.1778mm, different sensitive components have obvious differences to the K-L divergence values of different fault types, so that the method can be used for feature extraction of different fault types, and from fig. 5, it can be seen that under the condition of the same fault type (inner ring fault), the K-L divergence values of different fault diameters have obvious differences at different sensitive components.
From FIG. 4, it can be seen thati）- Hf1（Xi）<0.7, judging that the bearing rolling body has a fault; if 0.8<H（Xi）- Hf1（Xi）<1.4, judging that the bearing inner ring has a fault; if 1.4<H（Xi）- Hf1（Xi）<And 2, judging that the outer ring of the bearing has a fault. Therefore, the method can effectively extract the characteristics of different fault diameters.
The method can effectively extract the characteristics of the early fault of the rolling bearing which is most prone to fault in the transmission part of the mine hoist, and realizes fault diagnosis of the rolling bearing, so that the reliability and the safety of the whole transmission part of the mine hoist are improved.
Claims (6)
1. A method for diagnosing bearing faults in a transmission part of a mine hoist is characterized by comprising the following steps:
(1) collecting vibration analog signals of a bearing in a normal state and a fault state through a vibration acceleration sensor, and converting the collected analog signals into digital signals;
(2) the method for extracting entropy characteristics of the digital signals by adopting a set empirical mode decomposition sample entropy obtains the information entropy H (X) of the bearing in a normal statei) And information entropy H under fault conditionf1（Xi）；
(3) And comparing the information entropy of the bearing in the normal state with that in the fault state, and judging the fault type through the information entropy comparison.
2. The method of claim 1, wherein the step (1) comprises conditioning the vibration analog signal and converting the conditioned signal into digital signal, and processing the digital signal in real time.
3. The method of claim 1, wherein the step (2) of decomposing the real-time processed digital signal using an ensemble empirical modeExtracting data to obtain data residual r between actual output and expected output of sensoriBy data residual riCalculating the information entropy H (X) of the vibration acceleration sensor in the normal state and the fault state of the bearingi) And Hf1（Xi) The calculation formula is as follows:
in the formula, the covariance matrix of multivariate normal distribution is shown, and n is a data dimension.
4. The method of claim 3, wherein the formula (1) introduces H (X)i）-Hf1（Xi) To obtain
In the formula: is a function of the probability density at which the bearing fails.
5. The method of claim 4, wherein the formula (2) conforms to the expression of K-L divergence, i.e., the formula (2) is a method for diagnosing bearing failure in a transmission member of a mine hoist
6. The method of claim 5, wherein the introducing a mahalanobis transformation to the calculation formula (1) is modified by the formula:
in the formula: the covariance matrix is a multivariate normal distribution covariance matrix, and n is a data dimension;
introducing equation (4) into equation (3) yields:
in the formula: the covariance matrix of the bearing data when the fault does not occur is the covariance matrix of the bearing when the fault occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110908516.6A CN113591248A (en) | 2021-08-09 | 2021-08-09 | Bearing fault diagnosis method in mine hoist transmission part |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110908516.6A CN113591248A (en) | 2021-08-09 | 2021-08-09 | Bearing fault diagnosis method in mine hoist transmission part |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113591248A true CN113591248A (en) | 2021-11-02 |
Family
ID=78256423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110908516.6A Pending CN113591248A (en) | 2021-08-09 | 2021-08-09 | Bearing fault diagnosis method in mine hoist transmission part |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113591248A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116861218A (en) * | 2023-07-25 | 2023-10-10 | 上海华菱电站成套设备股份有限公司 | Mine winder key equipment state monitoring early warning system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104155108A (en) * | 2014-07-21 | 2014-11-19 | 天津大学 | Rolling bearing failure diagnosis method base on vibration temporal frequency analysis |
| CN109665399A (en) * | 2019-01-28 | 2019-04-23 | 枣庄学院 | A kind of fault diagnosis system and method for mine hoist wireless transmission |
| CN110044620A (en) * | 2019-03-15 | 2019-07-23 | 昆明理工大学 | A kind of Fault Diagnosis of Roller Bearings based on analysis of vibration signal |
| CN110909710A (en) * | 2019-12-03 | 2020-03-24 | 北京信息科技大学 | Self-adaptive main shaft performance degradation identification method based on S test piece |
| CN111444988A (en) * | 2020-05-11 | 2020-07-24 | 北华大学 | Rolling bearing fault diagnosis system |
| CN111723449A (en) * | 2020-06-30 | 2020-09-29 | 华北科技学院 | Performance degradation evaluation method for constant deceleration braking system of mine hoist |
| AU2020103681A4 (en) * | 2020-11-26 | 2021-02-04 | Anhui University Of Technology | Rolling Bearing Fault Diagnosis Method Based on Fourier Decomposition and Multi-scale Arrangement Entropy Partial Mean Value |
| CN113029566A (en) * | 2021-02-02 | 2021-06-25 | 王晓东 | Rolling bearing fault acoustic emission feature extraction method based on improved EEMD and MED |
| CN113092112A (en) * | 2021-03-30 | 2021-07-09 | 北京工业大学 | Bearing composite fault diagnosis method based on EEMD multi-feature fusion |
-
2021
- 2021-08-09 CN CN202110908516.6A patent/CN113591248A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104155108A (en) * | 2014-07-21 | 2014-11-19 | 天津大学 | Rolling bearing failure diagnosis method base on vibration temporal frequency analysis |
| CN109665399A (en) * | 2019-01-28 | 2019-04-23 | 枣庄学院 | A kind of fault diagnosis system and method for mine hoist wireless transmission |
| CN110044620A (en) * | 2019-03-15 | 2019-07-23 | 昆明理工大学 | A kind of Fault Diagnosis of Roller Bearings based on analysis of vibration signal |
| CN110909710A (en) * | 2019-12-03 | 2020-03-24 | 北京信息科技大学 | Self-adaptive main shaft performance degradation identification method based on S test piece |
| CN111444988A (en) * | 2020-05-11 | 2020-07-24 | 北华大学 | Rolling bearing fault diagnosis system |
| CN111723449A (en) * | 2020-06-30 | 2020-09-29 | 华北科技学院 | Performance degradation evaluation method for constant deceleration braking system of mine hoist |
| AU2020103681A4 (en) * | 2020-11-26 | 2021-02-04 | Anhui University Of Technology | Rolling Bearing Fault Diagnosis Method Based on Fourier Decomposition and Multi-scale Arrangement Entropy Partial Mean Value |
| CN113029566A (en) * | 2021-02-02 | 2021-06-25 | 王晓东 | Rolling bearing fault acoustic emission feature extraction method based on improved EEMD and MED |
| CN113092112A (en) * | 2021-03-30 | 2021-07-09 | 北京工业大学 | Bearing composite fault diagnosis method based on EEMD multi-feature fusion |
Non-Patent Citations (2)
| Title |
|---|
| 王志杰: "基于K-L散度的滚动轴承故障诊断及状态监测方法研究", 北京交通大学硕士专业学位论文, 15 January 2020 (2020-01-15), pages 13 - 51 * |
| 艾延廷等: "小波变换和EEMD-马氏距离的轴承故障诊断", 噪声与振动控制, vol. 35, no. 1, 28 February 2015 (2015-02-28), pages 235 - 239 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116861218A (en) * | 2023-07-25 | 2023-10-10 | 上海华菱电站成套设备股份有限公司 | Mine winder key equipment state monitoring early warning system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | An efficient approach to machine health diagnosis based on harmonic wavelet packet transform | |
| CN111089726B (en) | Rolling bearing fault diagnosis method based on optimal dimension singular spectrum decomposition | |
| CN108760327B (en) | Diagnosis method for rotor fault of aircraft engine | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN115688018B (en) | Method for monitoring state and diagnosing faults of bearing under multiple working conditions | |
| Dou et al. | A rule-based intelligent method for fault diagnosis of rotating machinery | |
| CN112098088B (en) | Rolling bearing fault diagnosis method based on KICA-fractal theory | |
| CN113607415A (en) | Bearing fault diagnosis method based on short-time stochastic resonance under variable rotating speed | |
| CN104596766A (en) | Early fault determining method for bearing | |
| CN113591248A (en) | Bearing fault diagnosis method in mine hoist transmission part | |
| CN111076934A (en) | Method for diagnosing potential fault of bearing based on S transformation | |
| CN111811819A (en) | Bearing fault diagnosis method and device based on machine learning | |
| CN112285494A (en) | Power cable partial discharge mode recognition analysis system | |
| CN112781877A (en) | Fault diagnosis method, device and system for bearings of walking parts | |
| CN110147637B (en) | Rub-impact fault diagnosis method based on wavelet and harmonic component greedy sparse identification | |
| CN114018581B (en) | Rolling bearing vibration signal decomposition method based on CEEMDAN | |
| JP4003086B2 (en) | Evaluation method and apparatus | |
| Zhang et al. | A novel hybrid compound fault pattern identification method for gearbox based on NIC, MFDFA and WOASVM | |
| Dey et al. | Autocorrelation based feature extraction for bearing fault detection in induction motors | |
| CN114781466A (en) | Fault diagnosis method and system based on harmonic fundamental frequency of rotary mechanical vibration signal | |
| CN112067296B (en) | Rolling bearing fault diagnosis method based on empirical mode decomposition and nuclear correlation | |
| CN113343887A (en) | Multi-sensor mixed fault signal blind separation method based on edge calculation and machine learning | |
| CN112528753A (en) | Preprocessing method for impact vibration signals in rolling process of rolling mill | |
| CN114199569A (en) | Fault diagnosis method for bearing and computer readable medium | |
| CN113994088A (en) | Method for computer-implemented monitoring of components of a wind turbine |
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 |